Kernel code may export it for complete or partial access.
GPIOs are identified as they are inside the kernel, using integers in
- the range 0..INT_MAX. See Documentation/gpio/gpio.txt for more information.
+ the range 0..INT_MAX. See Documentation/gpio for more information.
/sys/class/gpio
/export ... asks the kernel to export a GPIO to userspace
See files in Documentation/cpu-freq/ for more information.
- In particular, read Documentation/cpu-freq/user-guide.txt
- to learn how to control the knobs.
-
What: /sys/devices/system/cpu/cpu#/cpufreq/freqdomain_cpus
Date: June 2013
as follows:
<pre>
- 1 unsigned long gpnum;
- 2 unsigned long completed;
+ 1 unsigned long gp_seq;
</pre>
<p>RCU grace periods are numbered, and
-the <tt>->gpnum</tt> field contains the number of the grace
-period that started most recently.
-The <tt>->completed</tt> field contains the number of the
-grace period that completed most recently.
-If the two fields are equal, the RCU grace period that most recently
-started has already completed, and therefore the corresponding
-flavor of RCU is idle.
-If <tt>->gpnum</tt> is one greater than <tt>->completed</tt>,
-then <tt>->gpnum</tt> gives the number of the current RCU
-grace period, which has not yet completed.
-Any other combination of values indicates that something is broken.
-These two fields are protected by the root <tt>rcu_node</tt>'s
+the <tt>->gp_seq</tt> field contains the current grace-period
+sequence number.
+The bottom two bits are the state of the current grace period,
+which can be zero for not yet started or one for in progress.
+In other words, if the bottom two bits of <tt>->gp_seq</tt> are
+zero, the corresponding flavor of RCU is idle.
+Any other value in the bottom two bits indicates that something is broken.
+This field is protected by the root <tt>rcu_node</tt> structure's
<tt>->lock</tt> field.
-</p><p>There are <tt>->gpnum</tt> and <tt>->completed</tt> fields
+</p><p>There are <tt>->gp_seq</tt> fields
in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures
as well.
The fields in the <tt>rcu_state</tt> structure represent the
-most current values, and those of the other structures are compared
-in order to detect the start of a new grace period in a distributed
+most current value, and those of the other structures are compared
+in order to detect the beginnings and ends of grace periods in a distributed
fashion.
The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt>
(down the tree from the root to the leaves) to <tt>rcu_data</tt>.
as follows:
<pre>
- 1 unsigned long gpnum;
- 2 unsigned long completed;
+ 1 unsigned long gp_seq;
+ 2 unsigned long gp_seq_needed;
</pre>
-<p>These fields are the counterparts of the fields of the same name in
-the <tt>rcu_state</tt> structure.
-They each may lag up to one behind their <tt>rcu_state</tt>
-counterparts.
-If a given <tt>rcu_node</tt> structure's <tt>->gpnum</tt> and
-<tt>->complete</tt> fields are equal, then this <tt>rcu_node</tt>
+<p>The <tt>rcu_node</tt> structures' <tt>->gp_seq</tt> fields are
+the counterparts of the field of the same name in the <tt>rcu_state</tt>
+structure.
+They each may lag up to one step behind their <tt>rcu_state</tt>
+counterpart.
+If the bottom two bits of a given <tt>rcu_node</tt> structure's
+<tt>->gp_seq</tt> field is zero, then this <tt>rcu_node</tt>
structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> structure,
-the <tt>->gpnum</tt> field will be one greater than the
-<tt>->complete</tt> fields, with <tt>->gpnum</tt>
-indicating which grace period this <tt>rcu_node</tt> believes
-is still being waited for.
+</p><p>The <tt>>gp_seq</tt> field of each <tt>rcu_node</tt>
+structure is updated at the beginning and the end
+of each grace period.
+
+<p>The <tt>->gp_seq_needed</tt> fields record the
+furthest-in-the-future grace period request seen by the corresponding
+<tt>rcu_node</tt> structure. The request is considered fulfilled when
+the value of the <tt>->gp_seq</tt> field equals or exceeds that of
+the <tt>->gp_seq_needed</tt> field.
-</p><p>The <tt>>gpnum</tt> field of each <tt>rcu_node</tt>
-structure is updated at the beginning
-of each grace period, and the <tt>->completed</tt> fields are
-updated at the end of each grace period.
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ Suppose that this <tt>rcu_node</tt> structure doesn't see
+ a request for a very long time.
+ Won't wrapping of the <tt>->gp_seq</tt> field cause
+ problems?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ No, because if the <tt>->gp_seq_needed</tt> field lags behind the
+ <tt>->gp_seq</tt> field, the <tt>->gp_seq_needed</tt> field
+ will be updated at the end of the grace period.
+ Modulo-arithmetic comparisons therefore will always get the
+ correct answer, even with wrapping.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
<h5>Quiescent-State Tracking</h5>
</ol>
<p><font color="ffffff">So the locking is absolutely required in
- order to coordinate
- clearing of the bits with the grace-period numbers in
- <tt>->gpnum</tt> and <tt>->completed</tt>.
+ order to coordinate clearing of the bits with updating of the
+ grace-period sequence number in <tt>->gp_seq</tt>.
</font></td></tr>
<tr><td> </td></tr>
</table>
as follows:
<pre>
- 1 unsigned long completed;
- 2 unsigned long gpnum;
+ 1 unsigned long gp_seq;
+ 2 unsigned long gp_seq_needed;
3 bool cpu_no_qs;
4 bool core_needs_qs;
5 bool gpwrap;
6 unsigned long rcu_qs_ctr_snap;
</pre>
-<p>The <tt>completed</tt> and <tt>gpnum</tt>
+<p>The <tt>->gp_seq</tt> and <tt>->gp_seq_needed</tt>
fields are the counterparts of the fields of the same name
in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures.
They may each lag up to one behind their <tt>rcu_node</tt>
<tt>CONFIG_NO_HZ_FULL</tt> kernels can lag
arbitrarily far behind for CPUs in dyntick-idle mode (but these counters
will catch up upon exit from dyntick-idle mode).
-If a given <tt>rcu_data</tt> structure's <tt>->gpnum</tt> and
-<tt>->complete</tt> fields are equal, then this <tt>rcu_data</tt>
+If the lower two bits of a given <tt>rcu_data</tt> structure's
+<tt>->gp_seq</tt> are zero, then this <tt>rcu_data</tt>
structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt>
-structure,
-the <tt>->gpnum</tt> field will be one greater than the
-<tt>->complete</tt> fields, with <tt>->gpnum</tt>
-indicating which grace period this <tt>rcu_data</tt> believes
-is still being waited for.
<table>
<tr><th> </th></tr>
<tr><td>
All this replication of the grace period numbers can only cause
massive confusion.
- Why not just keep a global pair of counters and be done with it???
+ Why not just keep a global sequence number and be done with it???
</td></tr>
<tr><th align="left">Answer:</th></tr>
<tr><td bgcolor="#ffffff"><font color="ffffff">
- Because if there was only a single global pair of grace-period
+ Because if there was only a single global sequence
numbers, there would need to be a single global lock to allow
- safely accessing and updating them.
+ safely accessing and updating it.
And if we are not going to have a single global lock, we need
to carefully manage the numbers on a per-node basis.
Recall from the answer to a previous Quick Quiz that the consequences
while the <tt>->core_needs_qs</tt> flag indicates that the
RCU core needs a quiescent state from the corresponding CPU.
The <tt>->gpwrap</tt> field indicates that the corresponding
-CPU has remained idle for so long that the <tt>completed</tt>
-and <tt>gpnum</tt> counters are in danger of overflow, which
+CPU has remained idle for so long that the
+<tt>gp_seq</tt> counter is in danger of overflow, which
will cause the CPU to disregard the values of its counters on
its next exit from idle.
Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect
whenever it notices that another RCU grace period has completed.
The CPU detects the completion of an RCU grace period by noticing
that the value of its <tt>rcu_data</tt> structure's
-<tt>->completed</tt> field differs from that of its leaf
+<tt>->gp_seq</tt> field differs from that of its leaf
<tt>rcu_node</tt> structure.
Recall that each <tt>rcu_node</tt> structure's
-<tt>->completed</tt> field is updated at the end of each
+<tt>->gp_seq</tt> field is updated at the beginnings and ends of each
grace period.
<p>
grace-period initialization.
<p>The first ordering-related grace-period initialization action is to
-increment the <tt>rcu_state</tt> structure's <tt>->gpnum</tt>
+advance the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt>
grace-period-number counter, as shown below:
</p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
<p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt>
tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
-<tt>->gpnum</tt> field to the newly incremented value from the
+<tt>->gp_seq</tt> field to the newly advanced value from the
<tt>rcu_state</tt> structure, as shown in the following diagram.
</p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
to notice that a new grace period has started, as described in the next
section.
But because the grace-period kthread started the grace period at the
-root (with the increment of the <tt>rcu_state</tt> structure's
-<tt>->gpnum</tt> field) before setting each leaf <tt>rcu_node</tt>
-structure's <tt>->gpnum</tt> field, each CPU's observation of
+root (with the advancing of the <tt>rcu_state</tt> structure's
+<tt>->gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt>
+structure's <tt>->gp_seq</tt> field, each CPU's observation of
the start of the grace period will happen after the actual start
of the grace period.
<tr><td>
But a RCU read-side critical section might have started
after the beginning of the grace period
- (the <tt>->gpnum++</tt> from earlier), so why should
+ (the advancing of <tt>->gp_seq</tt> from earlier), so why should
the grace period wait on such a critical section?
</td></tr>
<tr><th align="left">Answer:</th></tr>
<h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4>
<p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree
-breadth-first setting all the <tt>->completed</tt> fields equal
-to the number of the newly completed grace period, then it sets
-the <tt>rcu_state</tt> structure's <tt>->completed</tt> field,
-again to the number of the newly completed grace period.
+breadth-first advancing all the <tt>->gp_seq</tt> fields, then it
+advances the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt> field.
The ordering effects are shown below:
</p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%">
CPU has reported its quiescent state, but it may be some
milliseconds before RCU becomes aware of this.
The latest reasonable candidate is once the <tt>rcu_state</tt>
- structure's <tt>->completed</tt> field has been updated,
+ structure's <tt>->gp_seq</tt> field has been updated,
but it is quite possible that some CPUs have already completed
phase two of their updates by that time.
In short, if you are going to work with RCU, you need to
<h4><a name="Callback Invocation">Callback Invocation</a></h4>
<p>Once a given CPU's leaf <tt>rcu_node</tt> structure's
-<tt>->completed</tt> field has been updated, that CPU can begin
+<tt>->gp_seq</tt> field has been updated, that CPU can begin
invoking its RCU callbacks that were waiting for this grace period
to end.
These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
inkscape:window-height="1144"
id="namedview208"
showgrid="true"
- inkscape:zoom="0.70710678"
- inkscape:cx="617.89017"
- inkscape:cy="542.52419"
- inkscape:window-x="86"
- inkscape:window-y="28"
+ inkscape:zoom="0.78716603"
+ inkscape:cx="513.06403"
+ inkscape:cy="623.1214"
+ inkscape:window-x="102"
+ inkscape:window-y="38"
inkscape:window-maximized="0"
inkscape:current-layer="g3188-3"
fit-margin-top="5"
id="g3188">
<text
xml:space="preserve"
- x="3199.1516"
+ x="3145.9592"
y="13255.592"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3143">rcu_seq_end(&rnp->gp_seq)</tspan></text>
<g
id="g3107"
transform="translate(947.90548,11584.029)">
</g>
<text
xml:space="preserve"
- x="5324.5371"
- y="15414.598"
+ x="5264.4731"
+ y="15428.84"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-753"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-7"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
style="fill:none;stroke-width:0.025in"
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-6-0">Leaf</tspan></text>
- <text
- xml:space="preserve"
- x="7479.5796"
- y="17699.943"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-9"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
<path
sodipodi:nodetypes="cc"
inkscape:connector-curvature="0"
style="fill:none;stroke-width:0.025in"
transform="translate(-737.93887,7732.6672)"
id="g3188-3">
- <text
- xml:space="preserve"
- x="3225.7478"
- y="13175.802"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-60"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->completed =</text>
<g
id="g3107-62"
transform="translate(947.90548,11584.029)">
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-7">Root</tspan></text>
- <text
- xml:space="preserve"
- x="3225.7478"
- y="13390.038"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-60-3"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text>
<flowRoot
xml:space="preserve"
id="flowRoot3356"
height="63.63961"
x="332.34018"
y="681.87292" /></flowRegion><flowPara
- id="flowPara3362" /></flowRoot> </g>
+ id="flowPara3362" /></flowRoot> <text
+ xml:space="preserve"
+ x="3156.6121"
+ y="13317.754"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-6"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text>
+ </g>
<g
style="fill:none;stroke-width:0.025in"
transform="translate(-858.40227,7769.0342)"
id="path3414-8-3-6-6"
inkscape:connector-curvature="0"
sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ x="7418.769"
+ y="17646.104"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-70"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-93">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
transform="translate(-1642.5377,-11611.245)"
</g>
<text
xml:space="preserve"
- x="5327.3057"
+ x="5274.1133"
y="15428.84"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-36"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
transform="translate(-151.71746,-11647.612)"
id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7486.4907"
- y="17670.119"
+ x="7408.5918"
+ y="17619.504"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-6"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-2"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
transform="translate(-6817.1997,-11647.612)"
id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7474.1382"
- y="17688.926"
+ x="7416.8003"
+ y="17619.504"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-5"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-3"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-56">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
id="path3414-8-3-6"
inkscape:connector-curvature="0"
sodipodi:nodetypes="cc" />
- <text
- xml:space="preserve"
- x="7318.9653"
- y="6031.6353"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-2"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
<g
style="fill:none;stroke-width:0.025in"
id="g4504-3-9"
id="path3134-9-0-3-5"
d="m 6875.6003,15833.906 1595.7755,0"
style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" />
+ <text
+ xml:space="preserve"
+ x="7275.2612"
+ y="5971.8916"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-1"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-2">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</svg>
inkscape:window-height="1144"
id="namedview208"
showgrid="true"
- inkscape:zoom="0.70710678"
- inkscape:cx="617.89019"
- inkscape:cy="636.57143"
- inkscape:window-x="697"
+ inkscape:zoom="2.6330492"
+ inkscape:cx="524.82797"
+ inkscape:cy="519.31194"
+ inkscape:window-x="79"
inkscape:window-y="28"
inkscape:window-maximized="0"
- inkscape:current-layer="svg2"
+ inkscape:current-layer="g3188"
fit-margin-top="5"
fit-margin-right="5"
fit-margin-left="5"
id="g3188">
<text
xml:space="preserve"
- x="3305.5364"
+ x="3119.363"
y="13255.592"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text>
<g
id="g3107"
transform="translate(947.90548,11584.029)">
id="svg2"
version="1.1"
inkscape:version="0.48.4 r9939"
- sodipodi:docname="TreeRCU-gp-init-2.svg">
+ sodipodi:docname="TreeRCU-gp-init-3.svg">
<metadata
id="metadata212">
<rdf:RDF>
inkscape:window-width="1087"
inkscape:window-height="1144"
id="namedview208"
- showgrid="false"
- inkscape:zoom="0.70710678"
+ showgrid="true"
+ inkscape:zoom="0.68224756"
inkscape:cx="617.89019"
inkscape:cy="625.84293"
- inkscape:window-x="697"
+ inkscape:window-x="54"
inkscape:window-y="28"
inkscape:window-maximized="0"
- inkscape:current-layer="svg2"
+ inkscape:current-layer="g3153"
fit-margin-top="5"
fit-margin-right="5"
fit-margin-left="5"
- fit-margin-bottom="5" />
+ fit-margin-bottom="5">
+ <inkscape:grid
+ type="xygrid"
+ id="grid3090" />
+ </sodipodi:namedview>
<path
sodipodi:nodetypes="cccccccccccccccccccccccc"
inkscape:connector-curvature="0"
id="g3188">
<text
xml:space="preserve"
- x="3305.5364"
+ x="3145.9592"
y="13255.592"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gp_seq = rsp->gp_seq</text>
<g
id="g3107"
transform="translate(947.90548,11584.029)">
</g>
<text
xml:space="preserve"
- x="5392.3345"
- y="15407.104"
+ x="5253.6904"
+ y="15407.032"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-6"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
style="fill:none;stroke-width:0.025in"
id="tspan3104-6-5-6-0">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7536.4883"
- y="17640.934"
+ x="7415.4365"
+ y="17670.572"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-9"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-1642.5375,-11610.962)"
</g>
<text
xml:space="preserve"
- x="5378.4146"
- y="15436.927"
+ x="5258.0688"
+ y="15412.313"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-3"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-151.71726,-11647.329)"
id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7520.1294"
- y="17673.639"
+ x="7405.2607"
+ y="17670.572"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-35"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-6817.1998,-11647.329)"
id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7521.4663"
- y="17666.062"
+ x="7413.4688"
+ y="17670.566"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-75"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
sodipodi:nodetypes="cc" />
<text
xml:space="preserve"
- x="7370.856"
- y="5997.5972"
+ x="7271.9297"
+ y="6023.2412"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-62"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</svg>
inkscape:window-height="1144"
id="namedview208"
showgrid="true"
- inkscape:zoom="0.6004608"
- inkscape:cx="826.65969"
- inkscape:cy="483.3047"
- inkscape:window-x="66"
- inkscape:window-y="28"
+ inkscape:zoom="0.81932583"
+ inkscape:cx="840.45848"
+ inkscape:cy="5052.4242"
+ inkscape:window-x="787"
+ inkscape:window-y="24"
inkscape:window-maximized="0"
- inkscape:current-layer="svg2"
+ inkscape:current-layer="g4"
fit-margin-top="5"
fit-margin-right="5"
fit-margin-left="5"
style="fill:none;stroke-width:0.025in"
transform="translate(1749.0282,658.72243)"
id="g3188">
- <text
- xml:space="preserve"
- x="3305.5364"
- y="13255.592"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-5"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text>
<g
id="g3107-62"
transform="translate(947.90548,11584.029)">
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-7">Root</tspan></text>
+ <text
+ xml:space="preserve"
+ x="3137.9988"
+ y="13271.316"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-626"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text>
</g>
<rect
ry="0"
style="fill:none;stroke-width:0.025in"
transform="translate(1739.0986,17188.625)"
id="g3188-6">
- <text
- xml:space="preserve"
- x="3305.5364"
- y="13255.592"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-1"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text>
<g
id="g3107-5"
transform="translate(947.90548,11584.029)">
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-1">Root</tspan></text>
+ <text
+ xml:space="preserve"
+ x="3147.9268"
+ y="13240.524"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-1"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
style="fill:none;stroke-width:0.025in"
</g>
<text
xml:space="preserve"
- x="5392.3345"
- y="15407.104"
+ x="5263.1094"
+ y="15411.646"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-6-7"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ id="text202-92"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
style="fill:none;stroke-width:0.025in"
id="tspan3104-6-5-6-0-94">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7536.4883"
- y="17640.934"
+ x="7417.4053"
+ y="17655.502"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-9"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ id="text202-759"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-2353.8462,17224.992)"
</g>
<text
xml:space="preserve"
- x="5378.4146"
- y="15436.927"
+ x="5246.1548"
+ y="15411.648"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-3"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ id="text202-87"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-863.02613,17188.625)"
id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7520.1294"
- y="17673.639"
+ x="7433.8257"
+ y="17682.098"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-35"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ id="text202-2"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<g
transform="translate(-7528.5085,17188.625)"
id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7521.4663"
- y="17666.062"
+ x="7415.4404"
+ y="17682.098"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-75-1"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
+ id="text202-0"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
id="path3414-8-3-6-4"
inkscape:connector-curvature="0"
sodipodi:nodetypes="cc" />
- <text
- xml:space="preserve"
- x="6659.5469"
- y="34833.551"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-62"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text>
<path
sodipodi:nodetypes="ccc"
inkscape:connector-curvature="0"
font-weight="bold"
font-size="192"
id="text202-6-6-5"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text>
<text
xml:space="preserve"
x="5035.4155"
style="fill:none;stroke-width:0.025in"
transform="translate(1874.038,53203.538)"
id="g3188-7">
- <text
- xml:space="preserve"
- x="3199.1516"
- y="13255.592"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-82"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text>
<g
id="g3107-53"
transform="translate(947.90548,11584.029)">
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-19">Root</tspan></text>
+ <text
+ xml:space="preserve"
+ x="3175.896"
+ y="13240.11"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-3"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<rect
ry="0"
</g>
<text
xml:space="preserve"
- x="5324.5371"
- y="15414.598"
+ x="5264.4829"
+ y="15411.231"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-753"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-7"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
style="fill:none;stroke-width:0.025in"
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-6-0-4">Leaf</tspan></text>
- <text
- xml:space="preserve"
- x="10084.225"
- y="70903.312"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-9-0"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
<path
sodipodi:nodetypes="ccc"
inkscape:connector-curvature="0"
id="path3134-9-0-3-9"
d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0"
style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" />
- <text
- xml:space="preserve"
- x="5092.4683"
- y="74111.672"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-60"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp->completed =</text>
<g
style="fill:none;stroke-width:0.025in"
id="g3107-62-6"
sodipodi:linespacing="125%"><tspan
style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
id="tspan3104-6-5-7-7">Root</tspan></text>
- <text
- xml:space="preserve"
- x="5092.4683"
- y="74325.906"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-60-3"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text>
<g
style="fill:none;stroke-width:0.025in"
transform="translate(1746.2528,60972.572)"
</g>
<text
xml:space="preserve"
- x="5327.3057"
- y="15428.84"
+ x="5274.1216"
+ y="15411.231"
font-style="normal"
font-weight="bold"
font-size="192"
id="text202-36"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-6">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
transform="translate(-728.08545,53203.538)"
id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7486.4907"
- y="17670.119"
+ x="7435.1987"
+ y="17708.281"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-6-2"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-9"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-1">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<g
transform="translate(-7393.5687,53203.538)"
id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text>
<text
xml:space="preserve"
- x="7474.1382"
- y="17688.926"
+ x="7416.8125"
+ y="17708.281"
font-style="normal"
font-weight="bold"
font-size="192"
- id="text202-5-1"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
+ id="text202-36-35"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-62">rcu_seq_end(&rnp->gp_seq)</tspan></text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
id="path3414-8-3-6-67"
inkscape:connector-curvature="0"
sodipodi:nodetypes="cc" />
- <text
- xml:space="preserve"
- x="6742.6001"
- y="70882.617"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-2"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text>
<g
style="fill:none;stroke-width:0.025in"
id="g4504-3-9-6"
font-size="192"
id="text202-7-9-6-6-7"
style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text>
+ <text
+ xml:space="preserve"
+ x="6698.9019"
+ y="70885.211"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-2"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-7">rcu_seq_end(&rnp->gp_seq)</tspan></text>
+ <text
+ xml:space="preserve"
+ x="10023.457"
+ y="70885.234"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-0"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text>
+ <text
+ xml:space="preserve"
+ x="5023.3389"
+ y="74209.773"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-36-36"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+ style="font-size:172.87567139px"
+ id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text>
+ <text
+ xml:space="preserve"
+ x="6562.5884"
+ y="34870.727"
+ font-style="normal"
+ font-weight="bold"
+ font-size="192"
+ id="text202-3"
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text>
</g>
</svg>
inkscape:window-height="1144"
id="namedview208"
showgrid="true"
- inkscape:zoom="0.70710678"
- inkscape:cx="616.47598"
- inkscape:cy="595.41964"
- inkscape:window-x="813"
+ inkscape:zoom="0.96484375"
+ inkscape:cx="507.0191"
+ inkscape:cy="885.62207"
+ inkscape:window-x="47"
inkscape:window-y="28"
inkscape:window-maximized="0"
- inkscape:current-layer="g4405"
+ inkscape:current-layer="g3115"
fit-margin-top="5"
fit-margin-right="5"
fit-margin-left="5"
font-weight="bold"
font-size="192"
id="text202-6-6"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text>
<text
xml:space="preserve"
x="5035.4155"
INFO: rcu_sched detected stalls on CPUs/tasks:
2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0
16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0
- (detected by 32, t=2603 jiffies, g=7073, c=7072, q=625)
+ (detected by 32, t=2603 jiffies, g=7075, q=625)
This message indicates that CPU 32 detected that CPUs 2 and 16 were both
causing stalls, and that the stall was affecting RCU-sched. This message
period.
The "detected by" line indicates which CPU detected the stall (in this
-case, CPU 32), how many jiffies have elapsed since the start of the
-grace period (in this case 2603), the number of the last grace period
-to start and to complete (7073 and 7072, respectively), and an estimate
-of the total number of RCU callbacks queued across all CPUs (625 in
-this case).
+case, CPU 32), how many jiffies have elapsed since the start of the grace
+period (in this case 2603), the grace-period sequence number (7075), and
+an estimate of the total number of RCU callbacks queued across all CPUs
+(625 in this case).
In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
for each CPU:
the stall warning, as was the case in the "All QSes seen" line above,
the following additional line is printed:
- kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1
+ kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5
Starving the grace-period kthreads of CPU time can of course result
in RCU CPU stall warnings even when all CPUs and tasks have passed
-through the required quiescent states. The "g" and "c" numbers flag the
-number of the last grace period started and completed, respectively,
-the "f" precedes the ->gp_flags command to the grace-period kthread,
-the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short
-timeout, and the "state" precedes value of the task_struct ->state field.
+through the required quiescent states. The "g" number shows the current
+grace-period sequence number, the "f" precedes the ->gp_flags command
+to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the
+kthread is waiting for a short timeout, the "state" precedes value of the
+task_struct ->state field, and the "cpu" indicates that the grace-period
+kthread last ran on CPU 5.
Multiple Warnings From One Stall
void synchronize_rcu(void)
{
write_lock(&rcu_gp_mutex);
+ smp_mb__after_spinlock();
write_unlock(&rcu_gp_mutex);
}
The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
and release a global reader-writer lock. The synchronize_rcu()
-primitive write-acquires this same lock, then immediately releases
-it. This means that once synchronize_rcu() exits, all RCU read-side
-critical sections that were in progress before synchronize_rcu() was
-called are guaranteed to have completed -- there is no way that
-synchronize_rcu() would have been able to write-acquire the lock
-otherwise.
+primitive write-acquires this same lock, then releases it. This means
+that once synchronize_rcu() exits, all RCU read-side critical sections
+that were in progress before synchronize_rcu() was called are guaranteed
+to have completed -- there is no way that synchronize_rcu() would have
+been able to write-acquire the lock otherwise. The smp_mb__after_spinlock()
+promotes synchronize_rcu() to a full memory barrier in compliance with
+the "Memory-Barrier Guarantees" listed in:
+
+ Documentation/RCU/Design/Requirements/Requirements.html.
It is possible to nest rcu_read_lock(), since reader-writer locks may
be recursively acquired. Note also that rcu_read_lock() is immune
list_next_rcu
list_for_each_entry_rcu
list_for_each_entry_continue_rcu
+ list_for_each_entry_from_rcu
hlist_first_rcu
hlist_next_rcu
hlist_pprev_rcu
hlist_for_each_entry_rcu
hlist_for_each_entry_rcu_bh
+ hlist_for_each_entry_from_rcu
hlist_for_each_entry_continue_rcu
hlist_for_each_entry_continue_rcu_bh
hlist_nulls_first_rcu
(may crash computer or cause data corruption)
ALSA [HW,ALSA]
- See Documentation/sound/alsa/alsa-parameters.txt
+ See Documentation/sound/alsa-configuration.rst
alignment= [KNL,ARM]
Allow the default userspace alignment fault handler
nosync [HW,M68K] Disables sync negotiation for all devices.
- notsc [BUGS=X86-32] Disable Time Stamp Counter
-
nowatchdog [KNL] Disable both lockup detectors, i.e.
soft-lockup and NMI watchdog (hard-lockup).
This will also cause panics on machine check exceptions.
Useful together with panic=30 to trigger a reboot.
- OSS [HW,OSS]
- See Documentation/sound/oss/oss-parameters.txt
-
page_owner= [KNL] Boot-time page_owner enabling option.
Storage of the information about who allocated
each page is disabled in default. With this switch,
Set time (s) after boot for CPU-hotplug testing.
rcutorture.onoff_interval= [KNL]
- Set time (s) between CPU-hotplug operations, or
- zero to disable CPU-hotplug testing.
+ Set time (jiffies) between CPU-hotplug operations,
+ or zero to disable CPU-hotplug testing.
rcutorture.shuffle_interval= [KNL]
Set task-shuffle interval (s). Shuffling tasks
[FTRACE] Set and start specified trace events in order
to facilitate early boot debugging. The event-list is a
comma separated list of trace events to enable. See
- also Documentation/trace/events.txt
+ also Documentation/trace/events.rst
trace_options=[option-list]
[FTRACE] Enable or disable tracer options at boot.
trace_options=stacktrace
- See also Documentation/trace/ftrace.txt "trace options"
+ See also Documentation/trace/ftrace.rst "trace options"
section.
tp_printk[FTRACE]
xirc2ps_cs= [NET,PCMCIA]
Format:
<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
+
+ xhci-hcd.quirks [USB,KNL]
+ A hex value specifying bitmask with supplemental xhci
+ host controller quirks. Meaning of each bit can be
+ consulted in header drivers/usb/host/xhci.h.
``intel_pstate`` exposes several global attributes (files) in ``sysfs`` to
control its functionality at the system level. They are located in the
-``/sys/devices/system/cpu/cpufreq/intel_pstate/`` directory and affect all
-CPUs.
+``/sys/devices/system/cpu/intel_pstate/`` directory and affect all CPUs.
Some of them are not present if the ``intel_pstate=per_cpu_perf_limits``
argument is passed to the kernel in the command line.
but it affects the maximum possible value of per-policy P-state limits
(see `Interpretation of Policy Attributes`_ below for details).
+``hwp_dynamic_boost``
+ This attribute is only present if ``intel_pstate`` works in the
+ `active mode with the HWP feature enabled <Active Mode With HWP_>`_ in
+ the processor. If set (equal to 1), it causes the minimum P-state limit
+ to be increased dynamically for a short time whenever a task previously
+ waiting on I/O is selected to run on a given logical CPU (the purpose
+ of this mechanism is to improve performance).
+
+ This setting has no effect on logical CPUs whose minimum P-state limit
+ is directly set to the highest non-turbo P-state or above it.
+
.. _status_attr:
``status``
That only is supported in some configurations, though (for example, if
the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
the operation mode of the driver cannot be changed), and if it is not
- supported in the current configuration, writes to this attribute with
+ supported in the current configuration, writes to this attribute will
fail with an appropriate error.
Interpretation of Policy Attributes
operations before calling end_that_request_last()! For an example of a user
of these helpers, see the IDE tagged command queueing support.
-Certain hardware conditions may dictate a need to invalidate the block tag
-queue. For instance, on IDE any tagged request error needs to clear both
-the hardware and software block queue and enable the driver to sanely restart
-all the outstanding requests. There's a third helper to do that:
-
- blk_queue_invalidate_tags(struct request_queue *q)
-
- Clear the internal block tag queue and re-add all the pending requests
- to the request queue. The driver will receive them again on the
- next request_fn run, just like it did the first time it encountered
- them.
-
3.2.5.2 Tag info
Some block functions exist to query current tag status or to go from a
Most of the above is simple and straight forward, however busy_list may need
a bit of explaining. Normally we don't care too much about request ordering,
but in the event of any barrier requests in the tag queue we need to ensure
-that requests are restarted in the order they were queue. This may happen
-if the driver needs to use blk_queue_invalidate_tags().
+that requests are restarted in the order they were queue.
3.3 I/O Submission
local_t.
The first operations to implement for atomic_t's are the initializers and
-plain reads. ::
+plain writes. ::
#define ATOMIC_INIT(i) { (i) }
#define atomic_set(v, i) ((v)->counter = (i))
MTRR Handling
-------------
-.. kernel-doc:: arch/x86/kernel/cpu/mtrr/main.c
+.. kernel-doc:: arch/x86/kernel/cpu/mtrr/mtrr.c
:export:
Security Framework
Requirement
-----------
-You have to put at start of your tfm_ctx the struct crypto_engine_ctx
-struct your_tfm_ctx {
+You have to put at start of your tfm_ctx the struct crypto_engine_ctx::
+
+ struct your_tfm_ctx {
struct crypto_engine_ctx enginectx;
...
-};
+ };
+
Why: Since CE manage only crypto_async_request, it cannot know the underlying
request_type and so have access only on the TFM.
So using container_of for accessing __ctx is impossible.
size)
5. the number of optional parameters (the parameters with an argument
count as two)
+ start_sector n (default: 0)
+ offset from the start of cache device in 512-byte sectors
high_watermark n (default: 50)
start writeback when the number of used blocks reach this
watermark
- "insignal,arndale-octa" - for Exynos5420-based Insignal Arndale
Octa board.
- "insignal,origen" - for Exynos4210-based Insignal Origen board.
- - "insignal,origen4412 - for Exynos4412-based Insignal Origen board.
+ - "insignal,origen4412" - for Exynos4412-based Insignal Origen board.
Optional nodes:
Each subnode should use the binding described in [2]..[7]
[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-[3] Documentation/devicetree/bindings/clock/st,clkgen-mux.txt
-[4] Documentation/devicetree/bindings/clock/st,clkgen-pll.txt
-[7] Documentation/devicetree/bindings/clock/st,quadfs.txt
-[8] Documentation/devicetree/bindings/clock/st,flexgen.txt
+[3] Documentation/devicetree/bindings/clock/st/st,clkgen-mux.txt
+[4] Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
+[7] Documentation/devicetree/bindings/clock/st/st,quadfs.txt
+[8] Documentation/devicetree/bindings/clock/st/st,flexgen.txt
Required properties:
that is used.
[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-[2] Documentation/devicetree/bindings/clock/gate-clock.txt
+[2] Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
[3] Documentation/devicetree/bindings/clock/ti/clockdomain.txt
Required properties:
clock) and hardware autoidle enable / disable.
[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-[2] Documentation/devicetree/bindings/clock/gate-clock.txt
+[2] Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
Required properties:
- compatible : shall be one of:
"intermediate" - A parent of "cpu" clock which is used as "intermediate" clock
source (usually MAINPLL) when the original CPU PLL is under
transition and not stable yet.
- Please refer to Documentation/devicetree/bindings/clk/clock-bindings.txt for
+ Please refer to Documentation/devicetree/bindings/clock/clock-bindings.txt for
generic clock consumer properties.
- operating-points-v2: Please refer to Documentation/devicetree/bindings/opp/opp.txt
for detail.
- clocks: Phandles for clock specified in "clock-names" property
- clock-names : The name of clock used by the DFI, must be
"pclk_ddr_mon";
-- operating-points-v2: Refer to Documentation/devicetree/bindings/power/opp.txt
+- operating-points-v2: Refer to Documentation/devicetree/bindings/opp/opp.txt
for details.
- center-supply: DMC supply node.
- status: Marks the node enabled/disabled.
- nxp,calib-gpios: calibration GPIO, which must correspond with the
gpio used for the TDA998x interrupt pin.
-[1] Documentation/sound/alsa/soc/DAI.txt
+[1] Documentation/sound/soc/dai.rst
[2] include/dt-bindings/display/tda998x.h
Example:
- port/ports: to describe a connection to an external encoder. The
binding follows Documentation/devicetree/bindings/graph.txt and
- suppors a single port with a single endpoint.
+ supports a single port with a single endpoint.
- See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and
Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting
Nintendo Wii (Hollywood) GPIO controller
Required properties:
-- compatible: "nintendo,hollywood-gpio
+- compatible: "nintendo,hollywood-gpio"
- reg: Physical base address and length of the controller's registers.
- gpio-controller: Marks the device node as a GPIO controller.
- #gpio-cells: Should be <2>. The first cell is the pin number and the
- mali-supply : Phandle to regulator for the Mali device. Refer to
Documentation/devicetree/bindings/regulator/regulator.txt for details.
-- operating-points-v2 : Refer to Documentation/devicetree/bindings/power/opp.txt
+- operating-points-v2 : Refer to Documentation/devicetree/bindings/opp/opp.txt
for details.
- memory-region:
Memory region to allocate from, as defined in
- Documentation/devicetree/bindi/reserved-memory/reserved-memory.txt
+ Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
- mali-supply:
Phandle to regulator for the Mali device, as defined in
--- /dev/null
+Nuvoton NPCM7xx PWM and Fan Tacho controller device
+
+The Nuvoton BMC NPCM7XX supports 8 Pulse-width modulation (PWM)
+controller outputs and 16 Fan tachometer controller inputs.
+
+Required properties for pwm-fan node
+- #address-cells : should be 1.
+- #size-cells : should be 0.
+- compatible : "nuvoton,npcm750-pwm-fan" for Poleg NPCM7XX.
+- reg : specifies physical base address and size of the registers.
+- reg-names : must contain:
+ * "pwm" for the PWM registers.
+ * "fan" for the Fan registers.
+- clocks : phandle of reference clocks.
+- clock-names : must contain
+ * "pwm" for PWM controller operating clock.
+ * "fan" for Fan controller operating clock.
+- interrupts : contain the Fan interrupts with flags for falling edge.
+- pinctrl-names : a pinctrl state named "default" must be defined.
+- pinctrl-0 : phandle referencing pin configuration of the PWM and Fan
+ controller ports.
+
+fan subnode format:
+===================
+Under fan subnode can be upto 8 child nodes, each child node representing a fan.
+Each fan subnode must have one PWM channel and atleast one Fan tach channel.
+
+For PWM channel can be configured cooling-levels to create cooling device.
+Cooling device could be bound to a thermal zone for the thermal control.
+
+Required properties for each child node:
+- reg : specify the PWM output channel.
+ integer value in the range 0 through 7, that represent
+ the PWM channel number that used.
+
+- fan-tach-ch : specify the Fan tach input channel.
+ integer value in the range 0 through 15, that represent
+ the fan tach channel number that used.
+
+ At least one Fan tach input channel is required
+
+Optional property for each child node:
+- cooling-levels: PWM duty cycle values in a range from 0 to 255
+ which correspond to thermal cooling states.
+
+Examples:
+
+pwm_fan:pwm-fan-controller@103000 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "nuvoton,npcm750-pwm-fan";
+ reg = <0x103000 0x2000>,
+ <0x180000 0x8000>;
+ reg-names = "pwm", "fan";
+ clocks = <&clk NPCM7XX_CLK_APB3>,
+ <&clk NPCM7XX_CLK_APB4>;
+ clock-names = "pwm","fan";
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pwm0_pins &pwm1_pins &pwm2_pins
+ &fanin0_pins &fanin1_pins &fanin2_pins
+ &fanin3_pins &fanin4_pins>;
+ fan@0 {
+ reg = <0x00>;
+ fan-tach-ch = /bits/ 8 <0x00 0x01>;
+ cooling-levels = <127 255>;
+ };
+ fan@1 {
+ reg = <0x01>;
+ fan-tach-ch = /bits/ 8 <0x02 0x03>;
+ };
+ fan@2 {
+ reg = <0x02>;
+ fan-tach-ch = /bits/ 8 <0x04>;
+ };
+
+};
http://www.synaptics.com/sites/default/files/511-000136-01-Rev-E-RMI4-Interfacing-Guide.pdf
Optional Touch Properties:
-Description in Documentation/devicetree/bindings/input/touch
+Description in Documentation/devicetree/bindings/input/touchscreen
- touchscreen-inverted-x
- touchscreen-inverted-y
- touchscreen-swapped-x-y
This property is deprecated. Instead, a 'steps-per-period ' value should
be used, such as "rotary-encoder,steps-per-period = <2>".
-See Documentation/input/rotary-encoder.txt for more information.
+See Documentation/input/devices/rotary-encoder.rst for more information.
Example:
--- /dev/null
+Spreadtrum SC27xx PMIC Vibrator
+
+Required properties:
+- compatible: should be "sprd,sc2731-vibrator".
+- reg: address of vibrator control register.
+
+Example :
+
+ sc2731_pmic: pmic@0 {
+ compatible = "sprd,sc2731";
+ reg = <0>;
+ spi-max-frequency = <26000000>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ vibrator@eb4 {
+ compatible = "sprd,sc2731-vibrator";
+ reg = <0xeb4>;
+ };
+ };
reg = <0x6c>;
interrupt-parent = <&gpx1>;
interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
- vdd-supply = <&ldo15_reg>";
+ vdd-supply = <&ldo15_reg>;
vid-supply = <&ldo18_reg>;
reset-gpios = <&gpx1 5 0>;
touchscreen-size-x = <1080>;
- compatible : should be "ingenic,<socname>-intc". Valid strings are:
ingenic,jz4740-intc
+ ingenic,jz4725b-intc
ingenic,jz4770-intc
ingenic,jz4775-intc
ingenic,jz4780-intc
include "nvidia,tegra30-ictlr".
- reg : Specifies base physical address and size of the registers.
Each controller must be described separately (Tegra20 has 4 of them,
- whereas Tegra30 and later have 5"
+ whereas Tegra30 and later have 5).
- interrupt-controller : Identifies the node as an interrupt controller.
- #interrupt-cells : Specifies the number of cells needed to encode an
interrupt source. The value must be 3.
- "renesas,irqc-r8a73a4" (R-Mobile APE6)
- "renesas,irqc-r8a7743" (RZ/G1M)
- "renesas,irqc-r8a7745" (RZ/G1E)
+ - "renesas,irqc-r8a77470" (RZ/G1C)
- "renesas,irqc-r8a7790" (R-Car H2)
- "renesas,irqc-r8a7791" (R-Car M2-W)
- "renesas,irqc-r8a7792" (R-Car V2H)
- "renesas,intc-ex-r8a7796" (R-Car M3-W)
- "renesas,intc-ex-r8a77965" (R-Car M3-N)
- "renesas,intc-ex-r8a77970" (R-Car V3M)
+ - "renesas,intc-ex-r8a77980" (R-Car V3H)
- "renesas,intc-ex-r8a77995" (R-Car D3)
- #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
interrupts.txt in this directory
specifier, shall be 2
- interrupts: interrupts references to primary interrupt controller
(only needed for exti controller with multiple exti under
- same parent interrupt: st,stm32-exti and st,stm32h7-exti")
+ same parent interrupt: st,stm32-exti and st,stm32h7-exti)
Example:
- pinctrl-names : a pinctrl state named tsin%d-serial or tsin%d-parallel (where %d is tsin-num)
must be defined for each tsin child node.
- pinctrl-0 : phandle referencing pin configuration for this tsin configuration
-See: Documentation/devicetree/bindings/pinctrl/pinctrl-binding.txt
+See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
Required properties (tsin (child) node):
Following properties are require if pin control setting is required
at boot.
- pinctrl-names: A pinctrl state named "default" be defined, using the
- bindings in pinctrl/pinctrl-binding.txt.
+ bindings in pinctrl/pinctrl-bindings.txt.
- pinctrl[0...n]: Properties to contain the phandle that refer to
different nodes of pin control settings. These nodes represents
the pin control setting of state 0 to state n. Each of these
It is interfaced to host controller using SPI interface by a proprietary hardware
called PMIC wrapper or pwrap. MT6397/MT6323 MFD is a child device of pwrap.
See the following for pwarp node definitions:
-Documentation/devicetree/bindings/soc/pwrap.txt
+Documentation/devicetree/bindings/soc/mediatek/pwrap.txt
This document describes the binding for MFD device and its sub module.
- reg: The PRCM registers range
The prcm node may contain several subdevices definitions:
- - see Documentation/devicetree/clk/sunxi.txt for clock devices
- - see Documentation/devicetree/reset/allwinner,sunxi-clock-reset.txt for reset
+ - see Documentation/devicetree/bindings/clock/sunxi.txt for clock devices
+ - see Documentation/devicetree/bindings/reset/allwinner,sunxi-clock-reset.txt for reset
controller devices
- compatible : should contain one of:
"brcm,bcm7425-timers"
"brcm,bcm7429-timers"
- "brcm,bcm7435-timers and
+ "brcm,bcm7435-timers" and
"brcm,brcmstb-timers"
- reg : the timers register range
- interrupts : the interrupt line for this timer block
rest of the gpios (depending on the bus-width property) are the data lines in
no particular order. The format of the gpio specifier depends on the gpio
controller.
-(Deprecated - Refer to Documentation/devicetree/binding/pinctrl/samsung-pinctrl.txt)
+(Deprecated - Refer to Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt)
Example:
See: Documentation/devicetree/bindings/clock/clock-bindings.txt
- pinctrl-names: A pinctrl state names "default" must be defined.
- pinctrl-0: Phandle referencing pin configuration of the SDHCI controller.
- See: Documentation/devicetree/bindings/pinctrl/pinctrl-binding.txt
+ See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
Example:
- pinctrl-names: A pinctrl state names "default" must be defined.
- pinctrl-0: Phandle referencing pin configuration of the sd/emmc controller.
- See: Documentation/devicetree/bindings/pinctrl/pinctrl-binding.txt
+ See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
- reg: This must provide the host controller base address and it can also
contain the FlashSS Top register for TX/RX delay used by the driver
- compatible: For external switch chips, compatible string must be exactly one
of: "microchip,ksz9477"
-See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional
required and optional properties.
Examples:
- phy-mode: String, must be either "trgmii" or "rgmii" for port labeled
"cpu".
-See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional
required, optional properties and how the integrated switch subnodes must
be specified.
Must include one of the following:
- "fsl,fman-dtsec" for dTSEC MAC
- "fsl,fman-xgec" for XGEC MAC
- - "fsl,fman-memac for mEMAC MAC
+ - "fsl,fman-memac" for mEMAC MAC
- cell-index
Usage: required
Data cells:
Data cells are child nodes of eerpom node, bindings for which are
-documented in Documentation/bindings/nvmem/nvmem.txt
+documented in Documentation/devicetree/bindings/nvmem/nvmem.txt
Example:
HiSilicon PCIe host controller is based on the Synopsys DesignWare PCI core.
It shares common functions with the PCIe DesignWare core driver and inherits
common properties defined in
-Documentation/devicetree/bindings/pci/designware-pci.txt.
+Documentation/devicetree/bindings/pci/designware-pcie.txt.
Additional properties are described here:
Kirin PCIe host controller is based on the Synopsys DesignWare PCI core.
It shares common functions with the PCIe DesignWare core driver and
inherits common properties defined in
-Documentation/devicetree/bindings/pci/designware-pci.txt.
+Documentation/devicetree/bindings/pci/designware-pcie.txt.
Additional properties are described here:
Keystone PCI host Controller is based on the Synopsys DesignWare PCI
hardware version 3.65. It shares common functions with the PCIe DesignWare
core driver and inherits common properties defined in
-Documentation/devicetree/bindings/pci/designware-pci.txt
+Documentation/devicetree/bindings/pci/designware-pcie.txt
-Please refer to Documentation/devicetree/bindings/pci/designware-pci.txt
+Please refer to Documentation/devicetree/bindings/pci/designware-pcie.txt
for the details of DesignWare DT bindings. Additional properties are
described here as well as properties that are not applicable.
Required properties:
- compatible: "qca,ar7100-usb-phy"
- #phys-cells: should be 0
-- reset-names: "usb-phy"[, "usb-suspend-override"]
+- reset-names: "phy"[, "suspend-override"]
- resets: references to the reset controllers
Example:
usb-phy {
compatible = "qca,ar7100-usb-phy";
- reset-names = "usb-phy", "usb-suspend-override";
+ reset-names = "phy", "suspend-override";
resets = <&rst 4>, <&rst 3>;
#phy-cells = <0>;
--------------------------
Following properties are required if default setting of pins are required
at boot.
-- pinctrl-names: A pinctrl state named per <pinctrl-binding.txt>.
+- pinctrl-names: A pinctrl state named per <pinctrl-bindings.txt>.
- pinctrl[0...n]: Properties to contain the phandle for pinctrl states per
- <pinctrl-binding.txt>.
+ <pinctrl-bindings.txt>.
The pin configurations are defined as child of the pinctrl states node. Each
sub-node have following properties:
--------------------------
Following properties are required if default setting of pins are required
at boot.
-- pinctrl-names: A pinctrl state named per <pinctrl-binding.txt>.
+- pinctrl-names: A pinctrl state named per <pinctrl-bindings.txt>.
- pinctrl[0...n]: Properties to contain the phandle for pinctrl states per
- <pinctrl-binding.txt>.
+ <pinctrl-bindings.txt>.
The pin configurations are defined as child of the pinctrl states node. Each
sub-node have following properties:
--------------------------
Following properties are required if default setting of pins are required
at boot.
-- pinctrl-names: A pinctrl state named per <pinctrl-binding.txt>.
+- pinctrl-names: A pinctrl state named per <pinctrl-bindings.txt>.
- pinctrl[0...n]: Properties to contain the phandle for pinctrl states per
- <pinctrl-binding.txt>.
+ <pinctrl-bindings.txt>.
The pin configurations are defined as child of the pinctrl states node. Each
sub-node have following properties:
datasheet
- interrupts: Should contain one interrupt specifier for the GPC interrupt
- clocks: Must contain an entry for each entry in clock-names.
- See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.
+ See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
- clock-names: Must include the following entries:
- ipg
node with the label "power".
In the second example the consumer device are partitioned across two PM domains,
the first with index 0 and the second with index 1, of a power controller that
-is represented by a node with the label "power.
+is represented by a node with the label "power".
Optional properties:
- required-opps: This contains phandle to an OPP node in another device's OPP
};
For information on battery specific node, Ref:
-Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
+Documentation/devicetree/bindings/power/supply/ab8500/fg.txt
};
For information on battery specific node, Ref:
-Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
+Documentation/devicetree/bindings/power/supply/ab8500/fg.txt
};
For information on battery specific node, Ref:
-Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
+Documentation/devicetree/bindings/power/supply/ab8500/fg.txt
3. "has-tpo" Documentation/devicetree/bindings/rtc/rtc-opal.txt
4. "linux,wakeup" Documentation/devicetree/bindings/input/gpio-matrix-keypad.txt
Documentation/devicetree/bindings/mfd/tc3589x.txt
- Documentation/devicetree/bindings/input/ads7846.txt
+ Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
5. "linux,keypad-wakeup" Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
6. "linux,input-wakeup" Documentation/devicetree/bindings/input/samsung-keypad.txt
7. "nvidia,wakeup-source" Documentation/devicetree/bindings/input/nvidia,tegra20-kbc.txt
Optional properties:
- ti,enable-ext-control: This is applicable for DCDC1, DCDC2 and DCDC3.
If DCDCs are externally controlled then this property should be there.
-- "dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
+- dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
If DCDCs are externally controlled and if it is from GPIO then GPIO
number should be provided. If it is externally controlled and no GPIO
entry then driver will just configure this rails as external control
controller binding usage.
Required properties:
-- compatible: Should be st,stih407-softreset";
+- compatible: Should be "st,stih407-softreset";
- #reset-cells: 1, see below
example:
See: Documentation/devicetree/bindings/clock/clock-bindings.txt
- pinctrl-names: A pinctrl state names "default" must be defined.
- pinctrl-0: Phandle referencing pin configuration of the UART peripheral.
- See: Documentation/devicetree/bindings/pinctrl/pinctrl-binding.txt
+ See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
Optional properties:
- cts-gpios: CTS pin for UART
Optional property:
- clock-frequency: Desired I2C bus clock frequency in Hz.
- When missing default to 400000Hz.
+ When missing default to 100000Hz.
Child nodes should conform to I2C bus binding as described in i2c.txt.
Board connectors:
* Headset Mic
- * Secondary Mic",
+ * Secondary Mic
* DMIC
* Ext Spk
"Digital Mic3"
Audio pins and MicBias on WCD9335 Codec:
- "MIC_BIAS1
+ "MIC_BIAS1"
"MIC_BIAS2"
"MIC_BIAS3"
"MIC_BIAS4"
See Documentation/devicetree/bindings/dma/stm32-dma.txt.
- dma-names: Identifier for each DMA request line. Must be "tx" and "rx".
- pinctrl-names: should contain only value "default"
- - pinctrl-0: see Documentation/devicetree/bindings/pinctrl/pinctrl-stm32.txt
+ - pinctrl-0: see Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
Optional properties:
- resets: Reference to a reset controller asserting the reset controller
"tx": if sai sub-block is configured as playback DAI
"rx": if sai sub-block is configured as capture DAI
- pinctrl-names: should contain only value "default"
- - pinctrl-0: see Documentation/devicetree/bindings/pinctrl/pinctrl-stm32.txt
+ - pinctrl-0: see Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
SAI subnodes Optional properties:
- st,sync: specify synchronization mode.
- clocks : Must contain an entry for each name in clock-names
See ../clk/*
- pinctrl-names : Uses "default", can use "sleep" if provided
- See ../pinctrl/pinctrl-binding.txt
+ See ../pinctrl/pinctrl-bindings.txt
Optional properties:
- cs-gpios : List of GPIO chip selects
-Mediatek MT6577, MT6572 and MT6589 Timers
----------------------------------------
+Mediatek Timers
+---------------
+
+Mediatek SoCs have two different timers on different platforms,
+- GPT (General Purpose Timer)
+- SYST (System Timer)
+
+The proper timer will be selected automatically by driver.
Required properties:
- compatible should contain:
- * "mediatek,mt2701-timer" for MT2701 compatible timers
- * "mediatek,mt6580-timer" for MT6580 compatible timers
- * "mediatek,mt6589-timer" for MT6589 compatible timers
- * "mediatek,mt7623-timer" for MT7623 compatible timers
- * "mediatek,mt8127-timer" for MT8127 compatible timers
- * "mediatek,mt8135-timer" for MT8135 compatible timers
- * "mediatek,mt8173-timer" for MT8173 compatible timers
- * "mediatek,mt6577-timer" for MT6577 and all above compatible timers
-- reg: Should contain location and length for timers register.
-- clocks: Clocks driving the timer hardware. This list should include two
- clocks. The order is system clock and as second clock the RTC clock.
+ * "mediatek,mt2701-timer" for MT2701 compatible timers (GPT)
+ * "mediatek,mt6580-timer" for MT6580 compatible timers (GPT)
+ * "mediatek,mt6589-timer" for MT6589 compatible timers (GPT)
+ * "mediatek,mt7623-timer" for MT7623 compatible timers (GPT)
+ * "mediatek,mt8127-timer" for MT8127 compatible timers (GPT)
+ * "mediatek,mt8135-timer" for MT8135 compatible timers (GPT)
+ * "mediatek,mt8173-timer" for MT8173 compatible timers (GPT)
+ * "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT)
+ * "mediatek,mt6765-timer" for MT6765 compatible timers (SYST)
+- reg: Should contain location and length for timer register.
+- clocks: Should contain system clock.
Examples:
compatible = "mediatek,mt6577-timer";
reg = <0x10008000 0x80>;
interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>;
- clocks = <&system_clk>, <&rtc_clk>;
+ clocks = <&system_clk>;
};
the node is not important. The content of the node is defined in dwc3.txt.
Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/rockchip,dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY
+Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY
Example device nodes:
Examples:
- onewire@0 {
+ onewire {
compatible = "w1-gpio";
gpios = <&gpio 126 0>, <&gpio 105 0>;
};
enum gpiod_flags flags)
For a more detailed description of the con_id parameter in the DeviceTree case
-see Documentation/gpio/board.txt
+see Documentation/driver-api/gpio/board.rst
The flags parameter is used to optionally specify a direction and initial value
for the GPIO. Values can be:
Device Drivers DMA Management
-----------------------------
-.. kernel-doc:: drivers/base/dma-coherent.c
+.. kernel-doc:: kernel/dma/coherent.c
:export:
-.. kernel-doc:: drivers/base/dma-mapping.c
+.. kernel-doc:: kernel/dma/mapping.c
:export:
Device drivers PnP support
#
# Feature name: stackprotector
-# Kconfig: HAVE_CC_STACKPROTECTOR
+# Kconfig: HAVE_STACKPROTECTOR
# description: arch supports compiler driven stack overflow protection
#
-----------------------
#
# Architecture requirements
#
-# * arm64
+# * arm/arm64
#
-# Rely on eret context synchronization when returning from IPI handler, and
-# when returning to user-space.
+# Rely on implicit context synchronization as a result of exception return
+# when returning from IPI handler, and when returning to user-space.
#
# * x86
#
-----------------------
| alpha: | TODO |
| arc: | TODO |
- | arm: | TODO |
+ | arm: | ok |
| arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
- umode_t create_mode, int *opened);
+ umode_t create_mode);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
locking rules:
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
};
locking rules:
- All except for ->poll_mask may block.
+ All may block.
->llseek() locking has moved from llseek to the individual llseek
implementations. If your fs is not using generic_file_llseek, you
the lease within the individual filesystem to record the result of the
operation
-->poll_mask can be called with or without the waitqueue lock for the waitqueue
-returned from ->get_poll_head.
-
--------------------------- dquot_operations -------------------------------
prototypes:
int (*write_dquot) (struct dquot *);
address its connection to the monitor originates from.
wsize=X
- Specify the maximum write size in bytes. By default there is no
- maximum. Ceph will normally size writes based on the file stripe
- size.
+ Specify the maximum write size in bytes. Default: 16 MB.
rsize=X
- Specify the maximum read size in bytes. Default: 64 MB.
+ Specify the maximum read size in bytes. Default: 16 MB.
rasize=X
- Specify the maximum readahead. Default: 8 MB.
+ Specify the maximum readahead size in bytes. Default: 8 MB.
mount_timeout=X
Specify the timeout value for mount (in seconds), in the case
Scott Lovenberg
Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features)
Aurelien Aptel (for DFS SMB3 work and some key bug fixes)
-Ronnie Sahlberg (for SMB3 xattr work and bug fixes)
+Ronnie Sahlberg (for SMB3 xattr work, bug fixes, and lots of great work on compounding)
Shirish Pargaonkar (for many ACL patches over the years)
Sachin Prabhu (many bug fixes, including for reconnect, copy offload and security)
+Paulo Alcantara
+Long Li (some great work on RDMA, SMB Direct)
Test case and Bug Report contributors
bugs in error paths. Valuable suggestions also have come from Al Viro
and Dave Miller.
-And thanks to the IBM LTC and Power test teams and SuSE testers for
-finding multiple bugs during excellent stress test runs.
+And thanks to the IBM LTC and Power test teams and SuSE and Citrix and RedHat testers for finding multiple bugs during excellent stress test runs.
+See https://wiki.samba.org/index.php/LinuxCIFSKernel for
+more current information.
+
Version 1.62
------------
Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened
a) SMB3 (and SMB3.02) missing optional features:
- multichannel (started), integration with RDMA
- - directory leases (improved metadata caching)
- - T10 copy offload (copy chunk, and "Duplicate Extents" ioctl
+ - directory leases (improved metadata caching), started (root dir only)
+ - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
currently the only two server side copy mechanisms supported)
b) improved sparse file support
c) Directory entry caching relies on a 1 second timer, rather than
-using Directory Leases
+using Directory Leases, currently only the root file handle is cached longer
d) quota support (needs minor kernel change since quota calls
to make it to network filesystems or deviceless filesystems)
exists. Also better integration with winbind for resolving SID owners
k) Add tools to take advantage of more smb3 specific ioctls and features
+(passthrough ioctl/fsctl for sending various SMB3 fsctls to the server
+is in progress)
l) encrypted file support
secure) CIFS dialect can be disabled in environments that don't need it
and simplify the code.
-u) Finish up SMB3.1.1 dialect support
-
-v) POSIX Extensions for SMB3.1.1
+v) POSIX Extensions for SMB3.1.1 (started, create and mkdir support added
+so far).
KNOWN BUGS
====================================
1) check out max path names and max path name components against various server
types. Try nested symlinks (8 deep). Return max path name in stat -f information
-2) Improve xfstest's cifs enablement and adapt xfstests where needed to test
-cifs better
+2) Improve xfstest's cifs/smb3 enablement and adapt xfstests where needed to test
+cifs/smb3 better
3) Additional performance testing and optimization using iozone and similar -
there are some easy changes that can be done to parallelize sequential writes,
.. kernel-doc:: fs/block_dev.c
:export:
+.. kernel-doc:: fs/anon_inodes.c
+ :export:
+
+.. kernel-doc:: fs/attr.c
+ :export:
+
+.. kernel-doc:: fs/d_path.c
+ :export:
+
+.. kernel-doc:: fs/dax.c
+ :export:
+
+.. kernel-doc:: fs/direct-io.c
+ :export:
+
+.. kernel-doc:: fs/file_table.c
+ :export:
+
+.. kernel-doc:: fs/libfs.c
+ :export:
+
+.. kernel-doc:: fs/posix_acl.c
+ :export:
+
+.. kernel-doc:: fs/stat.c
+ :export:
+
+.. kernel-doc:: fs/sync.c
+ :export:
+
+.. kernel-doc:: fs/xattr.c
+ :export:
+
The proc filesystem
===================
dentry separately, and it now has request_mask and query_flags arguments
to specify the fields and sync type requested by statx. Filesystems not
supporting any statx-specific features may ignore the new arguments.
+--
+[mandatory]
+ ->atomic_open() calling conventions have changed. Gone is int *opened,
+ along with FILE_OPENED/FILE_CREATED. In place of those we have
+ FMODE_OPENED/FMODE_CREATED, set in file->f_mode. Additionally, return
+ value for 'called finish_no_open(), open it yourself' case has become
+ 0, not 1. Since finish_no_open() itself is returning 0 now, that part
+ does not need any changes in ->atomic_open() instances.
+--
+[mandatory]
+ alloc_file() has become static now; two wrappers are to be used instead.
+ alloc_file_pseudo(inode, vfsmount, name, flags, ops) is for the cases
+ when dentry needs to be created; that's the majority of old alloc_file()
+ users. Calling conventions: on success a reference to new struct file
+ is returned and callers reference to inode is subsumed by that. On
+ failure, ERR_PTR() is returned and no caller's references are affected,
+ so the caller needs to drop the inode reference it held.
+ alloc_file_clone(file, flags, ops) does not affect any caller's references.
+ On success you get a new struct file sharing the mount/dentry with the
+ original, on failure - ERR_PTR().
ssize_t (*listxattr) (struct dentry *, char *, size_t);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
- unsigned open_flag, umode_t create_mode, int *opened);
+ unsigned open_flag, umode_t create_mode);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
};
atomic_open: called on the last component of an open. Using this optional
method the filesystem can look up, possibly create and open the file in
- one atomic operation. If it cannot perform this (e.g. the file type
- turned out to be wrong) it may signal this by returning 1 instead of
- usual 0 or -ve . This method is only called if the last component is
- negative or needs lookup. Cached positive dentries are still handled by
- f_op->open(). If the file was created, the FILE_CREATED flag should be
- set in "opened". In case of O_EXCL the method must only succeed if the
- file didn't exist and hence FILE_CREATED shall always be set on success.
+ one atomic operation. If it wants to leave actual opening to the
+ caller (e.g. if the file turned out to be a symlink, device, or just
+ something filesystem won't do atomic open for), it may signal this by
+ returning finish_no_open(file, dentry). This method is only called if
+ the last component is negative or needs lookup. Cached positive dentries
+ are still handled by f_op->open(). If the file was created,
+ FMODE_CREATED flag should be set in file->f_mode. In case of O_EXCL
+ the method must only succeed if the file didn't exist and hence FMODE_CREATED
+ shall always be set on success.
tmpfile: called in the end of O_TMPFILE open(). Optional, equivalent to
atomically creating, opening and unlinking a file in given directory.
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
activity on this file and (optionally) go to sleep until there
is activity. Called by the select(2) and poll(2) system calls
- get_poll_head: Returns the struct wait_queue_head that callers can
- wait on. Callers need to check the returned events using ->poll_mask
- once woken. Can return NULL to indicate polling is not supported,
- or any error code using the ERR_PTR convention to indicate that a
- grave error occured and ->poll_mask shall not be called.
-
- poll_mask: return the mask of EPOLL* values describing the file descriptor
- state. Called either before going to sleep on the waitqueue returned by
- get_poll_head, or after it has been woken. If ->get_poll_head and
- ->poll_mask are implemented ->poll does not need to be implement.
-
unlocked_ioctl: called by the ioctl(2) system call.
compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
The shunt value in micro-ohms can be set via platform data or device tree at
compile-time or via the shunt_resistor attribute in sysfs at run-time. Please
-refer to the Documentation/devicetree/bindings/i2c/ina2xx.txt for bindings
+refer to the Documentation/devicetree/bindings/hwmon/ina2xx.txt for bindings
if the device tree is used.
Additionally ina226 supports update_interval attribute as described in
Prefixes: 'max34446'
Addresses scanned: -
Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
+ * Maxim MAX34451
+ PMBus 16-Channel V/I Monitor and 12-Channel Sequencer/Marginer
+ Prefixes: 'max34451'
+ Addresses scanned: -
+ Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34451.pdf
* Maxim MAX34460
PMBus 12-Channel Voltage Monitor & Sequencer
Prefix: 'max34460'
This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
-It also supports the MAX34460 and MAX34461 PMBus Voltage Monitor & Sequencers.
-The MAX34460 supports 12 voltage channels, and the MAX34461 supports 16 voltage
-channels.
+It also supports the MAX34451, MAX34460, and MAX34461 PMBus Voltage Monitor &
+Sequencers. The MAX34451 supports monitoring voltage or current of 12 channels
+based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
+supports 16 voltage channels.
The driver is a client driver to the core PMBus driver. Please see
Documentation/hwmon/pmbus for details on PMBus client drivers.
curr[1-6]_crit Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
curr[1-6]_max_alarm Current high alarm. From IOUT_OC_WARNING status.
curr[1-6]_crit_alarm Current critical high alarm. From IOUT_OC_FAULT status.
-curr[1-4]_average Historical average current (MAX34446 only).
+curr[1-4]_average Historical average current (MAX34446/34451 only).
curr[1-6]_highest Historical maximum current.
curr[1-6]_reset_history Write any value to reset history.
temp7 and temp8 attributes only exist for MAX34440.
MAX34446 only supports temp[1-3].
+MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on input pins)
+and temp[1-5].
MAX34460 supports attribute groups in[1-12] and temp[1-5].
MAX34461 supports attribute groups in[1-16] and temp[1-5].
--- /dev/null
+Kernel driver mlxreg-fan
+========================
+
+Provides FAN control for the next Mellanox systems:
+QMB700, equipped with 40x200GbE InfiniBand ports;
+MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
+MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
+MSN3800, equipped with 64x1000GbE Ethernet ports;
+These are the Top of the Rack systems, equipped with Mellanox switch
+board with Mellanox Quantum or Spectrume-2 devices.
+FAN controller is implemented by the programmable device logic.
+
+The default registers offsets set within the programmable device is as
+following:
+- pwm1 0xe3
+- fan1 (tacho1) 0xe4
+- fan2 (tacho2) 0xe5
+- fan3 (tacho3) 0xe6
+- fan4 (tacho4) 0xe7
+- fan5 (tacho5) 0xe8
+- fan6 (tacho6) 0xe9
+- fan7 (tacho7) 0xea
+- fan8 (tacho8) 0xeb
+- fan9 (tacho9) 0xec
+- fan10 (tacho10) 0xed
+- fan11 (tacho11) 0xee
+- fan12 (tacho12) 0xef
+This setup can be re-programmed with other registers.
+
+Author: Vadim Pasternak <vadimp@mellanox.com>
+
+Description
+-----------
+
+The driver implements a simple interface for driving a fan connected to
+a PWM output and tachometer inputs.
+This driver obtains PWM and tachometers registers location according to
+the system configuration and creates FAN/PWM hwmon objects and a cooling
+device. PWM and tachometers are sensed through the on-board programmable
+device, which exports its register map. This device could be attached to
+any bus type, for which register mapping is supported.
+Single instance is created with one PWM control, up to 12 tachometers and
+one cooling device. It could be as many instances as programmable device
+supports.
+The driver exposes the fan to the user space through the hwmon's and
+thermal's sysfs interfaces.
+
+/sys files in hwmon subsystem
+-----------------------------
+
+fan[1-12]_fault - RO files for tachometers TACH1-TACH12 fault indication
+fan[1-12]_input - RO files for tachometers TACH1-TACH12 input (in RPM)
+pwm1 - RW file for fan[1-12] target duty cycle (0..255)
+
+/sys files in thermal subsystem
+-------------------------------
+
+cur_state - RW file for current cooling state of the cooling device
+ (0..max_state)
+max_state - RO file for maximum cooling state of the cooling device
--- /dev/null
+Kernel driver npcm750-pwm-fan
+=============================
+
+Supported chips:
+ NUVOTON NPCM750/730/715/705
+
+Authors:
+ <tomer.maimon@nuvoton.com>
+
+Description:
+------------
+This driver implements support for NUVOTON NPCM7XX PWM and Fan Tacho
+controller. The PWM controller supports up to 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input ro provide current fan rotation value in RPM as reported
+ by the fan to the device.
+
+pwmX rw get or set PWM fan control value. This is an integer
+ value between 0(off) and 255(full speed).
user-space.
RO
+in[0-*]_enable
+ Enable or disable the sensors.
+ When disabled the sensor read will return -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
cpu[0-*]_vid CPU core reference voltage.
Unit: millivolt
RO
In all other cases, the label is provided by user-space.
RO
+fan[1-*]_enable
+ Enable or disable the sensors.
+ When disabled the sensor read will return -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
Also see the Alarms section for status flags associated with fans.
Reset temp_lowest and temp_highest for all sensors
WO
+temp[1-*]_enable
+ Enable or disable the sensors.
+ When disabled the sensor read will return -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
Some chips measure temperature using external thermistors and an ADC, and
report the temperature measurement as a voltage. Converting this voltage
back to a temperature (or the other way around for limits) requires
Reset currX_lowest and currX_highest for all sensors
WO
+curr[1-*]_enable
+ Enable or disable the sensors.
+ When disabled the sensor read will return -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
Also see the Alarms section for status flags associated with currents.
*********
Unit: microWatt
RW
+power[1-*]_enable Enable or disable the sensors.
+ When disabled the sensor read will return
+ -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
Also see the Alarms section for status flags associated with power readings.
**********
Unit: microJoule
RO
+energy[1-*]_enable Enable or disable the sensors.
+ When disabled the sensor read will return
+ -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
************
* Humidity *
RO
+humidity[1-*]_enable Enable or disable the sensors
+ When disabled the sensor read will return
+ -ENODATA.
+ 1: Enable
+ 0: Disable
+ RW
+
**********
* Alarms *
**********
--------------------------------------------------
Additional options used for $(LD) when linking modules.
+KBUILD_KCONFIG
+--------------------------------------------------
+Set the top-level Kconfig file to the value of this environment
+variable. The default name is "Kconfig".
+
KBUILD_VERBOSE
--------------------------------------------------
Set the kbuild verbosity. Can be assigned same values as "V=...".
directory name found in the arch/ directory.
But some architectures such as x86 and sparc have aliases.
x86: i386 for 32 bit, x86_64 for 64 bit
-sparc: sparc for 32 bit, sparc64 for 64 bit
+sh: sh for 32 bit, sh64 for 64 bit
+sparc: sparc32 for 32 bit, sparc64 for 64 bit
CROSS_COMPILE
--------------------------------------------------
the default option --strip-debug will be used. Otherwise,
INSTALL_MOD_STRIP value will be used as the options to the strip command.
-INSTALL_FW_PATH
---------------------------------------------------
-INSTALL_FW_PATH specifies where to install the firmware blobs.
-The default value is:
-
- $(INSTALL_MOD_PATH)/lib/firmware
-
-The value can be overridden in which case the default value is ignored.
-
INSTALL_HDR_PATH
--------------------------------------------------
INSTALL_HDR_PATH specifies where to install user space headers when
to use it. It should be placed at the top of the configuration, before any
other statement.
+'#' Kconfig source file comment:
+
+An unquoted '#' character anywhere in a source file line indicates
+the beginning of a source file comment. The remainder of that line
+is a comment.
+
Kconfig hints
-------------
Use "make help" to list all of the possible configuration targets.
-The xconfig ('qconf') and menuconfig ('mconf') programs also
-have embedded help text. Be sure to check it for navigation,
-search, and other general help text.
+The xconfig ('qconf'), menuconfig ('mconf'), and nconfig ('nconf')
+programs also have embedded help text. Be sure to check that for
+navigation, search, and other general help text.
======================================================================
General
for you, so you may find that you need to see what NEW kernel
symbols have been introduced.
-To see a list of new config symbols when using "make oldconfig", use
+To see a list of new config symbols, use
cp user/some/old.config .config
make listnewconfig
and the config program will list any new symbols, one per line.
+Alternatively, you can use the brute force method:
+
+ make oldconfig
scripts/diffconfig .config.old .config | less
______________________________________________________________________
This lists all config symbols that contain "hotplug",
e.g., HOTPLUG_CPU, MEMORY_HOTPLUG.
- For search help, enter / followed TAB-TAB-TAB (to highlight
+ For search help, enter / followed by TAB-TAB (to highlight
<Help>) and Enter. This will tell you that you can also use
regular expressions (regexes) in the search string, so if you
are not interested in MEMORY_HOTPLUG, you could try
make MENUCONFIG_MODE=single_menu menuconfig
+======================================================================
+nconfig
+--------------------------------------------------
+
+nconfig is an alternate text-based configurator. It lists function
+keys across the bottom of the terminal (window) that execute commands.
+You can also just use the corresponding numeric key to execute the
+commands unless you are in a data entry window. E.g., instead of F6
+for Save, you can just press 6.
+
+Use F1 for Global help or F3 for the Short help menu.
+
+Searching in nconfig:
+
+ You can search either in the menu entry "prompt" strings
+ or in the configuration symbols.
+
+ Use / to begin a search through the menu entries. This does
+ not support regular expressions. Use <Down> or <Up> for
+ Next hit and Previous hit, respectively. Use <Esc> to
+ terminate the search mode.
+
+ F8 (SymSearch) searches the configuration symbols for the
+ given string or regular expression (regex).
+
+NCONFIG_MODE
+--------------------------------------------------
+This mode shows all sub-menus in one large tree.
+
+Example:
+ make NCONFIG_MODE=single_menu nconfig
+
+
======================================================================
xconfig
--------------------------------------------------
Searching in gconfig:
- None (gconfig isn't maintained as well as xconfig or menuconfig);
- however, gconfig does have a few more viewing choices than
- xconfig does.
+ There is no search command in gconfig. However, gconfig does
+ have several different viewing choices, modes, and options.
###
"post_handler," if any, that is associated with the kprobe.
Execution then continues with the instruction following the probepoint.
+Changing Execution Path
+-----------------------
+
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
+
Return Probes
-------------
tweak the kernel's execution path, you need to suppress optimization,
using one of the following techniques:
-- Specify an empty function for the kprobe's post_handler or break_handler.
+- Specify an empty function for the kprobe's post_handler.
or
the bad probe, are safely unregistered before the register_*probes
function returns.
-- kps/rps/jps: an array of pointers to ``*probe`` data structures
+- kps/rps: an array of pointers to ``*probe`` data structures
- num: the number of the array entries.
.. note::
Kprobes does not use mutexes or allocate memory except during
registration and unregistration.
-Probe handlers are run with preemption disabled. Depending on the
-architecture and optimization state, handlers may also run with
-interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-handlers run without interrupt disabled on x86/x86-64). In any case,
-your handler should not yield the CPU (e.g., by attempting to acquire
-a semaphore).
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state. (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64). In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
Since a return probe is implemented by replacing the return
address with the trampoline's address, stack backtraces and calls
See following documents:
- - Documentation/trace/kprobetrace.txt
- - Documentation/trace/events.txt
+ - Documentation/trace/kprobetrace.rst
+ - Documentation/trace/events.rst
- tools/perf/Documentation/perf-probe.txt
that will create a signed tag called ``char-misc-4.15-rc1`` based on the
last commit in the ``char-misc-next`` branch, and sign it with your gpg key
-(see :ref:`Documentation/maintainer/configure_git.rst <configuregit>`).
+(see :ref:`Documentation/maintainer/configure-git.rst <configuregit>`).
Linus will only accept pull requests based on a signed tag. Other
maintainers may differ.
event_indicated = 1;
wake_up_process(event_daemon);
-A write memory barrier is implied by wake_up() and co. if and only if they
-wake something up. The barrier occurs before the task state is cleared, and so
-sits between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+A general memory barrier is executed by wake_up() if it wakes something up.
+If it doesn't wake anything up then a memory barrier may or may not be
+executed; you must not rely on it. The barrier occurs before the task state
+is accessed, in particular, it sits between the STORE to indicate the event
+and the STORE to set TASK_RUNNING:
- CPU 1 CPU 2
+ CPU 1 (Sleeper) CPU 2 (Waker)
=============================== ===============================
set_current_state(); STORE event_indicated
smp_store_mb(); wake_up();
- STORE current->state <write barrier>
- <general barrier> STORE current->state
- LOAD event_indicated
+ STORE current->state ...
+ <general barrier> <general barrier>
+ LOAD event_indicated if ((LOAD task->state) & TASK_NORMAL)
+ STORE task->state
-To repeat, this write memory barrier is present if and only if something
-is actually awakened. To see this, consider the following sequence of
-events, where X and Y are both initially zero:
+where "task" is the thread being woken up and it equals CPU 1's "current".
+
+To repeat, a general memory barrier is guaranteed to be executed by wake_up()
+if something is actually awakened, but otherwise there is no such guarantee.
+To see this, consider the following sequence of events, where X and Y are both
+initially zero:
CPU 1 CPU 2
=============================== ===============================
- X = 1; STORE event_indicated
+ X = 1; Y = 1;
smp_mb(); wake_up();
- Y = 1; wait_event(wq, Y == 1);
- wake_up(); load from Y sees 1, no memory barrier
- load from X might see 0
+ LOAD Y LOAD X
+
+If a wakeup does occur, one (at least) of the two loads must see 1. If, on
+the other hand, a wakeup does not occur, both loads might see 0.
-In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
-to see 1.
+wake_up_process() always executes a general memory barrier. The barrier again
+occurs before the task state is accessed. In particular, if the wake_up() in
+the previous snippet were replaced by a call to wake_up_process() then one of
+the two loads would be guaranteed to see 1.
The available waker functions include:
wake_up_poll();
wake_up_process();
+In terms of memory ordering, these functions all provide the same guarantees of
+a wake_up() (or stronger).
[!] Note that the memory barriers implied by the sleeper and the waker do _not_
order multiple stores before the wake-up with respect to loads of those stored
To configure the interval between learning packet transmits:
# echo 12 > /sys/class/net/bond0/bonding/lp_interval
- NOTE: the lp_inteval is the number of seconds between instances where
+ NOTE: the lp_interval is the number of seconds between instances where
the bonding driver sends learning packets to each slaves peer switch. The
default interval is 1 second.
transmission and reception of media dependent frames. Due to the
arbitration on the CAN bus the transmission of a low prio CAN-ID
may be delayed by the reception of a high prio CAN frame. To
-reflect the correct [*]_ traffic on the node the loopback of the sent
+reflect the correct [#f1]_ traffic on the node the loopback of the sent
data has to be performed right after a successful transmission. If
the CAN network interface is not capable of performing the loopback for
some reason the SocketCAN core can do this task as a fallback solution.
the RT-SocketCAN group the loopback optionally may be disabled for each
separate socket. See sockopts from the CAN RAW sockets in :ref:`socketcan-raw-sockets`.
-.. [*] you really like to have this when you're running analyser
+.. [#f1] you really like to have this when you're running analyser
tools like 'candump' or 'cansniffer' on the (same) node.
.. include:: <isonum.txt>
+=========================================================
DPAA2 (Data Path Acceleration Architecture Gen2) Overview
=========================================================
+==============================================================
Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
==============================================================
The default value for each parameter is generally the recommended setting,
unless otherwise noted.
-Rx Descriptors: Number of receive descriptors. A receive descriptor is a data
+Rx Descriptors:
+ Number of receive descriptors. A receive descriptor is a data
structure that describes a receive buffer and its attributes to the network
controller. The data in the descriptor is used by the controller to write
data from the controller to host memory. In the 3.x.x driver the valid range
for this parameter is 64-256. The default value is 256. This parameter can be
changed using the command::
- ethtool -G eth? rx n
+ ethtool -G eth? rx n
Where n is the number of desired Rx descriptors.
-Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data
+Tx Descriptors:
+ Number of transmit descriptors. A transmit descriptor is a data
structure that describes a transmit buffer and its attributes to the network
controller. The data in the descriptor is used by the controller to read
data from the host memory to the controller. In the 3.x.x driver the valid
range for this parameter is 64-256. The default value is 128. This parameter
can be changed using the command::
- ethtool -G eth? tx n
+ ethtool -G eth? tx n
Where n is the number of desired Tx descriptors.
-Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by
+Speed/Duplex:
+ The driver auto-negotiates the link speed and duplex settings by
default. The ethtool utility can be used as follows to force speed/duplex.::
- ethtool -s eth? autoneg off speed {10|100} duplex {full|half}
+ ethtool -s eth? autoneg off speed {10|100} duplex {full|half}
NOTE: setting the speed/duplex to incorrect values will cause the link to
fail.
-Event Log Message Level: The driver uses the message level flag to log events
+Event Log Message Level:
+ The driver uses the message level flag to log events
to syslog. The message level can be set at driver load time. It can also be
set using the command::
- ethtool -s eth? msglvl n
+ ethtool -s eth? msglvl n
Additional Configurations
=========================
- Configuring the Driver on Different Distributions
- -------------------------------------------------
+Configuring the Driver on Different Distributions
+-------------------------------------------------
- Configuring a network driver to load properly when the system is started is
- distribution dependent. Typically, the configuration process involves adding
- an alias line to /etc/modprobe.d/*.conf as well as editing other system
- startup scripts and/or configuration files. Many popular Linux
- distributions ship with tools to make these changes for you. To learn the
- proper way to configure a network device for your system, refer to your
- distribution documentation. If during this process you are asked for the
- driver or module name, the name for the Linux Base Driver for the Intel
- PRO/100 Family of Adapters is e100.
+Configuring a network driver to load properly when the system is started
+is distribution dependent. Typically, the configuration process involves
+adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other
+system startup scripts and/or configuration files. Many popular Linux
+distributions ship with tools to make these changes for you. To learn
+the proper way to configure a network device for your system, refer to
+your distribution documentation. If during this process you are asked
+for the driver or module name, the name for the Linux Base Driver for
+the Intel PRO/100 Family of Adapters is e100.
- As an example, if you install the e100 driver for two PRO/100 adapters
- (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/
+As an example, if you install the e100 driver for two PRO/100 adapters
+(eth0 and eth1), add the following to a configuration file in
+/etc/modprobe.d/::
alias eth0 e100
alias eth1 e100
- Viewing Link Messages
- ---------------------
- In order to see link messages and other Intel driver information on your
- console, you must set the dmesg level up to six. This can be done by
- entering the following on the command line before loading the e100 driver::
+Viewing Link Messages
+---------------------
+
+In order to see link messages and other Intel driver information on your
+console, you must set the dmesg level up to six. This can be done by
+entering the following on the command line before loading the e100
+driver::
dmesg -n 6
- If you wish to see all messages issued by the driver, including debug
- messages, set the dmesg level to eight.
+If you wish to see all messages issued by the driver, including debug
+messages, set the dmesg level to eight.
- NOTE: This setting is not saved across reboots.
+NOTE: This setting is not saved across reboots.
+ethtool
+-------
- ethtool
- -------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The ethtool
+version 1.6 or later is required for this functionality.
- The driver utilizes the ethtool interface for driver configuration and
- diagnostics, as well as displaying statistical information. The ethtool
- version 1.6 or later is required for this functionality.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
- The latest release of ethtool can be found from
- https://www.kernel.org/pub/software/network/ethtool/
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is provided through the ethtool* utility. For instructions on
+enabling WoL with ethtool, refer to the ethtool man page. WoL will be
+enabled on the system during the next shut down or reboot. For this
+driver version, in order to enable WoL, the e100 driver must be loaded
+when shutting down or rebooting the system.
- Enabling Wake on LAN* (WoL)
- ---------------------------
- WoL is provided through the ethtool* utility. For instructions on enabling
- WoL with ethtool, refer to the ethtool man page.
+NAPI
+----
- WoL will be enabled on the system during the next shut down or reboot. For
- this driver version, in order to enable WoL, the e100 driver must be
- loaded when shutting down or rebooting the system.
+NAPI (Rx polling mode) is supported in the e100 driver.
- NAPI
- ----
+See https://wiki.linuxfoundation.org/networking/napi for more
+information on NAPI.
- NAPI (Rx polling mode) is supported in the e100 driver.
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
- See https://wiki.linuxfoundation.org/networking/napi for more information
- on NAPI.
+Due to the default ARP behavior on Linux, it is not possible to have one
+system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected. All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
- Multiple Interfaces on Same Ethernet Broadcast Network
- ------------------------------------------------------
+If you have multiple interfaces in a server, either turn on ARP
+filtering by
- Due to the default ARP behavior on Linux, it is not possible to have
- one system on two IP networks in the same Ethernet broadcast domain
- (non-partitioned switch) behave as expected. All Ethernet interfaces
- will respond to IP traffic for any IP address assigned to the system.
- This results in unbalanced receive traffic.
+(1) entering::
- If you have multiple interfaces in a server, either turn on ARP
- filtering by
+ echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
- (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
- (this only works if your kernel's version is higher than 2.4.5), or
+ (this only works if your kernel's version is higher than 2.4.5), or
- (2) installing the interfaces in separate broadcast domains (either
- in different switches or in a switch partitioned to VLANs).
+(2) installing the interfaces in separate broadcast domains (either
+ in different switches or in a switch partitioned to VLANs).
Support
+===========================================================
Linux* Base Driver for Intel(R) Ethernet Network Connection
===========================================================
The default value for each parameter is generally the recommended setting,
unless otherwise noted.
-NOTES: For more information about the AutoNeg, Duplex, and Speed
+NOTES:
+ For more information about the AutoNeg, Duplex, and Speed
parameters, see the "Speed and Duplex Configuration" section in
this document.
AutoNeg
-------
+
(Supported only on adapters with copper connections)
-Valid Range: 0x01-0x0F, 0x20-0x2F
-Default Value: 0x2F
+
+:Valid Range: 0x01-0x0F, 0x20-0x2F
+:Default Value: 0x2F
This parameter is a bit-mask that specifies the speed and duplex settings
advertised by the adapter. When this parameter is used, the Speed and
Duplex parameters must not be specified.
-NOTE: Refer to the Speed and Duplex section of this readme for more
+NOTE:
+ Refer to the Speed and Duplex section of this readme for more
information on the AutoNeg parameter.
Duplex
------
+
(Supported only on adapters with copper connections)
-Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full)
-Default Value: 0
+
+:Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full)
+:Default Value: 0
This defines the direction in which data is allowed to flow. Can be
either one or two-directional. If both Duplex and the link partner are
FlowControl
-----------
-Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
-Default Value: Reads flow control settings from the EEPROM
+
+:Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
+:Default Value: Reads flow control settings from the EEPROM
This parameter controls the automatic generation(Tx) and response(Rx)
to Ethernet PAUSE frames.
InterruptThrottleRate
---------------------
+
(not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range: 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
- 4=simplified balancing)
-Default Value: 3
+
+:Valid Range:
+ 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+ 4=simplified balancing)
+:Default Value: 3
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to the
and may improve small packet latency, but is generally not suitable
for bulk throughput traffic.
-NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+NOTE:
+ InterruptThrottleRate takes precedence over the TxAbsIntDelay and
RxAbsIntDelay parameters. In other words, minimizing the receive
and/or transmit absolute delays does not force the controller to
generate more interrupts than what the Interrupt Throttle Rate
allows.
-CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection
+CAUTION:
+ If you are using the Intel(R) PRO/1000 CT Network Connection
(controller 82547), setting InterruptThrottleRate to a value
greater than 75,000, may hang (stop transmitting) adapters
under certain network conditions. If this occurs a NETDEV
hang, ensure that InterruptThrottleRate is set no greater
than 75,000 and is not set to 0.
-NOTE: When e1000 is loaded with default settings and multiple adapters
+NOTE:
+ When e1000 is loaded with default settings and multiple adapters
are in use simultaneously, the CPU utilization may increase non-
linearly. In order to limit the CPU utilization without impacting
the overall throughput, we recommend that you load the driver as
RxDescriptors
-------------
-Valid Range: 48-256 for 82542 and 82543-based adapters
- 48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+ - 48-256 for 82542 and 82543-based adapters
+ - 48-4096 for all other supported adapters
+:Default Value: 256
This value specifies the number of receive buffer descriptors allocated
by the driver. Increasing this value allows the driver to buffer more
descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
on the MTU setting. The maximum MTU size is 16110.
-NOTE: MTU designates the frame size. It only needs to be set for Jumbo
+NOTE:
+ MTU designates the frame size. It only needs to be set for Jumbo
Frames. Depending on the available system resources, the request
for a higher number of receive descriptors may be denied. In this
case, use a lower number.
RxIntDelay
----------
-Valid Range: 0-65535 (0=off)
-Default Value: 0
+
+:Valid Range: 0-65535 (0=off)
+:Default Value: 0
This value delays the generation of receive interrupts in units of 1.024
microseconds. Receive interrupt reduction can improve CPU efficiency if
may be set too high, causing the driver to run out of available receive
descriptors.
-CAUTION: When setting RxIntDelay to a value other than 0, adapters may
+CAUTION:
+ When setting RxIntDelay to a value other than 0, adapters may
hang (stop transmitting) under certain network conditions. If
this occurs a NETDEV WATCHDOG message is logged in the system
event log. In addition, the controller is automatically reset,
RxAbsIntDelay
-------------
+
(This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range: 0-65535 (0=off)
-Default Value: 128
+
+:Valid Range: 0-65535 (0=off)
+:Default Value: 128
This value, in units of 1.024 microseconds, limits the delay in which a
receive interrupt is generated. Useful only if RxIntDelay is non-zero,
Speed
-----
+
(This parameter is supported only on adapters with copper connections.)
-Valid Settings: 0, 10, 100, 1000
-Default Value: 0 (auto-negotiate at all supported speeds)
+
+:Valid Settings: 0, 10, 100, 1000
+:Default Value: 0 (auto-negotiate at all supported speeds)
Speed forces the line speed to the specified value in megabits per second
(Mbps). If this parameter is not specified or is set to 0 and the link
TxDescriptors
-------------
-Valid Range: 48-256 for 82542 and 82543-based adapters
- 48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+ - 48-256 for 82542 and 82543-based adapters
+ - 48-4096 for all other supported adapters
+:Default Value: 256
This value is the number of transmit descriptors allocated by the driver.
Increasing this value allows the driver to queue more transmits. Each
descriptor is 16 bytes.
-NOTE: Depending on the available system resources, the request for a
+NOTE:
+ Depending on the available system resources, the request for a
higher number of transmit descriptors may be denied. In this case,
use a lower number.
TxIntDelay
----------
-Valid Range: 0-65535 (0=off)
-Default Value: 8
+
+:Valid Range: 0-65535 (0=off)
+:Default Value: 8
This value delays the generation of transmit interrupts in units of
1.024 microseconds. Transmit interrupt reduction can improve CPU
TxAbsIntDelay
-------------
+
(This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range: 0-65535 (0=off)
-Default Value: 32
+
+:Valid Range: 0-65535 (0=off)
+:Default Value: 32
This value, in units of 1.024 microseconds, limits the delay in which a
transmit interrupt is generated. Useful only if TxIntDelay is non-zero,
XsumRX
------
+
(This parameter is NOT supported on the 82542-based adapter.)
-Valid Range: 0-1
-Default Value: 1
+
+:Valid Range: 0-1
+:Default Value: 1
A value of '1' indicates that the driver should enable IP checksum
offload for received packets (both UDP and TCP) to the adapter hardware.
Copybreak
---------
-Valid Range: 0-xxxxxxx (0=off)
-Default Value: 256
-Usage: modprobe e1000.ko copybreak=128
+
+:Valid Range: 0-xxxxxxx (0=off)
+:Default Value: 256
+:Usage: modprobe e1000.ko copybreak=128
Driver copies all packets below or equaling this size to a fresh RX
buffer before handing it up the stack.
SmartPowerDownEnable
--------------------
-Valid Range: 0-1
-Default Value: 0 (disabled)
+
+:Valid Range: 0-1
+:Default Value: 0 (disabled)
Allows PHY to turn off in lower power states. The user can turn off
this parameter in supported chipsets.
For copper-based boards, the keywords interact as follows:
- The default operation is auto-negotiate. The board advertises all
+- The default operation is auto-negotiate. The board advertises all
supported speed and duplex combinations, and it links at the highest
common speed and duplex mode IF the link partner is set to auto-negotiate.
- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
+- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
is advertised (The 1000BaseT spec requires auto-negotiation.)
- If Speed = 10 or 100, then both Speed and Duplex should be set. Auto-
+- If Speed = 10 or 100, then both Speed and Duplex should be set. Auto-
negotiation is disabled, and the AutoNeg parameter is ignored. Partner
SHOULD also be forced.
The parameter may be specified as either a decimal or hexadecimal value as
determined by the bitmap below.
+============== ====== ====== ======= ======= ====== ====== ======= ======
Bit position 7 6 5 4 3 2 1 0
Decimal Value 128 64 32 16 8 4 2 1
Hex value 80 40 20 10 8 4 2 1
Speed (Mbps) N/A N/A 1000 N/A 100 100 10 10
Duplex Full Full Half Full Half
+============== ====== ====== ======= ======= ====== ====== ======= ======
-Some examples of using AutoNeg:
+Some examples of using AutoNeg::
modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
modprobe e1000 AutoNeg=1 (Same as above)
Additional Configurations
=========================
- Jumbo Frames
- ------------
+Jumbo Frames
+------------
+
Jumbo Frames support is enabled by changing the MTU to a value larger than
the default of 1500. Use the ifconfig command to increase the MTU size.
For example::
MTU=9000
- to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example
- applies to the Red Hat distributions; other distributions may store this
- setting in a different location.
+ to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example
+ applies to the Red Hat distributions; other distributions may store this
+ setting in a different location.
- Notes:
+Notes:
Degradation in throughput performance may be observed in some Jumbo frames
environments. If this is observed, increasing the application's socket buffer
size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
poor performance or loss of link.
- Adapters based on the Intel(R) 82542 and 82573V/E controller do not
- support Jumbo Frames. These correspond to the following product names:
+ support Jumbo Frames. These correspond to the following product names::
+
Intel(R) PRO/1000 Gigabit Server Adapter
Intel(R) PRO/1000 PM Network Connection
- ethtool
- -------
+ethtool
+-------
+
The driver utilizes the ethtool interface for driver configuration and
diagnostics, as well as displaying statistical information. The ethtool
version 1.6 or later is required for this functionality.
The latest release of ethtool can be found from
https://www.kernel.org/pub/software/network/ethtool/
- Enabling Wake on LAN* (WoL)
- ---------------------------
+Enabling Wake on LAN* (WoL)
+---------------------------
+
WoL is configured through the ethtool* utility.
WoL will be enabled on the system during the next shut down or reboot.
Temporarily pause a stream parser. Message parsing is suspended
and no new messages are delivered to the upper layer.
-void strp_pause(struct strparser *strp)
+void strp_unpause(struct strparser *strp)
Unpause a paused stream parser.
--- /dev/null
+Supporting PMUs on RISC-V platforms
+==========================================
+Alan Kao <alankao@andestech.com>, Mar 2018
+
+Introduction
+------------
+
+As of this writing, perf_event-related features mentioned in The RISC-V ISA
+Privileged Version 1.10 are as follows:
+(please check the manual for more details)
+
+* [m|s]counteren
+* mcycle[h], cycle[h]
+* minstret[h], instret[h]
+* mhpeventx, mhpcounterx[h]
+
+With such function set only, porting perf would require a lot of work, due to
+the lack of the following general architectural performance monitoring features:
+
+* Enabling/Disabling counters
+ Counters are just free-running all the time in our case.
+* Interrupt caused by counter overflow
+ No such feature in the spec.
+* Interrupt indicator
+ It is not possible to have many interrupt ports for all counters, so an
+ interrupt indicator is required for software to tell which counter has
+ just overflowed.
+* Writing to counters
+ There will be an SBI to support this since the kernel cannot modify the
+ counters [1]. Alternatively, some vendor considers to implement
+ hardware-extension for M-S-U model machines to write counters directly.
+
+This document aims to provide developers a quick guide on supporting their
+PMUs in the kernel. The following sections briefly explain perf' mechanism
+and todos.
+
+You may check previous discussions here [1][2]. Also, it might be helpful
+to check the appendix for related kernel structures.
+
+
+1. Initialization
+-----------------
+
+*riscv_pmu* is a global pointer of type *struct riscv_pmu*, which contains
+various methods according to perf's internal convention and PMU-specific
+parameters. One should declare such instance to represent the PMU. By default,
+*riscv_pmu* points to a constant structure *riscv_base_pmu*, which has very
+basic support to a baseline QEMU model.
+
+Then he/she can either assign the instance's pointer to *riscv_pmu* so that
+the minimal and already-implemented logic can be leveraged, or invent his/her
+own *riscv_init_platform_pmu* implementation.
+
+In other words, existing sources of *riscv_base_pmu* merely provide a
+reference implementation. Developers can flexibly decide how many parts they
+can leverage, and in the most extreme case, they can customize every function
+according to their needs.
+
+
+2. Event Initialization
+-----------------------
+
+When a user launches a perf command to monitor some events, it is first
+interpreted by the userspace perf tool into multiple *perf_event_open*
+system calls, and then each of them calls to the body of *event_init*
+member function that was assigned in the previous step. In *riscv_base_pmu*'s
+case, it is *riscv_event_init*.
+
+The main purpose of this function is to translate the event provided by user
+into bitmap, so that HW-related control registers or counters can directly be
+manipulated. The translation is based on the mappings and methods provided in
+*riscv_pmu*.
+
+Note that some features can be done in this stage as well:
+
+(1) interrupt setting, which is stated in the next section;
+(2) privilege level setting (user space only, kernel space only, both);
+(3) destructor setting. Normally it is sufficient to apply *riscv_destroy_event*;
+(4) tweaks for non-sampling events, which will be utilized by functions such as
+*perf_adjust_period*, usually something like the follows:
+
+if (!is_sampling_event(event)) {
+ hwc->sample_period = x86_pmu.max_period;
+ hwc->last_period = hwc->sample_period;
+ local64_set(&hwc->period_left, hwc->sample_period);
+}
+
+In the case of *riscv_base_pmu*, only (3) is provided for now.
+
+
+3. Interrupt
+------------
+
+3.1. Interrupt Initialization
+
+This often occurs at the beginning of the *event_init* method. In common
+practice, this should be a code segment like
+
+int x86_reserve_hardware(void)
+{
+ int err = 0;
+
+ if (!atomic_inc_not_zero(&pmc_refcount)) {
+ mutex_lock(&pmc_reserve_mutex);
+ if (atomic_read(&pmc_refcount) == 0) {
+ if (!reserve_pmc_hardware())
+ err = -EBUSY;
+ else
+ reserve_ds_buffers();
+ }
+ if (!err)
+ atomic_inc(&pmc_refcount);
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+
+ return err;
+}
+
+And the magic is in *reserve_pmc_hardware*, which usually does atomic
+operations to make implemented IRQ accessible from some global function pointer.
+*release_pmc_hardware* serves the opposite purpose, and it is used in event
+destructors mentioned in previous section.
+
+(Note: From the implementations in all the architectures, the *reserve/release*
+pair are always IRQ settings, so the *pmc_hardware* seems somehow misleading.
+It does NOT deal with the binding between an event and a physical counter,
+which will be introduced in the next section.)
+
+3.2. IRQ Structure
+
+Basically, a IRQ runs the following pseudo code:
+
+for each hardware counter that triggered this overflow
+
+ get the event of this counter
+
+ // following two steps are defined as *read()*,
+ // check the section Reading/Writing Counters for details.
+ count the delta value since previous interrupt
+ update the event->count (# event occurs) by adding delta, and
+ event->hw.period_left by subtracting delta
+
+ if the event overflows
+ sample data
+ set the counter appropriately for the next overflow
+
+ if the event overflows again
+ too frequently, throttle this event
+ fi
+ fi
+
+end for
+
+However as of this writing, none of the RISC-V implementations have designed an
+interrupt for perf, so the details are to be completed in the future.
+
+4. Reading/Writing Counters
+---------------------------
+
+They seem symmetric but perf treats them quite differently. For reading, there
+is a *read* interface in *struct pmu*, but it serves more than just reading.
+According to the context, the *read* function not only reads the content of the
+counter (event->count), but also updates the left period to the next interrupt
+(event->hw.period_left).
+
+But the core of perf does not need direct write to counters. Writing counters
+is hidden behind the abstraction of 1) *pmu->start*, literally start counting so one
+has to set the counter to a good value for the next interrupt; 2) inside the IRQ
+it should set the counter to the same resonable value.
+
+Reading is not a problem in RISC-V but writing would need some effort, since
+counters are not allowed to be written by S-mode.
+
+
+5. add()/del()/start()/stop()
+-----------------------------
+
+Basic idea: add()/del() adds/deletes events to/from a PMU, and start()/stop()
+starts/stop the counter of some event in the PMU. All of them take the same
+arguments: *struct perf_event *event* and *int flag*.
+
+Consider perf as a state machine, then you will find that these functions serve
+as the state transition process between those states.
+Three states (event->hw.state) are defined:
+
+* PERF_HES_STOPPED: the counter is stopped
+* PERF_HES_UPTODATE: the event->count is up-to-date
+* PERF_HES_ARCH: arch-dependent usage ... we don't need this for now
+
+A normal flow of these state transitions are as follows:
+
+* A user launches a perf event, resulting in calling to *event_init*.
+* When being context-switched in, *add* is called by the perf core, with a flag
+ PERF_EF_START, which means that the event should be started after it is added.
+ At this stage, a general event is bound to a physical counter, if any.
+ The state changes to PERF_HES_STOPPED and PERF_HES_UPTODATE, because it is now
+ stopped, and the (software) event count does not need updating.
+** *start* is then called, and the counter is enabled.
+ With flag PERF_EF_RELOAD, it writes an appropriate value to the counter (check
+ previous section for detail).
+ Nothing is written if the flag does not contain PERF_EF_RELOAD.
+ The state now is reset to none, because it is neither stopped nor updated
+ (the counting already started)
+* When being context-switched out, *del* is called. It then checks out all the
+ events in the PMU and calls *stop* to update their counts.
+** *stop* is called by *del*
+ and the perf core with flag PERF_EF_UPDATE, and it often shares the same
+ subroutine as *read* with the same logic.
+ The state changes to PERF_HES_STOPPED and PERF_HES_UPTODATE, again.
+
+** Life cycle of these two pairs: *add* and *del* are called repeatedly as
+ tasks switch in-and-out; *start* and *stop* is also called when the perf core
+ needs a quick stop-and-start, for instance, when the interrupt period is being
+ adjusted.
+
+Current implementation is sufficient for now and can be easily extended to
+features in the future.
+
+A. Related Structures
+---------------------
+
+* struct pmu: include/linux/perf_event.h
+* struct riscv_pmu: arch/riscv/include/asm/perf_event.h
+
+ Both structures are designed to be read-only.
+
+ *struct pmu* defines some function pointer interfaces, and most of them take
+*struct perf_event* as a main argument, dealing with perf events according to
+perf's internal state machine (check kernel/events/core.c for details).
+
+ *struct riscv_pmu* defines PMU-specific parameters. The naming follows the
+convention of all other architectures.
+
+* struct perf_event: include/linux/perf_event.h
+* struct hw_perf_event
+
+ The generic structure that represents perf events, and the hardware-related
+details.
+
+* struct riscv_hw_events: arch/riscv/include/asm/perf_event.h
+
+ The structure that holds the status of events, has two fixed members:
+the number of events and the array of the events.
+
+References
+----------
+
+[1] https://github.com/riscv/riscv-linux/pull/124
+[2] https://groups.google.com/a/groups.riscv.org/forum/#!topic/sw-dev/f19TmCNP6yA
# common globals
# ==============================================================================
-# The version numbering follows numbering of the specification
-# (Documentation/books/kernel-doc-HOWTO).
__version__ = '1.0'
PY3 = sys.version_info[0] == 3
Details on how to use the generic STM API can be found here [2].
[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
-[2]. Documentation/trace/stm.txt
+[2]. Documentation/trace/stm.rst
[3]. https://github.com/Linaro/perf-opencsd
1. Introduction
===============
-Tracepoints (see Documentation/trace/tracepoints.txt) can be used
+Tracepoints (see Documentation/trace/tracepoints.rst) can be used
without creating custom kernel modules to register probe functions
using the event tracing infrastructure.
The @buf can also be a glob expression to enable all functions that
match a specific pattern.
-See Filter Commands in :file:`Documentation/trace/ftrace.txt`.
+See Filter Commands in :file:`Documentation/trace/ftrace.rst`.
To just trace the schedule function:
Histogram triggers are special event triggers that can be used to
aggregate trace event data into histograms. For information on
- trace events and event triggers, see Documentation/trace/events.txt.
+ trace events and event triggers, see Documentation/trace/events.rst.
2. Histogram Trigger Command
associated event field will be saved in a variable but won't be summed
as a value:
- # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger
+ # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
Multiple variables can be assigned at the same time. The below would
result in both ts0 and b being created as variables, with both
common_timestamp and field1 additionally being summed as values:
- # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \
+ # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
event/trigger
Note that variable assignments can appear either preceding or
following their use. The command below behaves identically to the
command above:
- # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \
+ # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
event/trigger
Any number of variables not bound to a 'vals=' prefix can also be
assigned by simply separating them with colons. Below is the same
thing but without the values being summed in the histogram:
- # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger
+ # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
Variables set as above can be referenced and used in expressions on
another event.
For example, here's how a latency can be calculated:
- # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger
- # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger
+ # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
+ # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
In the first line above, the event's timetamp is saved into the
variable ts0. In the next line, ts0 is subtracted from the second
makes use of the wakeup_lat variable to compute a combined latency
using the same key and variable from yet another event:
- # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger
+ # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
2.2.2 Synthetic Events
----------------------
At this point, there isn't yet an actual 'wakeup_latency' event
instantiated in the event subsytem - for this to happen, a 'hist
trigger action' needs to be instantiated and bound to actual fields
-and variables defined on other events (see Section 6.3.3 below).
+and variables defined on other events (see Section 2.2.3 below on
+how that is done using hist trigger 'onmatch' action). Once that is
+done, the 'wakeup_latency' synthetic event instance is created.
-Once that is done, an event instance is created, and a histogram can
-be defined using it:
+A histogram can now be defined for the new synthetic event:
# echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
/sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
back to that pid, the timestamp difference is calculated. If the
resulting latency, stored in wakeup_lat, exceeds the current
maximum latency, the values specified in the save() fields are
- recoreded:
+ recorded:
# echo 'hist:keys=pid:ts0=common_timestamp.usecs \
if comm=="cyclictest"' >> \
STH registers an stm class device, through which it provides interface
to userspace and kernelspace software trace sources. See
-Documentation/trace/stm.txt for more information on that.
+Documentation/trace/stm.rst for more information on that.
MSU can be configured to collect trace data into a system memory
buffer, which can later on be read from its device nodes via read() or
1. Introduction
===============
-Tracepoints (see Documentation/trace/tracepoints.txt) can be used without
+Tracepoints (see Documentation/trace/tracepoints.rst) can be used without
creating custom kernel modules to register probe functions using the event
tracing infrastructure.
3.1 System-Wide Event Enabling
------------------------------
-See Documentation/trace/events.txt for a proper description on how events
+See Documentation/trace/events.rst for a proper description on how events
can be enabled system-wide. A short example of enabling all events related
to page allocation would look something like::
3.4 Local Event Enabling
------------------------
-Documentation/trace/ftrace.txt describes how to enable events on a per-thread
+Documentation/trace/ftrace.rst describes how to enable events on a per-thread
basis using set_ftrace_pid.
3.5 Local Event Enablement with PCL
4. Event Filtering
==================
-Documentation/trace/ftrace.txt covers in-depth how to filter events in
+Documentation/trace/ftrace.rst covers in-depth how to filter events in
ftrace. Obviously using grep and awk of trace_pipe is an option as well
as any script reading trace_pipe.
NOTE:
-This is a version of Documentation/HOWTO translated into Japanese.
+This is a version of Documentation/process/howto.rst translated into Japanese.
This document is maintained by Tsugikazu Shibata <tshibata@ab.jp.nec.com>
If you find any difference between this document and the original file or
a problem with the translation, please contact the maintainer of this file.
ています。 カーネルに関して初めての人はここからスタートすると良い
でしょう。
- :ref:`Documentation/Process/changes.rst <changes>`
+ :ref:`Documentation/process/changes.rst <changes>`
このファイルはカーネルをうまく生成(訳注 build )し、走らせるのに最
小限のレベルで必要な数々のソフトウェアパッケージの一覧を示してい
ます。
독특한 행동에 관하여 흔히 있는 오해들과 혼란들을 해소하고 있기
때문이다.
- :ref:`Documentation/process/stable_kernel_rules.rst <stable_kernel_rules>`
+ :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
이 문서는 안정적인 커널 배포가 이루어지는 규칙을 설명하고 있으며
여러분들이 이러한 배포들 중 하나에 변경을 하길 원한다면
무엇을 해야 하는지를 설명한다.
/* 소유권을 수정 */
desc->status = DEVICE_OWN;
- /* MMIO 를 통해 디바이스에 공지를 하기 전에 메모리를 동기화 */
- wmb();
-
/* 업데이트된 디스크립터의 디바이스에 공지 */
writel(DESC_NOTIFY, doorbell);
}
dma_rmb() 는 디스크립터로부터 데이터를 읽어오기 전에 디바이스가 소유권을
- 내놓았음을 보장하게 하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
- 가졌음을 보기 전에 디스크립터에 데이터가 쓰였음을 보장합니다. wmb() 는
- 캐시 일관성이 없는 (cache incoherent) MMIO 영역에 쓰기를 시도하기 전에
- 캐시 일관성이 있는 메모리 (cache coherent memory) 쓰기가 완료되었음을
- 보장해주기 위해 필요합니다.
-
- consistent memory 에 대한 자세한 내용을 위해선 Documentation/DMA-API.txt
- 문서를 참고하세요.
+ 내려놓았을 것을 보장하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
+ 가졌음을 보기 전에 디스크립터에 데이터가 쓰였을 것을 보장합니다. 참고로,
+ writel() 을 사용하면 캐시 일관성이 있는 메모리 (cache coherent memory)
+ 쓰기가 MMIO 영역에의 쓰기 전에 완료되었을 것을 보장하므로 writel() 앞에
+ wmb() 를 실행할 필요가 없음을 알아두시기 바랍니다. writel() 보다 비용이
+ 저렴한 writel_relaxed() 는 이런 보장을 제공하지 않으므로 여기선 사용되지
+ 않아야 합니다.
+
+ writel_relaxed() 와 같은 완화된 I/O 접근자들에 대한 자세한 내용을 위해서는
+ "커널 I/O 배리어의 효과" 섹션을, consistent memory 에 대한 자세한 내용을
+ 위해선 Documentation/DMA-API.txt 문서를 참고하세요.
MMIO 쓰기 배리어
程序测试的指导，请参阅
Documentation/power/drivers-testing.txt。有关驱动程序电
源管理问题相对全面的概述，请参阅
- Documentation/power/admin-guide/devices.rst。
+ Documentation/driver-api/pm/devices.rst。
管理： 如果一个驱动程序的作者还在进行有效的维护，那么通常除了那
些明显正确且不需要任何检查的补丁以外，其他所有的补丁都会
-Chinese translated version of Documentation/gpio.txt
+Chinese translated version of Documentation/gpio
If you have any comment or update to the content, please contact the
original document maintainer directly. However, if you have a problem
Linus Walleij <linus.walleij@linaro.org>
Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
---------------------------------------------------------------------
-Documentation/gpio.txt 的中文翻译
+Documentation/gpio 的中文翻译
如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
-Chinese translated version of Documentation/io_orderings.txt
+Chinese translated version of Documentation/io_ordering.txt
If you have any comment or update to the content, please contact the
original document maintainer directly. However, if you have a problem
-Chinese translated version of Documentation/magic-number.txt
+Chinese translated version of Documentation/process/magic-number.rst
If you have any comment or update to the content, please post to LKML directly.
However, if you have problem communicating in English you can also ask the
Chinese maintainer: Jia Wei Wei <harryxiyou@gmail.com>
---------------------------------------------------------------------
-Documentation/magic-number.txt的中文翻译
+Documentation/process/magic-number.rst的中文翻译
如果想评论或更新本文的内容，请直接发信到LKML。如果你使用英文交流有困难的话，也可
以向中文版维护者求助。如果本翻译更新不及时或者翻译存在问题，请联系中文版维护者。
-Chinese translated version of Documentation/video4linux/omap3isp.txt
+Chinese translated version of Documentation/media/v4l-drivers/omap3isp.rst
If you have any comment or update to the content, please contact the
original document maintainer directly. However, if you have a problem
David Cohen <dacohen@gmail.com>
Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
---------------------------------------------------------------------
-Documentation/video4linux/omap3isp.txt 的中文翻译
+Documentation/media/v4l-drivers/omap3isp.rst 的中文翻译
如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
-Chinese translated version of Documentation/video4linux/v4l2-framework.txt
+Chinese translated version of Documentation/media/media_kapi.rst
If you have any comment or update to the content, please contact the
original document maintainer directly. However, if you have a problem
Maintainer: Mauro Carvalho Chehab <mchehab@kernel.org>
Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
---------------------------------------------------------------------
-Documentation/video4linux/v4l2-framework.txt 的中文翻译
+Documentation/media/media_kapi.rst 的中文翻译
如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
线性 DMA(videobuf-dma-contig)以及大多用于 USB 设备的用 vmalloc
分配的缓冲(videobuf-vmalloc)。
-请参阅 Documentation/video4linux/videobuf，以获得更多关于 videobuf
+请参阅 Documentation/media/kapi/v4l2-videobuf.rst，以获得更多关于 videobuf
层的使用信息。
v4l2_fh 结构体
where <config name>.<number> specify the configuration and <function> is
a symlink to a function being removed from the configuration, e.g.:
-$ rm configfs/c.1/ncm.usb0
+$ rm configs/c.1/ncm.usb0
...
...
Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+ or cmma is enabled
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
8. Other capabilities.
----------------------
reset, migration and nested KVM for branch prediction blocking. The stfle
facility 82 should not be provided to the guest without this capability.
-8.14 KVM_CAP_HYPERV_TLBFLUSH
+8.18 KVM_CAP_HYPERV_TLBFLUSH
Architectures: x86
L2 and L3 CDP are controlled seperately.
RDT features are orthogonal. A particular system may support only
-monitoring, only control, or both monitoring and control.
+monitoring, only control, or both monitoring and control. Cache
+pseudo-locking is a unique way of using cache control to "pin" or
+"lock" data in the cache. Details can be found in
+"Cache Pseudo-Locking".
+
The mount succeeds if either of allocation or monitoring is present, but
only those files and directories supported by the system will be created.
some platforms support devices that have their
own settings for cache use which can over-ride
these bits.
+"bit_usage": Annotated capacity bitmasks showing how all
+ instances of the resource are used. The legend is:
+ "0" - Corresponding region is unused. When the system's
+ resources have been allocated and a "0" is found
+ in "bit_usage" it is a sign that resources are
+ wasted.
+ "H" - Corresponding region is used by hardware only
+ but available for software use. If a resource
+ has bits set in "shareable_bits" but not all
+ of these bits appear in the resource groups'
+ schematas then the bits appearing in
+ "shareable_bits" but no resource group will
+ be marked as "H".
+ "X" - Corresponding region is available for sharing and
+ used by hardware and software. These are the
+ bits that appear in "shareable_bits" as
+ well as a resource group's allocation.
+ "S" - Corresponding region is used by software
+ and available for sharing.
+ "E" - Corresponding region is used exclusively by
+ one resource group. No sharing allowed.
+ "P" - Corresponding region is pseudo-locked. No
+ sharing allowed.
Memory bandwitdh(MB) subdirectory contains the following files
with respect to allocation:
CPUs to/from this group. As with the tasks file a hierarchy is
maintained where MON groups may only include CPUs owned by the
parent CTRL_MON group.
+ When the resouce group is in pseudo-locked mode this file will
+ only be readable, reflecting the CPUs associated with the
+ pseudo-locked region.
"cpus_list":
A list of all the resources available to this group.
Each resource has its own line and format - see below for details.
+"size":
+ Mirrors the display of the "schemata" file to display the size in
+ bytes of each allocation instead of the bits representing the
+ allocation.
+
+"mode":
+ The "mode" of the resource group dictates the sharing of its
+ allocations. A "shareable" resource group allows sharing of its
+ allocations while an "exclusive" resource group does not. A
+ cache pseudo-locked region is created by first writing
+ "pseudo-locksetup" to the "mode" file before writing the cache
+ pseudo-locked region's schemata to the resource group's "schemata"
+ file. On successful pseudo-locked region creation the mode will
+ automatically change to "pseudo-locked".
+
When monitoring is enabled all MON groups will also contain:
"mon_data":
L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
+Cache Pseudo-Locking
+--------------------
+CAT enables a user to specify the amount of cache space that an
+application can fill. Cache pseudo-locking builds on the fact that a
+CPU can still read and write data pre-allocated outside its current
+allocated area on a cache hit. With cache pseudo-locking, data can be
+preloaded into a reserved portion of cache that no application can
+fill, and from that point on will only serve cache hits. The cache
+pseudo-locked memory is made accessible to user space where an
+application can map it into its virtual address space and thus have
+a region of memory with reduced average read latency.
+
+The creation of a cache pseudo-locked region is triggered by a request
+from the user to do so that is accompanied by a schemata of the region
+to be pseudo-locked. The cache pseudo-locked region is created as follows:
+- Create a CAT allocation CLOSNEW with a CBM matching the schemata
+ from the user of the cache region that will contain the pseudo-locked
+ memory. This region must not overlap with any current CAT allocation/CLOS
+ on the system and no future overlap with this cache region is allowed
+ while the pseudo-locked region exists.
+- Create a contiguous region of memory of the same size as the cache
+ region.
+- Flush the cache, disable hardware prefetchers, disable preemption.
+- Make CLOSNEW the active CLOS and touch the allocated memory to load
+ it into the cache.
+- Set the previous CLOS as active.
+- At this point the closid CLOSNEW can be released - the cache
+ pseudo-locked region is protected as long as its CBM does not appear in
+ any CAT allocation. Even though the cache pseudo-locked region will from
+ this point on not appear in any CBM of any CLOS an application running with
+ any CLOS will be able to access the memory in the pseudo-locked region since
+ the region continues to serve cache hits.
+- The contiguous region of memory loaded into the cache is exposed to
+ user-space as a character device.
+
+Cache pseudo-locking increases the probability that data will remain
+in the cache via carefully configuring the CAT feature and controlling
+application behavior. There is no guarantee that data is placed in
+cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict
+“locked” data from cache. Power management C-states may shrink or
+power off cache. Deeper C-states will automatically be restricted on
+pseudo-locked region creation.
+
+It is required that an application using a pseudo-locked region runs
+with affinity to the cores (or a subset of the cores) associated
+with the cache on which the pseudo-locked region resides. A sanity check
+within the code will not allow an application to map pseudo-locked memory
+unless it runs with affinity to cores associated with the cache on which the
+pseudo-locked region resides. The sanity check is only done during the
+initial mmap() handling, there is no enforcement afterwards and the
+application self needs to ensure it remains affine to the correct cores.
+
+Pseudo-locking is accomplished in two stages:
+1) During the first stage the system administrator allocates a portion
+ of cache that should be dedicated to pseudo-locking. At this time an
+ equivalent portion of memory is allocated, loaded into allocated
+ cache portion, and exposed as a character device.
+2) During the second stage a user-space application maps (mmap()) the
+ pseudo-locked memory into its address space.
+
+Cache Pseudo-Locking Interface
+------------------------------
+A pseudo-locked region is created using the resctrl interface as follows:
+
+1) Create a new resource group by creating a new directory in /sys/fs/resctrl.
+2) Change the new resource group's mode to "pseudo-locksetup" by writing
+ "pseudo-locksetup" to the "mode" file.
+3) Write the schemata of the pseudo-locked region to the "schemata" file. All
+ bits within the schemata should be "unused" according to the "bit_usage"
+ file.
+
+On successful pseudo-locked region creation the "mode" file will contain
+"pseudo-locked" and a new character device with the same name as the resource
+group will exist in /dev/pseudo_lock. This character device can be mmap()'ed
+by user space in order to obtain access to the pseudo-locked memory region.
+
+An example of cache pseudo-locked region creation and usage can be found below.
+
+Cache Pseudo-Locking Debugging Interface
+---------------------------------------
+The pseudo-locking debugging interface is enabled by default (if
+CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl.
+
+There is no explicit way for the kernel to test if a provided memory
+location is present in the cache. The pseudo-locking debugging interface uses
+the tracing infrastructure to provide two ways to measure cache residency of
+the pseudo-locked region:
+1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data
+ from these measurements are best visualized using a hist trigger (see
+ example below). In this test the pseudo-locked region is traversed at
+ a stride of 32 bytes while hardware prefetchers and preemption
+ are disabled. This also provides a substitute visualization of cache
+ hits and misses.
+2) Cache hit and miss measurements using model specific precision counters if
+ available. Depending on the levels of cache on the system the pseudo_lock_l2
+ and pseudo_lock_l3 tracepoints are available.
+ WARNING: triggering this measurement uses from two (for just L2
+ measurements) to four (for L2 and L3 measurements) precision counters on
+ the system, if any other measurements are in progress the counters and
+ their corresponding event registers will be clobbered.
+
+When a pseudo-locked region is created a new debugfs directory is created for
+it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single
+write-only file, pseudo_lock_measure, is present in this directory. The
+measurement on the pseudo-locked region depends on the number, 1 or 2,
+written to this debugfs file. Since the measurements are recorded with the
+tracing infrastructure the relevant tracepoints need to be enabled before the
+measurement is triggered.
+
+Example of latency debugging interface:
+In this example a pseudo-locked region named "newlock" was created. Here is
+how we can measure the latency in cycles of reading from this region and
+visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS
+is set:
+# :> /sys/kernel/debug/tracing/trace
+# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist
+
+# event histogram
+#
+# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active]
+#
+
+{ latency: 456 } hitcount: 1
+{ latency: 50 } hitcount: 83
+{ latency: 36 } hitcount: 96
+{ latency: 44 } hitcount: 174
+{ latency: 48 } hitcount: 195
+{ latency: 46 } hitcount: 262
+{ latency: 42 } hitcount: 693
+{ latency: 40 } hitcount: 3204
+{ latency: 38 } hitcount: 3484
+
+Totals:
+ Hits: 8192
+ Entries: 9
+ Dropped: 0
+
+Example of cache hits/misses debugging:
+In this example a pseudo-locked region named "newlock" was created on the L2
+cache of a platform. Here is how we can obtain details of the cache hits
+and misses using the platform's precision counters.
+
+# :> /sys/kernel/debug/tracing/trace
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# cat /sys/kernel/debug/tracing/trace
+
+# tracer: nop
+#
+# _-----=> irqs-off
+# / _----=> need-resched
+# | / _---=> hardirq/softirq
+# || / _--=> preempt-depth
+# ||| / delay
+# TASK-PID CPU# |||| TIMESTAMP FUNCTION
+# | | | |||| | |
+ pseudo_lock_mea-1672 [002] .... 3132.860500: pseudo_lock_l2: hits=4097 miss=0
+
+
Examples for RDT allocation usage:
Example 1
# echo F0 > p0/cpus
-4) Locking between applications
+Example 4
+---------
+
+The resource groups in previous examples were all in the default "shareable"
+mode allowing sharing of their cache allocations. If one resource group
+configures a cache allocation then nothing prevents another resource group
+to overlap with that allocation.
+
+In this example a new exclusive resource group will be created on a L2 CAT
+system with two L2 cache instances that can be configured with an 8-bit
+capacity bitmask. The new exclusive resource group will be configured to use
+25% of each cache instance.
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+First, we observe that the default group is configured to allocate to all L2
+cache:
+
+# cat schemata
+L2:0=ff;1=ff
+
+We could attempt to create the new resource group at this point, but it will
+fail because of the overlap with the schemata of the default group:
+# mkdir p0
+# echo 'L2:0=0x3;1=0x3' > p0/schemata
+# cat p0/mode
+shareable
+# echo exclusive > p0/mode
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+schemata overlaps
+
+To ensure that there is no overlap with another resource group the default
+resource group's schemata has to change, making it possible for the new
+resource group to become exclusive.
+# echo 'L2:0=0xfc;1=0xfc' > schemata
+# echo exclusive > p0/mode
+# grep . p0/*
+p0/cpus:0
+p0/mode:exclusive
+p0/schemata:L2:0=03;1=03
+p0/size:L2:0=262144;1=262144
+
+A new resource group will on creation not overlap with an exclusive resource
+group:
+# mkdir p1
+# grep . p1/*
+p1/cpus:0
+p1/mode:shareable
+p1/schemata:L2:0=fc;1=fc
+p1/size:L2:0=786432;1=786432
+
+The bit_usage will reflect how the cache is used:
+# cat info/L2/bit_usage
+0=SSSSSSEE;1=SSSSSSEE
+
+A resource group cannot be forced to overlap with an exclusive resource group:
+# echo 'L2:0=0x1;1=0x1' > p1/schemata
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+overlaps with exclusive group
+
+Example of Cache Pseudo-Locking
+-------------------------------
+Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked
+region is exposed at /dev/pseudo_lock/newlock that can be provided to
+application for argument to mmap().
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+Ensure that there are bits available that can be pseudo-locked, since only
+unused bits can be pseudo-locked the bits to be pseudo-locked needs to be
+removed from the default resource group's schemata:
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSSS
+# echo 'L2:1=0xfc' > schemata
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSS00
+
+Create a new resource group that will be associated with the pseudo-locked
+region, indicate that it will be used for a pseudo-locked region, and
+configure the requested pseudo-locked region capacity bitmask:
+
+# mkdir newlock
+# echo pseudo-locksetup > newlock/mode
+# echo 'L2:1=0x3' > newlock/schemata
+
+On success the resource group's mode will change to pseudo-locked, the
+bit_usage will reflect the pseudo-locked region, and the character device
+exposing the pseudo-locked region will exist:
+
+# cat newlock/mode
+pseudo-locked
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSPP
+# ls -l /dev/pseudo_lock/newlock
+crw------- 1 root root 243, 0 Apr 3 05:01 /dev/pseudo_lock/newlock
+
+/*
+ * Example code to access one page of pseudo-locked cache region
+ * from user space.
+ */
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+/*
+ * It is required that the application runs with affinity to only
+ * cores associated with the pseudo-locked region. Here the cpu
+ * is hardcoded for convenience of example.
+ */
+static int cpuid = 2;
+
+int main(int argc, char *argv[])
+{
+ cpu_set_t cpuset;
+ long page_size;
+ void *mapping;
+ int dev_fd;
+ int ret;
+
+ page_size = sysconf(_SC_PAGESIZE);
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpuid, &cpuset);
+ ret = sched_setaffinity(0, sizeof(cpuset), &cpuset);
+ if (ret < 0) {
+ perror("sched_setaffinity");
+ exit(EXIT_FAILURE);
+ }
+
+ dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR);
+ if (dev_fd < 0) {
+ perror("open");
+ exit(EXIT_FAILURE);
+ }
+
+ mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+ dev_fd, 0);
+ if (mapping == MAP_FAILED) {
+ perror("mmap");
+ close(dev_fd);
+ exit(EXIT_FAILURE);
+ }
+
+ /* Application interacts with pseudo-locked memory @mapping */
+
+ ret = munmap(mapping, page_size);
+ if (ret < 0) {
+ perror("munmap");
+ close(dev_fd);
+ exit(EXIT_FAILURE);
+ }
+
+ close(dev_fd);
+ exit(EXIT_SUCCESS);
+}
+
+Locking between applications
+----------------------------
Certain operations on the resctrl filesystem, composed of read/writes
to/from multiple files, must be atomic.
As an example, the allocation of an exclusive reservation of L3 cache
involves:
- 1. Read the cbmmasks from each directory
+ 1. Read the cbmmasks from each directory or the per-resource "bit_usage"
2. Find a contiguous set of bits in the global CBM bitmask that is clear
in any of the directory cbmmasks
3. Create a new directory
Timing
notsc
- Don't use the CPU time stamp counter to read the wall time.
- This can be used to work around timing problems on multiprocessor systems
- with not properly synchronized CPUs.
+ Deprecated, use tsc=unstable instead.
nohpet
Don't use the HPET timer.
If given as an integer, fills all system RAM with N fake nodes
interleaved over physical nodes.
+ numa=fake=<N>U
+ If given as an integer followed by 'U', it will divide each
+ physical node into N emulated nodes.
+
ACPI
acpi=off Don't enable ACPI
AGPGART DRIVER
M: David Airlie <airlied@linux.ie>
-T: git git://people.freedesktop.org/~airlied/linux (part of drm maint)
+T: git git://anongit.freedesktop.org/drm/drm
S: Maintained
F: drivers/char/agp/
F: include/linux/agp*
F: arch/arm/boot/dts/nuvoton-npcm*
F: include/dt-bindings/clock/nuvoton,npcm7xx-clks.h
F: drivers/*/*npcm*
-F: Documentation/*/*npcm*
+F: Documentation/devicetree/bindings/*/*npcm*
+F: Documentation/devicetree/bindings/*/*/*npcm*
ARM/NUVOTON W90X900 ARM ARCHITECTURE
M: Wan ZongShun <mcuos.com@gmail.com>
F: drivers/scsi/esas2r
ATUSB IEEE 802.15.4 RADIO DRIVER
-M: Stefan Schmidt <stefan@osg.samsung.com>
+M: Stefan Schmidt <stefan@datenfreihafen.org>
L: linux-wpan@vger.kernel.org
S: Maintained
F: drivers/net/ieee802154/atusb.c
N: bcm586*
N: bcm88312
N: hr2
-F: arch/arm64/boot/dts/broadcom/ns2*
+N: stingray
+F: arch/arm64/boot/dts/broadcom/northstar2/*
+F: arch/arm64/boot/dts/broadcom/stingray/*
F: drivers/clk/bcm/clk-ns*
+F: drivers/clk/bcm/clk-sr*
F: drivers/pinctrl/bcm/pinctrl-ns*
+F: include/dt-bindings/clock/bcm-sr*
BROADCOM KONA GPIO DRIVER
M: Ray Jui <rjui@broadcom.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
T: git git://git.alsa-project.org/alsa-kernel.git
S: Maintained
-F: Documentation/sound/alsa/Bt87x.txt
+F: Documentation/sound/cards/bt87x.rst
F: sound/pci/bt87x.c
BT8XXGPIO DRIVER
M: David Woodhouse <dwmw2@infradead.org>
L: keyrings@vger.kernel.org
S: Maintained
-F: Documentation/module-signing.txt
+F: Documentation/admin-guide/module-signing.rst
F: certs/
F: scripts/sign-file.c
F: scripts/extract-cert.c
T: git git://git.infradead.org/users/hch/dma-mapping.git
W: http://git.infradead.org/users/hch/dma-mapping.git
S: Supported
-F: lib/dma-debug.c
-F: lib/dma-direct.c
-F: lib/dma-noncoherent.c
-F: lib/dma-virt.c
-F: drivers/base/dma-mapping.c
-F: drivers/base/dma-coherent.c
+F: kernel/dma/
F: include/asm-generic/dma-mapping.h
F: include/linux/dma-direct.h
F: include/linux/dma-mapping.h
DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+R: "Rafael J. Wysocki" <rafael@kernel.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
S: Supported
F: Documentation/kobject.txt
M: David Lechner <david@lechnology.com>
S: Maintained
F: drivers/gpu/drm/tinydrm/ili9225.c
-F: Documentation/devicetree/bindings/display/ili9225.txt
+F: Documentation/devicetree/bindings/display/ilitek,ili9225.txt
DRM DRIVER FOR INTEL I810 VIDEO CARDS
S: Orphan / Obsolete
M: David Lechner <david@lechnology.com>
S: Maintained
F: drivers/gpu/drm/tinydrm/st7586.c
-F: Documentation/devicetree/bindings/display/st7586.txt
+F: Documentation/devicetree/bindings/display/sitronix,st7586.txt
DRM DRIVER FOR SITRONIX ST7735R PANELS
M: David Lechner <david@lechnology.com>
S: Maintained
F: drivers/gpu/drm/tinydrm/st7735r.c
-F: Documentation/devicetree/bindings/display/st7735r.txt
+F: Documentation/devicetree/bindings/display/sitronix,st7735r.txt
DRM DRIVER FOR TDFX VIDEO CARDS
S: Orphan / Obsolete
DRM DRIVERS
M: David Airlie <airlied@linux.ie>
L: dri-devel@lists.freedesktop.org
-T: git git://people.freedesktop.org/~airlied/linux
+T: git git://anongit.freedesktop.org/drm/drm
B: https://bugs.freedesktop.org/
C: irc://chat.freenode.net/dri-devel
S: Maintained
F: drivers/gpu/vga/
F: Documentation/devicetree/bindings/display/
F: Documentation/devicetree/bindings/gpu/
-F: Documentation/devicetree/bindings/video/
F: Documentation/gpu/
F: include/drm/
F: include/uapi/drm/
L: dri-devel@lists.freedesktop.org
S: Supported
F: drivers/gpu/drm/atmel-hlcdc/
-F: Documentation/devicetree/bindings/drm/atmel/
+F: Documentation/devicetree/bindings/display/atmel/
T: git git://anongit.freedesktop.org/drm/drm-misc
DRM DRIVERS FOR BRIDGE CHIPS
F: drivers/gpu/drm/fsl-dcu/
F: Documentation/devicetree/bindings/display/fsl,dcu.txt
F: Documentation/devicetree/bindings/display/fsl,tcon.txt
-F: Documentation/devicetree/bindings/display/panel/nec,nl4827hc19_05b.txt
+F: Documentation/devicetree/bindings/display/panel/nec,nl4827hc19-05b.txt
DRM DRIVERS FOR FREESCALE IMX
M: Philipp Zabel <p.zabel@pengutronix.de>
S: Supported
F: drivers/gpu/drm/v3d/
F: include/uapi/drm/v3d_drm.h
-F: Documentation/devicetree/bindings/display/brcm,bcm-v3d.txt
+F: Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.txt
T: git git://anongit.freedesktop.org/drm/drm-misc
DRM DRIVERS FOR VC4
EZchip NPS platform support
M: Vineet Gupta <vgupta@synopsys.com>
+M: Ofer Levi <oferle@mellanox.com>
S: Supported
F: arch/arc/plat-eznps
F: arch/arc/boot/dts/eznps.dts
F: Documentation/devicetree/bindings/crypto/fsl-sec4.txt
FREESCALE DIU FRAMEBUFFER DRIVER
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: drivers/video/fbdev/fsl-diu-fb.*
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/freescale/fman
-F: Documentation/devicetree/bindings/powerpc/fsl/fman.txt
+F: Documentation/devicetree/bindings/net/fsl-fman.txt
FREESCALE QORIQ PTP CLOCK DRIVER
M: Yangbo Lu <yangbo.lu@nxp.com>
F: drivers/net/wan/fsl_ucc_hdlc*
FREESCALE QUICC ENGINE UCC UART DRIVER
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
F: drivers/tty/serial/ucc_uart.c
FREESCALE SOC FS_ENET DRIVER
M: Pantelis Antoniou <pantelis.antoniou@gmail.com>
-M: Vitaly Bordug <vbordug@ru.mvista.com>
L: linuxppc-dev@lists.ozlabs.org
L: netdev@vger.kernel.org
S: Maintained
F: include/linux/fs_enet_pd.h
FREESCALE SOC SOUND DRIVERS
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
M: Nicolin Chen <nicoleotsuka@gmail.com>
M: Xiubo Li <Xiubo.Lee@gmail.com>
R: Fabio Estevam <fabio.estevam@nxp.com>
GDB KERNEL DEBUGGING HELPER SCRIPTS
M: Jan Kiszka <jan.kiszka@siemens.com>
-M: Kieran Bingham <kieran@bingham.xyz>
+M: Kieran Bingham <kbingham@kernel.org>
S: Supported
F: scripts/gdb/
S: Maintained
F: mm/hmm*
F: include/linux/hmm*
-F: Documentation/vm/hmm.txt
+F: Documentation/vm/hmm.rst
HOST AP DRIVER
M: Jouni Malinen <j@w1.fi>
IEEE 802.15.4 SUBSYSTEM
M: Alexander Aring <alex.aring@gmail.com>
-M: Stefan Schmidt <stefan@osg.samsung.com>
+M: Stefan Schmidt <stefan@datenfreihafen.org>
L: linux-wpan@vger.kernel.org
W: http://wpan.cakelab.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
M: Peter Rosin <peda@axentia.se>
L: linux-iio@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/iio/multiplexer/iio-mux.txt
+F: Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
F: drivers/iio/multiplexer/iio-mux.c
IIO SUBSYSTEM AND DRIVERS
F: include/uapi/linux/input-event-codes.h
F: include/linux/input/
F: Documentation/devicetree/bindings/input/
+F: Documentation/devicetree/bindings/serio/
F: Documentation/input/
INPUT MULTITOUCH (MT) PROTOCOL
INTEL(R) TRACE HUB
M: Alexander Shishkin <alexander.shishkin@linux.intel.com>
S: Supported
-F: Documentation/trace/intel_th.txt
+F: Documentation/trace/intel_th.rst
F: drivers/hwtracing/intel_th/
INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT)
L: linux-iio@vger.kernel.org
S: Maintained
F: drivers/iio/gyro/mpu3050*
-F: Documentation/devicetree/bindings/iio/gyroscope/inv,mpu3050.txt
+F: Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
IOC3 ETHERNET DRIVER
M: Ralf Baechle <ralf@linux-mips.org>
F: tools/testing/selftests/kmod/
KPROBES
-M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
+M: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
M: "David S. Miller" <davem@davemloft.net>
M: Masami Hiramatsu <mhiramat@kernel.org>
M: Luc Maranget <luc.maranget@inria.fr>
M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
R: Akira Yokosawa <akiyks@gmail.com>
+R: Daniel Lustig <dlustig@nvidia.com>
L: linux-kernel@vger.kernel.org
+L: linux-arch@vger.kernel.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
F: tools/memory-model/
+F: Documentation/atomic_bitops.txt
+F: Documentation/atomic_t.txt
+F: Documentation/core-api/atomic_ops.rst
+F: Documentation/core-api/refcount-vs-atomic.rst
F: Documentation/memory-barriers.txt
LINUX SECURITY MODULE (LSM) FRAMEWORK
M: Amitkumar Karwar <amitkarwar@gmail.com>
M: Nishant Sarmukadam <nishants@marvell.com>
M: Ganapathi Bhat <gbhat@marvell.com>
-M: Xinming Hu <huxm@marvell.com>
+M: Xinming Hu <huxinming820@gmail.com>
L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/net/wireless/marvell/mwifiex/
L: linux-hwmon@vger.kernel.org
S: Maintained
F: Documentation/hwmon/max6697
-F: Documentation/devicetree/bindings/i2c/max6697.txt
+F: Documentation/devicetree/bindings/hwmon/max6697.txt
F: drivers/hwmon/max6697.c
F: include/linux/platform_data/max6697.h
F: drivers/usb/mtu3/
MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES
-M: Peter Senna Tschudin <peter.senna@collabora.com>
+M: Peter Senna Tschudin <peter.senna@gmail.com>
M: Martin Donnelly <martin.donnelly@ge.com>
M: Martyn Welch <martyn.welch@collabora.co.uk>
S: Maintained
F: drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
-F: Documentation/devicetree/bindings/video/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
+F: Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
MEGARAID SCSI/SAS DRIVERS
M: Kashyap Desai <kashyap.desai@broadcom.com>
MULTIPLEXER SUBSYSTEM
M: Peter Rosin <peda@axentia.se>
S: Maintained
-F: Documentation/ABI/testing/mux/sysfs-class-mux*
+F: Documentation/ABI/testing/sysfs-class-mux*
F: Documentation/devicetree/bindings/mux/
F: include/linux/dt-bindings/mux/
F: include/linux/mux/
M: Marek Vasut <marex@denx.de>
S: Supported
F: drivers/gpu/drm/mxsfb/
-F: Documentation/devicetree/bindings/display/mxsfb-drm.txt
+F: Documentation/devicetree/bindings/display/mxsfb.txt
MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
M: Chris Lee <christopher.lee@cspi.com>
S: Maintained
F: drivers/scsi/NCR_D700.*
+NCSI LIBRARY:
+M: Samuel Mendoza-Jonas <sam@mendozajonas.com>
+S: Maintained
+F: net/ncsi/
+
NCT6775 HARDWARE MONITOR DRIVER
M: Guenter Roeck <linux@roeck-us.net>
L: linux-hwmon@vger.kernel.org
M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
M: Florian Fainelli <f.fainelli@gmail.com>
S: Maintained
+F: Documentation/devicetree/bindings/net/dsa/
F: net/dsa/
F: include/net/dsa.h
F: include/linux/dsa/
NXP TDA998X DRM DRIVER
M: Russell King <linux@armlinux.org.uk>
-S: Supported
+S: Maintained
T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-devel
T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-fixes
F: drivers/gpu/drm/i2c/tda998x_drv.c
F: include/drm/i2c/tda998x.h
+F: include/dt-bindings/display/tda998x.h
+K: "nxp,tda998x"
NXP TFA9879 DRIVER
M: Peter Rosin <peda@axentia.se>
F: drivers/misc/ocxl/
F: include/misc/ocxl*
F: include/uapi/misc/ocxl.h
-F: Documentation/accelerators/ocxl.txt
+F: Documentation/accelerators/ocxl.rst
OMAP AUDIO SUPPORT
M: Peter Ujfalusi <peter.ujfalusi@ti.com>
F: arch/arm/boot/dts/*dra7*
OMAP DISPLAY SUBSYSTEM and FRAMEBUFFER SUPPORT (DSS2)
-M: Tomi Valkeinen <tomi.valkeinen@ti.com>
L: linux-omap@vger.kernel.org
L: linux-fbdev@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/video/fbdev/omap2/
F: Documentation/arm/OMAP/DSS
OMAP FRAMEBUFFER SUPPORT
-M: Tomi Valkeinen <tomi.valkeinen@ti.com>
L: linux-fbdev@vger.kernel.org
L: linux-omap@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/video/fbdev/omap/
OMAP GENERAL PURPOSE MEMORY CONTROLLER SUPPORT
M: Willy Tarreau <willy@haproxy.com>
M: Ksenija Stanojevic <ksenija.stanojevic@gmail.com>
S: Odd Fixes
-F: Documentation/misc-devices/lcd-panel-cgram.txt
+F: Documentation/auxdisplay/lcd-panel-cgram.txt
F: drivers/misc/panel.c
PARALLEL PORT SUBSYSTEM
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-F: Documentation/devicetree/bindings/pci/controller-generic-pci.txt
+F: Documentation/devicetree/bindings/pci/host-generic-pci.txt
F: drivers/pci/controller/pci-host-common.c
F: drivers/pci/controller/pci-host-generic.c
M: Binghui Wang <wangbinghui@hisilicon.com>
L: linux-pci@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/pci/pcie-kirin.txt
+F: Documentation/devicetree/bindings/pci/kirin-pcie.txt
F: drivers/pci/controller/dwc/pcie-kirin.c
PCIE DRIVER FOR HISILICON STB
S: Obsolete
F: drivers/net/wireless/intersil/prism54/
+PROC FILESYSTEM
+R: Alexey Dobriyan <adobriyan@gmail.com>
+L: linux-kernel@vger.kernel.org
+L: linux-fsdevel@vger.kernel.org
+S: Maintained
+F: fs/proc/
+F: include/linux/proc_fs.h
+F: tools/testing/selftests/proc/
+
PROC SYSCTL
M: "Luis R. Rodriguez" <mcgrof@kernel.org>
M: Kees Cook <keescook@chromium.org>
F: drivers/cpufreq/qcom-cpufreq-kryo.c
QUALCOMM EMAC GIGABIT ETHERNET DRIVER
-M: Timur Tabi <timur@codeaurora.org>
+M: Timur Tabi <timur@kernel.org>
L: netdev@vger.kernel.org
-S: Supported
+S: Maintained
F: drivers/net/ethernet/qualcomm/emac/
QUALCOMM HEXAGON ARCHITECTURE
F: arch/hexagon/
QUALCOMM HIDMA DRIVER
-M: Sinan Kaya <okaya@codeaurora.org>
+M: Sinan Kaya <okaya@kernel.org>
L: linux-arm-kernel@lists.infradead.org
L: linux-arm-msm@vger.kernel.org
L: dmaengine@vger.kernel.org
F: Documentation/RCU/
X: Documentation/RCU/torture.txt
F: include/linux/rcu*
-X: include/linux/srcu.h
+X: include/linux/srcu*.h
F: kernel/rcu/
-X: kernel/torture.c
+X: kernel/rcu/srcu*.c
REAL TIME CLOCK (RTC) SUBSYSTEM
M: Alessandro Zummo <a.zummo@towertech.it>
RISC-V ARCHITECTURE
M: Palmer Dabbelt <palmer@sifive.com>
-M: Albert Ou <albert@sifive.com>
+M: Albert Ou <aou@eecs.berkeley.edu>
L: linux-riscv@lists.infradead.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git
S: Supported
S390 VFIO-CCW DRIVER
M: Cornelia Huck <cohuck@redhat.com>
-M: Dong Jia Shi <bjsdjshi@linux.ibm.com>
M: Halil Pasic <pasic@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: kvm@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Maintained
F: drivers/crypto/exynos-rng.c
-F: Documentation/devicetree/bindings/crypto/samsung,exynos-rng4.txt
+F: Documentation/devicetree/bindings/rng/samsung,exynos4-rng.txt
SAMSUNG EXYNOS TRUE RANDOM NUMBER GENERATOR (TRNG) DRIVER
M: Łukasz Stelmach <l.stelmach@samsung.com>
F: drivers/media/usb/siano/
F: drivers/media/mmc/siano/
+SIFIVE DRIVERS
+M: Palmer Dabbelt <palmer@sifive.com>
+L: linux-riscv@lists.infradead.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git
+S: Supported
+K: sifive
+N: sifive
+
SILEAD TOUCHSCREEN DRIVER
M: Hans de Goede <hdegoede@redhat.com>
L: linux-input@vger.kernel.org
W: http://www.rdrop.com/users/paulmck/RCU/
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-F: include/linux/srcu.h
-F: kernel/rcu/srcu.c
+F: include/linux/srcu*.h
+F: kernel/rcu/srcu*.c
SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
S: Supported
-F: Documentation/sound/alsa/compress_offload.txt
+F: Documentation/sound/designs/compress-offload.rst
F: include/sound/compress_driver.h
F: include/uapi/sound/compress_*
F: sound/core/compress_offload.c
W: http://alsa-project.org/main/index.php/ASoC
S: Supported
F: Documentation/devicetree/bindings/sound/
-F: Documentation/sound/alsa/soc/
+F: Documentation/sound/soc/
F: sound/soc/
F: include/sound/soc*
F: drivers/pwm/pwm-stm32*
F: include/linux/*/stm32-*tim*
F: Documentation/ABI/testing/*timer-stm32
-F: Documentation/devicetree/bindings/*/stm32-*timer
+F: Documentation/devicetree/bindings/*/stm32-*timer*
F: Documentation/devicetree/bindings/pwm/pwm-stm32*
STMMAC ETHERNET DRIVER
L: iommu@lists.linux-foundation.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb.git
S: Supported
-F: lib/swiotlb.c
+F: kernel/dma/swiotlb.c
F: arch/*/kernel/pci-swiotlb.c
F: include/linux/swiotlb.h
M: Alexander Shishkin <alexander.shishkin@linux.intel.com>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/ash/stm.git
-F: Documentation/trace/stm.txt
+F: Documentation/trace/stm.rst
F: drivers/hwtracing/stm/
F: include/linux/stm.h
F: include/uapi/linux/stm.h
F: Documentation/RCU/torture.txt
F: kernel/torture.c
F: kernel/rcu/rcutorture.c
+F: kernel/rcu/rcuperf.c
F: kernel/locking/locktorture.c
TOSHIBA ACPI EXTRAS DRIVER
M: Ingo Molnar <mingo@redhat.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
S: Maintained
-F: Documentation/trace/ftrace.txt
+F: Documentation/trace/ftrace.rst
F: arch/*/*/*/ftrace.h
F: arch/*/kernel/ftrace.c
F: include/*/ftrace.h
L: linux-usb@vger.kernel.org
S: Maintained
F: Documentation/ABI/testing/sysfs-class-typec
-F: Documentation/usb/typec.rst
+F: Documentation/driver-api/usb/typec.rst
F: drivers/usb/typec/
F: include/linux/usb/typec.h
USER-MODE LINUX (UML)
M: Jeff Dike <jdike@addtoit.com>
M: Richard Weinberger <richard@nod.at>
-L: user-mode-linux-devel@lists.sourceforge.net
-L: user-mode-linux-user@lists.sourceforge.net
+L: linux-um@lists.infradead.org
W: http://user-mode-linux.sourceforge.net
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git
S: Maintained
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
S: Maintained
+F: Documentation/devicetree/bindings/x86/
F: Documentation/x86/
F: arch/x86/
+X86 ENTRY CODE
+M: Andy Lutomirski <luto@kernel.org>
+L: linux-kernel@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/asm
+S: Maintained
+F: arch/x86/entry/
+
X86 MCE INFRASTRUCTURE
M: Tony Luck <tony.luck@intel.com>
M: Borislav Petkov <bp@alien8.de>
F: drivers/platform/olpc/
X86 VDSO
-M: Andy Lutomirski <luto@amacapital.net>
+M: Andy Lutomirski <luto@kernel.org>
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
S: Maintained
M: Henk Vergonet <Henk.Vergonet@gmail.com>
L: usbb2k-api-dev@nongnu.org
S: Maintained
-F: Documentation/input/yealink.rst
+F: Documentation/input/devices/yealink.rst
F: drivers/input/misc/yealink.*
Z8530 DRIVER FOR AX.25
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
-PATCHLEVEL = 17
+PATCHLEVEL = 18
SUBLEVEL = 0
EXTRAVERSION =
NAME = Merciless Moray
else if [ -x /bin/bash ]; then echo /bin/bash; \
else echo sh; fi ; fi)
-HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS)
-HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS)
-HOST_LFS_LIBS := $(shell getconf LFS_LIBS)
+HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null)
+HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null)
+HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
HOSTCC = gcc
HOSTCXX = g++
KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y)
- CC_CAN_LINK := y
- export CC_CAN_LINK
-endif
-
# The expansion should be delayed until arch/$(SRCARCH)/Makefile is included.
# Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile.
# CC_VERSION_TEXT is referenced from Kconfig (so it needs export),
PHONY += FORCE
FORCE:
-# Declare the contents of the .PHONY variable as phony. We keep that
+# Declare the contents of the PHONY variable as phony. We keep that
# information in a variable so we can use it in if_changed and friends.
.PHONY: $(PHONY)
in terms of Berkeley Packet Filter programs which implement
task-defined system call filtering polices.
- See Documentation/prctl/seccomp_filter.txt for details.
+ See Documentation/userspace-api/seccomp_filter.rst for details.
preferred-plugin-hostcc := $(if-success,[ $(gcc-version) -ge 40800 ],$(HOSTCXX),$(HOSTCC))
in structures. This reduces the performance hit of RANDSTRUCT
at the cost of weakened randomization.
-config HAVE_CC_STACKPROTECTOR
+config HAVE_STACKPROTECTOR
bool
help
An arch should select this symbol if:
config STACKPROTECTOR
bool "Stack Protector buffer overflow detection"
- depends on HAVE_CC_STACKPROTECTOR
+ depends on HAVE_STACKPROTECTOR
depends on $(cc-option,-fstack-protector)
default y
help
If you don't know what to do here, say N.
-config HAVE_DEC_LOCK
- bool
- depends on SMP
- default y
-
config NR_CPUS
int "Maximum number of CPUs (2-32)"
range 2 32
* To ensure dependency ordering is preserved for the _relaxed and
* _release atomics, an smp_read_barrier_depends() is unconditionally
* inserted into the _relaxed variants, which are used to build the
- * barriered versions. To avoid redundant back-to-back fences, we can
- * define the _acquire and _fence versions explicitly.
+ * barriered versions. Avoid redundant back-to-back fences in the
+ * _acquire and _fence versions.
*/
-#define __atomic_op_acquire(op, args...) op##_relaxed(args)
-#define __atomic_op_fence __atomic_op_release
+#define __atomic_acquire_fence()
+#define __atomic_post_full_fence()
#define ATOMIC_INIT(i) { (i) }
#define ATOMIC64_INIT(i) { (i) }
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
/**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
* Atomically adds @a to @v, so long as it was not @u.
* Returns the old value of @v.
*/
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int c, new, old;
smp_mb();
smp_mb();
return old;
}
-
+#define atomic_fetch_add_unless atomic_fetch_add_unless
/**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
* Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
+ * Returns the old value of @v.
*/
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
{
- long c, tmp;
+ long c, new, old;
smp_mb();
__asm__ __volatile__(
- "1: ldq_l %[tmp],%[mem]\n"
- " cmpeq %[tmp],%[u],%[c]\n"
- " addq %[tmp],%[a],%[tmp]\n"
+ "1: ldq_l %[old],%[mem]\n"
+ " cmpeq %[old],%[u],%[c]\n"
+ " addq %[old],%[a],%[new]\n"
" bne %[c],2f\n"
- " stq_c %[tmp],%[mem]\n"
- " beq %[tmp],3f\n"
+ " stq_c %[new],%[mem]\n"
+ " beq %[new],3f\n"
"2:\n"
".subsection 2\n"
"3: br 1b\n"
".previous"
- : [tmp] "=&r"(tmp), [c] "=&r"(c)
+ : [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
: "memory");
smp_mb();
- return !c;
+ return old;
}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
/*
* atomic64_dec_if_positive - decrement by 1 if old value positive
smp_mb();
return old - 1;
}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
-
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-#define atomic64_inc_return(v) atomic64_add_return(1,(v))
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v) atomic_add(1,(v))
-#define atomic64_inc(v) atomic64_add(1,(v))
-
-#define atomic_dec(v) atomic_sub(1,(v))
-#define atomic64_dec(v) atomic64_sub(1,(v))
+#define atomic64_dec_if_positive atomic64_dec_if_positive
#endif /* _ALPHA_ATOMIC_H */
SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
struct rusage32 __user *, ur)
{
- unsigned int status = 0;
struct rusage r;
- long err = kernel_wait4(pid, &status, options, &r);
+ long err = kernel_wait4(pid, ustatus, options, &r);
if (err <= 0)
return err;
- if (put_user(status, ustatus))
- return -EFAULT;
if (!ur)
return err;
if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
callback_srm.o srm_puts.o srm_printk.o \
fls.o
-lib-$(CONFIG_SMP) += dec_and_lock.o
-
# The division routines are built from single source, with different defines.
AFLAGS___divqu.o = -DDIV
AFLAGS___remqu.o = -DREM
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/alpha/lib/dec_and_lock.c
- *
- * ll/sc version of atomic_dec_and_lock()
- *
- */
-
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-#include <linux/export.h>
-
- asm (".text \n\
- .global _atomic_dec_and_lock \n\
- .ent _atomic_dec_and_lock \n\
- .align 4 \n\
-_atomic_dec_and_lock: \n\
- .prologue 0 \n\
-1: ldl_l $1, 0($16) \n\
- subl $1, 1, $1 \n\
- beq $1, 2f \n\
- stl_c $1, 0($16) \n\
- beq $1, 4f \n\
- mb \n\
- clr $0 \n\
- ret \n\
-2: br $29, 3f \n\
-3: ldgp $29, 0($29) \n\
- br $atomic_dec_and_lock_1..ng \n\
- .subsection 2 \n\
-4: br 1b \n\
- .previous \n\
- .end _atomic_dec_and_lock");
-
-static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock)
-{
- /* Slow path */
- spin_lock(lock);
- if (atomic_dec_and_test(atomic))
- return 1;
- spin_unlock(lock);
- return 0;
-}
-EXPORT_SYMBOL(_atomic_dec_and_lock);
select HAVE_KERNEL_LZMA
select ARCH_HAS_PTE_SPECIAL
+config ARCH_HAS_CACHE_LINE_SIZE
+ def_bool y
+
config MIGHT_HAVE_PCI
bool
config ARC_HAS_ACCL_REGS
bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
- default n
+ default y
help
Depending on the configuration, CPU can contain accumulator reg-pair
(also referred to as r58:r59). These can also be used by gcc as GPR so
KBUILD_DEFCONFIG := nsim_700_defconfig
-cflags-y += -fno-common -pipe -fno-builtin -D__linux__
+cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7
cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
-
-# Hacks to enable final link due to absence of link-time branch relexation
-# and gcc choosing optimal(shorter) branches at -O3
-#
-# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
-# However lib/decompress_inflate.o (.init.text) calls
-# zlib_inflate_workspacesize (.text) causing relocation errors.
-# Thus forcing all exten calls in this file to be long calls
-export CFLAGS_decompress_inflate.o = -mmedium-calls
-export CFLAGS_initramfs.o = -mmedium-calls
-ifdef CONFIG_SMP
-export CFLAGS_core.o = -mmedium-calls
-endif
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_EXPERT=y
CONFIG_PERF_EVENTS=y
# CONFIG_COMPAT_BRK is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
CONFIG_PERF_EVENTS=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
CONFIG_PERF_EVENTS=y
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
# CONFIG_INPUT is not set
# CONFIG_SERIO is not set
# CONFIG_VT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
# CONFIG_LEGACY_PTYS is not set
# CONFIG_DEVKMEM is not set
CONFIG_SERIAL_8250=y
ATOMIC_OPS(add, +=, add)
ATOMIC_OPS(sub, -=, sub)
-#define atomic_andnot atomic_andnot
+#define atomic_andnot atomic_andnot
+#define atomic_fetch_andnot atomic_fetch_andnot
#undef ATOMIC_OPS
#define ATOMIC_OPS(op, c_op, asm_op) \
ATOMIC_FETCH_OP(op, c_op, asm_op)
ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
-#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v
- */
-#define __atomic_add_unless(v, a, u) \
-({ \
- int c, old; \
- \
- /* \
- * Explicit full memory barrier needed before/after as \
- * LLOCK/SCOND thmeselves don't provide any such semantics \
- */ \
- smp_mb(); \
- \
- c = atomic_read(v); \
- while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
- c = old; \
- \
- smp_mb(); \
- \
- c; \
-})
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic_dec(v) atomic_sub(1, v)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-
-
#ifdef CONFIG_GENERIC_ATOMIC64
#include <asm-generic/atomic64.h>
ATOMIC64_OP_RETURN(op, op1, op2) \
ATOMIC64_FETCH_OP(op, op1, op2)
-#define atomic64_andnot atomic64_andnot
+#define atomic64_andnot atomic64_andnot
+#define atomic64_fetch_andnot atomic64_fetch_andnot
ATOMIC64_OPS(add, add.f, adc)
ATOMIC64_OPS(sub, sub.f, sbc)
return val;
}
+#define atomic64_dec_if_positive atomic64_dec_if_positive
/**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
- * if (v != u) { v += a; ret = 1} else {ret = 0}
- * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ * Atomically adds @a to @v, if it was not @u.
+ * Returns the old value of @v
*/
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+ long long u)
{
- long long val;
- int op_done;
+ long long old, temp;
smp_mb();
__asm__ __volatile__(
"1: llockd %0, [%2] \n"
- " mov %1, 1 \n"
" brne %L0, %L4, 2f # continue to add since v != u \n"
" breq.d %H0, %H4, 3f # return since v == u \n"
- " mov %1, 0 \n"
"2: \n"
- " add.f %L0, %L0, %L3 \n"
- " adc %H0, %H0, %H3 \n"
- " scondd %0, [%2] \n"
+ " add.f %L1, %L0, %L3 \n"
+ " adc %H1, %H0, %H3 \n"
+ " scondd %1, [%2] \n"
" bnz 1b \n"
"3: \n"
- : "=&r"(val), "=&r" (op_done)
+ : "=&r"(old), "=&r" (temp)
: "r"(&v->counter), "r"(a), "r"(u)
: "cc"); /* memory clobber comes from smp_mb() */
smp_mb();
- return op_done;
+ return old;
}
-
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v) atomic64_add(1LL, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v) atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
#endif /* !CONFIG_GENERIC_ATOMIC64 */
})
/* Largest line length for either L1 or L2 is 128 bytes */
-#define ARCH_DMA_MINALIGN 128
+#define SMP_CACHE_BYTES 128
+#define cache_line_size() SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES
extern void arc_cache_init(void);
extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
#ifndef __ASM_ARC_UDELAY_H
#define __ASM_ARC_UDELAY_H
+#include <asm-generic/types.h>
#include <asm/param.h> /* HZ */
+extern unsigned long loops_per_jiffy;
+
static inline void __delay(unsigned long loops)
{
__asm__ __volatile__(
POP gp
RESTORE_R12_TO_R0
+#ifdef CONFIG_ARC_CURR_IN_REG
+ ld r25, [sp, 12]
+#endif
ld sp, [sp] /* restore original sp */
/* orig_r0, ECR, user_r25 skipped automatically */
.endm
POP gp
RESTORE_R12_TO_R0
+#ifdef CONFIG_ARC_CURR_IN_REG
+ ld r25, [sp, 12]
+#endif
ld sp, [sp] /* restore original sp */
/* orig_r0, ECR, user_r25 skipped automatically */
.endm
POP r1
POP r0
-#ifdef CONFIG_ARC_CURR_IN_REG
- ld r25, [sp, 12]
-#endif
.endm
/*--------------------------------------------------------------
struct kprobe_ctlblk {
unsigned int kprobe_status;
- struct pt_regs jprobe_saved_regs;
- char jprobes_stack[MAX_STACK_SIZE];
struct prev_kprobe prev_kprobe;
};
const char *name;
const char **dt_compat;
void (*init_early)(void);
-#ifdef CONFIG_SMP
void (*init_per_cpu)(unsigned int);
-#endif
void (*init_machine)(void);
void (*init_late)(void);
#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
/* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#define WANT_PAGE_VIRTUAL 1
/* Decode a PTE containing swap "identifier "into constituents */
#define __swp_type(pte_lookalike) (((pte_lookalike).val) & 0x1f)
-#define __swp_offset(pte_lookalike) ((pte_lookalike).val << 13)
+#define __swp_offset(pte_lookalike) ((pte_lookalike).val >> 13)
/* NOPs, to keep generic kernel happy */
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
/* a SMP H/w block could do IPI IRQ request here */
if (plat_smp_ops.init_per_cpu)
plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif
if (machine_desc->init_per_cpu)
machine_desc->init_per_cpu(smp_processor_id());
-#endif
}
/*
/* If we have no pre-handler or it returned 0, we continue with
* normal processing. If we have a pre-handler and it returned
- * non-zero - which is expected from setjmp_pre_handler for
- * jprobe, we return without single stepping and leave that to
- * the break-handler which is invoked by a kprobe from
- * jprobe_return
+ * non-zero - which means user handler setup registers to exit
+ * to another instruction, we must skip the single stepping.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
+ } else {
+ reset_current_kprobe();
+ preempt_enable_no_resched();
}
return 1;
- } else if (kprobe_running()) {
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- setup_singlestep(p, regs);
- kcb->kprobe_status = KPROBE_HIT_SS;
- return 1;
- }
}
/* no_kprobe: */
return ret;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- unsigned long sp_addr = regs->sp;
-
- kcb->jprobe_saved_regs = *regs;
- memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
- regs->ret = (unsigned long)(jp->entry);
-
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- __asm__ __volatile__("unimp_s");
- return;
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- unsigned long sp_addr;
-
- *regs = kcb->jprobe_saved_regs;
- sp_addr = regs->sp;
- memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
- preempt_enable_no_resched();
-
- return 1;
-}
-
static void __used kretprobe_trampoline_holder(void)
{
__asm__ __volatile__(".global kretprobe_trampoline\n"
kretprobe_assert(ri, orig_ret_address, trampoline_address);
regs->ret = orig_ret_address;
- reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
{
struct pt_regs *regs = current_pt_regs();
- int uval = -EFAULT;
+ u32 uval;
+ int ret;
/*
* This is only for old cores lacking LLOCK/SCOND, which by defintion
/* Z indicates to userspace if operation succeded */
regs->status32 &= ~STATUS_Z_MASK;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
- return -EFAULT;
+ ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr));
+ if (!ret)
+ goto fail;
+again:
preempt_disable();
- if (__get_user(uval, uaddr))
- goto done;
+ ret = __get_user(uval, uaddr);
+ if (ret)
+ goto fault;
- if (uval == expected) {
- if (!__put_user(new, uaddr))
- regs->status32 |= STATUS_Z_MASK;
- }
+ if (uval != expected)
+ goto out;
-done:
- preempt_enable();
+ ret = __put_user(new, uaddr);
+ if (ret)
+ goto fault;
+
+ regs->status32 |= STATUS_Z_MASK;
+out:
+ preempt_enable();
return uval;
+
+fault:
+ preempt_enable();
+
+ if (unlikely(ret != -EFAULT))
+ goto fail;
+
+ down_read(¤t->mm->mmap_sem);
+ ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+ FAULT_FLAG_WRITE, NULL);
+ up_read(¤t->mm->mmap_sem);
+
+ if (likely(!ret))
+ goto again;
+
+fail:
+ force_sig(SIGSEGV, current);
+ return ret;
}
#ifdef CONFIG_ISA_ARCV2
void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
unsigned long pfn)
{
- unsigned int paddr = pfn << PAGE_SHIFT;
+ phys_addr_t paddr = pfn << PAGE_SHIFT;
u_vaddr &= PAGE_MASK;
unsigned long u_vaddr)
{
/* TBD: do we really need to clear the kernel mapping */
- __flush_dcache_page(page_address(page), u_vaddr);
- __flush_dcache_page(page_address(page), page_address(page));
+ __flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+ __flush_dcache_page((phys_addr_t)page_address(page),
+ (phys_addr_t)page_address(page));
}
}
}
+ /*
+ * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+ * or equal to any cache line length.
+ */
+ BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+ "SMP_CACHE_BYTES must be >= any cache line length");
+ if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+ panic("L2 Cache line [%d] > kernel Config [%d]\n",
+ l2_line_sz, SMP_CACHE_BYTES);
+
/* Note that SLC disable not formally supported till HS 3.0 */
if (is_isa_arcv2() && l2_line_sz && !slc_enable)
arc_slc_disable();
return ret;
}
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lkml.org/lkml/2018/5/18/979
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ * | map == for_device | unmap == for_cpu
+ * |----------------------------------------------------------------
+ * TO_DEV | writeback writeback | none none
+ * FROM_DEV | invalidate invalidate | invalidate* invalidate*
+ * BIDIR | writeback+inv writeback+inv | invalidate invalidate
+ *
+ * [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir)
{
- dma_cache_wback(paddr, size);
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ dma_cache_wback(paddr, size);
+ break;
+
+ case DMA_FROM_DEVICE:
+ dma_cache_inv(paddr, size);
+ break;
+
+ case DMA_BIDIRECTIONAL:
+ dma_cache_wback_inv(paddr, size);
+ break;
+
+ default:
+ break;
+ }
}
void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir)
{
- dma_cache_inv(paddr, size);
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ break;
+
+ /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+ case DMA_FROM_DEVICE:
+ case DMA_BIDIRECTIONAL:
+ dma_cache_inv(paddr, size);
+ break;
+
+ default:
+ break;
+ }
}
#error "Incorrect ctop.h include"
#endif
+#include <linux/types.h>
#include <soc/nps/common.h>
/* core auxiliary registers */
};
/* AUX registers definition */
+struct nps_host_reg_aux_dpc {
+ union {
+ struct {
+ u32 ien:1, men:1, hen:1, reserved:29;
+ };
+ u32 value;
+ };
+};
+
struct nps_host_reg_aux_udmc {
union {
struct {
*/
#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
#include <linux/io.h>
#include <linux/log2.h>
#include <asm/arcregs.h>
/* Verify and set the value of the mtm hs counter */
static int __init set_mtm_hs_ctr(char *ctr_str)
{
- long hs_ctr;
+ int hs_ctr;
int ret;
- ret = kstrtol(ctr_str, 0, &hs_ctr);
+ ret = kstrtoint(ctr_str, 0, &hs_ctr);
if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) {
pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n",
menuconfig ARC_SOC_HSDK
bool "ARC HS Development Kit SOC"
+ depends on ISA_ARCV2
+ select ARC_HAS_ACCL_REGS
select CLK_HSDK
select RESET_HSDK
+ select MIGHT_HAVE_PCI
#define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108)
#define SDIO_UHS_REG_EXT_DIV_2 (2 << 30)
+#define HSDK_GPIO_INTC (ARC_PERIPHERAL_BASE + 0x3000)
+
+static void __init hsdk_enable_gpio_intc_wire(void)
+{
+ /*
+ * Peripherals on CPU Card are wired to cpu intc via intermediate
+ * DW APB GPIO blocks (mainly for debouncing)
+ *
+ * ---------------------
+ * | snps,archs-intc |
+ * ---------------------
+ * |
+ * ----------------------
+ * | snps,archs-idu-intc |
+ * ----------------------
+ * | | | | |
+ * | [eth] [USB] [... other peripherals]
+ * |
+ * -------------------
+ * | snps,dw-apb-intc |
+ * -------------------
+ * | | | |
+ * [Bt] [HAPS] [... other peripherals]
+ *
+ * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+ * with stacked INTCs. In particular problem happens if its master INTC
+ * not yet instantiated. See discussion here -
+ * https://lkml.org/lkml/2015/3/4/755
+ *
+ * So setup the first gpio block as a passive pass thru and hide it from
+ * DT hardware topology - connect intc directly to cpu intc
+ * The GPIO "wire" needs to be init nevertheless (here)
+ *
+ * One side adv is that peripheral interrupt handling avoids one nested
+ * intc ISR hop
+ *
+ * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping"
+ * we have the following GPIO input lines used as sources of interrupt:
+ * - GPIO[0] - Bluetooth interrupt of RS9113 module
+ * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector)
+ * - GPIO[3] - Audio codec (MAX9880A) interrupt
+ * - GPIO[8-23] - Available on Arduino and PMOD_x headers
+ * For now there's no use of Arduino and PMOD_x headers in Linux
+ * use-case so we only enable lines 0, 2 and 3.
+ *
+ * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf
+ */
+#define GPIO_INTEN (HSDK_GPIO_INTC + 0x30)
+#define GPIO_INTMASK (HSDK_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL (HSDK_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY (HSDK_GPIO_INTC + 0x3c)
+#define GPIO_INT_CONNECTED_MASK 0x0d
+
+ iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK);
+ iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK);
+ iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL);
+ iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY);
+ iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
+}
+
static void __init hsdk_init_early(void)
{
/*
* minimum possible div-by-2.
*/
iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+ hsdk_enable_gpio_intc_wire();
}
static const char *hsdk_compat[] __initconst = {
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
+ select ARCH_HAS_KCOV
+ select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
- select ARCH_HAS_SET_MEMORY
select ARCH_HAS_PHYS_TO_DMA
+ select ARCH_HAS_SET_MEMORY
select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
select ARCH_HAS_STRICT_MODULE_RWX if MMU
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select HAVE_ARCH_TRACEHOOK
select HAVE_ARM_SMCCC if CPU_V7
select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
- select HAVE_CC_STACKPROTECTOR
select HAVE_CONTEXT_TRACKING
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RSEQ
+ select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UID16
select HAVE_VIRT_CPU_ACCOUNTING_GEN
select TIMER_OF
select COMMON_CLK
select GENERIC_CLOCKEVENTS
+ select GENERIC_IRQ_MULTI_HANDLER
select MIGHT_HAVE_PCI
- select MULTI_IRQ_HANDLER
select PCI_DOMAINS if PCI
select SPARSE_IRQ
select USE_OF
bool "Marvell Dove"
select CPU_PJ4
select GENERIC_CLOCKEVENTS
+ select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
select MIGHT_HAVE_PCI
- select MULTI_IRQ_HANDLER
select MVEBU_MBUS
select PINCTRL
select PINCTRL_DOVE
select COMMON_CLK
select CPU_ARM926T
select GENERIC_CLOCKEVENTS
+ select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
- select MULTI_IRQ_HANDLER
select SPARSE_IRQ
select USE_OF
help
select TIMER_OF
select CPU_XSCALE if !CPU_XSC3
select GENERIC_CLOCKEVENTS
+ select GENERIC_IRQ_MULTI_HANDLER
select GPIO_PXA
select GPIOLIB
select HAVE_IDE
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
select PLAT_PXA
select SPARSE_IRQ
help
select CPU_FREQ
select CPU_SA1100
select GENERIC_CLOCKEVENTS
+ select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
select HAVE_IDE
select IRQ_DOMAIN
select ISA
- select MULTI_IRQ_HANDLER
select NEED_MACH_MEMORY_H
select SPARSE_IRQ
help
select GENERIC_CLOCKEVENTS
select GPIO_SAMSUNG
select GPIOLIB
+ select GENERIC_IRQ_MULTI_HANDLER
select HAVE_S3C2410_I2C if I2C
select HAVE_S3C2410_WATCHDOG if WATCHDOG
select HAVE_S3C_RTC if RTC_CLASS
- select MULTI_IRQ_HANDLER
select NEED_MACH_IO_H
select SAMSUNG_ATAGS
select USE_OF
select CLKSRC_MMIO
select GENERIC_CLOCKEVENTS
select GENERIC_IRQ_CHIP
+ select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
select HAVE_IDE
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
select NEED_MACH_IO_H if PCCARD
select NEED_MACH_MEMORY_H
select SPARSE_IRQ
Enable support for iWMMXt context switching at run time if
running on a CPU that supports it.
-config MULTI_IRQ_HANDLER
- bool
- help
- Allow each machine to specify it's own IRQ handler at run time.
-
if !MMU
source "arch/arm/Kconfig-nommu"
endif
VESA. If you have PCI, say Y, otherwise N.
config PCI_DOMAINS
- bool
+ bool "Support for multiple PCI domains"
depends on PCI
+ help
+ Enable PCI domains kernel management. Say Y if your machine
+ has a PCI bus hierarchy that requires more than one PCI
+ domain (aka segment) to be correctly managed. Say N otherwise.
+
+ If you don't know what to do here, say N.
config PCI_DOMAINS_GENERIC
def_bool PCI_DOMAINS
will run faster if you say N here.
See also <file:Documentation/x86/i386/IO-APIC.txt>,
- <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
+ <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at
<http://tldp.org/HOWTO/SMP-HOWTO.html>.
If you don't know what to do here, say N.
KBUILD_CPPFLAGS += -mbig-endian
CHECKFLAGS += -D__ARMEB__
AS += -EB
-LD += -EB
+LDFLAGS += -EB
else
KBUILD_CPPFLAGS += -mlittle-endian
CHECKFLAGS += -D__ARMEL__
AS += -EL
-LD += -EL
+LDFLAGS += -EL
endif
#
GCOV_PROFILE := n
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
#
# Architecture dependencies
#
AM33XX_IOPAD(0x8f0, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_dat3.mmc0_dat3 */
AM33XX_IOPAD(0x904, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_cmd.mmc0_cmd */
AM33XX_IOPAD(0x900, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_clk.mmc0_clk */
- AM33XX_IOPAD(0x9a0, PIN_INPUT | MUX_MODE4) /* mcasp0_aclkr.mmc0_sdwp */
>;
};
ti,davinci-ctrl-ram-size = <0x2000>;
ti,davinci-rmii-en = /bits/ 8 <1>;
local-mac-address = [ 00 00 00 00 00 00 ];
+ clocks = <&emac_ick>;
+ clock-names = "ick";
};
davinci_mdio: ethernet@5c030000 {
bus_freq = <1000000>;
#address-cells = <1>;
#size-cells = <0>;
+ clocks = <&emac_fck>;
+ clock-names = "fck";
};
uart4: serial@4809e000 {
};
};
+/* Table Table 5-79 of the TRM shows 480ab000 is reserved */
+&usb_otg_hs {
+ status = "disabled";
+};
+
&iva {
status = "disabled";
};
touchscreen-size-x = <480>;
touchscreen-size-y = <272>;
+
+ wakeup-source;
};
tlv320aic3106: tlv320aic3106@1b {
3700 5
3900 6
4000 7>;
- cooling-cells = <2>;
+ #cooling-cells = <2>;
};
gpio-leds {
thermal: thermal@e8078 {
compatible = "marvell,armada380-thermal";
- reg = <0xe4078 0x4>, <0xe4074 0x4>;
+ reg = <0xe4078 0x4>, <0xe4070 0x8>;
status = "okay";
};
reg = <0x18008000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 85 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x1800b000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>,
- <GIC_SPI 97 IRQ_TYPE_NONE>,
- <GIC_SPI 98 IRQ_TYPE_NONE>,
- <GIC_SPI 99 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 102 IRQ_TYPE_NONE>,
- <GIC_SPI 103 IRQ_TYPE_NONE>,
- <GIC_SPI 104 IRQ_TYPE_NONE>,
- <GIC_SPI 105 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
};
};
reg = <0x38000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 95 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
};
reg = <0x3b000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 182 IRQ_TYPE_NONE>,
- <GIC_SPI 183 IRQ_TYPE_NONE>,
- <GIC_SPI 184 IRQ_TYPE_NONE>,
- <GIC_SPI 185 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 188 IRQ_TYPE_NONE>,
- <GIC_SPI 189 IRQ_TYPE_NONE>,
- <GIC_SPI 190 IRQ_TYPE_NONE>,
- <GIC_SPI 191 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
reg = <0x38000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 89 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
dma-coherent;
status = "disabled";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 127 IRQ_TYPE_NONE>,
- <GIC_SPI 128 IRQ_TYPE_NONE>,
- <GIC_SPI 129 IRQ_TYPE_NONE>,
- <GIC_SPI 130 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 133 IRQ_TYPE_NONE>,
- <GIC_SPI 134 IRQ_TYPE_NONE>,
- <GIC_SPI 135 IRQ_TYPE_NONE>,
- <GIC_SPI 136 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <2>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 139 IRQ_TYPE_NONE>,
- <GIC_SPI 140 IRQ_TYPE_NONE>,
- <GIC_SPI 141 IRQ_TYPE_NONE>,
- <GIC_SPI 142 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
i2c0: i2c@18009000 {
compatible = "brcm,iproc-i2c";
reg = <0x18009000 0x50>;
- interrupts = <GIC_SPI 121 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
clock-frequency = <100000>;
gpio-controller;
#gpio-cells = <2>;
reg = <0x226000 0x1000>;
- interrupts = <42 IRQ_TYPE_EDGE_BOTH
- 43 IRQ_TYPE_EDGE_BOTH 44 IRQ_TYPE_EDGE_BOTH
- 45 IRQ_TYPE_EDGE_BOTH 46 IRQ_TYPE_EDGE_BOTH
- 47 IRQ_TYPE_EDGE_BOTH 48 IRQ_TYPE_EDGE_BOTH
- 49 IRQ_TYPE_EDGE_BOTH 50 IRQ_TYPE_EDGE_BOTH>;
+ interrupts = <42 43 44 45 46 47 48 49 50>;
ti,ngpio = <144>;
ti,davinci-gpio-unbanked = <0>;
status = "disabled";
dr_mode = "otg";
snps,dis_u3_susphy_quirk;
snps,dis_u2_susphy_quirk;
- snps,dis_metastability_quirk;
};
};
dr_mode = "otg";
snps,dis_u3_susphy_quirk;
snps,dis_u2_susphy_quirk;
+ snps,dis_metastability_quirk;
};
};
pinctrl_ts: tsgrp {
fsl,pins = <
- MX51_PAD_CSI1_D8__GPIO3_12 0x85
+ MX51_PAD_CSI1_D8__GPIO3_12 0x04
MX51_PAD_CSI1_D9__GPIO3_13 0x85
>;
};
clocks = <&clks IMX6Q_CLK_ECSPI5>,
<&clks IMX6Q_CLK_ECSPI5>;
clock-names = "ipg", "per";
- dmas = <&sdma 11 7 1>, <&sdma 12 7 2>;
+ dmas = <&sdma 11 8 1>, <&sdma 12 8 2>;
dma-names = "rx", "tx";
status = "disabled";
};
dsa,member = <0 0>;
eeprom-length = <512>;
interrupt-parent = <&gpio6>;
- interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+ interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
interrupt-controller;
#interrupt-cells = <2>;
ranges = <0x81000000 0 0 0x08f80000 0 0x00010000 /* downstream I/O */
0x82000000 0 0x08000000 0x08000000 0 0x00f00000>; /* non-prefetchable memory */
num-lanes = <1>;
- interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "msi";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0x7>;
dais = <&mcbsp2_port>, <&mcbsp3_port>;
};
-};
-
-&dss {
- status = "okay";
-};
-&gpio6 {
pwm8: dmtimer-pwm-8 {
pinctrl-names = "default";
pinctrl-0 = <&vibrator_direction_pin>;
pwm-names = "enable", "direction";
direction-duty-cycle-ns = <10000000>;
};
+};
+&dss {
+ status = "okay";
};
&dsi1 {
nand0: nand@ff900000 {
#address-cells = <0x1>;
#size-cells = <0x1>;
- compatible = "denali,denali-nand-dt";
+ compatible = "altr,socfpga-denali-nand";
reg = <0xff900000 0x100000>,
<0xffb80000 0x10000>;
reg-names = "nand_data", "denali_reg";
interrupts = <0x0 0x90 0x4>;
dma-mask = <0xffffffff>;
- clocks = <&nand_clk>;
+ clocks = <&nand_x_clk>;
status = "disabled";
};
#size-cells = <0>;
reg = <0xffda5000 0x100>;
interrupts = <0 102 4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
/*32bit_access;*/
tx-dma-channel = <&pdma 16>;
rx-dma-channel = <&pdma 17>;
nand: nand@ffb90000 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "denali,denali-nand-dt", "altr,socfpga-denali-nand";
+ compatible = "altr,socfpga-denali-nand";
reg = <0xffb90000 0x72000>,
<0xffb80000 0x10000>;
reg-names = "nand_data", "denali_reg";
obj-$(CONFIG_SHARP_LOCOMO) += locomo.o
obj-$(CONFIG_SHARP_PARAM) += sharpsl_param.o
obj-$(CONFIG_SHARP_SCOOP) += scoop.o
-obj-$(CONFIG_SMP) += secure_cntvoff.o
+obj-$(CONFIG_CPU_V7) += secure_cntvoff.o
obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o
obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
CFLAGS_REMOVE_mcpm_entry.o = -pg
CONFIG_USB_CHIPIDEA=y
CONFIG_USB_CHIPIDEA_UDC=y
CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
CONFIG_NOP_USB_XCEIV=y
CONFIG_USB_GADGET=y
CONFIG_USB_ETH=m
+CONFIG_USB_ULPI_BUS=y
CONFIG_MMC=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_USB_CHIPIDEA=y
CONFIG_USB_CHIPIDEA_UDC=y
CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
CONFIG_USB_SERIAL=m
CONFIG_USB_SERIAL_GENERIC=y
CONFIG_USB_SERIAL_FTDI_SIO=m
CONFIG_USB_FUNCTIONFS=m
CONFIG_USB_MASS_STORAGE=m
CONFIG_USB_G_SERIAL=m
+CONFIG_USB_ULPI_BUS=y
CONFIG_MMC=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_CGROUPS=y
CONFIG_MODULE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_CMDLINE_PARTITION=y
-CONFIG_ARCH_MULTI_V7=y
-# CONFIG_ARCH_MULTI_V5 is not set
-# CONFIG_ARCH_MULTI_V4 is not set
CONFIG_ARCH_VIRT=y
CONFIG_ARCH_ALPINE=y
CONFIG_ARCH_ARTPEC=y
CONFIG_MACH_ARTPEC6=y
-CONFIG_ARCH_MVEBU=y
-CONFIG_MACH_ARMADA_370=y
-CONFIG_MACH_ARMADA_375=y
-CONFIG_MACH_ARMADA_38X=y
-CONFIG_MACH_ARMADA_39X=y
-CONFIG_MACH_ARMADA_XP=y
-CONFIG_MACH_DOVE=y
CONFIG_ARCH_AT91=y
CONFIG_SOC_SAMA5D2=y
CONFIG_SOC_SAMA5D3=y
CONFIG_ARCH_BCM_CYGNUS=y
CONFIG_ARCH_BCM_HR2=y
CONFIG_ARCH_BCM_NSP=y
-CONFIG_ARCH_BCM_21664=y
-CONFIG_ARCH_BCM_281XX=y
CONFIG_ARCH_BCM_5301X=y
+CONFIG_ARCH_BCM_281XX=y
+CONFIG_ARCH_BCM_21664=y
CONFIG_ARCH_BCM2835=y
CONFIG_ARCH_BCM_63XX=y
CONFIG_ARCH_BRCMSTB=y
CONFIG_MACH_BERLIN_BG2CD=y
CONFIG_MACH_BERLIN_BG2Q=y
CONFIG_ARCH_DIGICOLOR=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_EXYNOS5420_MCPM=y
CONFIG_ARCH_HIGHBANK=y
CONFIG_ARCH_HISI=y
CONFIG_ARCH_HI3xxx=y
-CONFIG_ARCH_HIX5HD2=y
CONFIG_ARCH_HIP01=y
CONFIG_ARCH_HIP04=y
-CONFIG_ARCH_KEYSTONE=y
-CONFIG_ARCH_MESON=y
+CONFIG_ARCH_HIX5HD2=y
CONFIG_ARCH_MXC=y
CONFIG_SOC_IMX50=y
CONFIG_SOC_IMX51=y
CONFIG_SOC_IMX6SX=y
CONFIG_SOC_IMX6UL=y
CONFIG_SOC_IMX7D=y
-CONFIG_SOC_VF610=y
CONFIG_SOC_LS1021A=y
+CONFIG_SOC_VF610=y
+CONFIG_ARCH_KEYSTONE=y
+CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_MESON=y
+CONFIG_ARCH_MVEBU=y
+CONFIG_MACH_ARMADA_370=y
+CONFIG_MACH_ARMADA_375=y
+CONFIG_MACH_ARMADA_38X=y
+CONFIG_MACH_ARMADA_39X=y
+CONFIG_MACH_ARMADA_XP=y
+CONFIG_MACH_DOVE=y
CONFIG_ARCH_OMAP3=y
CONFIG_ARCH_OMAP4=y
CONFIG_SOC_OMAP5=y
CONFIG_SOC_AM33XX=y
CONFIG_SOC_AM43XX=y
CONFIG_SOC_DRA7XX=y
+CONFIG_ARCH_SIRF=y
CONFIG_ARCH_QCOM=y
-CONFIG_ARCH_MEDIATEK=y
CONFIG_ARCH_MSM8X60=y
CONFIG_ARCH_MSM8960=y
CONFIG_ARCH_MSM8974=y
CONFIG_ARCH_ROCKCHIP=y
-CONFIG_ARCH_SOCFPGA=y
-CONFIG_PLAT_SPEAR=y
-CONFIG_ARCH_SPEAR13XX=y
-CONFIG_MACH_SPEAR1310=y
-CONFIG_MACH_SPEAR1340=y
-CONFIG_ARCH_STI=y
-CONFIG_ARCH_STM32=y
-CONFIG_ARCH_EXYNOS=y
-CONFIG_EXYNOS5420_MCPM=y
CONFIG_ARCH_RENESAS=y
CONFIG_ARCH_EMEV2=y
CONFIG_ARCH_R7S72100=y
CONFIG_ARCH_R8A7793=y
CONFIG_ARCH_R8A7794=y
CONFIG_ARCH_SH73A0=y
+CONFIG_ARCH_SOCFPGA=y
+CONFIG_PLAT_SPEAR=y
+CONFIG_ARCH_SPEAR13XX=y
+CONFIG_MACH_SPEAR1310=y
+CONFIG_MACH_SPEAR1340=y
+CONFIG_ARCH_STI=y
+CONFIG_ARCH_STM32=y
CONFIG_ARCH_SUNXI=y
-CONFIG_ARCH_SIRF=y
CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_TEGRA_2x_SOC=y
-CONFIG_ARCH_TEGRA_3x_SOC=y
-CONFIG_ARCH_TEGRA_114_SOC=y
-CONFIG_ARCH_TEGRA_124_SOC=y
CONFIG_ARCH_UNIPHIER=y
CONFIG_ARCH_U8500=y
-CONFIG_MACH_HREFV60=y
-CONFIG_MACH_SNOWBALL=y
CONFIG_ARCH_VEXPRESS=y
CONFIG_ARCH_VEXPRESS_TC2_PM=y
CONFIG_ARCH_WM8850=y
CONFIG_ARCH_ZYNQ=y
-CONFIG_TRUSTED_FOUNDATIONS=y
-CONFIG_PCI=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCI_DRA7XX=y
-CONFIG_PCI_DRA7XX_EP=y
-CONFIG_PCI_KEYSTONE=y
-CONFIG_PCI_MSI=y
+CONFIG_PCIEPORTBUS=y
CONFIG_PCI_MVEBU=y
CONFIG_PCI_TEGRA=y
CONFIG_PCI_RCAR_GEN2=y
CONFIG_PCIE_RCAR=y
-CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_KEYSTONE=y
CONFIG_PCI_ENDPOINT=y
CONFIG_PCI_ENDPOINT_CONFIGFS=y
CONFIG_PCI_EPF_TEST=m
CONFIG_SMP=y
CONFIG_NR_CPUS=16
-CONFIG_HIGHPTE=y
-CONFIG_CMA=y
CONFIG_SECCOMP=y
CONFIG_ARM_APPENDED_DTB=y
CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
+CONFIG_CPUFREQ_DT=y
CONFIG_ARM_IMX6Q_CPUFREQ=y
CONFIG_QORIQ_CPUFREQ=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_CPUIDLE=y
-CONFIG_NEON=y
-CONFIG_KERNEL_MODE_NEON=y
CONFIG_ARM_ZYNQ_CPUIDLE=y
CONFIG_ARM_EXYNOS_CPUIDLE=y
+CONFIG_KERNEL_MODE_NEON=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_IPV6_TUNNEL=m
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_NET_DSA=m
-CONFIG_NET_SWITCHDEV=y
CONFIG_CAN=y
-CONFIG_CAN_RAW=y
-CONFIG_CAN_BCM=y
-CONFIG_CAN_DEV=y
CONFIG_CAN_AT91=m
CONFIG_CAN_FLEXCAN=m
-CONFIG_CAN_RCAR=m
+CONFIG_CAN_SUN4I=y
CONFIG_CAN_XILINXCAN=y
+CONFIG_CAN_RCAR=m
CONFIG_CAN_MCP251X=y
-CONFIG_NET_DSA_BCM_SF2=m
-CONFIG_B53=m
-CONFIG_B53_SPI_DRIVER=m
-CONFIG_B53_MDIO_DRIVER=m
-CONFIG_B53_MMAP_DRIVER=m
-CONFIG_B53_SRAB_DRIVER=m
-CONFIG_CAN_SUN4I=y
CONFIG_BT=m
CONFIG_BT_HCIUART=m
CONFIG_BT_HCIUART_BCM=y
CONFIG_RFKILL_GPIO=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=64
CONFIG_OMAP_OCP2SCP=y
CONFIG_SIMPLE_PM_BUS=y
-CONFIG_SUNXI_RSB=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
CONFIG_EEPROM_AT24=y
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_MULTI_LUN=y
CONFIG_ATA=y
CONFIG_SATA_AHCI=y
CONFIG_SATA_AHCI_PLATFORM=y
CONFIG_SATA_RCAR=y
CONFIG_NETDEVICES=y
CONFIG_VIRTIO_NET=y
-CONFIG_HIX5HD2_GMAC=y
+CONFIG_B53_SPI_DRIVER=m
+CONFIG_B53_MDIO_DRIVER=m
+CONFIG_B53_MMAP_DRIVER=m
+CONFIG_B53_SRAB_DRIVER=m
+CONFIG_NET_DSA_BCM_SF2=m
CONFIG_SUN4I_EMAC=y
-CONFIG_MACB=y
CONFIG_BCMGENET=m
CONFIG_BGMAC_BCMA=y
CONFIG_SYSTEMPORT=m
+CONFIG_MACB=y
CONFIG_NET_CALXEDA_XGMAC=y
CONFIG_GIANFAR=y
+CONFIG_HIX5HD2_GMAC=y
+CONFIG_E1000E=y
CONFIG_IGB=y
CONFIG_MV643XX_ETH=y
CONFIG_MVNETA=y
CONFIG_SH_ETH=y
CONFIG_SMSC911X=y
CONFIG_STMMAC_ETH=y
-CONFIG_STMMAC_PLATFORM=y
CONFIG_DWMAC_DWC_QOS_ETH=y
CONFIG_TI_CPSW=y
CONFIG_XILINX_EMACLITE=y
CONFIG_AT803X_PHY=y
-CONFIG_MARVELL_PHY=y
-CONFIG_SMSC_PHY=y
CONFIG_BROADCOM_PHY=y
CONFIG_ICPLUS_PHY=y
-CONFIG_REALTEK_PHY=y
+CONFIG_MARVELL_PHY=y
CONFIG_MICREL_PHY=y
-CONFIG_FIXED_PHY=y
+CONFIG_REALTEK_PHY=y
CONFIG_ROCKCHIP_PHY=y
+CONFIG_SMSC_PHY=y
CONFIG_USB_PEGASUS=y
CONFIG_USB_RTL8152=m
CONFIG_USB_LAN78XX=m
CONFIG_USB_NET_SMSC75XX=y
CONFIG_USB_NET_SMSC95XX=y
CONFIG_BRCMFMAC=m
-CONFIG_RT2X00=m
-CONFIG_RT2800USB=m
CONFIG_MWIFIEX=m
CONFIG_MWIFIEX_SDIO=m
+CONFIG_RT2X00=m
+CONFIG_RT2800USB=m
CONFIG_INPUT_JOYDEV=y
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_QT1070=m
CONFIG_KEYBOARD_GPIO=y
CONFIG_KEYBOARD_TEGRA=y
-CONFIG_KEYBOARD_SPEAR=y
+CONFIG_KEYBOARD_SAMSUNG=m
CONFIG_KEYBOARD_ST_KEYSCAN=y
+CONFIG_KEYBOARD_SPEAR=y
CONFIG_KEYBOARD_CROS_EC=m
-CONFIG_KEYBOARD_SAMSUNG=m
CONFIG_MOUSE_PS2_ELANTECH=y
CONFIG_MOUSE_CYAPA=m
CONFIG_MOUSE_ELAN_I2C=y
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_ATMEL_MXT=m
CONFIG_TOUCHSCREEN_MMS114=m
+CONFIG_TOUCHSCREEN_WM97XX=m
CONFIG_TOUCHSCREEN_ST1232=m
CONFIG_TOUCHSCREEN_STMPE=y
CONFIG_TOUCHSCREEN_SUN4I=y
-CONFIG_TOUCHSCREEN_WM97XX=m
CONFIG_INPUT_MISC=y
CONFIG_INPUT_MAX77693_HAPTIC=m
CONFIG_INPUT_MAX8997_HAPTIC=m
CONFIG_SERIAL_8250_EM=y
CONFIG_SERIAL_8250_MT6577=y
CONFIG_SERIAL_8250_UNIPHIER=y
+CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
CONFIG_SERIAL_ATMEL=y
CONFIG_SERIAL_ATMEL_CONSOLE=y
CONFIG_SERIAL_ATMEL_TTYAT=y
-CONFIG_SERIAL_BCM63XX=y
-CONFIG_SERIAL_BCM63XX_CONSOLE=y
CONFIG_SERIAL_MESON=y
CONFIG_SERIAL_MESON_CONSOLE=y
CONFIG_SERIAL_SAMSUNG=y
CONFIG_SERIAL_IMX_CONSOLE=y
CONFIG_SERIAL_SH_SCI=y
CONFIG_SERIAL_SH_SCI_NR_UARTS=20
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_SH_SCI_DMA=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_VT8500=y
CONFIG_SERIAL_VT8500_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_OMAP=y
CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_SERIAL_BCM63XX=y
+CONFIG_SERIAL_BCM63XX_CONSOLE=y
CONFIG_SERIAL_XILINX_PS_UART=y
CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
CONFIG_SERIAL_FSL_LPUART=y
CONFIG_SERIAL_STM32=y
CONFIG_SERIAL_STM32_CONSOLE=y
CONFIG_SERIAL_DEV_BUS=y
-CONFIG_HVC_DRIVER=y
CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_ST=y
CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_DAVINCI=y
-CONFIG_I2C_MESON=y
-CONFIG_I2C_MUX=y
CONFIG_I2C_ARB_GPIO_CHALLENGE=m
CONFIG_I2C_MUX_PCA954x=y
CONFIG_I2C_MUX_PINCTRL=y
CONFIG_I2C_AT91=m
CONFIG_I2C_BCM2835=y
CONFIG_I2C_CADENCE=y
+CONFIG_I2C_DAVINCI=y
CONFIG_I2C_DESIGNWARE_PLATFORM=y
CONFIG_I2C_DIGICOLOR=m
CONFIG_I2C_EMEV2=m
CONFIG_I2C_GPIO=m
-CONFIG_I2C_EXYNOS5=y
CONFIG_I2C_IMX=y
+CONFIG_I2C_MESON=y
CONFIG_I2C_MV64XXX=y
CONFIG_I2C_RIIC=y
CONFIG_I2C_RK3X=y
CONFIG_SPMI=y
CONFIG_PINCTRL_AS3722=y
CONFIG_PINCTRL_PALMAS=y
-CONFIG_PINCTRL_BCM2835=y
CONFIG_PINCTRL_APQ8064=y
CONFIG_PINCTRL_APQ8084=y
CONFIG_PINCTRL_IPQ8064=y
CONFIG_PINCTRL_MSM8916=y
CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
-CONFIG_GPIO_GENERIC_PLATFORM=y
CONFIG_GPIO_DAVINCI=y
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_EM=y
CONFIG_GPIO_RCAR=y
+CONFIG_GPIO_SYSCON=y
CONFIG_GPIO_UNIPHIER=y
CONFIG_GPIO_XILINX=y
CONFIG_GPIO_ZYNQ=y
CONFIG_GPIO_PCA953X=y
CONFIG_GPIO_PCA953X_IRQ=y
CONFIG_GPIO_PCF857X=y
-CONFIG_GPIO_TWL4030=y
CONFIG_GPIO_PALMAS=y
-CONFIG_GPIO_SYSCON=y
CONFIG_GPIO_TPS6586X=y
CONFIG_GPIO_TPS65910=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_POWER_AVS=y
+CONFIG_ROCKCHIP_IODOMAIN=y
+CONFIG_POWER_RESET_AS3722=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_RESET_GPIO_RESTART=y
+CONFIG_POWER_RESET_ST=y
+CONFIG_POWER_RESET_KEYSTONE=y
+CONFIG_POWER_RESET_RMOBILE=y
CONFIG_BATTERY_ACT8945A=y
CONFIG_BATTERY_CPCAP=m
CONFIG_BATTERY_SBS=y
+CONFIG_AXP20X_POWER=m
CONFIG_BATTERY_MAX17040=m
CONFIG_BATTERY_MAX17042=m
CONFIG_CHARGER_CPCAP=m
CONFIG_CHARGER_MAX8997=m
CONFIG_CHARGER_MAX8998=m
CONFIG_CHARGER_TPS65090=y
-CONFIG_AXP20X_POWER=m
-CONFIG_POWER_RESET_AS3722=y
-CONFIG_POWER_RESET_GPIO=y
-CONFIG_POWER_RESET_GPIO_RESTART=y
-CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_RMOBILE=y
-CONFIG_POWER_RESET_ST=y
-CONFIG_POWER_AVS=y
-CONFIG_ROCKCHIP_IODOMAIN=y
CONFIG_SENSORS_IIO_HWMON=y
CONFIG_SENSORS_LM90=y
CONFIG_SENSORS_LM95245=y
CONFIG_SENSORS_PWM_FAN=m
CONFIG_SENSORS_INA2XX=m
CONFIG_CPU_THERMAL=y
-CONFIG_BCM2835_THERMAL=m
-CONFIG_BRCMSTB_THERMAL=m
CONFIG_IMX_THERMAL=y
CONFIG_ROCKCHIP_THERMAL=y
CONFIG_RCAR_THERMAL=y
CONFIG_ARMADA_THERMAL=y
-CONFIG_DAVINCI_WATCHDOG=m
-CONFIG_EXYNOS_THERMAL=m
+CONFIG_BCM2835_THERMAL=m
+CONFIG_BRCMSTB_THERMAL=m
CONFIG_ST_THERMAL_MEMMAP=y
CONFIG_WATCHDOG=y
CONFIG_DA9063_WATCHDOG=m
CONFIG_ARM_SP805_WATCHDOG=y
CONFIG_AT91SAM9X_WATCHDOG=y
CONFIG_SAMA5D4_WATCHDOG=y
+CONFIG_DW_WATCHDOG=y
+CONFIG_DAVINCI_WATCHDOG=m
CONFIG_ORION_WATCHDOG=y
CONFIG_RN5T618_WATCHDOG=y
-CONFIG_ST_LPC_WATCHDOG=y
CONFIG_SUNXI_WATCHDOG=y
CONFIG_IMX2_WDT=y
+CONFIG_ST_LPC_WATCHDOG=y
CONFIG_TEGRA_WATCHDOG=m
CONFIG_MESON_WATCHDOG=y
-CONFIG_DW_WATCHDOG=y
CONFIG_DIGICOLOR_WATCHDOG=y
CONFIG_RENESAS_WDT=m
-CONFIG_BCM2835_WDT=y
CONFIG_BCM47XX_WDT=y
-CONFIG_BCM7038_WDT=m
+CONFIG_BCM2835_WDT=y
CONFIG_BCM_KONA_WDT=y
+CONFIG_BCM7038_WDT=m
+CONFIG_BCMA_HOST_SOC=y
+CONFIG_BCMA_DRIVER_GMAC_CMN=y
+CONFIG_BCMA_DRIVER_GPIO=y
CONFIG_MFD_ACT8945A=y
CONFIG_MFD_AS3711=y
CONFIG_MFD_AS3722=y
CONFIG_MFD_ATMEL_HLCDC=m
CONFIG_MFD_BCM590XX=y
CONFIG_MFD_AC100=y
-CONFIG_MFD_AXP20X=y
CONFIG_MFD_AXP20X_I2C=y
CONFIG_MFD_AXP20X_RSB=y
CONFIG_MFD_CROS_EC=m
CONFIG_MFD_MAX8907=y
CONFIG_MFD_MAX8997=y
CONFIG_MFD_MAX8998=y
-CONFIG_MFD_RK808=y
CONFIG_MFD_CPCAP=y
CONFIG_MFD_PM8XXX=y
CONFIG_MFD_QCOM_RPM=y
CONFIG_MFD_SPMI_PMIC=y
+CONFIG_MFD_RK808=y
CONFIG_MFD_RN5T618=y
CONFIG_MFD_SEC_CORE=y
CONFIG_MFD_STMPE=y
CONFIG_MFD_TPS65218=y
CONFIG_MFD_TPS6586X=y
CONFIG_MFD_TPS65910=y
-CONFIG_REGULATOR_ACT8945A=y
-CONFIG_REGULATOR_AB8500=y
CONFIG_REGULATOR_ACT8865=y
+CONFIG_REGULATOR_ACT8945A=y
CONFIG_REGULATOR_ANATOP=y
+CONFIG_REGULATOR_AB8500=y
CONFIG_REGULATOR_AS3711=y
CONFIG_REGULATOR_AS3722=y
CONFIG_REGULATOR_AXP20X=y
CONFIG_REGULATOR_CPCAP=y
CONFIG_REGULATOR_DA9210=y
CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_GPIO=y
-CONFIG_MFD_SYSCON=y
-CONFIG_POWER_RESET_SYSCON=y
CONFIG_REGULATOR_LP872X=y
CONFIG_REGULATOR_MAX14577=m
CONFIG_REGULATOR_MAX8907=y
CONFIG_REGULATOR_PBIAS=y
CONFIG_REGULATOR_PWM=y
CONFIG_REGULATOR_QCOM_RPM=y
-CONFIG_REGULATOR_QCOM_SMD_RPM=y
+CONFIG_REGULATOR_QCOM_SMD_RPM=m
+CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_RN5T618=y
CONFIG_REGULATOR_S2MPS11=y
CONFIG_REGULATOR_S5M8767=y
CONFIG_MEDIA_CONTROLLER=y
CONFIG_VIDEO_V4L2_SUBDEV_API=y
CONFIG_MEDIA_USB_SUPPORT=y
-CONFIG_USB_VIDEO_CLASS=y
-CONFIG_USB_GSPCA=y
+CONFIG_USB_VIDEO_CLASS=m
CONFIG_V4L_PLATFORM_DRIVERS=y
CONFIG_SOC_CAMERA=m
CONFIG_SOC_CAMERA_PLATFORM=m
-CONFIG_VIDEO_RCAR_VIN=m
-CONFIG_VIDEO_ATMEL_ISI=m
CONFIG_VIDEO_SAMSUNG_EXYNOS4_IS=m
CONFIG_VIDEO_S5P_FIMC=m
CONFIG_VIDEO_S5P_MIPI_CSIS=m
CONFIG_VIDEO_EXYNOS_FIMC_LITE=m
CONFIG_VIDEO_EXYNOS4_FIMC_IS=m
+CONFIG_VIDEO_RCAR_VIN=m
+CONFIG_VIDEO_ATMEL_ISI=m
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
CONFIG_VIDEO_RENESAS_JPU=m
CONFIG_VIDEO_RENESAS_VSP1=m
CONFIG_V4L_TEST_DRIVERS=y
+CONFIG_VIDEO_VIVID=m
CONFIG_CEC_PLATFORM_DRIVERS=y
CONFIG_VIDEO_SAMSUNG_S5P_CEC=m
# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
CONFIG_VIDEO_ADV7180=m
CONFIG_VIDEO_ML86V7667=m
CONFIG_DRM=y
-CONFIG_DRM_I2C_ADV7511=m
-CONFIG_DRM_I2C_ADV7511_AUDIO=y
# CONFIG_DRM_I2C_CH7006 is not set
# CONFIG_DRM_I2C_SIL164 is not set
-CONFIG_DRM_DUMB_VGA_DAC=m
-CONFIG_DRM_NXP_PTN3460=m
-CONFIG_DRM_PARADE_PS8622=m
CONFIG_DRM_NOUVEAU=m
CONFIG_DRM_EXYNOS=m
CONFIG_DRM_EXYNOS_FIMD=y
CONFIG_DRM_SUN4I=m
CONFIG_DRM_FSL_DCU=m
CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SIMPLE=y
CONFIG_DRM_PANEL_SAMSUNG_LD9040=m
CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03=m
CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
-CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_DUMB_VGA_DAC=m
+CONFIG_DRM_NXP_PTN3460=m
+CONFIG_DRM_PARADE_PS8622=m
CONFIG_DRM_SII9234=m
+CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_I2C_ADV7511_AUDIO=y
CONFIG_DRM_STI=m
-CONFIG_DRM_VC4=y
+CONFIG_DRM_VC4=m
CONFIG_DRM_ETNAVIV=m
CONFIG_DRM_MXSFB=m
CONFIG_FB_ARMCLCD=y
CONFIG_FB_WM8505=y
CONFIG_FB_SH_MOBILE_LCDC=y
CONFIG_FB_SIMPLE=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_LCD_PLATFORM=m
CONFIG_BACKLIGHT_PWM=y
CONFIG_BACKLIGHT_AS3711=y
CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_DYNAMIC_MINORS=y
CONFIG_SND_HDA_TEGRA=m
CONFIG_SND_HDA_INPUT_BEEP=y
CONFIG_SND_HDA_PATCH_LOADER=y
CONFIG_SND_SOC_ODROID=m
CONFIG_SND_SOC_SH4_FSI=m
CONFIG_SND_SOC_RCAR=m
-CONFIG_SND_SIMPLE_SCU_CARD=m
+CONFIG_SND_SOC_STI=m
CONFIG_SND_SUN4I_CODEC=m
CONFIG_SND_SOC_TEGRA=m
CONFIG_SND_SOC_TEGRA20_I2S=m
CONFIG_SND_SOC_TEGRA_WM9712=m
CONFIG_SND_SOC_TEGRA_TRIMSLICE=m
CONFIG_SND_SOC_TEGRA_ALC5632=m
-CONFIG_SND_SOC_CPCAP=m
CONFIG_SND_SOC_TEGRA_MAX98090=m
CONFIG_SND_SOC_AK4642=m
+CONFIG_SND_SOC_CPCAP=m
CONFIG_SND_SOC_SGTL5000=m
CONFIG_SND_SOC_SPDIF=m
-CONFIG_SND_SOC_WM8978=m
-CONFIG_SND_SOC_STI=m
CONFIG_SND_SOC_STI_SAS=m
-CONFIG_SND_SIMPLE_CARD=m
+CONFIG_SND_SOC_WM8978=m
+CONFIG_SND_SIMPLE_SCU_CARD=m
CONFIG_USB=y
CONFIG_USB_OTG=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_XHCI_MVEBU=y
-CONFIG_USB_XHCI_RCAR=m
CONFIG_USB_XHCI_TEGRA=m
CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_MSM=m
-CONFIG_USB_EHCI_EXYNOS=y
-CONFIG_USB_EHCI_TEGRA=y
CONFIG_USB_EHCI_HCD_STI=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760=y
+CONFIG_USB_EHCI_TEGRA=y
+CONFIG_USB_EHCI_EXYNOS=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_STI=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_OHCI_EXYNOS=m
CONFIG_USB_R8A66597_HCD=m
CONFIG_USB_RENESAS_USBHS=m
CONFIG_USB_TUSB_OMAP_DMA=y
CONFIG_USB_DWC3=y
CONFIG_USB_DWC2=y
-CONFIG_USB_HSIC_USB3503=y
CONFIG_USB_CHIPIDEA=y
CONFIG_USB_CHIPIDEA_UDC=y
CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_ISP1760=y
+CONFIG_USB_HSIC_USB3503=y
CONFIG_AB8500_USB=y
-CONFIG_KEYSTONE_USB_PHY=y
+CONFIG_KEYSTONE_USB_PHY=m
CONFIG_NOP_USB_XCEIV=m
CONFIG_AM335X_PHY_USB=m
CONFIG_TWL6030_USB=m
CONFIG_USB_GPIO_VBUS=y
CONFIG_USB_ISP1301=y
-CONFIG_USB_MSM_OTG=m
CONFIG_USB_MXS_PHY=y
CONFIG_USB_GADGET=y
CONFIG_USB_FSL_USB2=y
CONFIG_MMC_SDHCI_ESDHC_IMX=y
CONFIG_MMC_SDHCI_DOVE=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_S3C=y
CONFIG_MMC_SDHCI_PXAV3=y
CONFIG_MMC_SDHCI_SPEAR=y
-CONFIG_MMC_SDHCI_S3C=y
CONFIG_MMC_SDHCI_S3C_DMA=y
CONFIG_MMC_SDHCI_BCM_KONA=y
+CONFIG_MMC_MESON_MX_SDIO=y
CONFIG_MMC_SDHCI_ST=y
CONFIG_MMC_OMAP=y
CONFIG_MMC_OMAP_HS=y
CONFIG_MMC_ATMELMCI=y
CONFIG_MMC_SDHCI_MSM=y
-CONFIG_MMC_MESON_MX_SDIO=y
CONFIG_MMC_MVSDIO=y
CONFIG_MMC_SDHI=y
CONFIG_MMC_DW=y
-CONFIG_MMC_DW_PLTFM=y
CONFIG_MMC_DW_EXYNOS=y
CONFIG_MMC_DW_ROCKCHIP=y
CONFIG_MMC_SH_MMCIF=y
CONFIG_RTC_DRV_RK808=m
CONFIG_RTC_DRV_RS5C372=m
CONFIG_RTC_DRV_BQ32K=m
-CONFIG_RTC_DRV_PALMAS=y
-CONFIG_RTC_DRV_ST_LPC=y
CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_PALMAS=y
CONFIG_RTC_DRV_TPS6586X=y
CONFIG_RTC_DRV_TPS65910=y
CONFIG_RTC_DRV_S35390A=m
CONFIG_RTC_DRV_RX8581=m
CONFIG_RTC_DRV_EM3027=y
+CONFIG_RTC_DRV_S5M=m
CONFIG_RTC_DRV_DA9063=m
CONFIG_RTC_DRV_EFI=m
CONFIG_RTC_DRV_DIGICOLOR=m
-CONFIG_RTC_DRV_S5M=m
CONFIG_RTC_DRV_S3C=m
CONFIG_RTC_DRV_PL031=y
CONFIG_RTC_DRV_AT91RM9200=m
CONFIG_RTC_DRV_AT91SAM9=m
CONFIG_RTC_DRV_VT8500=y
-CONFIG_RTC_DRV_SUN6I=y
CONFIG_RTC_DRV_SUNXI=y
CONFIG_RTC_DRV_MV=y
CONFIG_RTC_DRV_TEGRA=y
+CONFIG_RTC_DRV_ST_LPC=y
CONFIG_RTC_DRV_CPCAP=m
CONFIG_DMADEVICES=y
-CONFIG_DW_DMAC=y
CONFIG_AT_HDMAC=y
CONFIG_AT_XDMAC=y
+CONFIG_DMA_BCM2835=y
+CONFIG_DMA_SUN6I=y
CONFIG_FSL_EDMA=y
+CONFIG_IMX_DMA=y
+CONFIG_IMX_SDMA=y
CONFIG_MV_XOR=y
+CONFIG_MXS_DMA=y
+CONFIG_PL330_DMA=y
+CONFIG_SIRF_DMA=y
+CONFIG_STE_DMA40=y
+CONFIG_ST_FDMA=m
CONFIG_TEGRA20_APB_DMA=y
+CONFIG_XILINX_DMA=y
+CONFIG_QCOM_BAM_DMA=y
+CONFIG_DW_DMAC=y
CONFIG_SH_DMAE=y
CONFIG_RCAR_DMAC=y
CONFIG_RENESAS_USB_DMAC=m
-CONFIG_STE_DMA40=y
-CONFIG_SIRF_DMA=y
-CONFIG_TI_EDMA=y
-CONFIG_PL330_DMA=y
-CONFIG_IMX_SDMA=y
-CONFIG_IMX_DMA=y
-CONFIG_MXS_DMA=y
-CONFIG_DMA_BCM2835=y
-CONFIG_DMA_OMAP=y
-CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_DMA=y
-CONFIG_DMA_SUN6I=y
-CONFIG_ST_FDMA=m
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
CONFIG_STAGING=y
-CONFIG_SENSORS_ISL29018=y
-CONFIG_SENSORS_ISL29028=y
CONFIG_MFD_NVEC=y
CONFIG_KEYBOARD_NVEC=y
CONFIG_SERIO_NVEC_PS2=y
CONFIG_NVEC_POWER=y
CONFIG_NVEC_PAZ00=y
-CONFIG_BCMA=y
-CONFIG_BCMA_HOST_SOC=y
-CONFIG_BCMA_DRIVER_GMAC_CMN=y
-CONFIG_BCMA_DRIVER_GPIO=y
-CONFIG_QCOM_GSBI=y
-CONFIG_QCOM_PM=y
-CONFIG_QCOM_SMEM=y
-CONFIG_QCOM_SMD_RPM=y
-CONFIG_QCOM_SMP2P=y
-CONFIG_QCOM_SMSM=y
-CONFIG_QCOM_WCNSS_CTRL=m
-CONFIG_ROCKCHIP_PM_DOMAINS=y
-CONFIG_COMMON_CLK_QCOM=y
-CONFIG_QCOM_CLK_RPM=y
-CONFIG_CHROME_PLATFORMS=y
CONFIG_STAGING_BOARD=y
-CONFIG_CROS_EC_CHARDEV=m
CONFIG_COMMON_CLK_MAX77686=y
CONFIG_COMMON_CLK_RK808=m
CONFIG_COMMON_CLK_S2MPS11=m
+CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_RPM=y
CONFIG_APQ_MMCC_8084=y
CONFIG_MSM_GCC_8660=y
CONFIG_MSM_MMCC_8960=y
CONFIG_MSM_MMCC_8974=y
-CONFIG_HWSPINLOCK_QCOM=y
+CONFIG_BCM2835_MBOX=y
CONFIG_ROCKCHIP_IOMMU=y
CONFIG_TEGRA_IOMMU_GART=y
CONFIG_TEGRA_IOMMU_SMMU=y
CONFIG_REMOTEPROC=m
CONFIG_ST_REMOTEPROC=m
CONFIG_RPMSG_VIRTIO=m
+CONFIG_RASPBERRYPI_POWER=y
+CONFIG_QCOM_GSBI=y
+CONFIG_QCOM_PM=y
+CONFIG_QCOM_SMD_RPM=m
+CONFIG_QCOM_WCNSS_CTRL=m
+CONFIG_ROCKCHIP_PM_DOMAINS=y
+CONFIG_ARCH_TEGRA_2x_SOC=y
+CONFIG_ARCH_TEGRA_3x_SOC=y
+CONFIG_ARCH_TEGRA_114_SOC=y
+CONFIG_ARCH_TEGRA_124_SOC=y
CONFIG_PM_DEVFREQ=y
CONFIG_ARM_TEGRA_DEVFREQ=m
-CONFIG_MEMORY=y
-CONFIG_EXTCON=y
CONFIG_TI_AEMIF=y
CONFIG_IIO=y
CONFIG_IIO_SW_TRIGGER=y
CONFIG_XILINX_XADC=y
CONFIG_MPU3050_I2C=y
CONFIG_CM36651=m
+CONFIG_SENSORS_ISL29018=y
+CONFIG_SENSORS_ISL29028=y
CONFIG_AK8975=y
-CONFIG_RASPBERRYPI_POWER=y
CONFIG_IIO_HRTIMER_TRIGGER=y
CONFIG_PWM=y
CONFIG_PWM_ATMEL=m
CONFIG_PWM_ATMEL_HLCDC_PWM=m
CONFIG_PWM_ATMEL_TCB=m
+CONFIG_PWM_BCM2835=y
+CONFIG_PWM_BRCMSTB=m
CONFIG_PWM_FSL_FTM=m
CONFIG_PWM_MESON=m
CONFIG_PWM_RCAR=m
CONFIG_PWM_RENESAS_TPU=y
CONFIG_PWM_ROCKCHIP=m
CONFIG_PWM_SAMSUNG=m
+CONFIG_PWM_STI=y
CONFIG_PWM_SUN4I=y
CONFIG_PWM_TEGRA=y
CONFIG_PWM_VT8500=y
+CONFIG_KEYSTONE_IRQ=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_SUN9I_USB=y
CONFIG_PHY_HIX5HD2_SATA=y
-CONFIG_E1000E=y
-CONFIG_PWM_STI=y
-CONFIG_PWM_BCM2835=y
-CONFIG_PWM_BRCMSTB=m
-CONFIG_PHY_DM816X_USB=m
-CONFIG_OMAP_USB2=y
-CONFIG_TI_PIPE3=y
-CONFIG_TWL4030_USB=m
+CONFIG_PHY_BERLIN_SATA=y
CONFIG_PHY_BERLIN_USB=y
CONFIG_PHY_CPCAP_USB=m
-CONFIG_PHY_BERLIN_SATA=y
+CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_RCAR_GEN2=m
CONFIG_PHY_ROCKCHIP_DP=m
CONFIG_PHY_ROCKCHIP_USB=y
-CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_SAMSUNG_USB2=m
CONFIG_PHY_MIPHY28LP=y
-CONFIG_PHY_RCAR_GEN2=m
CONFIG_PHY_STIH407_USB=y
CONFIG_PHY_STM32_USBPHYC=y
-CONFIG_PHY_SUN4I_USB=y
-CONFIG_PHY_SUN9I_USB=y
-CONFIG_PHY_SAMSUNG_USB2=m
CONFIG_PHY_TEGRA_XUSB=y
-CONFIG_PHY_BRCM_SATA=y
-CONFIG_NVMEM=y
+CONFIG_PHY_DM816X_USB=m
+CONFIG_OMAP_USB2=y
+CONFIG_TI_PIPE3=y
+CONFIG_TWL4030_USB=m
CONFIG_NVMEM_IMX_OCOTP=y
CONFIG_NVMEM_SUNXI_SID=y
CONFIG_NVMEM_VF610_OCOTP=y
-CONFIG_BCM2835_MBOX=y
CONFIG_RASPBERRYPI_FIRMWARE=y
-CONFIG_EFI_VARS=m
-CONFIG_EFI_CAPSULE_LOADER=m
CONFIG_BCM47XX_NVRAM=y
CONFIG_BCM47XX_SPROM=y
+CONFIG_EFI_VARS=m
+CONFIG_EFI_CAPSULE_LOADER=m
CONFIG_EXT4_FS=y
CONFIG_AUTOFS4_FS=y
CONFIG_MSDOS_FS=y
CONFIG_NTFS_FS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_UBIFS_FS=y
-CONFIG_TMPFS=y
CONFIG_SQUASHFS=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=y
CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
-CONFIG_LOCKUP_DETECTOR=y
-CONFIG_CPUFREQ_DT=y
-CONFIG_KEYSTONE_IRQ=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_ST=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_DEV_MARVELL_CESA=m
CONFIG_CRYPTO_DEV_EXYNOS_RNG=m
CONFIG_CRYPTO_DEV_S5P=m
+CONFIG_CRYPTO_DEV_ATMEL_AES=m
+CONFIG_CRYPTO_DEV_ATMEL_TDES=m
+CONFIG_CRYPTO_DEV_ATMEL_SHA=m
CONFIG_CRYPTO_DEV_SUN4I_SS=m
CONFIG_CRYPTO_DEV_ROCKCHIP=m
CONFIG_ARM_CRYPTO=y
-CONFIG_CRYPTO_SHA1_ARM=m
CONFIG_CRYPTO_SHA1_ARM_NEON=m
CONFIG_CRYPTO_SHA1_ARM_CE=m
CONFIG_CRYPTO_SHA2_ARM_CE=m
-CONFIG_CRYPTO_SHA256_ARM=m
CONFIG_CRYPTO_SHA512_ARM=m
CONFIG_CRYPTO_AES_ARM=m
CONFIG_CRYPTO_AES_ARM_BS=m
CONFIG_CRYPTO_AES_ARM_CE=m
-CONFIG_CRYPTO_CHACHA20_NEON=m
-CONFIG_CRYPTO_CRC32_ARM_CE=m
-CONFIG_CRYPTO_CRCT10DIF_ARM_CE=m
CONFIG_CRYPTO_GHASH_ARM_CE=m
-CONFIG_CRYPTO_DEV_ATMEL_AES=m
-CONFIG_CRYPTO_DEV_ATMEL_TDES=m
-CONFIG_CRYPTO_DEV_ATMEL_SHA=m
-CONFIG_VIDEO_VIVID=m
-CONFIG_VIRTIO=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_PCI_LEGACY=y
-CONFIG_VIRTIO_MMIO=y
+CONFIG_CRYPTO_CRC32_ARM_CE=m
+CONFIG_CRYPTO_CHACHA20_NEON=m
* Allocate stack space to store 128 bytes worth of tweaks. For
* performance, this space is aligned to a 16-byte boundary so that we
* can use the load/store instructions that declare 16-byte alignment.
+ * For Thumb2 compatibility, don't do the 'bic' directly on 'sp'.
*/
- sub sp, #128
- bic sp, #0xf
+ sub r12, sp, #128
+ bic r12, #0xf
+ mov sp, r12
.if \n == 64
// Load first tweak
obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
+
+# tf_generic_smc() fails to build with -fsanitize-coverage=trace-pc
+KCOV_INSTRUMENT := n
adds \tmp, \addr, #\size - 1
sbcccs \tmp, \tmp, \limit
bcs \bad
+#ifdef CONFIG_CPU_SPECTRE
+ movcs \addr, #0
+ csdb
+#endif
#endif
.endm
}
#define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int oldval, newval;
unsigned long tmp;
return oldval;
}
+#define atomic_fetch_add_unless atomic_fetch_add_unless
#else /* ARM_ARCH_6 */
return ret;
}
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
-
- c = atomic_read(v);
- while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
- c = old;
- return c;
-}
+#define atomic_fetch_andnot atomic_fetch_andnot
#endif /* __LINUX_ARM_ARCH__ */
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic_dec(v) atomic_sub(1, v)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v))
-#define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
-
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
long long counter;
return result;
}
+#define atomic64_dec_if_positive atomic64_dec_if_positive
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+ long long u)
{
- long long val;
+ long long oldval, newval;
unsigned long tmp;
- int ret = 1;
smp_mb();
prefetchw(&v->counter);
"1: ldrexd %0, %H0, [%4]\n"
" teq %0, %5\n"
" teqeq %H0, %H5\n"
-" moveq %1, #0\n"
" beq 2f\n"
-" adds %Q0, %Q0, %Q6\n"
-" adc %R0, %R0, %R6\n"
-" strexd %2, %0, %H0, [%4]\n"
+" adds %Q1, %Q0, %Q6\n"
+" adc %R1, %R0, %R6\n"
+" strexd %2, %1, %H1, [%4]\n"
" teq %2, #0\n"
" bne 1b\n"
"2:"
- : "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+ : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
: "r" (&v->counter), "r" (u), "r" (a)
: "cc");
- if (ret)
+ if (oldval != u)
smp_mb();
- return ret;
+ return oldval;
}
-
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v) atomic64_add(1LL, (v))
-#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v) atomic64_sub(1LL, (v))
-#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v))
-#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
#endif /* !CONFIG_GENERIC_ATOMIC64 */
#endif
#if __LINUX_ARM_ARCH__ < 5
-#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/fls.h>
#else
-static inline int constant_fls(int x)
-{
- int r = 32;
-
- if (!x)
- return 0;
- if (!(x & 0xffff0000u)) {
- x <<= 16;
- r -= 16;
- }
- if (!(x & 0xff000000u)) {
- x <<= 8;
- r -= 8;
- }
- if (!(x & 0xf0000000u)) {
- x <<= 4;
- r -= 4;
- }
- if (!(x & 0xc0000000u)) {
- x <<= 2;
- r -= 2;
- }
- if (!(x & 0x80000000u)) {
- x <<= 1;
- r -= 1;
- }
- return r;
-}
-
-/*
- * On ARMv5 and above those functions can be implemented around the
- * clz instruction for much better code efficiency. __clz returns
- * the number of leading zeros, zero input will return 32, and
- * 0x80000000 will return 0.
- */
-static inline unsigned int __clz(unsigned int x)
-{
- unsigned int ret;
-
- asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-
- return ret;
-}
-
-/*
- * fls() returns zero if the input is zero, otherwise returns the bit
- * position of the last set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int fls(int x)
-{
- if (__builtin_constant_p(x))
- return constant_fls(x);
-
- return 32 - __clz(x);
-}
-
-/*
- * __fls() returns the bit position of the last bit set, where the
- * LSB is 0 and MSB is 31. Zero input is undefined.
- */
-static inline unsigned long __fls(unsigned long x)
-{
- return fls(x) - 1;
-}
-
-/*
- * ffs() returns zero if the input was zero, otherwise returns the bit
- * position of the first set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int ffs(int x)
-{
- return fls(x & -x);
-}
-
/*
- * __ffs() returns the bit position of the first bit set, where the
- * LSB is 0 and MSB is 31. Zero input is undefined.
+ * On ARMv5 and above, the gcc built-ins may rely on the clz instruction
+ * and produce optimal inlined code in all cases. On ARMv7 it is even
+ * better by also using the rbit instruction.
*/
-static inline unsigned long __ffs(unsigned long x)
-{
- return ffs(x) - 1;
-}
-
-#define ffz(x) __ffs( ~(x) )
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-fls.h>
+#include <asm-generic/bitops/builtin-ffs.h>
#endif
+#include <asm-generic/bitops/ffz.h>
+
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/sched.h>
* Start addresses are inclusive and end addresses are exclusive;
* start addresses should be rounded down, end addresses up.
*
- * See Documentation/cachetlb.txt for more information.
+ * See Documentation/core-api/cachetlb.rst for more information.
* Please note that the implementation of these, and the required
* effects are cache-type (VIVT/VIPT/PIPT) specific.
*
#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__)
#define efi_is_64bit() (false)
+#define efi_table_attr(table, attr, instance) \
+ ((table##_t *)instance)->attr
+
#define efi_call_proto(protocol, f, instance, ...) \
((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
} while (0)
+struct perf_event_attr;
struct notifier_block;
struct perf_event;
struct pmu;
extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
int *gen_len, int *gen_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
void handle_IRQ(unsigned int, struct pt_regs *);
void init_IRQ(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-extern void (*handle_arch_irq)(struct pt_regs *);
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-#endif
-
#ifdef CONFIG_SMP
extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self);
struct kprobe_ctlblk {
unsigned int kprobe_status;
struct prev_kprobe prev_kprobe;
- struct pt_regs jprobe_saved_regs;
- char jprobes_stack[MAX_STACK_SIZE];
};
void arch_remove_kprobe(struct kprobe *);
void (*init_time)(void);
void (*init_machine)(void);
void (*init_late)(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
void (*handle_irq)(struct pt_regs *);
#endif
void (*restart)(enum reboot_mode, const char *);
extern void timer_tick(void);
typedef void (*clock_access_fn)(struct timespec64 *);
-extern int register_persistent_clock(clock_access_fn read_boot,
- clock_access_fn read_persistent);
+extern int register_persistent_clock(clock_access_fn read_persistent);
#endif
* We assume one instruction can consume at most 64 bytes stack, which is
* 'push {r0-r15}'. Instructions consume more or unknown stack space like
* 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
*/
#define MAX_STACK_SIZE 64
extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
struct user_vfp_exc __user *);
-extern int vfp_restore_user_hwstate(struct user_vfp __user *,
- struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp *,
+ struct user_vfp_exc *);
#endif
/*
{
}
+static inline void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+}
+
+static inline void tlb_flush_remove_tables_local(void *arg)
+{
+}
+
#endif /* CONFIG_MMU */
#endif
: "cc"); \
flag; })
+/*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __inttype(x) \
+ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
+
/*
* Single-value transfer routines. They automatically use the right
* size if we just have the right pointer type. Note that the functions
({ \
unsigned long __limit = current_thread_info()->addr_limit - 1; \
register typeof(*(p)) __user *__p asm("r0") = (p); \
- register typeof(x) __r2 asm("r2"); \
+ register __inttype(x) __r2 asm("r2"); \
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
unsigned int __ua_flags = uaccess_save_and_enable(); \
#define user_addr_max() \
(uaccess_kernel() ? ~0UL : get_fs())
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1, it is not worth fixing the non-
+ * verifying accessors, because we need to add verification of the
+ * address space there. Force these to use the standard get_user()
+ * version instead.
+ */
+#define __get_user(x, ptr) get_user(x, ptr)
+#else
+
/*
* The "__xxx" versions of the user access functions do not verify the
* address space - it must have been done previously with a separate
__gu_err; \
})
-#define __get_user_error(x, ptr, err) \
-({ \
- __get_user_err((x), (ptr), err); \
- (void) 0; \
-})
-
#define __get_user_err(x, ptr, err) \
do { \
unsigned long __gu_addr = (unsigned long)(ptr); \
#define __get_user_asm_word(x, addr, err) \
__get_user_asm(x, addr, err, ldr)
+#endif
#define __put_user_switch(x, ptr, __err, __fn) \
#include <asm/glue-df.h>
#include <asm/glue-pf.h>
#include <asm/vfpmacros.h>
-#ifndef CONFIG_MULTI_IRQ_HANDLER
+#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER
#include <mach/entry-macro.S>
#endif
#include <asm/thread_notify.h>
* Interrupt handling.
*/
.macro irq_handler
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
ldr r1, =handle_arch_irq
mov r0, sp
badr lr, 9997f
.globl cr_alignment
cr_alignment:
.space 4
-
-#ifdef CONFIG_MULTI_IRQ_HANDLER
- .globl handle_arch_irq
-handle_arch_irq:
- .space 4
-#endif
* from those features make this path too inefficient.
*/
ret_fast_syscall:
+__ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
* call.
*/
ret_fast_syscall:
+__ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls?
bne __sys_trace
- invoke_syscall tbl, scno, r10, ret_fast_syscall
+ invoke_syscall tbl, scno, r10, __ret_fast_syscall
add r1, sp, #S_OFF
2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
THUMB(1: )
#endif
- setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
+#ifdef CONFIG_ARM_VIRT_EXT
+ bl __hyp_stub_install
+#endif
+ @ ensure svc mode and all interrupts masked
+ safe_svcmode_maskall r9
@ and irqs disabled
#if defined(CONFIG_CPU_CP15)
mrc p15, 0, r9, c0, c0 @ get processor id
* the processor type - there is no need to check the machine type
* as it has already been validated by the primary processor.
*/
- setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+#ifdef CONFIG_ARM_VIRT_EXT
+ bl __hyp_stub_install_secondary
+#endif
+ safe_svcmode_maskall r9
+
#ifndef CONFIG_CPU_CP15
ldr r9, =CONFIG_PROCESSOR_ID
#else
bic r0, r0, #CR_I
#endif
mcr p15, 0, r0, c1, c0, 0 @ write control reg
- isb
+ instr_sync
#elif defined (CONFIG_CPU_V7M)
#ifdef CONFIG_ARM_MPU
ldreq r3, [r12, MPU_CTRL]
/*
* Check whether bp virtual address is in kernel space.
*/
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
unsigned int len;
unsigned long va;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- va = info->address;
- len = get_hbp_len(info->ctrl.len);
+ va = hw->address;
+ len = get_hbp_len(hw->ctrl.len);
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
/*
* Construct an arch_hw_breakpoint from a perf_event.
*/
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
/* Type */
- switch (bp->attr.bp_type) {
+ switch (attr->bp_type) {
case HW_BREAKPOINT_X:
- info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+ hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
break;
case HW_BREAKPOINT_R:
- info->ctrl.type = ARM_BREAKPOINT_LOAD;
+ hw->ctrl.type = ARM_BREAKPOINT_LOAD;
break;
case HW_BREAKPOINT_W:
- info->ctrl.type = ARM_BREAKPOINT_STORE;
+ hw->ctrl.type = ARM_BREAKPOINT_STORE;
break;
case HW_BREAKPOINT_RW:
- info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+ hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
break;
default:
return -EINVAL;
}
/* Len */
- switch (bp->attr.bp_len) {
+ switch (attr->bp_len) {
case HW_BREAKPOINT_LEN_1:
- info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
break;
case HW_BREAKPOINT_LEN_2:
- info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
break;
case HW_BREAKPOINT_LEN_4:
- info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
break;
case HW_BREAKPOINT_LEN_8:
- info->ctrl.len = ARM_BREAKPOINT_LEN_8;
- if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
+ if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
&& max_watchpoint_len >= 8)
break;
default:
* by the hardware and must be aligned to the appropriate number of
* bytes.
*/
- if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
- info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
- info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+ if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+ hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+ hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
return -EINVAL;
/* Address */
- info->address = bp->attr.bp_addr;
+ hw->address = attr->bp_addr;
/* Privilege */
- info->ctrl.privilege = ARM_BREAKPOINT_USER;
- if (arch_check_bp_in_kernelspace(bp))
- info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+ hw->ctrl.privilege = ARM_BREAKPOINT_USER;
+ if (arch_check_bp_in_kernelspace(hw))
+ hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
/* Enabled? */
- info->ctrl.enabled = !bp->attr.disabled;
+ hw->ctrl.enabled = !attr->disabled;
/* Mismatch */
- info->ctrl.mismatch = 0;
+ hw->ctrl.mismatch = 0;
return 0;
}
/*
* Validate the arch-specific HW Breakpoint register settings.
*/
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
int ret = 0;
u32 offset, alignment_mask = 0x3;
return -ENODEV;
/* Build the arch_hw_breakpoint. */
- ret = arch_build_bp_info(bp);
+ ret = arch_build_bp_info(bp, attr, hw);
if (ret)
goto out;
/* Check address alignment. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
alignment_mask = 0x7;
- offset = info->address & alignment_mask;
+ offset = hw->address & alignment_mask;
switch (offset) {
case 0:
/* Aligned */
case 1:
case 2:
/* Allow halfword watchpoints and breakpoints. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
break;
case 3:
/* Allow single byte watchpoint. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
break;
default:
ret = -EINVAL;
goto out;
}
- info->address &= ~alignment_mask;
- info->ctrl.len <<= offset;
+ hw->address &= ~alignment_mask;
+ hw->ctrl.len <<= offset;
if (is_default_overflow_handler(bp)) {
/*
return -EINVAL;
/* We don't allow mismatch breakpoints in kernel space. */
- if (arch_check_bp_in_kernelspace(bp))
+ if (arch_check_bp_in_kernelspace(hw))
return -EPERM;
/*
* reports them.
*/
if (!debug_exception_updates_fsr() &&
- (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
- info->ctrl.type == ARM_BREAKPOINT_STORE))
+ (hw->ctrl.type == ARM_BREAKPOINT_LOAD ||
+ hw->ctrl.type == ARM_BREAKPOINT_STORE))
return -EINVAL;
}
uniphier_cache_init();
}
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
- if (handle_arch_irq)
- return;
-
- handle_arch_irq = handle_irq;
-}
-#endif
-
#ifdef CONFIG_SPARSE_IRQ
int __init arch_probe_nr_irqs(void)
{
static int __init gate_vma_init(void)
{
+ vma_init(&gate_vma, NULL);
gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
return 0;
}
reserve_crashkernel();
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
handle_arch_irq = mdesc->handle_irq;
#endif
static int restore_vfp_context(char __user **auxp)
{
- struct vfp_sigframe __user *frame =
- (struct vfp_sigframe __user *)*auxp;
- unsigned long magic;
- unsigned long size;
- int err = 0;
-
- __get_user_error(magic, &frame->magic, err);
- __get_user_error(size, &frame->size, err);
+ struct vfp_sigframe frame;
+ int err;
+ err = __copy_from_user(&frame, *auxp, sizeof(frame));
if (err)
- return -EFAULT;
- if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+ return err;
+
+ if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE)
return -EINVAL;
- *auxp += size;
- return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
+ *auxp += sizeof(frame);
+ return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc);
}
#endif
static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
{
+ struct sigcontext context;
char __user *aux;
sigset_t set;
int err;
if (err == 0)
set_current_blocked(&set);
- __get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
- __get_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
- __get_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
- __get_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
- __get_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
- __get_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
- __get_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
- __get_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
- __get_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
- __get_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
- __get_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
- __get_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
- __get_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
- __get_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
- __get_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
- __get_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
- __get_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
+ err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context));
+ if (err == 0) {
+ regs->ARM_r0 = context.arm_r0;
+ regs->ARM_r1 = context.arm_r1;
+ regs->ARM_r2 = context.arm_r2;
+ regs->ARM_r3 = context.arm_r3;
+ regs->ARM_r4 = context.arm_r4;
+ regs->ARM_r5 = context.arm_r5;
+ regs->ARM_r6 = context.arm_r6;
+ regs->ARM_r7 = context.arm_r7;
+ regs->ARM_r8 = context.arm_r8;
+ regs->ARM_r9 = context.arm_r9;
+ regs->ARM_r10 = context.arm_r10;
+ regs->ARM_fp = context.arm_fp;
+ regs->ARM_ip = context.arm_ip;
+ regs->ARM_sp = context.arm_sp;
+ regs->ARM_lr = context.arm_lr;
+ regs->ARM_pc = context.arm_pc;
+ regs->ARM_cpsr = context.arm_cpsr;
+ }
err |= !valid_user_regs(regs);
* Increment event counter and perform fixup for the pre-signal
* frame.
*/
- rseq_signal_deliver(regs);
+ rseq_signal_deliver(ksig, regs);
/*
* Set up the stack frame
} else {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
}
local_irq_disable();
return -ENOMEM;
err = 0;
for (i = 0; i < nsops; i++) {
- __get_user_error(sops[i].sem_num, &tsops->sem_num, err);
- __get_user_error(sops[i].sem_op, &tsops->sem_op, err);
- __get_user_error(sops[i].sem_flg, &tsops->sem_flg, err);
+ struct oabi_sembuf osb;
+ err |= __copy_from_user(&osb, tsops, sizeof(osb));
+ sops[i].sem_num = osb.sem_num;
+ sops[i].sem_op = osb.sem_op;
+ sops[i].sem_flg = osb.sem_flg;
tsops++;
}
if (timeout) {
}
static clock_access_fn __read_persistent_clock = dummy_clock_access;
-static clock_access_fn __read_boot_clock = dummy_clock_access;
void read_persistent_clock64(struct timespec64 *ts)
{
__read_persistent_clock(ts);
}
-void read_boot_clock64(struct timespec64 *ts)
-{
- __read_boot_clock(ts);
-}
-
-int __init register_persistent_clock(clock_access_fn read_boot,
- clock_access_fn read_persistent)
+int __init register_persistent_clock(clock_access_fn read_persistent)
{
/* Only allow the clockaccess functions to be registered once */
- if (__read_persistent_clock == dummy_clock_access &&
- __read_boot_clock == dummy_clock_access) {
- if (read_boot)
- __read_boot_clock = read_boot;
+ if (__read_persistent_clock == dummy_clock_access) {
if (read_persistent)
__read_persistent_clock = read_persistent;
-
return 0;
}
obj-$(CONFIG_KVM_ARM_HOST) += switch.o
CFLAGS_switch.o += $(CFLAGS_ARMV7VE)
obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
+
+# KVM code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE := n
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
.text
ENTRY(arm_copy_from_user)
+#ifdef CONFIG_CPU_SPECTRE
+ get_thread_info r3
+ ldr r3, [r3, #TI_ADDR_LIMIT]
+ adds ip, r1, r2 @ ip=addr+size
+ sub r3, r3, #1 @ addr_limit - 1
+ cmpcc ip, r3 @ if (addr+size > addr_limit - 1)
+ movcs r1, #0 @ addr = NULL
+ csdb
+#endif
#include "copy_template.S"
select GPIOLIB
select ARM_AMBA
select PINCTRL
+ select PCI_DOMAINS if PCI
help
This enables support for systems based on Broadcom IPROC architected SoCs.
The IPROC complex contains one or more ARM CPUs along with common
GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
GPIO_ACTIVE_LOW),
GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
- GPIO_ACTIVE_LOW),
+ GPIO_ACTIVE_HIGH),
},
};
static inline void omap5_erratum_workaround_801819(void) { }
#endif
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/*
+ * Configure ACR and enable ACTLR[0] (Enable invalidates of BTB with
+ * ICIALLU) to activate the workaround for secondary Core.
+ * NOTE: it is assumed that the primary core's configuration is done
+ * by the boot loader (kernel will detect a misconfiguration and complain
+ * if this is not done).
+ *
+ * In General Purpose(GP) devices, ACR bit settings can only be done
+ * by ROM code in "secure world" using the smc call and there is no
+ * option to update the "firmware" on such devices. This also works for
+ * High security(HS) devices, as a backup option in case the
+ * "update" is not done in the "security firmware".
+ */
+static void omap5_secondary_harden_predictor(void)
+{
+ u32 acr, acr_mask;
+
+ asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+
+ /*
+ * ACTLR[0] (Enable invalidates of BTB with ICIALLU)
+ */
+ acr_mask = BIT(0);
+
+ /* Do we already have it done.. if yes, skip expensive smc */
+ if ((acr & acr_mask) == acr_mask)
+ return;
+
+ acr |= acr_mask;
+ omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+
+ pr_debug("%s: ARM ACR setup for CVE_2017_5715 applied on CPU%d\n",
+ __func__, smp_processor_id());
+}
+#else
+static inline void omap5_secondary_harden_predictor(void) { }
+#endif
+
static void omap4_secondary_init(unsigned int cpu)
{
/*
set_cntfreq();
/* Configure ACR to disable streaming WA for 801819 */
omap5_erratum_workaround_801819();
+ /* Enable ACR to allow for ICUALLU workaround */
+ omap5_secondary_harden_predictor();
}
/*
{
int i;
- for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+ for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
void __iomem *base = irq_base(i);
saved_icmr[i] = __raw_readl(base + ICMR);
{
int i;
- for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+ for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
void __iomem *base = irq_base(i);
__raw_writel(saved_icmr[i], base + ICMR);
*/
static void ecard_init_pgtables(struct mm_struct *mm)
{
- struct vm_area_struct vma;
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC);
/* We want to set up the page tables for the following mapping:
* Virtual Physical
memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
- vma.vm_flags = VM_EXEC;
- vma.vm_mm = mm;
-
flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
}
select HAVE_ARM_SCU
select HAVE_ARM_TWD if SMP
select MFD_SYSCON
+ select PCI_DOMAINS if PCI
if ARCH_SOCFPGA
config SOCFPGA_SUSPEND
config ARM_VIRT_EXT
bool
- depends on MMU
default y if CPU_V7
help
Enable the kernel to make use of the ARM Virtualization
return 0;
}
+static int kernel_set_to_readonly __read_mostly;
+
void mark_rodata_ro(void)
{
+ kernel_set_to_readonly = 1;
stop_machine(__mark_rodata_ro, NULL, NULL);
debug_checkwx();
}
void set_kernel_text_rw(void)
{
+ if (!kernel_set_to_readonly)
+ return;
+
set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
current->active_mm);
}
void set_kernel_text_ro(void)
{
+ if (!kernel_set_to_readonly)
+ return;
+
set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
current->active_mm);
}
{
/* Check CPUID Identification Scheme before ID_PFR1 read */
if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
- return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ return cpuid_feature_extract(CPUID_EXT_PFR1, 4) ||
+ cpuid_feature_extract(CPUID_EXT_PFR1, 20);
return 0;
}
void __init tcm_init(void);
#else
/* No TCM support, just blank inlines to be optimized out */
-inline void tcm_init(void)
+static inline void tcm_init(void)
{
}
#endif
/* there are 2 passes here */
bpf_jit_dump(prog->len, image_size, 2, ctx.target);
- set_memory_ro((unsigned long)header, header->pages);
+ bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)ctx.target;
prog->jited = 1;
prog->jited_len = image_size;
}
sched_clock_register(omap_32k_read_sched_clock, 32, 32768);
- register_persistent_clock(NULL, omap_read_persistent_clock64);
+ register_persistent_clock(omap_read_persistent_clock64);
pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n");
return 0;
(unsigned long)(addr) + \
(size))
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR 0xffffffff
-
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
break;
case KPROBE_REENTER:
/* A nested probe was hit in FIQ, it is a BUG */
- pr_warn("Unrecoverable kprobe detected at %p.\n",
- p->addr);
+ pr_warn("Unrecoverable kprobe detected.\n");
+ dump_kprobe(p);
/* fall through */
default:
/* impossible cases */
/*
* If we have no pre-handler or it returned 0, we
- * continue with normal processing. If we have a
- * pre-handler and it returned non-zero, it prepped
- * for calling the break_handler below on re-entry,
- * so get out doing nothing more here.
+ * continue with normal processing. If we have a
+ * pre-handler and it returned non-zero, it will
+ * modify the execution path and no need to single
+ * stepping. Let's just reset current kprobe and exit.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
kcb->kprobe_status = KPROBE_HIT_SS;
kcb->kprobe_status = KPROBE_HIT_SSDONE;
p->post_handler(p, regs, 0);
}
- reset_current_kprobe();
- }
- }
- } else if (cur) {
- /* We probably hit a jprobe. Call its break handler. */
- if (cur->break_handler && cur->break_handler(cur, regs)) {
- kcb->kprobe_status = KPROBE_HIT_SS;
- singlestep(cur, regs, kcb);
- if (cur->post_handler) {
- kcb->kprobe_status = KPROBE_HIT_SSDONE;
- cur->post_handler(cur, regs, 0);
}
+ reset_current_kprobe();
}
- reset_current_kprobe();
} else {
/*
* The probe was removed and a race is in progress.
regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- long sp_addr = regs->ARM_sp;
- long cpsr;
-
- kcb->jprobe_saved_regs = *regs;
- memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
- regs->ARM_pc = (long)jp->entry;
-
- cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
- /* Set correct Thumb state in cpsr */
- if (regs->ARM_pc & 1)
- cpsr |= PSR_T_BIT;
- else
- cpsr &= ~PSR_T_BIT;
-#endif
- regs->ARM_cpsr = cpsr;
-
- preempt_disable();
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- __asm__ __volatile__ (
- /*
- * Setup an empty pt_regs. Fill SP and PC fields as
- * they're needed by longjmp_break_handler.
- *
- * We allocate some slack between the original SP and start of
- * our fabricated regs. To be precise we want to have worst case
- * covered which is STMFD with all 16 regs so we allocate 2 *
- * sizeof(struct_pt_regs)).
- *
- * This is to prevent any simulated instruction from writing
- * over the regs when they are accessing the stack.
- */
-#ifdef CONFIG_THUMB2_KERNEL
- "sub r0, %0, %1 \n\t"
- "mov sp, r0 \n\t"
-#else
- "sub sp, %0, %1 \n\t"
-#endif
- "ldr r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
- "str %0, [sp, %2] \n\t"
- "str r0, [sp, %3] \n\t"
- "mov r0, sp \n\t"
- "bl kprobe_handler \n\t"
-
- /*
- * Return to the context saved by setjmp_pre_handler
- * and restored by longjmp_break_handler.
- */
-#ifdef CONFIG_THUMB2_KERNEL
- "ldr lr, [sp, %2] \n\t" /* lr = saved sp */
- "ldrd r0, r1, [sp, %5] \n\t" /* r0,r1 = saved lr,pc */
- "ldr r2, [sp, %4] \n\t" /* r2 = saved psr */
- "stmdb lr!, {r0, r1, r2} \n\t" /* push saved lr and */
- /* rfe context */
- "ldmia sp, {r0 - r12} \n\t"
- "mov sp, lr \n\t"
- "ldr lr, [sp], #4 \n\t"
- "rfeia sp! \n\t"
-#else
- "ldr r0, [sp, %4] \n\t"
- "msr cpsr_cxsf, r0 \n\t"
- "ldmia sp, {r0 - pc} \n\t"
-#endif
- :
- : "r" (kcb->jprobe_saved_regs.ARM_sp),
- "I" (sizeof(struct pt_regs) * 2),
- "J" (offsetof(struct pt_regs, ARM_sp)),
- "J" (offsetof(struct pt_regs, ARM_pc)),
- "J" (offsetof(struct pt_regs, ARM_cpsr)),
- "J" (offsetof(struct pt_regs, ARM_lr))
- : "memory", "cc");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- long stack_addr = kcb->jprobe_saved_regs.ARM_sp;
- long orig_sp = regs->ARM_sp;
- struct jprobe *jp = container_of(p, struct jprobe, kp);
-
- if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
- if (orig_sp != stack_addr) {
- struct pt_regs *saved_regs =
- (struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
- printk("current sp %lx does not match saved sp %lx\n",
- orig_sp, stack_addr);
- printk("Saved registers for jprobe %p\n", jp);
- show_regs(saved_regs);
- printk("Current registers\n");
- show_regs(regs);
- BUG();
- }
- *regs = kcb->jprobe_saved_regs;
- memcpy((void *)stack_addr, kcb->jprobes_stack,
- MIN_STACK_SIZE(stack_addr));
- preempt_enable_no_resched();
- return 1;
- }
- return 0;
-}
-
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
return 0;
print_registers(&result_regs);
if (mem) {
- pr_err("current_stack=%p\n", current_stack);
pr_err("expected_memory:\n");
print_memory(expected_memory, mem_size);
pr_err("result_memory:\n");
# Disable gcov profiling for VDSO code
GCOV_PROFILE := n
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
# Force dependency
$(obj)/vdso.o : $(obj)/vdso.so
# asflags-y := -DDEBUG
KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft)
-LDFLAGS +=--no-warn-mismatch
-obj-y += vfp.o
-
-vfp-$(CONFIG_VFP) += vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
+obj-y += vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
}
/* Sanitise and restore the current VFP state from the provided structures. */
-int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
- struct user_vfp_exc __user *ufp_exc)
+int vfp_restore_user_hwstate(struct user_vfp *ufp, struct user_vfp_exc *ufp_exc)
{
struct thread_info *thread = current_thread_info();
struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
unsigned long fpexc;
- int err = 0;
/* Disable VFP to avoid corrupting the new thread state. */
vfp_flush_hwstate(thread);
* Copy the floating point registers. There can be unused
* registers see asm/hwcap.h for details.
*/
- err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
- sizeof(hwstate->fpregs));
+ memcpy(&hwstate->fpregs, &ufp->fpregs, sizeof(hwstate->fpregs));
/*
* Copy the status and control register.
*/
- __get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+ hwstate->fpscr = ufp->fpscr;
/*
* Sanitise and restore the exception registers.
*/
- __get_user_error(fpexc, &ufp_exc->fpexc, err);
+ fpexc = ufp_exc->fpexc;
/* Ensure the VFP is enabled. */
fpexc |= FPEXC_EN;
fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
hwstate->fpexc = fpexc;
- __get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
- __get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+ hwstate->fpinst = ufp_exc->fpinst;
+ hwstate->fpinst2 = ufp_exc->fpinst2;
- return err ? -EFAULT : 0;
+ return 0;
}
/*
static __read_mostly unsigned int xen_events_irq;
+uint32_t xen_start_flags;
+EXPORT_SYMBOL(xen_start_flags);
+
int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t *gfn, int nr,
xen_setup_features();
if (xen_feature(XENFEAT_dom0))
- xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
- else
- xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
+ xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
if (!console_set_on_cmdline && !xen_initial_domain())
add_preferred_console("hvc", 0, NULL);
select GENERIC_CPU_AUTOPROBE
select GENERIC_EARLY_IOREMAP
select GENERIC_IDLE_POLL_SETUP
+ select GENERIC_IRQ_MULTI_HANDLER
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL
select HAVE_ARM_SMCCC
select HAVE_EBPF_JIT
select HAVE_C_RECORDMCOUNT
- select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_CONTEXT_TRACKING
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
+ select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_KPROBES
select HAVE_KRETPROBES
config ARCH_PROC_KCORE_TEXT
def_bool y
-config MULTI_IRQ_HANDLER
- def_bool y
-
source "init/Kconfig"
source "kernel/Kconfig.freezer"
#
# Copyright (C) 1995-2001 by Russell King
-LDFLAGS_vmlinux :=-p --no-undefined -X
+LDFLAGS_vmlinux :=--no-undefined -X
CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
GZFLAGS :=-9
KBUILD_CPPFLAGS += -mbig-endian
CHECKFLAGS += -D__AARCH64EB__
AS += -EB
-LD += -EB
-LDFLAGS += -maarch64linuxb
+# We must use the linux target here, since distributions don't tend to package
+# the ELF linker scripts with binutils, and this results in a build failure.
+LDFLAGS += -EB -maarch64linuxb
UTS_MACHINE := aarch64_be
else
KBUILD_CPPFLAGS += -mlittle-endian
CHECKFLAGS += -D__AARCH64EL__
AS += -EL
-LD += -EL
-LDFLAGS += -maarch64linux
+LDFLAGS += -EL -maarch64linux # See comment above
UTS_MACHINE := aarch64
endif
interrupts = <0 99 4>;
resets = <&rst SPIM0_RESET>;
reg-io-width = <4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
status = "disabled";
};
interrupts = <0 100 4>;
resets = <&rst SPIM1_RESET>;
reg-io-width = <4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
status = "disabled";
};
ðmac {
status = "okay";
- phy-mode = "rgmii";
pinctrl-0 = <ð_rgmii_y_pins>;
pinctrl-names = "default";
+ phy-handle = <ð_phy0>;
+ phy-mode = "rgmii";
+
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eth_phy0: ethernet-phy@0 {
+ /* Realtek RTL8211F (0x001cc916) */
+ reg = <0>;
+ eee-broken-1000t;
+ };
+ };
};
&uart_A {
sd_emmc_b: sd@5000 {
compatible = "amlogic,meson-axg-mmc";
- reg = <0x0 0x5000 0x0 0x2000>;
+ reg = <0x0 0x5000 0x0 0x800>;
interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_B>,
sd_emmc_c: mmc@7000 {
compatible = "amlogic,meson-axg-mmc";
- reg = <0x0 0x7000 0x0 0x2000>;
+ reg = <0x0 0x7000 0x0 0x800>;
interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_C>,
no-map;
};
+ /* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
+ secmon_reserved_alt: secmon@5000000 {
+ reg = <0x0 0x05000000 0x0 0x300000>;
+ no-map;
+ };
+
linux,cma {
compatible = "shared-dma-pool";
reusable;
sd_emmc_a: mmc@70000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x70000 0x0 0x2000>;
+ reg = <0x0 0x70000 0x0 0x800>;
interrupts = <GIC_SPI 216 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
sd_emmc_b: mmc@72000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x72000 0x0 0x2000>;
+ reg = <0x0 0x72000 0x0 0x800>;
interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
sd_emmc_c: mmc@74000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x74000 0x0 0x2000>;
+ reg = <0x0 0x74000 0x0 0x800>;
interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
&apb {
mali: gpu@c0000 {
- compatible = "amlogic,meson-gxbb-mali", "arm,mali-450";
+ compatible = "amlogic,meson-gxl-mali", "arm,mali-450";
reg = <0x0 0xc0000 0x0 0x40000>;
interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
bus-width = <4>;
cap-sd-highspeed;
- sd-uhs-sdr12;
- sd-uhs-sdr25;
- sd-uhs-sdr50;
max-frequency = <100000000>;
disable-wp;
&usb0 {
status = "okay";
};
+
+&usb2_phy0 {
+ /*
+ * HDMI_5V is also used as supply for the USB VBUS.
+ */
+ phy-supply = <&hdmi_5v>;
+};
/ {
compatible = "amlogic,meson-gxl";
- reserved-memory {
- /* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
- secmon_reserved_alt: secmon@5000000 {
- reg = <0x0 0x05000000 0x0 0x300000>;
- no-map;
- };
- };
-
soc {
usb0: usb@c9000000 {
status = "disabled";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <4>;
reg = <0x66080000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 394 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 394 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x660b0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 395 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
enet-phy-lane-swap;
};
+&sdio0 {
+ mmc-ddr-1_8v;
+};
+
&uart2 {
status = "okay";
};
&gphy0 {
enet-phy-lane-swap;
};
+
+&sdio0 {
+ mmc-ddr-1_8v;
+};
reg = <0x000b0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 177 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x000e0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 178 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
vmmc-supply = <&wlan_en>;
ti,non-removable;
non-removable;
+ cap-power-off-card;
+ keep-power-in-suspend;
#address-cells = <0x1>;
#size-cells = <0x0>;
status = "ok";
dwmmc_2: dwmmc2@f723f000 {
bus-width = <0x4>;
non-removable;
+ cap-power-off-card;
+ keep-power-in-suspend;
vmmc-supply = <®_vdd_3v3>;
mmc-pwrseq = <&wl1835_pwrseq>;
CP110_LABEL(icu): interrupt-controller@1e0000 {
compatible = "marvell,cp110-icu";
- reg = <0x1e0000 0x10>;
+ reg = <0x1e0000 0x440>;
#interrupt-cells = <3>;
interrupt-controller;
msi-parent = <&gicp>;
serial@75b1000 {
label = "LS-UART0";
- status = "okay";
+ status = "disabled";
pinctrl-names = "default", "sleep";
pinctrl-0 = <&blsp2_uart2_4pins_default>;
pinctrl-1 = <&blsp2_uart2_4pins_sleep>;
port@0 {
reg = <0>;
- etf_out: endpoint {
+ etf_in: endpoint {
slave-mode;
remote-endpoint = <&funnel0_out>;
};
};
port@1 {
reg = <0>;
- etf_in: endpoint {
+ etf_out: endpoint {
remote-endpoint = <&replicator_in>;
};
};
sound {
compatible = "audio-graph-card";
label = "UniPhier LD11";
- widgets = "Headphone", "Headphone Jack";
+ widgets = "Headphone", "Headphones";
dais = <&i2s_port2
&i2s_port3
&i2s_port4
sound {
compatible = "audio-graph-card";
label = "UniPhier LD20";
- widgets = "Headphone", "Headphone Jack";
+ widgets = "Headphone", "Headphones";
dais = <&i2s_port2
&i2s_port3
&i2s_port4
CONFIG_ARCH_QCOM=y
CONFIG_ARCH_ROCKCHIP=y
CONFIG_ARCH_SEATTLE=y
+CONFIG_ARCH_SYNQUACER=y
CONFIG_ARCH_RENESAS=y
CONFIG_ARCH_R8A7795=y
CONFIG_ARCH_R8A7796=y
CONFIG_ARCH_STRATIX10=y
CONFIG_ARCH_TEGRA=y
CONFIG_ARCH_SPRD=y
-CONFIG_ARCH_SYNQUACER=y
CONFIG_ARCH_THUNDER=y
CONFIG_ARCH_THUNDER2=y
CONFIG_ARCH_UNIPHIER=y
CONFIG_ARCH_ZX=y
CONFIG_ARCH_ZYNQMP=y
CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI_PCIE=y
CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_ACPI=y
-CONFIG_PCI_LAYERSCAPE=y
-CONFIG_PCI_HISI=y
-CONFIG_PCIE_QCOM=y
-CONFIG_PCIE_KIRIN=y
-CONFIG_PCIE_ARMADA_8K=y
-CONFIG_PCIE_HISI_STB=y
CONFIG_PCI_AARDVARK=y
CONFIG_PCI_TEGRA=y
CONFIG_PCIE_RCAR=y
-CONFIG_PCIE_ROCKCHIP=y
-CONFIG_PCIE_ROCKCHIP_HOST=m
CONFIG_PCI_HOST_GENERIC=y
CONFIG_PCI_XGENE=y
CONFIG_PCI_HOST_THUNDER_PEM=y
CONFIG_PCI_HOST_THUNDER_ECAM=y
+CONFIG_PCIE_ROCKCHIP_HOST=m
+CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_HISI=y
+CONFIG_PCIE_QCOM=y
+CONFIG_PCIE_ARMADA_8K=y
+CONFIG_PCIE_KIRIN=y
+CONFIG_PCIE_HISI_STB=y
CONFIG_ARM64_VA_BITS_48=y
CONFIG_SCHED_MC=y
CONFIG_NUMA=y
CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
CONFIG_ARM_CPUIDLE=y
CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_GOV_ATTR_SET=y
-CONFIG_CPU_FREQ_GOV_COMMON=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_CPUFREQ_DT=y
+CONFIG_ACPI_CPPC_CPUFREQ=m
CONFIG_ARM_ARMADA_37XX_CPUFREQ=y
CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
CONFIG_ARM_SCPI_CPUFREQ=y
CONFIG_ARM_TEGRA186_CPUFREQ=y
-CONFIG_ACPI_CPPC_CPUFREQ=m
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_SNI_AVE=y
CONFIG_SNI_NETSEC=y
CONFIG_STMMAC_ETH=m
-CONFIG_DWMAC_IPQ806X=m
-CONFIG_DWMAC_MESON=m
-CONFIG_DWMAC_ROCKCHIP=m
-CONFIG_DWMAC_SUNXI=m
-CONFIG_DWMAC_SUN8I=m
CONFIG_MDIO_BUS_MUX_MMIOREG=y
CONFIG_AT803X_PHY=m
CONFIG_MARVELL_PHY=m
CONFIG_WLCORE_SDIO=m
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_ADC=m
-CONFIG_KEYBOARD_CROS_EC=y
CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_CROS_EC=y
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_ATMEL_MXT=m
CONFIG_INPUT_MISC=y
CONFIG_SERIAL_SAMSUNG_CONSOLE=y
CONFIG_SERIAL_TEGRA=y
CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=11
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_XILINX_PS_UART=y
CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
CONFIG_SERIAL_MVEBU_UART=y
CONFIG_SERIAL_DEV_BUS=y
-CONFIG_SERIAL_DEV_CTRL_TTYPORT=y
CONFIG_VIRTIO_CONSOLE=y
-CONFIG_I2C_HID=m
CONFIG_I2C_CHARDEV=y
CONFIG_I2C_MUX=y
CONFIG_I2C_MUX_PCA954x=y
CONFIG_I2C_CROS_EC_TUNNEL=y
CONFIG_SPI=y
CONFIG_SPI_ARMADA_3700=y
-CONFIG_SPI_MESON_SPICC=m
-CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_BCM2835=m
CONFIG_SPI_BCM2835AUX=m
+CONFIG_SPI_MESON_SPICC=m
+CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_ORION=y
CONFIG_SPI_PL022=y
-CONFIG_SPI_QUP=y
CONFIG_SPI_ROCKCHIP=y
+CONFIG_SPI_QUP=y
CONFIG_SPI_S3C64XX=y
CONFIG_SPI_SPIDEV=m
CONFIG_SPMI=y
-CONFIG_PINCTRL_IPQ8074=y
CONFIG_PINCTRL_SINGLE=y
CONFIG_PINCTRL_MAX77620=y
+CONFIG_PINCTRL_IPQ8074=y
CONFIG_PINCTRL_MSM8916=y
CONFIG_PINCTRL_MSM8994=y
CONFIG_PINCTRL_MSM8996=y
-CONFIG_PINCTRL_MT7622=y
CONFIG_PINCTRL_QDF2XXX=y
CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
+CONFIG_PINCTRL_MT7622=y
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_MB86S7X=y
CONFIG_GPIO_PL061=y
CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
CONFIG_CPU_THERMAL=y
CONFIG_THERMAL_EMULATION=y
+CONFIG_ROCKCHIP_THERMAL=m
+CONFIG_RCAR_GEN3_THERMAL=y
CONFIG_ARMADA_THERMAL=y
CONFIG_BRCMSTB_THERMAL=m
CONFIG_EXYNOS_THERMAL=y
-CONFIG_RCAR_GEN3_THERMAL=y
-CONFIG_QCOM_TSENS=y
-CONFIG_ROCKCHIP_THERMAL=m
CONFIG_TEGRA_BPMP_THERMAL=m
+CONFIG_QCOM_TSENS=y
CONFIG_UNIPHIER_THERMAL=y
CONFIG_WATCHDOG=y
CONFIG_S3C2410_WATCHDOG=y
CONFIG_MFD_SPMI_PMIC=y
CONFIG_MFD_RK808=y
CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_AXP20X=y
CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_GPIO=y
CONFIG_REGULATOR_HI6421V530=y
CONFIG_REGULATOR_HI655X=y
CONFIG_REGULATOR_QCOM_SPMI=y
CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_S2MPS11=y
+CONFIG_RC_CORE=m
+CONFIG_RC_DECODERS=y
+CONFIG_RC_DEVICES=y
+CONFIG_IR_MESON=m
CONFIG_MEDIA_SUPPORT=m
CONFIG_MEDIA_CAMERA_SUPPORT=y
CONFIG_MEDIA_ANALOG_TV_SUPPORT=y
CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y
CONFIG_MEDIA_CONTROLLER=y
-CONFIG_MEDIA_RC_SUPPORT=y
-CONFIG_RC_CORE=m
-CONFIG_RC_DEVICES=y
-CONFIG_RC_DECODERS=y
-CONFIG_IR_MESON=m
CONFIG_VIDEO_V4L2_SUBDEV_API=y
# CONFIG_DVB_NET is not set
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_ROCKCHIP_DW_MIPI_DSI=y
CONFIG_ROCKCHIP_INNO_HDMI=y
CONFIG_DRM_RCAR_DU=m
-CONFIG_DRM_RCAR_LVDS=y
-CONFIG_DRM_RCAR_VSP=y
+CONFIG_DRM_RCAR_LVDS=m
CONFIG_DRM_TEGRA=m
CONFIG_DRM_PANEL_SIMPLE=m
CONFIG_DRM_I2C_ADV7511=m
CONFIG_BACKLIGHT_GENERIC=m
CONFIG_BACKLIGHT_PWM=m
CONFIG_BACKLIGHT_LP855X=m
-CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_SND_SOC_AK4613=m
CONFIG_SND_SIMPLE_CARD=m
CONFIG_SND_AUDIO_GRAPH_CARD=m
+CONFIG_I2C_HID=m
CONFIG_USB=y
CONFIG_USB_OTG=y
CONFIG_USB_XHCI_HCD=y
CONFIG_MMC_ARMMMCI=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_ACPI=y
-CONFIG_MMC_SDHCI_F_SDH30=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI_OF_ARASAN=y
CONFIG_MMC_SDHCI_OF_ESDHC=y
CONFIG_MMC_SDHCI_CADENCE=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_F_SDH30=y
CONFIG_MMC_MESON_GX=y
CONFIG_MMC_SDHCI_MSM=y
CONFIG_MMC_SPI=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_PWM=y
CONFIG_LEDS_SYSCON=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_CPU=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
CONFIG_LEDS_TRIGGER_PANIC=y
-CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_EDAC=y
CONFIG_EDAC_GHES=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_S5M=y
CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_CROS_EC=y
CONFIG_RTC_DRV_S3C=y
CONFIG_RTC_DRV_PL031=y
CONFIG_RTC_DRV_SUN6I=y
CONFIG_RTC_DRV_ARMADA38X=y
CONFIG_RTC_DRV_TEGRA=y
CONFIG_RTC_DRV_XGENE=y
-CONFIG_RTC_DRV_CROS_EC=y
CONFIG_DMADEVICES=y
CONFIG_DMA_BCM2835=m
CONFIG_K3_DMA=y
CONFIG_ARM_MHU=y
CONFIG_PLATFORM_MHU=y
CONFIG_BCM2835_MBOX=y
-CONFIG_HI6220_MBOX=y
CONFIG_QCOM_APCS_IPC=y
CONFIG_ROCKCHIP_IOMMU=y
CONFIG_TEGRA_IOMMU_SMMU=y
CONFIG_EXTCON_USB_GPIO=y
CONFIG_EXTCON_USBC_CROS_EC=y
CONFIG_MEMORY=y
-CONFIG_TEGRA_MC=y
CONFIG_IIO=y
CONFIG_EXYNOS_ADC=y
CONFIG_ROCKCHIP_SARADC=m
CONFIG_PWM_ROCKCHIP=y
CONFIG_PWM_SAMSUNG=y
CONFIG_PWM_TEGRA=m
+CONFIG_PHY_XGENE=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_HI6220_USB=y
CONFIG_PHY_HISTB_COMBPHY=y
CONFIG_PHY_HISI_INNO_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB3=m
-CONFIG_PHY_HI6220_USB=y
-CONFIG_PHY_QCOM_USB_HS=y
-CONFIG_PHY_SUN4I_USB=y
CONFIG_PHY_MVEBU_CP110_COMPHY=y
CONFIG_PHY_QCOM_QMP=m
-CONFIG_PHY_ROCKCHIP_INNO_USB2=y
+CONFIG_PHY_QCOM_USB_HS=y
+CONFIG_PHY_RCAR_GEN3_USB2=y
+CONFIG_PHY_RCAR_GEN3_USB3=m
CONFIG_PHY_ROCKCHIP_EMMC=y
+CONFIG_PHY_ROCKCHIP_INNO_USB2=y
CONFIG_PHY_ROCKCHIP_PCIE=m
CONFIG_PHY_ROCKCHIP_TYPEC=y
-CONFIG_PHY_XGENE=y
CONFIG_PHY_TEGRA_XUSB=y
CONFIG_QCOM_L2_PMU=y
CONFIG_QCOM_L3_PMU=y
-CONFIG_MESON_EFUSE=m
CONFIG_QCOM_QFPROM=y
CONFIG_ROCKCHIP_EFUSE=y
CONFIG_UNIPHIER_EFUSE=y
+CONFIG_MESON_EFUSE=m
CONFIG_TEE=y
CONFIG_OPTEE=y
CONFIG_ARM_SCPI_PROTOCOL=y
CONFIG_ACPI=y
CONFIG_ACPI_APEI=y
CONFIG_ACPI_APEI_GHES=y
-CONFIG_ACPI_APEI_PCIEAER=y
CONFIG_ACPI_APEI_MEMORY_FAILURE=y
CONFIG_ACPI_APEI_EINJ=y
CONFIG_EXT2_FS=y
CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
-CONFIG_LOCKUP_DETECTOR=y
# CONFIG_SCHED_DEBUG is not set
# CONFIG_DEBUG_PREEMPT is not set
# CONFIG_FTRACE is not set
CONFIG_CRYPTO_ECHAINIV=y
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_ARM64_CRYPTO=y
-CONFIG_CRYPTO_SHA256_ARM64=m
-CONFIG_CRYPTO_SHA512_ARM64=m
CONFIG_CRYPTO_SHA1_ARM64_CE=y
CONFIG_CRYPTO_SHA2_ARM64_CE=y
+CONFIG_CRYPTO_SHA512_ARM64_CE=m
+CONFIG_CRYPTO_SHA3_ARM64=m
+CONFIG_CRYPTO_SM3_ARM64_CE=m
CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m
CONFIG_CRYPTO_CRC32_ARM64_CE=m
-CONFIG_CRYPTO_AES_ARM64=m
-CONFIG_CRYPTO_AES_ARM64_CE=m
CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
-CONFIG_CRYPTO_AES_ARM64_NEON_BLK=m
CONFIG_CRYPTO_CHACHA20_NEON=m
CONFIG_CRYPTO_AES_ARM64_BS=m
-CONFIG_CRYPTO_SHA512_ARM64_CE=m
-CONFIG_CRYPTO_SHA3_ARM64=m
-CONFIG_CRYPTO_SM3_ARM64_CE=m
* u32 *macp, u8 const rk[], u32 rounds);
*/
ENTRY(ce_aes_ccm_auth_data)
- frame_push 7
-
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
-
- ldr w25, [x22] /* leftover from prev round? */
+ ldr w8, [x3] /* leftover from prev round? */
ld1 {v0.16b}, [x0] /* load mac */
- cbz w25, 1f
- sub w25, w25, #16
+ cbz w8, 1f
+ sub w8, w8, #16
eor v1.16b, v1.16b, v1.16b
-0: ldrb w7, [x20], #1 /* get 1 byte of input */
- subs w21, w21, #1
- add w25, w25, #1
+0: ldrb w7, [x1], #1 /* get 1 byte of input */
+ subs w2, w2, #1
+ add w8, w8, #1
ins v1.b[0], w7
ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */
beq 8f /* out of input? */
- cbnz w25, 0b
+ cbnz w8, 0b
eor v0.16b, v0.16b, v1.16b
-1: ld1 {v3.4s}, [x23] /* load first round key */
- prfm pldl1strm, [x20]
- cmp w24, #12 /* which key size? */
- add x6, x23, #16
- sub w7, w24, #2 /* modified # of rounds */
+1: ld1 {v3.4s}, [x4] /* load first round key */
+ prfm pldl1strm, [x1]
+ cmp w5, #12 /* which key size? */
+ add x6, x4, #16
+ sub w7, w5, #2 /* modified # of rounds */
bmi 2f
bne 5f
mov v5.16b, v3.16b
ld1 {v5.4s}, [x6], #16 /* load next round key */
bpl 3b
aese v0.16b, v4.16b
- subs w21, w21, #16 /* last data? */
+ subs w2, w2, #16 /* last data? */
eor v0.16b, v0.16b, v5.16b /* final round */
bmi 6f
- ld1 {v1.16b}, [x20], #16 /* load next input block */
+ ld1 {v1.16b}, [x1], #16 /* load next input block */
eor v0.16b, v0.16b, v1.16b /* xor with mac */
- beq 6f
-
- if_will_cond_yield_neon
- st1 {v0.16b}, [x19] /* store mac */
- do_cond_yield_neon
- ld1 {v0.16b}, [x19] /* reload mac */
- endif_yield_neon
-
- b 1b
-6: st1 {v0.16b}, [x19] /* store mac */
+ bne 1b
+6: st1 {v0.16b}, [x0] /* store mac */
beq 10f
- adds w21, w21, #16
+ adds w2, w2, #16
beq 10f
- mov w25, w21
-7: ldrb w7, [x20], #1
+ mov w8, w2
+7: ldrb w7, [x1], #1
umov w6, v0.b[0]
eor w6, w6, w7
- strb w6, [x19], #1
- subs w21, w21, #1
+ strb w6, [x0], #1
+ subs w2, w2, #1
beq 10f
ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */
b 7b
-8: mov w7, w25
- add w25, w25, #16
+8: mov w7, w8
+ add w8, w8, #16
9: ext v1.16b, v1.16b, v1.16b, #1
adds w7, w7, #1
bne 9b
eor v0.16b, v0.16b, v1.16b
- st1 {v0.16b}, [x19]
-10: str w25, [x22]
-
- frame_pop
+ st1 {v0.16b}, [x0]
+10: str w8, [x3]
ret
ENDPROC(ce_aes_ccm_auth_data)
ENDPROC(ce_aes_ccm_final)
.macro aes_ccm_do_crypt,enc
- frame_push 8
-
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
- mov x25, x6
-
- ldr x26, [x25, #8] /* load lower ctr */
- ld1 {v0.16b}, [x24] /* load mac */
-CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */
+ ldr x8, [x6, #8] /* load lower ctr */
+ ld1 {v0.16b}, [x5] /* load mac */
+CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
0: /* outer loop */
- ld1 {v1.8b}, [x25] /* load upper ctr */
- prfm pldl1strm, [x20]
- add x26, x26, #1
- rev x9, x26
- cmp w23, #12 /* which key size? */
- sub w7, w23, #2 /* get modified # of rounds */
+ ld1 {v1.8b}, [x6] /* load upper ctr */
+ prfm pldl1strm, [x1]
+ add x8, x8, #1
+ rev x9, x8
+ cmp w4, #12 /* which key size? */
+ sub w7, w4, #2 /* get modified # of rounds */
ins v1.d[1], x9 /* no carry in lower ctr */
- ld1 {v3.4s}, [x22] /* load first round key */
- add x10, x22, #16
+ ld1 {v3.4s}, [x3] /* load first round key */
+ add x10, x3, #16
bmi 1f
bne 4f
mov v5.16b, v3.16b
bpl 2b
aese v0.16b, v4.16b
aese v1.16b, v4.16b
- subs w21, w21, #16
- bmi 7f /* partial block? */
- ld1 {v2.16b}, [x20], #16 /* load next input block */
+ subs w2, w2, #16
+ bmi 6f /* partial block? */
+ ld1 {v2.16b}, [x1], #16 /* load next input block */
.if \enc == 1
eor v2.16b, v2.16b, v5.16b /* final round enc+mac */
eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */
eor v1.16b, v2.16b, v5.16b /* final round enc */
.endif
eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
- st1 {v1.16b}, [x19], #16 /* write output block */
- beq 5f
-
- if_will_cond_yield_neon
- st1 {v0.16b}, [x24] /* store mac */
- do_cond_yield_neon
- ld1 {v0.16b}, [x24] /* reload mac */
- endif_yield_neon
-
- b 0b
-5:
-CPU_LE( rev x26, x26 )
- st1 {v0.16b}, [x24] /* store mac */
- str x26, [x25, #8] /* store lsb end of ctr (BE) */
-
-6: frame_pop
- ret
-
-7: eor v0.16b, v0.16b, v5.16b /* final round mac */
+ st1 {v1.16b}, [x0], #16 /* write output block */
+ bne 0b
+CPU_LE( rev x8, x8 )
+ st1 {v0.16b}, [x5] /* store mac */
+ str x8, [x6, #8] /* store lsb end of ctr (BE) */
+5: ret
+
+6: eor v0.16b, v0.16b, v5.16b /* final round mac */
eor v1.16b, v1.16b, v5.16b /* final round enc */
- st1 {v0.16b}, [x24] /* store mac */
- add w21, w21, #16 /* process partial tail block */
-8: ldrb w9, [x20], #1 /* get 1 byte of input */
+ st1 {v0.16b}, [x5] /* store mac */
+ add w2, w2, #16 /* process partial tail block */
+7: ldrb w9, [x1], #1 /* get 1 byte of input */
umov w6, v1.b[0] /* get top crypted ctr byte */
umov w7, v0.b[0] /* get top mac byte */
.if \enc == 1
eor w9, w9, w6
eor w7, w7, w9
.endif
- strb w9, [x19], #1 /* store out byte */
- strb w7, [x24], #1 /* store mac byte */
- subs w21, w21, #1
- beq 6b
+ strb w9, [x0], #1 /* store out byte */
+ strb w7, [x5], #1 /* store mac byte */
+ subs w2, w2, #1
+ beq 5b
ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */
ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */
- b 8b
+ b 7b
.endm
/*
kernel_neon_begin();
aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
- err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
if (walk.nbytes) {
u8 __aligned(8) tail[AES_BLOCK_SIZE];
.endm
.macro pmull_gcm_do_crypt, enc
- frame_push 10
+ ld1 {SHASH.2d}, [x4]
+ ld1 {XL.2d}, [x1]
+ ldr x8, [x5, #8] // load lower counter
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
- mov x25, x6
- mov x26, x7
- .if \enc == 1
- ldr x27, [sp, #96] // first stacked arg
- .endif
-
- ldr x28, [x24, #8] // load lower counter
-CPU_LE( rev x28, x28 )
-
-0: mov x0, x25
- load_round_keys w26, x0
- ld1 {SHASH.2d}, [x23]
- ld1 {XL.2d}, [x20]
+ load_round_keys w7, x6
movi MASK.16b, #0xe1
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
+CPU_LE( rev x8, x8 )
shl MASK.2d, MASK.2d, #57
eor SHASH2.16b, SHASH2.16b, SHASH.16b
.if \enc == 1
- ld1 {KS.16b}, [x27]
+ ldr x10, [sp]
+ ld1 {KS.16b}, [x10]
.endif
-1: ld1 {CTR.8b}, [x24] // load upper counter
- ld1 {INP.16b}, [x22], #16
- rev x9, x28
- add x28, x28, #1
- sub w19, w19, #1
+0: ld1 {CTR.8b}, [x5] // load upper counter
+ ld1 {INP.16b}, [x3], #16
+ rev x9, x8
+ add x8, x8, #1
+ sub w0, w0, #1
ins CTR.d[1], x9 // set lower counter
.if \enc == 1
eor INP.16b, INP.16b, KS.16b // encrypt input
- st1 {INP.16b}, [x21], #16
+ st1 {INP.16b}, [x2], #16
.endif
rev64 T1.16b, INP.16b
- cmp w26, #12
- b.ge 4f // AES-192/256?
+ cmp w7, #12
+ b.ge 2f // AES-192/256?
-2: enc_round CTR, v21
+1: enc_round CTR, v21
ext T2.16b, XL.16b, XL.16b, #8
ext IN1.16b, T1.16b, T1.16b, #8
.if \enc == 0
eor INP.16b, INP.16b, KS.16b
- st1 {INP.16b}, [x21], #16
+ st1 {INP.16b}, [x2], #16
.endif
- cbz w19, 3f
+ cbnz w0, 0b
- if_will_cond_yield_neon
- st1 {XL.2d}, [x20]
- .if \enc == 1
- st1 {KS.16b}, [x27]
- .endif
- do_cond_yield_neon
- b 0b
- endif_yield_neon
+CPU_LE( rev x8, x8 )
+ st1 {XL.2d}, [x1]
+ str x8, [x5, #8] // store lower counter
- b 1b
-
-3: st1 {XL.2d}, [x20]
.if \enc == 1
- st1 {KS.16b}, [x27]
+ st1 {KS.16b}, [x10]
.endif
-CPU_LE( rev x28, x28 )
- str x28, [x24, #8] // store lower counter
-
- frame_pop
ret
-4: b.eq 5f // AES-192?
+2: b.eq 3f // AES-192?
enc_round CTR, v17
enc_round CTR, v18
-5: enc_round CTR, v19
+3: enc_round CTR, v19
enc_round CTR, v20
- b 2b
+ b 1b
.endm
/*
err = skcipher_walk_done(&walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (walk.nbytes)
- pmull_gcm_encrypt_block(iv, iv, NULL,
+ if (walk.nbytes) {
+ kernel_neon_begin();
+ pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
num_rounds(&ctx->aes_key));
+ kernel_neon_end();
+ }
+
} else {
__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
num_rounds(&ctx->aes_key));
__le32 *origptr, __le32 *updptr, int nr_inst);
void __init apply_alternatives_all(void);
-void apply_alternatives(void *start, size_t length);
+
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length);
+#else
+static inline void apply_alternatives_module(void *start, size_t length) { }
+#endif
#define ALTINSTR_ENTRY(feature,cb) \
" .word 661b - .\n" /* label */ \
#include <asm/cmpxchg.h>
-#define ___atomic_add_unless(v, a, u, sfx) \
-({ \
- typeof((v)->counter) c, old; \
- \
- c = atomic##sfx##_read(v); \
- while (c != (u) && \
- (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \
- c = old; \
- c; \
- })
-
#define ATOMIC_INIT(i) { (i) }
#define atomic_read(v) READ_ONCE((v)->counter)
#define atomic_add_return_release atomic_add_return_release
#define atomic_add_return atomic_add_return
-#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v))
-#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v))
-#define atomic_inc_return_release(v) atomic_add_return_release(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
#define atomic_sub_return_relaxed atomic_sub_return_relaxed
#define atomic_sub_return_acquire atomic_sub_return_acquire
#define atomic_sub_return_release atomic_sub_return_release
#define atomic_sub_return atomic_sub_return
-#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v))
-#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v))
-#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v))
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-
#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
#define atomic_fetch_add_acquire atomic_fetch_add_acquire
#define atomic_fetch_add_release atomic_fetch_add_release
cmpxchg_release(&((v)->counter), (old), (new))
#define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new))
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0)
-#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,)
#define atomic_andnot atomic_andnot
/*
#define atomic64_add_return_release atomic64_add_return_release
#define atomic64_add_return atomic64_add_return
-#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v))
-#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v))
-#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
#define atomic64_sub_return_acquire atomic64_sub_return_acquire
#define atomic64_sub_return_release atomic64_sub_return_release
#define atomic64_sub_return atomic64_sub_return
-#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v))
-#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v))
-#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v))
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-
#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
#define atomic64_fetch_add_acquire atomic64_fetch_add_acquire
#define atomic64_fetch_add_release atomic64_fetch_add_release
#define atomic64_cmpxchg_release atomic_cmpxchg_release
#define atomic64_cmpxchg atomic_cmpxchg
-#define atomic64_inc(v) atomic64_add(1, (v))
-#define atomic64_dec(v) atomic64_sub(1, (v))
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0)
-#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u)
#define atomic64_andnot atomic64_andnot
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+#define atomic64_dec_if_positive atomic64_dec_if_positive
#endif
#endif
#define __ASM_BITOPS_H
#include <linux/compiler.h>
-#include <asm/barrier.h>
#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
#endif
-/*
- * Little endian assembly atomic bitops.
- */
-extern void set_bit(int nr, volatile unsigned long *p);
-extern void clear_bit(int nr, volatile unsigned long *p);
-extern void change_bit(int nr, volatile unsigned long *p);
-extern int test_and_set_bit(int nr, volatile unsigned long *p);
-extern int test_and_clear_bit(int nr, volatile unsigned long *p);
-extern int test_and_change_bit(int nr, volatile unsigned long *p);
-
#include <asm-generic/bitops/builtin-__ffs.h>
#include <asm-generic/bitops/builtin-ffs.h>
#include <asm-generic/bitops/builtin-__fls.h>
#include <asm-generic/bitops/sched.h>
#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
#include <asm-generic/bitops/non-atomic.h>
#include <asm-generic/bitops/le.h>
-
-/*
- * Ext2 is defined to use little-endian byte ordering.
- */
-#define ext2_set_bit_atomic(lock, nr, p) test_and_set_bit_le(nr, p)
-#define ext2_clear_bit_atomic(lock, nr, p) test_and_clear_bit_le(nr, p)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
#endif /* __ASM_BITOPS_H */
* Start addresses are inclusive and end addresses are exclusive; start
* addresses should be rounded down, end addresses up.
*
- * See Documentation/cachetlb.txt for more information. Please note that
+ * See Documentation/core-api/cachetlb.rst for more information. Please note that
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
* VIPT I-cache.
*
#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__)
#define efi_is_64bit() (true)
+#define efi_table_attr(table, attr, instance) \
+ ((table##_t *)instance)->attr
+
#define efi_call_proto(protocol, f, instance, ...) \
((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
struct task_struct;
struct notifier_block;
+struct perf_event_attr;
struct perf_event;
struct pmu;
extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
int *gen_len, int *gen_type, int *offset);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
struct pt_regs;
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
static inline int nr_legacy_irqs(void)
{
return 0;
unsigned long saved_irqflag;
struct prev_kprobe prev_kprobe;
struct kprobe_step_ctx ss_ctx;
- struct pt_regs jprobe_saved_regs;
};
void arch_remove_kprobe(struct kprobe *);
#define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */
#define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */
#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */
+#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */
#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs)
* Only if the new pte is valid and kernel, otherwise TLB maintenance
* or update_mmu_cache() have the necessary barriers.
*/
- if (pte_valid_not_user(pte)) {
+ if (pte_valid_not_user(pte))
dsb(ishst);
- isb();
- }
}
extern void __sync_icache_dcache(pte_t pteval);
{
WRITE_ONCE(*pmdp, pmd);
dsb(ishst);
- isb();
}
static inline void pmd_clear(pmd_t *pmdp)
{
WRITE_ONCE(*pudp, pud);
dsb(ishst);
- isb();
}
static inline void pud_clear(pud_t *pudp)
static __must_check inline bool may_use_simd(void)
{
/*
- * The raw_cpu_read() is racy if called with preemption enabled.
- * This is not a bug: kernel_neon_busy is only set when
- * preemption is disabled, so we cannot migrate to another CPU
- * while it is set, nor can we migrate to a CPU where it is set.
- * So, if we find it clear on some CPU then we're guaranteed to
- * find it clear on any CPU we could migrate to.
- *
- * If we are in between kernel_neon_begin()...kernel_neon_end(),
- * the flag will be set, but preemption is also disabled, so we
- * can't migrate to another CPU and spuriously see it become
- * false.
+ * kernel_neon_busy is only set while preemption is disabled,
+ * and is clear whenever preemption is enabled. Since
+ * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
+ * cannot change under our feet -- if it's set we cannot be
+ * migrated, and if it's clear we cannot be migrated to a CPU
+ * where it is set.
*/
return !in_irq() && !irqs_disabled() && !in_nmi() &&
- !raw_cpu_read(kernel_neon_busy);
+ !this_cpu_read(kernel_neon_busy);
}
#else /* ! CONFIG_KERNEL_MODE_NEON */
asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
} while (0)
+/*
+ * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the
+ * set mask are set. Other bits are left as-is.
+ */
+#define sysreg_clear_set(sysreg, clear, set) do { \
+ u64 __scs_val = read_sysreg(sysreg); \
+ u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
+ if (__scs_new != __scs_val) \
+ write_sysreg(__scs_new, sysreg); \
+} while (0)
+
static inline void config_sctlr_el1(u32 clear, u32 set)
{
u32 val;
static inline void tlb_flush(struct mmu_gather *tlb)
{
- struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+ struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
/*
* The ASID allocator will either invalidate the ASID or mark
}
}
-static void __apply_alternatives(void *alt_region, bool use_linear_alias)
+/*
+ * We provide our own, private D-cache cleaning function so that we don't
+ * accidentally call into the cache.S code, which is patched by us at
+ * runtime.
+ */
+static void clean_dcache_range_nopatch(u64 start, u64 end)
+{
+ u64 cur, d_size, ctr_el0;
+
+ ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
+ d_size = 4 << cpuid_feature_extract_unsigned_field(ctr_el0,
+ CTR_DMINLINE_SHIFT);
+ cur = start & ~(d_size - 1);
+ do {
+ /*
+ * We must clean+invalidate to the PoC in order to avoid
+ * Cortex-A53 errata 826319, 827319, 824069 and 819472
+ * (this corresponds to ARM64_WORKAROUND_CLEAN_CACHE)
+ */
+ asm volatile("dc civac, %0" : : "r" (cur) : "memory");
+ } while (cur += d_size, cur < end);
+}
+
+static void __apply_alternatives(void *alt_region, bool is_module)
{
struct alt_instr *alt;
struct alt_region *region = alt_region;
pr_info_once("patching kernel code\n");
origptr = ALT_ORIG_PTR(alt);
- updptr = use_linear_alias ? lm_alias(origptr) : origptr;
+ updptr = is_module ? origptr : lm_alias(origptr);
nr_inst = alt->orig_len / AARCH64_INSN_SIZE;
if (alt->cpufeature < ARM64_CB_PATCH)
alt_cb(alt, origptr, updptr, nr_inst);
- flush_icache_range((uintptr_t)origptr,
- (uintptr_t)(origptr + nr_inst));
+ if (!is_module) {
+ clean_dcache_range_nopatch((u64)origptr,
+ (u64)(origptr + nr_inst));
+ }
+ }
+
+ /*
+ * The core module code takes care of cache maintenance in
+ * flush_module_icache().
+ */
+ if (!is_module) {
+ dsb(ish);
+ __flush_icache_all();
+ isb();
}
}
isb();
} else {
BUG_ON(alternatives_applied);
- __apply_alternatives(®ion, true);
+ __apply_alternatives(®ion, false);
/* Barriers provided by the cache flushing */
WRITE_ONCE(alternatives_applied, 1);
}
stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
}
-void apply_alternatives(void *start, size_t length)
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length)
{
struct alt_region region = {
.begin = start,
.end = start + length,
};
- __apply_alternatives(®ion, false);
+ __apply_alternatives(®ion, true);
}
+#endif
__kpti_forced = enabled ? 1 : -1;
return 0;
}
-__setup("kpti=", parse_kpti);
+early_param("kpti", parse_kpti);
#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
#ifdef CONFIG_ARM64_HW_AFDBM
static void update_cpu_capabilities(u16 scope_mask)
{
- __update_cpu_capabilities(arm64_features, scope_mask, "detected:");
__update_cpu_capabilities(arm64_errata, scope_mask,
"enabling workaround for");
+ __update_cpu_capabilities(arm64_features, scope_mask, "detected:");
}
static int __enable_cpu_capability(void *arg)
static void __init enable_cpu_capabilities(u16 scope_mask)
{
- __enable_cpu_capabilities(arm64_features, scope_mask);
__enable_cpu_capabilities(arm64_errata, scope_mask);
+ __enable_cpu_capabilities(arm64_features, scope_mask);
}
/*
/*
* Check whether bp virtual address is in kernel space.
*/
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
unsigned int len;
unsigned long va;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- va = info->address;
- len = get_hbp_len(info->ctrl.len);
+ va = hw->address;
+ len = get_hbp_len(hw->ctrl.len);
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
/*
* Construct an arch_hw_breakpoint from a perf_event.
*/
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
/* Type */
- switch (bp->attr.bp_type) {
+ switch (attr->bp_type) {
case HW_BREAKPOINT_X:
- info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+ hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
break;
case HW_BREAKPOINT_R:
- info->ctrl.type = ARM_BREAKPOINT_LOAD;
+ hw->ctrl.type = ARM_BREAKPOINT_LOAD;
break;
case HW_BREAKPOINT_W:
- info->ctrl.type = ARM_BREAKPOINT_STORE;
+ hw->ctrl.type = ARM_BREAKPOINT_STORE;
break;
case HW_BREAKPOINT_RW:
- info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+ hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
break;
default:
return -EINVAL;
}
/* Len */
- switch (bp->attr.bp_len) {
+ switch (attr->bp_len) {
case HW_BREAKPOINT_LEN_1:
- info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
break;
case HW_BREAKPOINT_LEN_2:
- info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
break;
case HW_BREAKPOINT_LEN_3:
- info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_3;
break;
case HW_BREAKPOINT_LEN_4:
- info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
break;
case HW_BREAKPOINT_LEN_5:
- info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_5;
break;
case HW_BREAKPOINT_LEN_6:
- info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_6;
break;
case HW_BREAKPOINT_LEN_7:
- info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_7;
break;
case HW_BREAKPOINT_LEN_8:
- info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
break;
default:
return -EINVAL;
* AArch32 also requires breakpoints of length 2 for Thumb.
* Watchpoints can be of length 1, 2, 4 or 8 bytes.
*/
- if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+ if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
if (is_compat_bp(bp)) {
- if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
- info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+ if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+ hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
return -EINVAL;
- } else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) {
+ } else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) {
/*
* FIXME: Some tools (I'm looking at you perf) assume
* that breakpoints should be sizeof(long). This
* is nonsense. For now, we fix up the parameter
* but we should probably return -EINVAL instead.
*/
- info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+ hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
}
}
/* Address */
- info->address = bp->attr.bp_addr;
+ hw->address = attr->bp_addr;
/*
* Privilege
* Note that we disallow combined EL0/EL1 breakpoints because
* that would complicate the stepping code.
*/
- if (arch_check_bp_in_kernelspace(bp))
- info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
+ if (arch_check_bp_in_kernelspace(hw))
+ hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
else
- info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
+ hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
/* Enabled? */
- info->ctrl.enabled = !bp->attr.disabled;
+ hw->ctrl.enabled = !attr->disabled;
return 0;
}
/*
* Validate the arch-specific HW Breakpoint register settings.
*/
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
int ret;
u64 alignment_mask, offset;
/* Build the arch_hw_breakpoint. */
- ret = arch_build_bp_info(bp);
+ ret = arch_build_bp_info(bp, attr, hw);
if (ret)
return ret;
* that here.
*/
if (is_compat_bp(bp)) {
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
alignment_mask = 0x7;
else
alignment_mask = 0x3;
- offset = info->address & alignment_mask;
+ offset = hw->address & alignment_mask;
switch (offset) {
case 0:
/* Aligned */
break;
case 1:
/* Allow single byte watchpoint. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
break;
case 2:
/* Allow halfword watchpoints and breakpoints. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
break;
default:
return -EINVAL;
}
} else {
- if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
+ if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE)
alignment_mask = 0x3;
else
alignment_mask = 0x7;
- offset = info->address & alignment_mask;
+ offset = hw->address & alignment_mask;
}
- info->address &= ~alignment_mask;
- info->ctrl.len <<= offset;
+ hw->address &= ~alignment_mask;
+ hw->ctrl.len <<= offset;
/*
* Disallow per-task kernel breakpoints since these would
* complicate the stepping code.
*/
- if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
+ if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
return -EINVAL;
return 0;
return 0;
}
-void (*handle_arch_irq)(struct pt_regs *) = NULL;
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
- if (handle_arch_irq)
- return;
-
- handle_arch_irq = handle_irq;
-}
-
#ifdef CONFIG_VMAP_STACK
static void init_irq_stacks(void)
{
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
- if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) {
- apply_alternatives((void *)s->sh_addr, s->sh_size);
- }
+ if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
+ apply_alternatives_module((void *)s->sh_addr, s->sh_size);
#ifdef CONFIG_ARM64_MODULE_PLTS
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
!strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
break;
case KPROBE_HIT_SS:
case KPROBE_REENTER:
- pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+ pr_warn("Unrecoverable kprobe detected.\n");
dump_kprobe(p);
BUG();
break;
/*
* If we have no pre-handler or it returned 0, we
* continue with normal processing. If we have a
- * pre-handler and it returned non-zero, it prepped
- * for calling the break_handler below on re-entry,
- * so get out doing nothing more here.
+ * pre-handler and it returned non-zero, it will
+ * modify the execution path and no need to single
+ * stepping. Let's just reset current kprobe and exit.
*
* pre_handler can hit a breakpoint and can step thru
* before return, keep PSTATE D-flag enabled until
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs, kcb, 0);
- return;
- }
- }
- } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
- BRK64_OPCODE_KPROBES) && cur_kprobe) {
- /* We probably hit a jprobe. Call its break handler. */
- if (cur_kprobe->break_handler &&
- cur_kprobe->break_handler(cur_kprobe, regs)) {
- setup_singlestep(cur_kprobe, regs, kcb, 0);
- return;
+ } else
+ reset_current_kprobe();
}
}
/*
return DBG_HOOK_HANDLED;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- kcb->jprobe_saved_regs = *regs;
- /*
- * Since we can't be sure where in the stack frame "stacked"
- * pass-by-value arguments are stored we just don't try to
- * duplicate any of the stack. Do not use jprobes on functions that
- * use more than 64 bytes (after padding each to an 8 byte boundary)
- * of arguments, or pass individual arguments larger than 16 bytes.
- */
-
- instruction_pointer_set(regs, (unsigned long) jp->entry);
- preempt_disable();
- pause_graph_tracing();
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- /*
- * Jprobe handler return by entering break exception,
- * encoded same as kprobe, but with following conditions
- * -a special PC to identify it from the other kprobes.
- * -restore stack addr to original saved pt_regs
- */
- asm volatile(" mov sp, %0 \n"
- "jprobe_return_break: brk %1 \n"
- :
- : "r" (kcb->jprobe_saved_regs.sp),
- "I" (BRK64_ESR_KPROBES)
- : "memory");
-
- unreachable();
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- long stack_addr = kcb->jprobe_saved_regs.sp;
- long orig_sp = kernel_stack_pointer(regs);
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- extern const char jprobe_return_break[];
-
- if (instruction_pointer(regs) != (u64) jprobe_return_break)
- return 0;
-
- if (orig_sp != stack_addr) {
- struct pt_regs *saved_regs =
- (struct pt_regs *)kcb->jprobe_saved_regs.sp;
- pr_err("current sp %lx does not match saved sp %lx\n",
- orig_sp, stack_addr);
- pr_err("Saved registers for jprobe %p\n", jp);
- __show_regs(saved_regs);
- pr_err("Current registers\n");
- __show_regs(regs);
- BUG();
- }
- unpause_graph_tracing();
- *regs = kcb->jprobe_saved_regs;
- preempt_enable_no_resched();
- return 1;
-}
-
bool arch_within_kprobe_blacklist(unsigned long addr)
{
if ((addr >= (unsigned long)__kprobes_text_start &&
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
*/
-asmlinkage void secondary_start_kernel(void)
+asmlinkage notrace void secondary_start_kernel(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
* Copyright 2018 Arm Limited
* Author: Dave Martin <Dave.Martin@arm.com>
*/
-#include <linux/bottom_half.h>
+#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
#include <linux/kvm_host.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_host.h>
#include <asm/kvm_mmu.h>
+#include <asm/sysreg.h>
/*
* Called on entry to KVM_RUN unless this vcpu previously ran at least
{
BUG_ON(!current->mm);
- vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE);
+ vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+ KVM_ARM64_HOST_SVE_IN_USE |
+ KVM_ARM64_HOST_SVE_ENABLED);
vcpu->arch.flags |= KVM_ARM64_FP_HOST;
+
if (test_thread_flag(TIF_SVE))
vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE;
+
+ if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
+ vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
}
/*
*/
void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
{
- local_bh_disable();
+ unsigned long flags;
- update_thread_flag(TIF_SVE,
- vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+ local_irq_save(flags);
if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
/* Clean guest FP state to memory and invalidate cpu view */
fpsimd_save();
fpsimd_flush_cpu_state();
- } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
- /* Ensure user trap controls are correctly restored */
- fpsimd_bind_task_to_cpu();
+ } else if (system_supports_sve()) {
+ /*
+ * The FPSIMD/SVE state in the CPU has not been touched, and we
+ * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
+ * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE
+ * for EL0. To avoid spurious traps, restore the trap state
+ * seen by kvm_arch_vcpu_load_fp():
+ */
+ if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED)
+ sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
+ else
+ sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
}
- local_bh_enable();
+ update_thread_flag(TIF_SVE,
+ vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+
+ local_irq_restore(flags);
}
# SPDX-License-Identifier: GPL-2.0
-lib-y := bitops.o clear_user.o delay.o copy_from_user.o \
+lib-y := clear_user.o delay.o copy_from_user.o \
copy_to_user.o copy_in_user.o copy_page.o \
clear_page.o memchr.o memcpy.o memmove.o memset.o \
memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \
+++ /dev/null
-/*
- * Based on arch/arm/lib/bitops.h
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/lse.h>
-
-/*
- * x0: bits 5:0 bit offset
- * bits 31:6 word offset
- * x1: address
- */
- .macro bitop, name, llsc, lse
-ENTRY( \name )
- and w3, w0, #63 // Get bit offset
- eor w0, w0, w3 // Clear low bits
- mov x2, #1
- add x1, x1, x0, lsr #3 // Get word offset
-alt_lse " prfm pstl1strm, [x1]", "nop"
- lsl x3, x2, x3 // Create mask
-
-alt_lse "1: ldxr x2, [x1]", "\lse x3, [x1]"
-alt_lse " \llsc x2, x2, x3", "nop"
-alt_lse " stxr w0, x2, [x1]", "nop"
-alt_lse " cbnz w0, 1b", "nop"
-
- ret
-ENDPROC(\name )
- .endm
-
- .macro testop, name, llsc, lse
-ENTRY( \name )
- and w3, w0, #63 // Get bit offset
- eor w0, w0, w3 // Clear low bits
- mov x2, #1
- add x1, x1, x0, lsr #3 // Get word offset
-alt_lse " prfm pstl1strm, [x1]", "nop"
- lsl x4, x2, x3 // Create mask
-
-alt_lse "1: ldxr x2, [x1]", "\lse x4, x2, [x1]"
- lsr x0, x2, x3
-alt_lse " \llsc x2, x2, x4", "nop"
-alt_lse " stlxr w5, x2, [x1]", "nop"
-alt_lse " cbnz w5, 1b", "nop"
-alt_lse " dmb ish", "nop"
-
- and x0, x0, #1
- ret
-ENDPROC(\name )
- .endm
-
-/*
- * Atomic bit operations.
- */
- bitop change_bit, eor, steor
- bitop clear_bit, bic, stclr
- bitop set_bit, orr, stset
-
- testop test_and_change_bit, eor, ldeoral
- testop test_and_clear_bit, bic, ldclral
- testop test_and_set_bit, orr, ldsetal
size >> PAGE_SHIFT);
return NULL;
}
- if (!coherent)
- __dma_flush_area(page_to_virt(page), iosize);
-
addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
prot,
__builtin_return_address(0));
- if (!addr) {
+ if (addr) {
+ memset(addr, 0, size);
+ if (!coherent)
+ __dma_flush_area(page_to_virt(page), iosize);
+ } else {
iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
dma_release_from_contiguous(dev, page,
size >> PAGE_SHIFT);
unsigned long pgsize,
unsigned long ncontig)
{
- struct vm_area_struct vma = { .vm_mm = mm };
pte_t orig_pte = huge_ptep_get(ptep);
bool valid = pte_valid(orig_pte);
unsigned long i, saddr = addr;
orig_pte = pte_mkdirty(orig_pte);
}
- if (valid)
+ if (valid) {
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
flush_tlb_range(&vma, saddr, addr);
+ }
return orig_pte;
}
unsigned long pgsize,
unsigned long ncontig)
{
- struct vm_area_struct vma = { .vm_mm = mm };
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
unsigned long i, saddr = addr;
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
}
#endif
-static phys_addr_t memory_limit = (phys_addr_t)ULLONG_MAX;
+static phys_addr_t memory_limit = PHYS_ADDR_MAX;
/*
* Limit the memory size that was specified via FDT.
* high up in memory, add back the kernel region that must be accessible
* via the linear mapping.
*/
- if (memory_limit != (phys_addr_t)ULLONG_MAX) {
+ if (memory_limit != PHYS_ADDR_MAX) {
memblock_mem_limit_remove_map(memory_limit);
memblock_add(__pa_symbol(_text), (u64)(_end - _text));
}
BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64);
#endif
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Make sure we chose the upper bound of sizeof(struct page)
- * correctly.
+ * correctly when sizing the VMEMMAP array.
*/
BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+#endif
if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
extern int sysctl_overcommit_memory;
*/
static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p)
{
- if (memory_limit != (phys_addr_t)ULLONG_MAX) {
+ if (memory_limit != PHYS_ADDR_MAX) {
pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
} else {
pr_emerg("Memory Limit: none\n");
return 1;
}
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
return pud_none(*pud);
}
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
return pmd_none(*pmd);
}
.macro __idmap_kpti_put_pgtable_ent_ng, type
orr \type, \type, #PTE_NG // Same bit for blocks and pages
- str \type, [cur_\()\type\()p] // Update the entry and ensure it
- dc civac, cur_\()\type\()p // is visible to all CPUs.
+ str \type, [cur_\()\type\()p] // Update the entry and ensure
+ dmb sy // that it is visible to all
+ dc civac, cur_\()\type\()p // CPUs.
.endm
/*
#ifndef __ARCH_H8300_ATOMIC__
#define __ARCH_H8300_ATOMIC__
+#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/irqflags.h>
/*
* Atomic operations that C can't guarantee us. Useful for
#define atomic_read(v) READ_ONCE((v)->counter)
#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
-#include <linux/kernel.h>
-
#define ATOMIC_OP_RETURN(op, c_op) \
static inline int atomic_##op##_return(int i, atomic_t *v) \
{ \
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_inc_return(v) atomic_add_return(1, v)
-#define atomic_dec_return(v) atomic_sub_return(1, v)
-
-#define atomic_inc(v) (void)atomic_inc_return(v)
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec(v) (void)atomic_dec_return(v)
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-
static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
int ret;
return ret;
}
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int ret;
h8300flags flags;
arch_local_irq_restore(flags);
return ret;
}
+#define atomic_fetch_add_unless atomic_fetch_add_unless
#endif /* __ARCH_H8300_ATOMIC __ */
#undef ATOMIC_OP
/**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
* @v: pointer to value
* @a: amount to add
* @u: unless value is equal to u
*
*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int __oldval;
register int tmp;
);
return __oldval;
}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
+#define atomic_fetch_add_unless atomic_fetch_add_unless
#endif
/* A handy thing to have if one has the RAM. Declared in head.S */
extern unsigned long empty_zero_page;
-extern unsigned long zero_page_mask;
/*
* The PTE model described here is that of the Hexagon Virtual Machine,
*/
__vmsetvec(_K_VM_event_vector);
- printk(KERN_INFO "PHYS_OFFSET=0x%08x\n", PHYS_OFFSET);
+ printk(KERN_INFO "PHYS_OFFSET=0x%08lx\n", PHYS_OFFSET);
/*
* Simulator has a few differences from the hardware.
/* Set as variable to limit PMD copies */
int max_kernel_seg = 0x303;
-/* think this should be (page_size-1) the way it's used...*/
-unsigned long zero_page_mask;
-
/* indicate pfn's of high memory */
unsigned long highstart_pfn, highend_pfn;
(cmpxchg(&((v)->counter), old, new))
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
-
-static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
-{
- long c, old, dec;
- c = atomic64_read(v);
- for (;;) {
- dec = c - 1;
- if (unlikely(dec < 0))
- break;
- old = atomic64_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
- return dec;
-}
-
-/*
- * Atomically add I to V and return TRUE if the resulting value is
- * negative.
- */
-static __inline__ int
-atomic_add_negative (int i, atomic_t *v)
-{
- return atomic_add_return(i, v) < 0;
-}
-
-static __inline__ long
-atomic64_add_negative (__s64 i, atomic64_t *v)
-{
- return atomic64_add_return(i, v) < 0;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
#define atomic_add(i,v) (void)atomic_add_return((i), (v))
#define atomic_sub(i,v) (void)atomic_sub_return((i), (v))
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
#define atomic64_add(i,v) (void)atomic64_add_return((i), (v))
#define atomic64_sub(i,v) (void)atomic64_sub_return((i), (v))
-#define atomic64_inc(v) atomic64_add(1, (v))
-#define atomic64_dec(v) atomic64_sub(1, (v))
#endif /* _ASM_IA64_ATOMIC_H */
#define ARCH_PREV_KPROBE_SZ 2
struct kprobe_ctlblk {
unsigned long kprobe_status;
- struct pt_regs jprobe_saved_regs;
- unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE];
unsigned long *bsp;
unsigned long cfm;
atomic_t prev_kprobe_index;
flush_tlb_all();
} else {
/*
- * XXX fix me: flush_tlb_range() should take an mm pointer instead of a
- * vma pointer.
+ * flush_tlb_range() takes a vma instead of a mm pointer because
+ * some architectures want the vm_flags for ITLB/DTLB flush.
*/
- struct vm_area_struct vma;
+ struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
- vma.vm_mm = tlb->mm;
/* flush the address range from the tlb: */
flush_tlb_range(&vma, start, end);
/* now flush the virt. page-table area mapping the address range: */
*/
#define __IA64_BREAK_KDB 0x80100
#define __IA64_BREAK_KPROBE 0x81000 /* .. 0x81fff */
-#define __IA64_BREAK_JPROBE 0x82000
/*
* OS-specific break numbers:
obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o
obj-$(CONFIG_IA64_CYCLONE) += cyclone.o
obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o
-obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o
+obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+++ /dev/null
-/*
- * Jprobe specific operations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Intel Corporation, 2005
- *
- * 2005-May Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy
- * <anil.s.keshavamurthy@intel.com> initial implementation
- *
- * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a
- * probe to be inserted into the beginning of a function call. The fundamental
- * difference between a jprobe and a kprobe is the jprobe handler is executed
- * in the same context as the target function, while the kprobe handlers
- * are executed in interrupt context.
- *
- * For jprobes we initially gain control by placing a break point in the
- * first instruction of the targeted function. When we catch that specific
- * break, we:
- * * set the return address to our jprobe_inst_return() function
- * * jump to the jprobe handler function
- *
- * Since we fixed up the return address, the jprobe handler will return to our
- * jprobe_inst_return() function, giving us control again. At this point we
- * are back in the parents frame marker, so we do yet another call to our
- * jprobe_break() function to fix up the frame marker as it would normally
- * exist in the target function.
- *
- * Our jprobe_return function then transfers control back to kprobes.c by
- * executing a break instruction using one of our reserved numbers. When we
- * catch that break in kprobes.c, we continue like we do for a normal kprobe
- * by single stepping the emulated instruction, and then returning execution
- * to the correct location.
- */
-#include <asm/asmmacro.h>
-#include <asm/break.h>
-
- /*
- * void jprobe_break(void)
- */
- .section .kprobes.text, "ax"
-ENTRY(jprobe_break)
- break.m __IA64_BREAK_JPROBE
-END(jprobe_break)
-
- /*
- * void jprobe_inst_return(void)
- */
-GLOBAL_ENTRY(jprobe_inst_return)
- br.call.sptk.many b0=jprobe_break
-END(jprobe_inst_return)
-
-GLOBAL_ENTRY(invalidate_stacked_regs)
- movl r16=invalidate_restore_cfm
- ;;
- mov b6=r16
- ;;
- br.ret.sptk.many b6
- ;;
-invalidate_restore_cfm:
- mov r16=ar.rsc
- ;;
- mov ar.rsc=r0
- ;;
- loadrs
- ;;
- mov ar.rsc=r16
- ;;
- br.cond.sptk.many rp
-END(invalidate_stacked_regs)
-
-GLOBAL_ENTRY(flush_register_stack)
- // flush dirty regs to backing store (must be first in insn group)
- flushrs
- ;;
- br.ret.sptk.many rp
-END(flush_register_stack)
-
#include <asm/sections.h>
#include <asm/exception.h>
-extern void jprobe_inst_return(void);
-
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
*/
break;
}
-
kretprobe_assert(ri, orig_ret_address, trampoline_address);
- reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
prepare_ss(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
return 1;
- } else if (args->err == __IA64_BREAK_JPROBE) {
- /*
- * jprobe instrumented function just completed
- */
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- goto ss_probe;
- }
} else if (!is_ia64_break_inst(regs)) {
/* The breakpoint instruction was removed by
* another cpu right after we hit, no further
set_current_kprobe(p, kcb);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (p->pre_handler && p->pre_handler(p, regs))
- /*
- * Our pre-handler is specifically requesting that we just
- * do a return. This is used for both the jprobe pre-handler
- * and the kretprobe trampoline
- */
+ if (p->pre_handler && p->pre_handler(p, regs)) {
+ reset_current_kprobe();
+ preempt_enable_no_resched();
return 1;
+ }
-ss_probe:
#if !defined(CONFIG_PREEMPT)
if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
case DIE_BREAK:
/* err is break number from ia64_bad_break() */
if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12)
- || args->err == __IA64_BREAK_JPROBE
|| args->err == 0)
if (pre_kprobes_handler(args))
ret = NOTIFY_STOP;
return ((struct fnptr *)entry)->ip;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- unsigned long addr = arch_deref_entry_point(jp->entry);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- struct param_bsp_cfm pa;
- int bytes;
-
- /*
- * Callee owns the argument space and could overwrite it, eg
- * tail call optimization. So to be absolutely safe
- * we save the argument space before transferring the control
- * to instrumented jprobe function which runs in
- * the process context
- */
- pa.ip = regs->cr_iip;
- unw_init_running(ia64_get_bsp_cfm, &pa);
- bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f)
- - (char *)pa.bsp;
- memcpy( kcb->jprobes_saved_stacked_regs,
- pa.bsp,
- bytes );
- kcb->bsp = pa.bsp;
- kcb->cfm = pa.cfm;
-
- /* save architectural state */
- kcb->jprobe_saved_regs = *regs;
-
- /* after rfi, execute the jprobe instrumented function */
- regs->cr_iip = addr & ~0xFULL;
- ia64_psr(regs)->ri = addr & 0xf;
- regs->r1 = ((struct fnptr *)(jp->entry))->gp;
-
- /*
- * fix the return address to our jprobe_inst_return() function
- * in the jprobes.S file
- */
- regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip;
-
- return 1;
-}
-
-/* ia64 does not need this */
-void __kprobes jprobe_return(void)
-{
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- int bytes;
-
- /* restoring architectural state */
- *regs = kcb->jprobe_saved_regs;
-
- /* restoring the original argument space */
- flush_register_stack();
- bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f)
- - (char *)kcb->bsp;
- memcpy( kcb->bsp,
- kcb->jprobes_saved_stacked_regs,
- bytes );
- invalidate_stacked_regs();
-
- preempt_enable_no_resched();
- return 1;
-}
-
static struct kprobe trampoline_p = {
.pre_handler = trampoline_probe_handler
};
DPRINT(("smpl_buf @%p\n", smpl_buf));
/* allocate vma */
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(mm);
if (!vma) {
DPRINT(("Cannot allocate vma\n"));
goto error_kmem;
}
- INIT_LIST_HEAD(&vma->anon_vma_chain);
/*
* partially initialize the vma for the sampling buffer
*/
- vma->vm_mm = mm;
vma->vm_file = get_file(filp);
vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP;
vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */
return 0;
error:
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
error_kmem:
pfm_rvfree(smpl_buf, size);
* the problem. When the process attempts to write to the register backing store
* for the first time, it will get a SEGFAULT in this case.
*/
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(current->mm);
if (vma) {
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma->vm_mm = current->mm;
+ vma_set_anonymous(vma);
vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
vma->vm_end = vma->vm_start + PAGE_SIZE;
vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
down_write(¤t->mm->mmap_sem);
if (insert_vm_struct(current->mm, vma)) {
up_write(¤t->mm->mmap_sem);
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return;
}
up_write(¤t->mm->mmap_sem);
/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
if (!(current->personality & MMAP_PAGE_ZERO)) {
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(current->mm);
if (vma) {
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma->vm_mm = current->mm;
+ vma_set_anonymous(vma);
vma->vm_end = PAGE_SIZE;
vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
down_write(¤t->mm->mmap_sem);
if (insert_vm_struct(current->mm, vma)) {
up_write(¤t->mm->mmap_sem);
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return;
}
up_write(¤t->mm->mmap_sem);
static int __init gate_vma_init(void)
{
- gate_vma.vm_mm = NULL;
+ vma_init(&gate_vma, NULL);
gate_vma.vm_start = FIXADDR_USER_START;
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
config M68K
bool
default y
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
select ARCH_NO_COHERENT_DMA_MMAP if !MMU
select HAVE_IDE
select MODULES_USE_ELF_RELA
select OLD_SIGSUSPEND3
select OLD_SIGACTION
+ select DMA_NONCOHERENT_OPS if HAS_DMA
+ select HAVE_MEMBLOCK
+ select ARCH_DISCARD_MEMBLOCK
+ select NO_BOOTMEM
config CPU_BIG_ENDIAN
def_bool y
extern void dn_init_IRQ(void);
extern u32 dn_gettimeoffset(void);
extern int dn_dummy_hwclk(int, struct rtc_time *);
-extern int dn_dummy_set_clock_mmss(unsigned long);
extern void dn_dummy_reset(void);
#ifdef CONFIG_HEARTBEAT
static void dn_heartbeat(int on);
arch_gettimeoffset = dn_gettimeoffset;
mach_max_dma_address = 0xffffffff;
mach_hwclk = dn_dummy_hwclk; /* */
- mach_set_clock_mmss = dn_dummy_set_clock_mmss; /* */
mach_reset = dn_dummy_reset; /* */
#ifdef CONFIG_HEARTBEAT
mach_heartbeat = dn_heartbeat;
}
-int dn_dummy_set_clock_mmss(unsigned long nowtime)
-{
- pr_info("set_clock_mmss\n");
- return 0;
-}
-
void dn_dummy_reset(void) {
dn_serial_print("The end !\n");
extern u32 atari_gettimeoffset(void);
extern int atari_mste_hwclk (int, struct rtc_time *);
extern int atari_tt_hwclk (int, struct rtc_time *);
-extern int atari_mste_set_clock_mmss (unsigned long);
-extern int atari_tt_set_clock_mmss (unsigned long);
-
/* ++roman: This is a more elaborate test for an SCC chip, since the plain
* Medusa board generates DTACK at the SCC's standard addresses, but a SCC
ATARIHW_SET(TT_CLK);
pr_cont(" TT_CLK");
mach_hwclk = atari_tt_hwclk;
- mach_set_clock_mmss = atari_tt_set_clock_mmss;
}
if (hwreg_present(&mste_rtc.sec_ones)) {
ATARIHW_SET(MSTE_CLK);
pr_cont(" MSTE_CLK");
mach_hwclk = atari_mste_hwclk;
- mach_set_clock_mmss = atari_mste_set_clock_mmss;
}
if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) &&
hwreg_write(&dma_wd.fdc_speed, 0)) {
return( 0 );
}
-
-int atari_mste_set_clock_mmss (unsigned long nowtime)
-{
- short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
- struct MSTE_RTC val;
- unsigned char rtc_minutes;
-
- mste_read(&val);
- rtc_minutes= val.min_ones + val.min_tens * 10;
- if ((rtc_minutes < real_minutes
- ? real_minutes - rtc_minutes
- : rtc_minutes - real_minutes) < 30)
- {
- val.sec_ones = real_seconds % 10;
- val.sec_tens = real_seconds / 10;
- val.min_ones = real_minutes % 10;
- val.min_tens = real_minutes / 10;
- mste_write(&val);
- }
- else
- return -1;
- return 0;
-}
-
-int atari_tt_set_clock_mmss (unsigned long nowtime)
-{
- int retval = 0;
- short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
- unsigned char save_control, save_freq_select, rtc_minutes;
-
- save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */
- RTC_WRITE (RTC_CONTROL, save_control | RTC_SET);
-
- save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */
- RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2);
-
- rtc_minutes = RTC_READ (RTC_MINUTES);
- if (!(save_control & RTC_DM_BINARY))
- rtc_minutes = bcd2bin(rtc_minutes);
-
- /* Since we're only adjusting minutes and seconds, don't interfere
- with hour overflow. This avoids messing with unknown time zones
- but requires your RTC not to be off by more than 30 minutes. */
- if ((rtc_minutes < real_minutes
- ? real_minutes - rtc_minutes
- : rtc_minutes - real_minutes) < 30)
- {
- if (!(save_control & RTC_DM_BINARY))
- {
- real_seconds = bin2bcd(real_seconds);
- real_minutes = bin2bcd(real_minutes);
- }
- RTC_WRITE (RTC_SECONDS, real_seconds);
- RTC_WRITE (RTC_MINUTES, real_minutes);
- }
- else
- retval = -1;
-
- RTC_WRITE (RTC_FREQ_SELECT, save_freq_select);
- RTC_WRITE (RTC_CONTROL, save_control);
- return retval;
-}
-
/*
* Local variables:
* c-indent-level: 4
extern void bvme6000_sched_init(irq_handler_t handler);
extern u32 bvme6000_gettimeoffset(void);
extern int bvme6000_hwclk (int, struct rtc_time *);
-extern int bvme6000_set_clock_mmss (unsigned long);
extern void bvme6000_reset (void);
void bvme6000_set_vectors (void);
mach_init_IRQ = bvme6000_init_IRQ;
arch_gettimeoffset = bvme6000_gettimeoffset;
mach_hwclk = bvme6000_hwclk;
- mach_set_clock_mmss = bvme6000_set_clock_mmss;
mach_reset = bvme6000_reset;
mach_get_model = bvme6000_get_model;
return 0;
}
-
-/*
- * Set the minutes and seconds from seconds value 'nowtime'. Fail if
- * clock is out by > 30 minutes. Logic lifted from atari code.
- * Algorithm is to wait for the 10ms register to change, and then to
- * wait a short while, and then set it.
- */
-
-int bvme6000_set_clock_mmss (unsigned long nowtime)
-{
- int retval = 0;
- short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
- unsigned char rtc_minutes, rtc_tenms;
- volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
- unsigned char msr = rtc->msr & 0xc0;
- unsigned long flags;
- volatile int i;
-
- rtc->msr = 0; /* Ensure clock accessible */
- rtc_minutes = bcd2bin (rtc->bcd_min);
-
- if ((rtc_minutes < real_minutes
- ? real_minutes - rtc_minutes
- : rtc_minutes - real_minutes) < 30)
- {
- local_irq_save(flags);
- rtc_tenms = rtc->bcd_tenms;
- while (rtc_tenms == rtc->bcd_tenms)
- ;
- for (i = 0; i < 1000; i++)
- ;
- rtc->bcd_min = bin2bcd(real_minutes);
- rtc->bcd_sec = bin2bcd(real_seconds);
- local_irq_restore(flags);
- }
- else
- retval = -1;
-
- rtc->msr = msr;
-
- return retval;
-}
-
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_GVP11_SCSI=y
CONFIG_SCSI_A4000T=y
CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
CONFIG_MD=y
CONFIG_MD_LINEAR=m
CONFIG_BLK_DEV_DM=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_ARIADNE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CIRRUS is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
CONFIG_HYDRA=y
CONFIG_APNE=y
CONFIG_ZORRO8390=y
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
# CONFIG_NET_VENDOR_AMAZON is not set
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_ATARILANCE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
CONFIG_NE2000=y
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
# CONFIG_NET_VENDOR_AMAZON is not set
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
CONFIG_BVME6000_NET=y
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_HPLANCE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_MACMACE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
CONFIG_MAC89x0=y
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
CONFIG_MACSONIC=y
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_GVP11_SCSI=y
CONFIG_SCSI_A4000T=y
CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
CONFIG_ATARI_SCSI=y
CONFIG_MAC_SCSI=y
CONFIG_SCSI_MAC_ESP=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_MACMACE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
CONFIG_MAC89x0=y
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
CONFIG_MVME16x_NET=y
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
CONFIG_MACSONIC=y
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
CONFIG_HYDRA=y
CONFIG_MAC8390=y
CONFIG_NE2000=y
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PLIP=m
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_MVME147_NET=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
# CONFIG_NET_VENDOR_AMAZON is not set
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
CONFIG_MVME16x_NET=y
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
# CONFIG_NET_VENDOR_AMD is not set
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CIRRUS is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
CONFIG_NE2000=y
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PLIP=m
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_SUN3_82586=y
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_TLS=m
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
CONFIG_INET=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
CONFIG_NF_TABLES_INET=y
CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_MASQ=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NFT_FIB_NETDEV=m
CONFIG_IP_SET_HASH_NETIFACE=m
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
CONFIG_DNS_RESOLVER=y
CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
CONFIG_BATMAN_ADV_DAT=y
CONFIG_BATMAN_ADV_NC=y
CONFIG_BATMAN_ADV_MCAST=y
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=m
CONFIG_DM_RAID=m
CONFIG_SUN3LANCE=y
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_UHID=m
# CONFIG_HID_GENERIC is not set
# CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
# CONFIG_RTC_NVMEM is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
CONFIG_FUSE_FS=m
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
CONFIG_TEST_RHASHTABLE=m
CONFIG_TEST_HASH=m
CONFIG_TEST_USER_COPY=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_DRBG_HASH=y
CONFIG_CRYPTO_DRBG_CTR=y
generic-y += barrier.h
generic-y += compat.h
generic-y += device.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += exec.h
generic-y += extable.h
{
__asm__ __volatile__("addql #1,%0" : "+m" (*v));
}
+#define atomic_inc atomic_inc
static inline void atomic_dec(atomic_t *v)
{
__asm__ __volatile__("subql #1,%0" : "+m" (*v));
}
+#define atomic_dec atomic_dec
static inline int atomic_dec_and_test(atomic_t *v)
{
__asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v));
return c != 0;
}
+#define atomic_dec_and_test atomic_dec_and_test
static inline int atomic_dec_and_test_lt(atomic_t *v)
{
__asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v));
return c != 0;
}
+#define atomic_inc_and_test atomic_inc_and_test
#ifdef CONFIG_RMW_INSNS
#endif /* !CONFIG_RMW_INSNS */
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
static inline int atomic_sub_and_test(int i, atomic_t *v)
{
char c;
: ASM_DI (i));
return c != 0;
}
+#define atomic_sub_and_test atomic_sub_and_test
static inline int atomic_add_negative(int i, atomic_t *v)
{
: ASM_DI (i));
return c != 0;
}
-
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
+#define atomic_add_negative atomic_add_negative
#endif /* __ARCH_M68K_ATOMIC __ */
*/
#if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \
!defined(CONFIG_M68000) && !defined(CONFIG_MCPU32)
-static inline int __ffs(int x)
+static inline unsigned long __ffs(unsigned long x)
{
__asm__ __volatile__ ("bitrev %0; ff1 %0"
: "=d" (x)
: "dm" (x & -x));
return 32 - cnt;
}
-#define __ffs(x) (ffs(x) - 1)
+
+static inline unsigned long __ffs(unsigned long x)
+{
+ return ffs(x) - 1;
+}
/*
* fls: find last bit set.
#endif
+/* Simple test-and-set bit locks */
+#define test_and_set_bit_lock test_and_set_bit
+#define clear_bit_unlock clear_bit
+#define __clear_bit_unlock clear_bit_unlock
+
#include <asm-generic/bitops/ext2-atomic.h>
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/sched.h>
#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
#endif /* __KERNEL__ */
#endif /* _M68K_BITOPS_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_DMA_MAPPING_H
-#define _M68K_DMA_MAPPING_H
-
-extern const struct dma_map_ops m68k_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &m68k_dma_ops;
-}
-
-#endif /* _M68K_DMA_MAPPING_H */
/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _M68K_IO_H
+#define _M68K_IO_H
+
#if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
#include <asm/io_no.h>
#else
#include <asm/io_mm.h>
#endif
+
+#include <asm-generic/io.h>
+
+#endif /* _M68K_IO_H */
* isa_readX(),isa_writeX() are for ISA memory
*/
-#ifndef _IO_H
-#define _IO_H
+#ifndef _M68K_IO_MM_H
+#define _M68K_IO_MM_H
#ifdef __KERNEL__
-#define ARCH_HAS_IOREMAP_WT
-
#include <linux/compiler.h>
#include <asm/raw_io.h>
#include <asm/virtconvert.h>
#define writew(val, addr) out_le16((addr), (val))
#endif /* CONFIG_ATARI_ROM_ISA */
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
-/*
- * We need to define dummy functions for GENERIC_IOMAP support.
- */
-#define inb(port) 0xff
-#define inb_p(port) 0xff
-#define outb(val,port) ((void)0)
-#define outb_p(val,port) ((void)0)
-#define inw(port) 0xffff
-#define inw_p(port) 0xffff
-#define outw(val,port) ((void)0)
-#define outw_p(val,port) ((void)0)
-#define inl(port) 0xffffffffUL
-#define inl_p(port) 0xffffffffUL
-#define outl(val,port) ((void)0)
-#define outl_p(val,port) ((void)0)
-
-#define insb(port,buf,nr) ((void)0)
-#define outsb(port,buf,nr) ((void)0)
-#define insw(port,buf,nr) ((void)0)
-#define outsw(port,buf,nr) ((void)0)
-#define insl(port,buf,nr) ((void)0)
-#define outsl(port,buf,nr) ((void)0)
-
-/*
- * These should be valid on any ioremap()ed region
- */
-#define readb(addr) in_8(addr)
-#define writeb(val,addr) out_8((addr),(val))
-#define readw(addr) in_le16(addr)
-#define writew(val,addr) out_le16((addr),(val))
-
-#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
-
#define readl(addr) in_le32(addr)
#define writel(val,addr) out_le32((addr),(val))
#define writew_relaxed(b, addr) writew(b, addr)
#define writel_relaxed(b, addr) writel(b, addr)
-#endif /* _IO_H */
+#endif /* _M68K_IO_MM_H */
#define PCI_SPACE_LIMIT PCI_IO_MASK
#endif /* CONFIG_PCI */
-/*
- * These are defined in kmap.h as static inline functions. To maintain
- * previous behavior we put these define guards here so io_mm.h doesn't
- * see them.
- */
-#ifdef CONFIG_MMU
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
-#endif
-
#include <asm/kmap.h>
#include <asm/virtconvert.h>
-#include <asm-generic/io.h>
#endif /* _M68KNOMMU_IO_H */
#ifdef CONFIG_MMU
+#define ARCH_HAS_IOREMAP_WT
+
/* Values for nocacheflag and cmode */
#define IOMAP_FULL_CACHING 0
#define IOMAP_NOCACHE_SER 1
*/
extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
int cacheflag);
+#define iounmap iounmap
extern void iounmap(void __iomem *addr);
extern void __iounmap(void *addr, unsigned long size);
}
#define ioremap_uc ioremap_nocache
+#define ioremap_wt ioremap_wt
static inline void __iomem *ioremap_wt(unsigned long physaddr,
unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
}
-#define ioremap_fillcache ioremap_fullcache
+#define ioremap_fullcache ioremap_fullcache
static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
}
+#define memset_io memset_io
static inline void memset_io(volatile void __iomem *addr, unsigned char val,
int count)
{
__builtin_memset((void __force *) addr, val, count);
}
+#define memcpy_fromio memcpy_fromio
static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
int count)
{
__builtin_memcpy(dst, (void __force *) src, count);
}
+#define memcpy_toio memcpy_toio
static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
int count)
{
extern unsigned int (*mach_get_ss)(void);
extern int (*mach_get_rtc_pll)(struct rtc_pll_info *);
extern int (*mach_set_rtc_pll)(struct rtc_pll_info *);
-extern int (*mach_set_clock_mmss)(unsigned long);
extern void (*mach_reset)( void );
extern void (*mach_halt)( void );
extern void (*mach_power_off)( void );
#define MAC_SCSI_IIFX 5
#define MAC_SCSI_DUO 6
#define MAC_SCSI_LC 7
-#define MAC_SCSI_LATE 8
#define MAC_IDE_NONE 0
#define MAC_IDE_QUADRA 1
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
unsigned long address)
{
+ pgtable_page_dtor(page);
__free_page(page);
}
return page;
}
-extern inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, struct page *page)
{
+ pgtable_page_dtor(page);
__free_page(page);
}
#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
#define __pa(vaddr) ((unsigned long)(vaddr))
-#define __va(paddr) ((void *)(paddr))
+#define __va(paddr) ((void *)((unsigned long)(paddr)))
#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
#define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT)
#undef DEBUG
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
-static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
gfp_t flag, unsigned long attrs)
{
struct page *page, **map;
return addr;
}
-static void m68k_dma_free(struct device *dev, size_t size, void *addr,
+void arch_dma_free(struct device *dev, size_t size, void *addr,
dma_addr_t handle, unsigned long attrs)
{
pr_debug("dma_free_coherent: %p, %x\n", addr, handle);
#include <asm/cacheflush.h>
-static void *m68k_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
{
void *ret;
return ret;
}
-static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
free_pages((unsigned long)vaddr, get_order(size));
#endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
-static void m68k_dma_sync_single_for_device(struct device *dev,
- dma_addr_t handle, size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
+ size_t size, enum dma_data_direction dir)
{
switch (dir) {
case DMA_BIDIRECTIONAL:
}
}
-static void m68k_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sglist, int nents, enum dma_data_direction dir)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nents, i) {
- dma_sync_single_for_device(dev, sg->dma_address, sg->length,
- dir);
- }
-}
-
-static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t handle = page_to_phys(page) + offset;
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_sync_single_for_device(dev, handle, size, dir);
-
- return handle;
-}
-
-static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nents, i) {
- sg->dma_address = sg_phys(sg);
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- continue;
-
- dma_sync_single_for_device(dev, sg->dma_address, sg->length,
- dir);
- }
- return nents;
-}
-
-const struct dma_map_ops m68k_dma_ops = {
- .alloc = m68k_dma_alloc,
- .free = m68k_dma_free,
- .map_page = m68k_dma_map_page,
- .map_sg = m68k_dma_map_sg,
- .sync_single_for_device = m68k_dma_sync_single_for_device,
- .sync_sg_for_device = m68k_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(m68k_dma_ops);
-
void arch_setup_pdev_archdata(struct platform_device *pdev)
{
if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/module.h>
/* machine dependent timer functions */
int (*mach_hwclk) (int, struct rtc_time*);
EXPORT_SYMBOL(mach_hwclk);
-int (*mach_set_clock_mmss) (unsigned long);
unsigned int (*mach_get_ss)(void);
int (*mach_get_rtc_pll)(struct rtc_pll_info *);
int (*mach_set_rtc_pll)(struct rtc_pll_info *);
be32_to_cpu(m->addr);
m68k_memory[m68k_num_memory].size =
be32_to_cpu(m->size);
+ memblock_add(m68k_memory[m68k_num_memory].addr,
+ m68k_memory[m68k_num_memory].size);
m68k_num_memory++;
} else
pr_warn("%s: too many memory chunks\n",
void __init setup_arch(char **cmdline_p)
{
-#ifndef CONFIG_SUN3
- int i;
-#endif
-
/* The bootinfo is located right after the kernel */
if (!CPU_IS_COLDFIRE)
m68k_parse_bootinfo((const struct bi_record *)_end);
#endif
#ifndef CONFIG_SUN3
- for (i = 1; i < m68k_num_memory; i++)
- free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr,
- m68k_memory[i].size);
#ifdef CONFIG_BLK_DEV_INITRD
if (m68k_ramdisk.size) {
- reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)),
- m68k_ramdisk.addr, m68k_ramdisk.size,
- BOOTMEM_DEFAULT);
+ memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size);
initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr);
initrd_end = initrd_start + m68k_ramdisk.size;
pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/initrd.h>
/* machine dependent timer functions */
void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL;
-int (*mach_set_clock_mmss)(unsigned long);
int (*mach_hwclk) (int, struct rtc_time*);
/* machine dependent reboot functions */
void __init setup_arch(char **cmdline_p)
{
- int bootmap_size;
-
memory_start = PAGE_ALIGN(_ramstart);
memory_end = _ramend;
pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
__bss_stop, memory_start, memory_start, memory_end);
+ memblock_add(memory_start, memory_end - memory_start);
+
/* Keep a copy of command line */
*cmdline_p = &command_line[0];
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
min_low_pfn = PFN_DOWN(memory_start);
max_pfn = max_low_pfn = PFN_DOWN(memory_end);
- bootmap_size = init_bootmem_node(
- NODE_DATA(0),
- min_low_pfn, /* map goes here */
- PFN_DOWN(PAGE_OFFSET),
- max_pfn);
- /*
- * Free the usable memory, we have to make sure we do not free
- * the bootmem bitmap so we then reserve it after freeing it :-)
- */
- free_bootmem(memory_start, memory_end - memory_start);
- reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-
#if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD)
if ((initrd_start > 0) && (initrd_start < initrd_end) &&
(initrd_end < memory_end))
- reserve_bootmem(initrd_start, initrd_end - initrd_start,
- BOOTMEM_DEFAULT);
+ memblock_reserve(initrd_start, initrd_end - initrd_start);
#endif /* if defined(CONFIG_BLK_DEV_INITRD) */
/*
/* Mac specific timer functions */
extern u32 mac_gettimeoffset(void);
extern int mac_hwclk(int, struct rtc_time *);
-extern int mac_set_clock_mmss(unsigned long);
extern void iop_preinit(void);
extern void iop_init(void);
extern void via_init(void);
mach_get_model = mac_get_model;
arch_gettimeoffset = mac_gettimeoffset;
mach_hwclk = mac_hwclk;
- mach_set_clock_mmss = mac_set_clock_mmss;
mach_reset = mac_reset;
mach_halt = mac_poweroff;
mach_power_off = mac_poweroff;
.name = "PowerBook 520",
.adb_type = MAC_ADB_PB2,
.via_type = MAC_VIA_QUADRA,
- .scsi_type = MAC_SCSI_LATE,
+ .scsi_type = MAC_SCSI_OLD,
.scc_type = MAC_SCC_QUADRA,
.ether_type = MAC_ETHER_SONIC,
.floppy_type = MAC_FLOPPY_SWIM_ADDR2,
},
};
-static const struct resource mac_scsi_late_rsrc[] __initconst = {
- {
- .flags = IORESOURCE_IRQ,
- .start = IRQ_MAC_SCSI,
- .end = IRQ_MAC_SCSI,
- }, {
- .flags = IORESOURCE_MEM,
- .start = 0x50010000,
- .end = 0x50011FFF,
- },
-};
-
static const struct resource mac_scsi_ccl_rsrc[] __initconst = {
{
.flags = IORESOURCE_IRQ,
platform_device_register_simple("mac_scsi", 0,
mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc));
break;
- case MAC_SCSI_LATE:
- /* XXX PDMA support for PowerBook 500 series needs testing */
- platform_device_register_simple("mac_scsi", 0,
- mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc));
- break;
case MAC_SCSI_LC:
/* Addresses from Mac LC data in Designing Cards & Drivers 3ed.
* Also from the Developer Notes for Classic II, LC III,
#include <asm/machdep.h>
-/* Offset between Unix time (1970-based) and Mac time (1904-based) */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
#define RTC_OFFSET 2082844800
static void (*rom_reset)(void);
#ifdef CONFIG_ADB_CUDA
-static long cuda_read_time(void)
+static time64_t cuda_read_time(void)
{
struct adb_request req;
- long time;
+ time64_t time;
if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
return 0;
while (!req.complete)
cuda_poll();
- time = (req.reply[3] << 24) | (req.reply[4] << 16) |
- (req.reply[5] << 8) | req.reply[6];
+ time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) |
+ (req.reply[5] << 8) | req.reply[6]);
+
return time - RTC_OFFSET;
}
-static void cuda_write_time(long data)
+static void cuda_write_time(time64_t time)
{
struct adb_request req;
+ u32 data = lower_32_bits(time + RTC_OFFSET);
- data += RTC_OFFSET;
if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
(data >> 24) & 0xFF, (data >> 16) & 0xFF,
(data >> 8) & 0xFF, data & 0xFF) < 0)
#endif /* CONFIG_ADB_CUDA */
#ifdef CONFIG_ADB_PMU68K
-static long pmu_read_time(void)
+static time64_t pmu_read_time(void)
{
struct adb_request req;
- long time;
+ time64_t time;
if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
return 0;
while (!req.complete)
pmu_poll();
- time = (req.reply[1] << 24) | (req.reply[2] << 16) |
- (req.reply[3] << 8) | req.reply[4];
+ time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
+ (req.reply[3] << 8) | req.reply[4]);
+
return time - RTC_OFFSET;
}
-static void pmu_write_time(long data)
+static void pmu_write_time(time64_t time)
{
struct adb_request req;
+ u32 data = lower_32_bits(time + RTC_OFFSET);
- data += RTC_OFFSET;
if (pmu_request(&req, NULL, 5, PMU_SET_RTC,
(data >> 24) & 0xFF, (data >> 16) & 0xFF,
(data >> 8) & 0xFF, data & 0xFF) < 0)
* is basically any machine with Mac II-style ADB.
*/
-static long via_read_time(void)
+static time64_t via_read_time(void)
{
union {
__u8 cdata[4];
- long idata;
+ __u32 idata;
} result, last_result;
int count = 1;
via_pram_command(0x8D, &result.cdata[0]);
if (result.idata == last_result.idata)
- return result.idata - RTC_OFFSET;
+ return (time64_t)result.idata - RTC_OFFSET;
if (++count > 10)
break;
last_result.idata = result.idata;
}
- pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n",
- last_result.idata, result.idata);
+ pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n",
+ __func__, last_result.idata, result.idata);
return 0;
}
* is basically any machine with Mac II-style ADB.
*/
-static void via_write_time(long time)
+static void via_write_time(time64_t time)
{
union {
__u8 cdata[4];
- long idata;
+ __u32 idata;
} data;
__u8 temp;
temp = 0x55;
via_pram_command(0x35, &temp);
- data.idata = time + RTC_OFFSET;
+ data.idata = lower_32_bits(time + RTC_OFFSET);
via_pram_command(0x01, &data.cdata[3]);
via_pram_command(0x05, &data.cdata[2]);
via_pram_command(0x09, &data.cdata[1]);
* This function translates seconds since 1970 into a proper date.
*
* Algorithm cribbed from glibc2.1, __offtime().
+ *
+ * This is roughly same as rtc_time64_to_tm(), which we should probably
+ * use here, but it's only available when CONFIG_RTC_LIB is enabled.
*/
#define SECS_PER_MINUTE (60)
#define SECS_PER_HOUR (SECS_PER_MINUTE * 60)
#define SECS_PER_DAY (SECS_PER_HOUR * 24)
-static void unmktime(unsigned long time, long offset,
+static void unmktime(time64_t time, long offset,
int *yearp, int *monp, int *dayp,
int *hourp, int *minp, int *secp)
{
/* Leap years. */
{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
};
- long int days, rem, y, wday, yday;
+ int days, rem, y, wday, yday;
const unsigned short int *ip;
- days = time / SECS_PER_DAY;
- rem = time % SECS_PER_DAY;
+ days = div_u64_rem(time, SECS_PER_DAY, &rem);
rem += offset;
while (rem < 0) {
rem += SECS_PER_DAY;
int mac_hwclk(int op, struct rtc_time *t)
{
- unsigned long now;
+ time64_t now;
if (!op) { /* read */
switch (macintosh_config->adb_type) {
__func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
t->tm_hour, t->tm_min, t->tm_sec);
- now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
- t->tm_hour, t->tm_min, t->tm_sec);
+ now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+ t->tm_hour, t->tm_min, t->tm_sec);
switch (macintosh_config->adb_type) {
case MAC_ADB_IOP:
}
return 0;
}
-
-/*
- * Set minutes/seconds in the hardware clock
- */
-
-int mac_set_clock_mmss (unsigned long nowtime)
-{
- struct rtc_time now;
-
- mac_hwclk(0, &now);
- now.tm_sec = nowtime % 60;
- now.tm_min = (nowtime / 60) % 60;
- mac_hwclk(1, &now);
-
- return 0;
-}
pg_data_table[i] = pg_data_map + node;
}
#endif
- pg_data_map[node].bdata = bootmem_node_data + node;
node_set_online(node);
}
#include <linux/init.h>
#include <linux/string.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <asm/setup.h>
#include <asm/page.h>
void __init cf_bootmem_alloc(void)
{
- unsigned long start_pfn;
unsigned long memstart;
/* _rambase and _ramend will be naturally page aligned */
m68k_memory[0].addr = _rambase;
m68k_memory[0].size = _ramend - _rambase;
+ memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+
/* compute total pages in system */
num_pages = PFN_DOWN(_ramend - _rambase);
/* page numbers */
memstart = PAGE_ALIGN(_ramstart);
min_low_pfn = PFN_DOWN(_rambase);
- start_pfn = PFN_DOWN(memstart);
max_pfn = max_low_pfn = PFN_DOWN(_ramend);
high_memory = (void *)_ramend;
+ /* Reserve kernel text/data/bss */
+ memblock_reserve(memstart, memstart - _rambase);
+
m68k_virt_to_node_shift = fls(_ramend - 1) - 6;
module_fixup(NULL, __start_fixup, __stop_fixup);
- /* setup bootmem data */
+ /* setup node data */
m68k_setup_node(0);
- memstart += init_bootmem_node(NODE_DATA(0), start_pfn,
- min_low_pfn, max_low_pfn);
- free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart);
}
/*
#include <linux/types.h>
#include <linux/init.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/gfp.h>
#include <asm/setup.h>
{
unsigned long zones_size[MAX_NR_ZONES] = { 0, };
unsigned long min_addr, max_addr;
- unsigned long addr, size, end;
+ unsigned long addr;
int i;
#ifdef DEBUG
min_low_pfn = availmem >> PAGE_SHIFT;
max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
- for (i = 0; i < m68k_num_memory; i++) {
- addr = m68k_memory[i].addr;
- end = addr + m68k_memory[i].size;
- m68k_setup_node(i);
- availmem = PAGE_ALIGN(availmem);
- availmem += init_bootmem_node(NODE_DATA(i),
- availmem >> PAGE_SHIFT,
- addr >> PAGE_SHIFT,
- end >> PAGE_SHIFT);
- }
+ /* Reserve kernel text/data/bss and the memory allocated in head.S */
+ memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr);
/*
* Map the physical memory available into the kernel virtual
- * address space. First initialize the bootmem allocator with
- * the memory we already mapped, so map_node() has something
- * to allocate.
+ * address space. Make sure memblock will not try to allocate
+ * pages beyond the memory we already mapped in head.S
*/
- addr = m68k_memory[0].addr;
- size = m68k_memory[0].size;
- free_bootmem_node(NODE_DATA(0), availmem,
- min(m68k_init_mapped_size, size) - (availmem - addr));
- map_node(0);
- if (size > m68k_init_mapped_size)
- free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size,
- size - m68k_init_mapped_size);
-
- for (i = 1; i < m68k_num_memory; i++)
+ memblock_set_bottom_up(true);
+
+ for (i = 0; i < m68k_num_memory; i++) {
+ m68k_setup_node(i);
map_node(i);
+ }
flush_tlb_all();
extern void mvme147_sched_init(irq_handler_t handler);
extern u32 mvme147_gettimeoffset(void);
extern int mvme147_hwclk (int, struct rtc_time *);
-extern int mvme147_set_clock_mmss (unsigned long);
extern void mvme147_reset (void);
mach_init_IRQ = mvme147_init_IRQ;
arch_gettimeoffset = mvme147_gettimeoffset;
mach_hwclk = mvme147_hwclk;
- mach_set_clock_mmss = mvme147_set_clock_mmss;
mach_reset = mvme147_reset;
mach_get_model = mvme147_get_model;
}
return 0;
}
-
-int mvme147_set_clock_mmss (unsigned long nowtime)
-{
- return 0;
-}
extern void mvme16x_sched_init(irq_handler_t handler);
extern u32 mvme16x_gettimeoffset(void);
extern int mvme16x_hwclk (int, struct rtc_time *);
-extern int mvme16x_set_clock_mmss (unsigned long);
extern void mvme16x_reset (void);
int bcd2int (unsigned char b);
mach_init_IRQ = mvme16x_init_IRQ;
arch_gettimeoffset = mvme16x_gettimeoffset;
mach_hwclk = mvme16x_hwclk;
- mach_set_clock_mmss = mvme16x_set_clock_mmss;
mach_reset = mvme16x_reset;
mach_get_model = mvme16x_get_model;
mach_get_hardware_list = mvme16x_get_hardware_list;
}
return 0;
}
-
-int mvme16x_set_clock_mmss (unsigned long nowtime)
-{
- return 0;
-}
-
static u32 q40_gettimeoffset(void);
static int q40_hwclk(int, struct rtc_time *);
static unsigned int q40_get_ss(void);
-static int q40_set_clock_mmss(unsigned long);
static int q40_get_rtc_pll(struct rtc_pll_info *pll);
static int q40_set_rtc_pll(struct rtc_pll_info *pll);
mach_get_ss = q40_get_ss;
mach_get_rtc_pll = q40_get_rtc_pll;
mach_set_rtc_pll = q40_set_rtc_pll;
- mach_set_clock_mmss = q40_set_clock_mmss;
mach_reset = q40_reset;
mach_get_model = q40_get_model;
return bcd2bin(Q40_RTC_SECS);
}
-/*
- * Set the minutes and seconds from seconds value 'nowtime'. Fail if
- * clock is out by > 30 minutes. Logic lifted from atari code.
- */
-
-static int q40_set_clock_mmss(unsigned long nowtime)
-{
- int retval = 0;
- short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-
- int rtc_minutes;
-
- rtc_minutes = bcd2bin(Q40_RTC_MINS);
-
- if ((rtc_minutes < real_minutes ?
- real_minutes - rtc_minutes :
- rtc_minutes - real_minutes) < 30) {
- Q40_RTC_CTRL |= Q40_RTC_WRITE;
- Q40_RTC_MINS = bin2bcd(real_minutes);
- Q40_RTC_SECS = bin2bcd(real_seconds);
- Q40_RTC_CTRL &= ~(Q40_RTC_WRITE);
- } else
- retval = -1;
-
- return retval;
-}
-
-
/* get and set PLL calibration of RTC clock */
#define Q40_RTC_PLL_MASK ((1<<5)-1)
#define Q40_RTC_PLL_SIGN (1<<5)
availmem = memory_start;
m68k_setup_node(0);
- availmem += init_bootmem(start_page, num_pages);
- availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
-
- free_bootmem(__pa(availmem), memory_end - (availmem));
}
source "lib/Kconfig.debug"
-config HEART_BEAT
- bool "Heart beat function for kernel"
- default n
- help
- This option turns on/off heart beat kernel functionality.
- First GPIO node is taken.
-
endmenu
#include <linux/mm.h>
#include <linux/io.h>
-/* Look at Documentation/cachetlb.txt */
+/* Look at Documentation/core-api/cachetlb.rst */
/*
* Cache handling functions.
extern char *klimit;
-void microblaze_heartbeat(void);
-void microblaze_setup_heartbeat(void);
-
# ifdef CONFIG_MMU
extern void mmu_reset(void);
# endif /* CONFIG_MMU */
-extern void of_platform_reset_gpio_probe(void);
-
void time_init(void);
void init_IRQ(void);
void machine_early_init(const char *cmdline, unsigned int ram,
#endif /* __ASSEMBLY__ */
-#define __NR_syscalls 399
+#define __NR_syscalls 401
#endif /* _ASM_MICROBLAZE_UNISTD_H */
#define __NR_pkey_alloc 396
#define __NR_pkey_free 397
#define __NR_statx 398
+#define __NR_io_pgetevents 399
+#define __NR_rseq 400
#endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
CFLAGS_REMOVE_timer.o = -pg
CFLAGS_REMOVE_intc.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
-CFLAGS_REMOVE_heartbeat.o = -pg
CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_process.o = -pg
endif
obj-y += dma.o exceptions.o \
hw_exception_handler.o irq.o \
- platform.o process.o prom.o ptrace.o \
+ process.o prom.o ptrace.o \
reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o
obj-y += cpu/
-obj-$(CONFIG_HEART_BEAT) += heartbeat.o
obj-$(CONFIG_MODULES) += microblaze_ksyms.o module.o
obj-$(CONFIG_MMU) += misc.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
+++ /dev/null
-/*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2007-2009 PetaLogix
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/sched.h>
-#include <linux/sched/loadavg.h>
-#include <linux/io.h>
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/prom.h>
-
-static unsigned int base_addr;
-
-void microblaze_heartbeat(void)
-{
- static unsigned int cnt, period, dist;
-
- if (base_addr) {
- if (cnt == 0 || cnt == dist)
- out_be32(base_addr, 1);
- else if (cnt == 7 || cnt == dist + 7)
- out_be32(base_addr, 0);
-
- if (++cnt > period) {
- cnt = 0;
- /*
- * The hyperbolic function below modifies the heartbeat
- * period length in dependency of the current (5min)
- * load. It goes through the points f(0)=126, f(1)=86,
- * f(5)=51, f(inf)->30.
- */
- period = ((672 << FSHIFT) / (5 * avenrun[0] +
- (7 << FSHIFT))) + 30;
- dist = period / 4;
- }
- }
-}
-
-void microblaze_setup_heartbeat(void)
-{
- struct device_node *gpio = NULL;
- int *prop;
- int j;
- const char * const gpio_list[] = {
- "xlnx,xps-gpio-1.00.a",
- NULL
- };
-
- for (j = 0; gpio_list[j] != NULL; j++) {
- gpio = of_find_compatible_node(NULL, NULL, gpio_list[j]);
- if (gpio)
- break;
- }
-
- if (gpio) {
- base_addr = be32_to_cpup(of_get_property(gpio, "reg", NULL));
- base_addr = (unsigned long) ioremap(base_addr, PAGE_SIZE);
- pr_notice("Heartbeat GPIO at 0x%x\n", base_addr);
-
- /* GPIO is configured as output */
- prop = (int *) of_get_property(gpio, "xlnx,is-bidir", NULL);
- if (prop)
- out_be32(base_addr + 4, 0);
- }
-}
+++ /dev/null
-/*
- * Copyright 2008 Michal Simek <monstr@monstr.eu>
- *
- * based on virtex.c file
- *
- * Copyright 2007 Secret Lab Technologies Ltd.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-#include <asm/setup.h>
-
-static struct of_device_id xilinx_of_bus_ids[] __initdata = {
- { .compatible = "simple-bus", },
- { .compatible = "xlnx,compound", },
- {}
-};
-
-static int __init microblaze_device_probe(void)
-{
- of_platform_bus_probe(NULL, xilinx_of_bus_ids, NULL);
- of_platform_reset_gpio_probe();
- return 0;
-}
-device_initcall(microblaze_device_probe);
static int handle; /* reset pin handle */
static unsigned int reset_val;
-void of_platform_reset_gpio_probe(void)
+static int of_platform_reset_gpio_probe(void)
{
int ret;
handle = of_get_named_gpio(of_find_node_by_path("/"),
if (!gpio_is_valid(handle)) {
pr_info("Skipping unavailable RESET gpio %d (%s)\n",
handle, "reset");
- return;
+ return -ENODEV;
}
ret = gpio_request(handle, "reset");
if (ret < 0) {
pr_info("GPIO pin is already allocated\n");
- return;
+ return ret;
}
/* get current setup value */
pr_info("RESET: Registered gpio device: %d, current val: %d\n",
handle, reset_val);
- return;
+ return 0;
err:
gpio_free(handle);
- return;
+ return ret;
}
+device_initcall(of_platform_reset_gpio_probe);
static void gpio_system_reset(void)
.long sys_pkey_alloc
.long sys_pkey_free
.long sys_statx
+ .long sys_io_pgetevents
+ .long sys_rseq
static irqreturn_t timer_interrupt(int irq, void *dev_id)
{
struct clock_event_device *evt = &clockevent_xilinx_timer;
-#ifdef CONFIG_HEART_BEAT
- microblaze_heartbeat();
-#endif
timer_ack();
evt->event_handler(evt);
return IRQ_HANDLED;
return ret;
}
-#ifdef CONFIG_HEART_BEAT
- microblaze_setup_heartbeat();
-#endif
-
ret = xilinx_clocksource_init();
if (ret)
return ret;
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select CPU_PM if CPU_IDLE
+ select DMA_DIRECT_OPS
select GENERIC_ATOMIC64 if !64BIT
select GENERIC_CLOCKEVENTS
select GENERIC_CMOS_UPDATE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT
select HAVE_CBPF_JIT if (!64BIT && !CPU_MICROMIPS)
select HAVE_EBPF_JIT if (64BIT && !CPU_MICROMIPS)
- select HAVE_CC_STACKPROTECTOR
select HAVE_CONTEXT_TRACKING
select HAVE_COPY_THREAD_TLS
select HAVE_C_RECORDMCOUNT
select HAVE_OPROFILE
select HAVE_PERF_EVENTS
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_RSEQ
+ select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP
select IRQ_FORCED_THREADING
select HW_HAS_PCI
select IRQ_MIPS_CPU
select LIBFDT
+ select MIPS_AUTO_PFN_OFFSET
select MIPS_CPU_SCACHE
select MIPS_GIC
select MIPS_L1_CACHE_SHIFT_7
select CSRC_R4K
select DMA_NONCOHERENT
select GPIOLIB
+ select PINCTRL
select HAVE_CLK
select COMMON_CLK
select CLKDEV_LOOKUP
config BMIPS_GENERIC
bool "Broadcom Generic BMIPS kernel"
+ select ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+ select ARCH_HAS_PHYS_TO_DMA
select BOOT_RAW
select NO_EXCEPT_FILL
select USE_OF
config MACH_LOONGSON64
bool "Loongson-2/3 family of machines"
- select ARCH_HAS_PHYS_TO_DMA
select SYS_SUPPORTS_ZBOOT
help
This enables the support of Loongson-2/3 family of machines.
config SGI_IP27
bool "SGI IP27 (Origin200/2000)"
+ select ARCH_HAS_PHYS_TO_DMA
select FW_ARC
select FW_ARC64
select BOOT_ELF64
select DEFAULT_SGI_PARTITION
- select DMA_COHERENT
select SYS_HAS_EARLY_PRINTK
select HW_HAS_PCI
select NR_CPUS_DEFAULT_64
config SGI_IP32
bool "SGI IP32 (O2)"
+ select ARCH_HAS_PHYS_TO_DMA
select FW_ARC
select FW_ARC32
select BOOT_ELF32
config SIBYTE_CRHINE
bool "Sibyte BCM91120C-CRhine"
select BOOT_ELF32
- select DMA_COHERENT
select SIBYTE_BCM1120
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
config SIBYTE_CARMEL
bool "Sibyte BCM91120x-Carmel"
select BOOT_ELF32
- select DMA_COHERENT
select SIBYTE_BCM1120
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
config SIBYTE_CRHONE
bool "Sibyte BCM91125C-CRhone"
select BOOT_ELF32
- select DMA_COHERENT
select SIBYTE_BCM1125
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
config SIBYTE_RHONE
bool "Sibyte BCM91125E-Rhone"
select BOOT_ELF32
- select DMA_COHERENT
select SIBYTE_BCM1125H
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
config SIBYTE_SWARM
bool "Sibyte BCM91250A-SWARM"
select BOOT_ELF32
- select DMA_COHERENT
select HAVE_PATA_PLATFORM
select SIBYTE_SB1250
select SWAP_IO_SPACE
config SIBYTE_LITTLESUR
bool "Sibyte BCM91250C2-LittleSur"
select BOOT_ELF32
- select DMA_COHERENT
select HAVE_PATA_PLATFORM
select SIBYTE_SB1250
select SWAP_IO_SPACE
config SIBYTE_SENTOSA
bool "Sibyte BCM91250E-Sentosa"
select BOOT_ELF32
- select DMA_COHERENT
select SIBYTE_SB1250
select SWAP_IO_SPACE
select SYS_HAS_CPU_SB1
config SIBYTE_BIGSUR
bool "Sibyte BCM91480B-BigSur"
select BOOT_ELF32
- select DMA_COHERENT
select NR_CPUS_DEFAULT_4
select SIBYTE_BCM1x80
select SWAP_IO_SPACE
bool "Cavium Networks Octeon SoC based boards"
select CEVT_R4K
select ARCH_HAS_PHYS_TO_DMA
+ select HAS_RAPIDIO
select PHYS_ADDR_T_64BIT
- select DMA_COHERENT
select SYS_SUPPORTS_64BIT_KERNEL
select SYS_SUPPORTS_BIG_ENDIAN
select EDAC_SUPPORT
select PHYS_ADDR_T_64BIT
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_HIGHMEM
- select DMA_COHERENT
select NR_CPUS_DEFAULT_32
select CEVT_R4K
select CSRC_R4K
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_SUPPORTS_HIGHMEM
- select DMA_COHERENT
select NR_CPUS_DEFAULT_32
select CEVT_R4K
select CSRC_R4K
bool "Para-Virtualized guest system"
select CEVT_R4K
select CSRC_R4K
- select DMA_COHERENT
select SYS_SUPPORTS_64BIT_KERNEL
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_BIG_ENDIAN
bool
select DMA_MAYBE_COHERENT
-config DMA_COHERENT
- bool
-
config DMA_NONCOHERENT
bool
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
select NEED_DMA_MAP_STATE
+ select DMA_NONCOHERENT_MMAP
+ select DMA_NONCOHERENT_CACHE_SYNC
+ select DMA_NONCOHERENT_OPS
config SYS_HAS_EARLY_PRINTK
bool
config CPU_LOONGSON3
bool "Loongson 3 CPU"
depends on SYS_HAS_CPU_LOONGSON3
+ select ARCH_HAS_PHYS_TO_DMA
select CPU_SUPPORTS_64BIT_KERNEL
select CPU_SUPPORTS_HIGHMEM
select CPU_SUPPORTS_HUGEPAGES
select LEDS_GPIO_REGISTER
help
The Loongson 1B is a 32-bit SoC, which implements the MIPS32
- release 2 instruction set.
+ Release 1 instruction set and part of the MIPS32 Release 2
+ instruction set.
config CPU_LOONGSON1C
bool "Loongson 1C"
select LEDS_GPIO_REGISTER
help
The Loongson 1C is a 32-bit SoC, which implements the MIPS32
- release 2 instruction set.
+ Release 1 instruction set and part of the MIPS32 Release 2
+ instruction set.
config CPU_MIPS32_R1
bool "MIPS32 Release 1"
select CPU_SUPPORTS_64BIT_KERNEL
select CPU_SUPPORTS_HIGHMEM
select CPU_SUPPORTS_HUGEPAGES
+ select ARCH_HAS_PHYS_TO_DMA
config CPU_LOONGSON1
bool
select CPU_MIPS32
- select CPU_MIPSR2
+ select CPU_MIPSR1
select CPU_HAS_PREFETCH
select CPU_SUPPORTS_32BIT_KERNEL
select CPU_SUPPORTS_HIGHMEM
config SYS_HAS_CPU_XLP
bool
-config MIPS_MALTA_PM
- depends on MIPS_MALTA
- depends on PCI
- bool
- default y
-
#
# CPU may reorder R->R, R->W, W->R, W->W
# Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
default 3 if 64BIT && !PAGE_SIZE_64KB
default 2
+config MIPS_AUTO_PFN_OFFSET
+ bool
+
source "init/Kconfig"
source "kernel/Kconfig.freezer"
source "drivers/pcmcia/Kconfig"
+config HAS_RAPIDIO
+ bool
+ default n
+
config RAPIDIO
tristate "RapidIO support"
- depends on PCI
- default n
+ depends on HAS_RAPIDIO || PCI
help
If you say Y here, the kernel will include drivers and
infrastructure code to support RapidIO interconnect devices.
# are used, so we kludge that here. A bug has been filed at
# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413.
#
+# clang doesn't suffer from these issues and our checks against -dumpmachine
+# don't work so well when cross compiling, since without providing --target
+# clang's output will be based upon the build machine. So for clang we simply
+# unconditionally specify -EB or -EL as appropriate.
+#
+ifeq ($(cc-name),clang)
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -EL
+else
undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__
undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__
predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__
predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__
cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be))
cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le))
+endif
cflags-$(CONFIG_SB1XXX_CORELIS) += $(call cc-option,-mno-sched-prolog) \
-fno-omit-frame-pointer
cflags-$(CONFIG_CPU_VR41XX) += -march=r4100 -Wa,--trap
cflags-$(CONFIG_CPU_R4X00) += -march=r4600 -Wa,--trap
cflags-$(CONFIG_CPU_TX49XX) += -march=r4600 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R1) += $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
- -Wa,-mips32 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R2) += $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
- -Wa,-mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R1) += -march=mips32 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R2) += -march=mips32r2 -Wa,--trap
cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap -modd-spreg
-cflags-$(CONFIG_CPU_MIPS64_R1) += $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
- -Wa,-mips64 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS64_R2) += $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
- -Wa,-mips64r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R1) += -march=mips64 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R2) += -march=mips64r2 -Wa,--trap
cflags-$(CONFIG_CPU_MIPS64_R6) += -march=mips64r6 -Wa,--trap
cflags-$(CONFIG_CPU_R5000) += -march=r5000 -Wa,--trap
cflags-$(CONFIG_CPU_R5432) += $(call cc-option,-march=r5400,-march=r5000) \
#include <asm/bootinfo.h>
#include <asm/idle.h>
#include <asm/reboot.h>
+#include <asm/setup.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/gpio-au1000.h>
#include <prom.h>
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
{
alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
}
#include <mtd/mtd-abi.h>
#include <asm/bootinfo.h>
#include <asm/reboot.h>
+#include <asm/setup.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/gpio-au1000.h>
#include <asm/mach-au1x00/au1xxx_eth.h>
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
{
alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
}
#include <linux/pm.h>
#include <asm/bootinfo.h>
#include <asm/reboot.h>
+#include <asm/setup.h>
#include <asm/mach-au1x00/au1000.h>
#include <prom.h>
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
{
alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
}
#include <asm/bootinfo.h>
#include <asm/idle.h>
#include <asm/reboot.h>
+#include <asm/setup.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-db1x00/bcsr.h>
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
{
if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300)
alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
/* adjust vbus clock rate */
vbus_clk.rate = bus_clk.rate / 2;
}
+
+/* dummy functions, should not be called */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+ WARN_ON(clk);
+ return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+ WARN_ON(clk);
+ return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+ WARN_ON(clk);
+ return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+ WARN_ON(clk);
+ return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
#include <linux/string.h>
#include <linux/io.h>
#include <asm/bootinfo.h>
+#include <asm/setup.h>
#include <asm/mach-ar7/ar7.h>
#include <asm/mach-ar7/prom.h>
writel(value, (void *)PORT(offset));
}
-int prom_putchar(char c)
+void prom_putchar(char c)
{
while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0)
;
serial_out(UART_TX, c);
- return 1;
}
config PCI_AR2315
bool "Atheros AR2315 PCI controller support"
depends on SOC_AR2315
+ select ARCH_HAS_PHYS_TO_DMA
select HW_HAS_PCI
select PCI
default y
pr_info("Fixing up empty mac addresses\n");
config->reset_config_gpio = 0xffff;
config->sys_led_gpio = 0xffff;
- random_ether_addr(config->wlan0_mac);
+ eth_random_addr(config->wlan0_mac);
config->wlan0_mac[0] &= ~0x06;
- random_ether_addr(config->enet0_mac);
- random_ether_addr(config->enet1_mac);
+ eth_random_addr(config->enet0_mac);
+ eth_random_addr(config->enet1_mac);
}
}
#include <linux/mm.h>
#include <linux/io.h>
#include <linux/serial_reg.h>
+#include <asm/setup.h>
#include "devices.h"
#include "ar2315_regs.h"
return __raw_readl(base + 4 * reg);
}
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
{
static void __iomem *base;
while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
;
- prom_uart_wr(base, UART_TX, ch);
+ prom_uart_wr(base, UART_TX, (unsigned char)ch);
while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
;
}
iounmap(dpll_base);
}
+static void __init qca953x_clocks_init(void)
+{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
+ u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
+ u32 cpu_pll, ddr_pll;
+ u32 bootstrap;
+
+ bootstrap = ath79_reset_rr(QCA953X_RESET_REG_BOOTSTRAP);
+ if (bootstrap & QCA953X_BOOTSTRAP_REF_CLK_40)
+ ref_rate = 40 * 1000 * 1000;
+ else
+ ref_rate = 25 * 1000 * 1000;
+
+ pll = ath79_pll_rr(QCA953X_PLL_CPU_CONFIG_REG);
+ out_div = (pll >> QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+ QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK;
+ ref_div = (pll >> QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+ QCA953X_PLL_CPU_CONFIG_REFDIV_MASK;
+ nint = (pll >> QCA953X_PLL_CPU_CONFIG_NINT_SHIFT) &
+ QCA953X_PLL_CPU_CONFIG_NINT_MASK;
+ frac = (pll >> QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
+ QCA953X_PLL_CPU_CONFIG_NFRAC_MASK;
+
+ cpu_pll = nint * ref_rate / ref_div;
+ cpu_pll += frac * (ref_rate >> 6) / ref_div;
+ cpu_pll /= (1 << out_div);
+
+ pll = ath79_pll_rr(QCA953X_PLL_DDR_CONFIG_REG);
+ out_div = (pll >> QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+ QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK;
+ ref_div = (pll >> QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+ QCA953X_PLL_DDR_CONFIG_REFDIV_MASK;
+ nint = (pll >> QCA953X_PLL_DDR_CONFIG_NINT_SHIFT) &
+ QCA953X_PLL_DDR_CONFIG_NINT_MASK;
+ frac = (pll >> QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
+ QCA953X_PLL_DDR_CONFIG_NFRAC_MASK;
+
+ ddr_pll = nint * ref_rate / ref_div;
+ ddr_pll += frac * (ref_rate >> 6) / (ref_div << 4);
+ ddr_pll /= (1 << out_div);
+
+ clk_ctrl = ath79_pll_rr(QCA953X_PLL_CLK_CTRL_REG);
+
+ postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+ QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+ cpu_rate = ref_rate;
+ else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
+ cpu_rate = cpu_pll / (postdiv + 1);
+ else
+ cpu_rate = ddr_pll / (postdiv + 1);
+
+ postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+ QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+ ddr_rate = ref_rate;
+ else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
+ ddr_rate = ddr_pll / (postdiv + 1);
+ else
+ ddr_rate = cpu_pll / (postdiv + 1);
+
+ postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+ QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+ ahb_rate = ref_rate;
+ else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+ ahb_rate = ddr_pll / (postdiv + 1);
+ else
+ ahb_rate = cpu_pll / (postdiv + 1);
+
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ref", NULL);
+ clk_add_alias("uart", NULL, "ref", NULL);
+}
+
static void __init qca955x_clocks_init(void)
{
unsigned long ref_rate;
clk_add_alias("uart", NULL, "ref", NULL);
}
+static void __init qca956x_clocks_init(void)
+{
+ unsigned long ref_rate;
+ unsigned long cpu_rate;
+ unsigned long ddr_rate;
+ unsigned long ahb_rate;
+ u32 pll, out_div, ref_div, nint, hfrac, lfrac, clk_ctrl, postdiv;
+ u32 cpu_pll, ddr_pll;
+ u32 bootstrap;
+
+ /*
+ * QCA956x timer init workaround has to be applied right before setting
+ * up the clock. Else, there will be no jiffies
+ */
+ u32 misc;
+
+ misc = ath79_reset_rr(AR71XX_RESET_REG_MISC_INT_ENABLE);
+ misc |= MISC_INT_MIPS_SI_TIMERINT_MASK;
+ ath79_reset_wr(AR71XX_RESET_REG_MISC_INT_ENABLE, misc);
+
+ bootstrap = ath79_reset_rr(QCA956X_RESET_REG_BOOTSTRAP);
+ if (bootstrap & QCA956X_BOOTSTRAP_REF_CLK_40)
+ ref_rate = 40 * 1000 * 1000;
+ else
+ ref_rate = 25 * 1000 * 1000;
+
+ pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG_REG);
+ out_div = (pll >> QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+ QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK;
+ ref_div = (pll >> QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+ QCA956X_PLL_CPU_CONFIG_REFDIV_MASK;
+
+ pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG1_REG);
+ nint = (pll >> QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT) &
+ QCA956X_PLL_CPU_CONFIG1_NINT_MASK;
+ hfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT) &
+ QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK;
+ lfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT) &
+ QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK;
+
+ cpu_pll = nint * ref_rate / ref_div;
+ cpu_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+ cpu_pll += (hfrac >> 13) * ref_rate / ref_div;
+ cpu_pll /= (1 << out_div);
+
+ pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG_REG);
+ out_div = (pll >> QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+ QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK;
+ ref_div = (pll >> QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+ QCA956X_PLL_DDR_CONFIG_REFDIV_MASK;
+ pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG1_REG);
+ nint = (pll >> QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT) &
+ QCA956X_PLL_DDR_CONFIG1_NINT_MASK;
+ hfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT) &
+ QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK;
+ lfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT) &
+ QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK;
+
+ ddr_pll = nint * ref_rate / ref_div;
+ ddr_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+ ddr_pll += (hfrac >> 13) * ref_rate / ref_div;
+ ddr_pll /= (1 << out_div);
+
+ clk_ctrl = ath79_pll_rr(QCA956X_PLL_CLK_CTRL_REG);
+
+ postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+ QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+ cpu_rate = ref_rate;
+ else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL)
+ cpu_rate = ddr_pll / (postdiv + 1);
+ else
+ cpu_rate = cpu_pll / (postdiv + 1);
+
+ postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+ QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+ ddr_rate = ref_rate;
+ else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL)
+ ddr_rate = cpu_pll / (postdiv + 1);
+ else
+ ddr_rate = ddr_pll / (postdiv + 1);
+
+ postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+ QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+ if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+ ahb_rate = ref_rate;
+ else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+ ahb_rate = ddr_pll / (postdiv + 1);
+ else
+ ahb_rate = cpu_pll / (postdiv + 1);
+
+ ath79_add_sys_clkdev("ref", ref_rate);
+ ath79_add_sys_clkdev("cpu", cpu_rate);
+ ath79_add_sys_clkdev("ddr", ddr_rate);
+ ath79_add_sys_clkdev("ahb", ahb_rate);
+
+ clk_add_alias("wdt", NULL, "ref", NULL);
+ clk_add_alias("uart", NULL, "ref", NULL);
+}
+
void __init ath79_clocks_init(void)
{
if (soc_is_ar71xx())
ar933x_clocks_init();
else if (soc_is_ar934x())
ar934x_clocks_init();
+ else if (soc_is_qca953x())
+ qca953x_clocks_init();
else if (soc_is_qca955x())
qca955x_clocks_init();
+ else if (soc_is_qca956x() || soc_is_tp9343())
+ qca956x_clocks_init();
else
BUG();
}
void ath79_ddr_wb_flush(u32 reg)
{
- void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+ void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
/* Flush the DDR write buffer. */
__raw_writel(0x1, flush_reg);
reg = AR933X_RESET_REG_RESET_MODULE;
else if (soc_is_ar934x())
reg = AR934X_RESET_REG_RESET_MODULE;
+ else if (soc_is_qca953x())
+ reg = QCA953X_RESET_REG_RESET_MODULE;
else if (soc_is_qca955x())
reg = QCA955X_RESET_REG_RESET_MODULE;
+ else if (soc_is_qca956x() || soc_is_tp9343())
+ reg = QCA956X_RESET_REG_RESET_MODULE;
else
BUG();
reg = AR933X_RESET_REG_RESET_MODULE;
else if (soc_is_ar934x())
reg = AR934X_RESET_REG_RESET_MODULE;
+ else if (soc_is_qca953x())
+ reg = QCA953X_RESET_REG_RESET_MODULE;
else if (soc_is_qca955x())
reg = QCA955X_RESET_REG_RESET_MODULE;
+ else if (soc_is_qca956x() || soc_is_tp9343())
+ reg = QCA956X_RESET_REG_RESET_MODULE;
else
BUG();
#include <linux/errno.h>
#include <linux/serial_reg.h>
#include <asm/addrspace.h>
+#include <asm/setup.h>
#include <asm/mach-ath79/ath79.h>
#include <asm/mach-ath79/ar71xx_regs.h>
#include <asm/mach-ath79/ar933x_uart.h>
-static void (*_prom_putchar) (unsigned char);
+static void (*_prom_putchar)(char);
static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
{
#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
-static void prom_putchar_ar71xx(unsigned char ch)
+static void prom_putchar_ar71xx(char ch)
{
void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
- __raw_writel(ch, base + UART_TX * 4);
+ __raw_writel((unsigned char)ch, base + UART_TX * 4);
prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
}
-static void prom_putchar_ar933x(unsigned char ch)
+static void prom_putchar_ar933x(char ch)
{
void __iomem *base = (void __iomem *)(KSEG1ADDR(AR933X_UART_BASE));
prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
AR933X_UART_DATA_TX_CSR);
- __raw_writel(AR933X_UART_DATA_TX_CSR | ch, base + AR933X_UART_DATA_REG);
+ __raw_writel(AR933X_UART_DATA_TX_CSR | (unsigned char)ch,
+ base + AR933X_UART_DATA_REG);
prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
AR933X_UART_DATA_TX_CSR);
}
-static void prom_putchar_dummy(unsigned char ch)
+static void prom_putchar_dummy(char ch)
{
/* nothing to do */
}
+static void prom_enable_uart(u32 id)
+{
+ void __iomem *gpio_base;
+ u32 uart_en;
+ u32 t;
+
+ switch (id) {
+ case REV_ID_MAJOR_AR71XX:
+ uart_en = AR71XX_GPIO_FUNC_UART_EN;
+ break;
+
+ case REV_ID_MAJOR_AR7240:
+ case REV_ID_MAJOR_AR7241:
+ case REV_ID_MAJOR_AR7242:
+ uart_en = AR724X_GPIO_FUNC_UART_EN;
+ break;
+
+ case REV_ID_MAJOR_AR913X:
+ uart_en = AR913X_GPIO_FUNC_UART_EN;
+ break;
+
+ case REV_ID_MAJOR_AR9330:
+ case REV_ID_MAJOR_AR9331:
+ uart_en = AR933X_GPIO_FUNC_UART_EN;
+ break;
+
+ case REV_ID_MAJOR_AR9341:
+ case REV_ID_MAJOR_AR9342:
+ case REV_ID_MAJOR_AR9344:
+ /* TODO */
+ default:
+ return;
+ }
+
+ gpio_base = (void __iomem *)KSEG1ADDR(AR71XX_GPIO_BASE);
+ t = __raw_readl(gpio_base + AR71XX_GPIO_REG_FUNC);
+ t |= uart_en;
+ __raw_writel(t, gpio_base + AR71XX_GPIO_REG_FUNC);
+}
+
static void prom_putchar_init(void)
{
void __iomem *base;
case REV_ID_MAJOR_AR9341:
case REV_ID_MAJOR_AR9342:
case REV_ID_MAJOR_AR9344:
+ case REV_ID_MAJOR_QCA9533:
+ case REV_ID_MAJOR_QCA9533_V2:
case REV_ID_MAJOR_QCA9556:
case REV_ID_MAJOR_QCA9558:
+ case REV_ID_MAJOR_TP9343:
+ case REV_ID_MAJOR_QCA956X:
_prom_putchar = prom_putchar_ar71xx;
break;
default:
_prom_putchar = prom_putchar_dummy;
- break;
+ return;
}
+
+ prom_enable_uart(id);
}
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
{
if (!_prom_putchar)
prom_putchar_init();
#define PB44_KEYS_DEBOUNCE_INTERVAL (3 * PB44_KEYS_POLL_INTERVAL)
static struct gpiod_lookup_table pb44_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
static void ath79_restart(char *command)
{
+ local_irq_disable();
ath79_device_reset_set(AR71XX_RESET_FULL_CHIP);
for (;;)
if (cpu_wait)
u32 major;
u32 minor;
u32 rev = 0;
+ u32 ver = 1;
id = ath79_reset_rr(AR71XX_RESET_REG_REV_ID);
major = id & REV_ID_MAJOR_MASK;
rev = id & AR934X_REV_ID_REVISION_MASK;
break;
+ case REV_ID_MAJOR_QCA9533_V2:
+ ver = 2;
+ ath79_soc_rev = 2;
+ /* drop through */
+
+ case REV_ID_MAJOR_QCA9533:
+ ath79_soc = ATH79_SOC_QCA9533;
+ chip = "9533";
+ rev = id & QCA953X_REV_ID_REVISION_MASK;
+ break;
+
case REV_ID_MAJOR_QCA9556:
ath79_soc = ATH79_SOC_QCA9556;
chip = "9556";
rev = id & QCA955X_REV_ID_REVISION_MASK;
break;
+ case REV_ID_MAJOR_QCA956X:
+ ath79_soc = ATH79_SOC_QCA956X;
+ chip = "956X";
+ rev = id & QCA956X_REV_ID_REVISION_MASK;
+ break;
+
+ case REV_ID_MAJOR_TP9343:
+ ath79_soc = ATH79_SOC_TP9343;
+ chip = "9343";
+ rev = id & QCA956X_REV_ID_REVISION_MASK;
+ break;
+
default:
panic("ath79: unknown SoC, id:0x%08x", id);
}
- ath79_soc_rev = rev;
+ if (ver == 1)
+ ath79_soc_rev = rev;
- if (soc_is_qca955x())
- sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s rev %u",
+ if (soc_is_qca953x() || soc_is_qca955x() || soc_is_qca956x())
+ sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s ver %u rev %u",
+ chip, ver, rev);
+ else if (soc_is_tp9343())
+ sprintf(ath79_sys_type, "Qualcomm Atheros TP%s rev %u",
chip, rev);
else
sprintf(ath79_sys_type, "Atheros AR%s rev %u", chip, rev);
#include <bcm63xx_io.h>
#include <linux/serial_bcm63xx.h>
+#include <asm/setup.h>
static void wait_xfered(void)
{
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/types.h>
-#include <dma-coherence.h>
+#include <asm/bmips.h>
/*
* BCM338x has configurable address translation windows which allow the
#define FLUSH_RAC 0x100
-static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
{
struct bmips_dma_range *r;
return pa;
}
-dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
- return bmips_phys_to_dma(dev, virt_to_phys(addr));
-}
-
-dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
- return bmips_phys_to_dma(dev, page_to_phys(page));
-}
-
-unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
{
struct bmips_dma_range *r;
return dma_addr;
}
+void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+ void __iomem *cbr = BMIPS_GET_CBR();
+ u32 cfg;
+
+ if (boot_cpu_type() != CPU_BMIPS3300 &&
+ boot_cpu_type() != CPU_BMIPS4350 &&
+ boot_cpu_type() != CPU_BMIPS4380)
+ return;
+
+ /* Flush stale data out of the readahead cache */
+ cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
+ __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
+ __raw_readl(cbr + BMIPS_RAC_CONFIG);
+}
+
static int __init bmips_init_dma_ranges(void)
{
struct device_node *np =
of_node_put(np);
}
-int __init plat_of_setup(void)
-{
- return __dt_register_buses("simple-bus", NULL);
-}
-
-arch_initcall(plat_of_setup);
-
static int __init plat_dev_init(void)
{
of_clk_init(NULL);
# Flattened Image Tree (.itb) images
#
-targets += vmlinux.itb
-targets += vmlinux.gz.itb
-targets += vmlinux.bz2.itb
-targets += vmlinux.lzma.itb
-targets += vmlinux.lzo.itb
-
ifeq ($(ADDR_BITS),32)
- itb_addr_cells = 1
+itb_addr_cells = 1
endif
ifeq ($(ADDR_BITS),64)
- itb_addr_cells = 2
+itb_addr_cells = 2
endif
+targets += vmlinux.its.S
+
quiet_cmd_its_cat = CAT $@
- cmd_its_cat = cat $^ >$@
+ cmd_its_cat = cat $(filter-out $(PHONY), $^) >$@
-$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS))
+$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE
$(call if_changed,its_cat)
+targets += vmlinux.its
+targets += vmlinux.gz.its
+targets += vmlinux.bz2.its
+targets += vmlinux.lzmo.its
+targets += vmlinux.lzo.its
+
quiet_cmd_cpp_its_S = ITS $@
- cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
- -D__ASSEMBLY__ \
+ cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \
-DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
-DVMLINUX_BINARY="\"$(3)\"" \
-DVMLINUX_COMPRESSION="\"$(2)\"" \
-DADDR_CELLS=$(itb_addr_cells)
$(obj)/vmlinux.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
- $(call if_changed_dep,cpp_its_S,none,vmlinux.bin)
+ $(call if_changed,cpp_its_S,none,vmlinux.bin)
$(obj)/vmlinux.gz.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
- $(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz)
+ $(call if_changed,cpp_its_S,gzip,vmlinux.bin.gz)
$(obj)/vmlinux.bz2.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
- $(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2)
+ $(call if_changed,cpp_its_S,bzip2,vmlinux.bin.bz2)
$(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
- $(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma)
+ $(call if_changed,cpp_its_S,lzma,vmlinux.bin.lzma)
$(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
- $(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo)
+ $(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo)
+
+targets += vmlinux.itb
+targets += vmlinux.gz.itb
+targets += vmlinux.bz2.itb
+targets += vmlinux.lzma.itb
+targets += vmlinux.lzo.itb
quiet_cmd_itb-image = ITB $@
cmd_itb-image = \
$(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE
$(call if_changed,itb-image,$<)
-$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE
- $(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE
- $(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE
- $(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE
+$(obj)/vmlinux.%.itb: $(obj)/vmlinux.%.its $(obj)/vmlinux.bin.% FORCE
$(call if_changed,itb-image,$<)
// SPDX-License-Identifier: GPL-2.0
-
-extern void prom_putchar(unsigned char ch);
+#include <asm/setup.h>
void putc(char c)
{
};
};
+ spi_gpio {
+ compatible = "spi-gpio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ num-chipselects = <2>;
+
+ gpio-miso = <&gpe 14 0>;
+ gpio-sck = <&gpe 15 0>;
+ gpio-mosi = <&gpe 17 0>;
+ cs-gpios = <&gpe 16 0
+ &gpe 18 0>;
+
+ spidev@0 {
+ compatible = "spidev";
+ reg = <0>;
+ spi-max-frequency = <1000000>;
+ };
+ };
+
uart0: serial@10030000 {
compatible = "ingenic,jz4780-uart";
reg = <0x10030000 0x100>;
-dtb-$(CONFIG_LEGACY_BOARD_OCELOT) += ocelot_pcb123.dtb
+dtb-$(CONFIG_MSCC_OCELOT) += ocelot_pcb123.dtb
obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y))
status = "disabled";
};
+ spi: spi@101000 {
+ compatible = "mscc,ocelot-spi", "snps,dw-apb-ssi";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x101000 0x100>, <0x3c 0x18>;
+ interrupts = <9>;
+ clocks = <&ahb_clk>;
+
+ status = "disabled";
+ };
+
switch@1010000 {
compatible = "mscc,vsc7514-switch";
reg = <0x1010000 0x10000>,
gpio-controller;
#gpio-cells = <2>;
gpio-ranges = <&gpio 0 0 22>;
+ interrupt-controller;
+ interrupts = <13>;
+ #interrupt-cells = <2>;
uart_pins: uart-pins {
pins = "GPIO_6", "GPIO_7";
pins = "GPIO_12", "GPIO_13";
function = "uart2";
};
+
+ miim1: miim1 {
+ pins = "GPIO_14", "GPIO_15";
+ function = "miim1";
+ };
};
mdio0: mdio@107009c {
#address-cells = <1>;
#size-cells = <0>;
compatible = "mscc,ocelot-miim";
- reg = <0x107009c 0x36>, <0x10700f0 0x8>;
+ reg = <0x107009c 0x24>, <0x10700f0 0x8>;
interrupts = <14>;
status = "disabled";
reg = <3>;
};
};
+
+ mdio1: mdio@10700c0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "mscc,ocelot-miim";
+ reg = <0x10700c0 0x24>;
+ interrupts = <15>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&miim1>;
+ status = "disabled";
+ };
};
};
status = "okay";
};
+&spi {
+ status = "okay";
+
+ flash@0 {
+ compatible = "macronix,mx25l25635f", "jedec,spi-nor";
+ spi-max-frequency = <20000000>;
+ reg = <0>;
+ };
+};
+
&mdio0 {
status = "okay";
};
usb_phy: usb-phy {
compatible = "qca,ar7100-usb-phy";
- reset-names = "usb-phy", "usb-suspend-override";
+ reset-names = "phy", "suspend-override";
resets = <&rst 4>, <&rst 3>;
#phy-cells = <0>;
};
gpio-keys {
- compatible = "gpio-keys-polled";
+ compatible = "gpio-keys";
#address-cells = <1>;
#size-cells = <0>;
- poll-interval = <20>;
button@0 {
label = "reset";
linux,code = <KEY_RESTART>;
usb_phy: usb-phy {
compatible = "qca,ar7100-usb-phy";
- reset-names = "usb-phy", "usb-suspend-override";
+ reset-names = "phy", "suspend-override";
resets = <&rst 4>, <&rst 3>;
#phy-cells = <0>;
};
};
- gpio-keys-polled {
- compatible = "gpio-keys-polled";
+ gpio-keys {
+ compatible = "gpio-keys";
#address-cells = <1>;
#size-cells = <0>;
- poll-interval = <100>;
button@0 {
label = "reset";
};
};
- gpio-keys-polled {
- compatible = "gpio-keys-polled";
+ gpio-keys {
+ compatible = "gpio-keys";
#address-cells = <1>;
#size-cells = <0>;
- poll-interval = <100>;
button@0 {
label = "jumpstart";
};
};
- gpio-keys-polled {
- compatible = "gpio-keys-polled";
+ gpio-keys {
+ compatible = "gpio-keys";
#address-cells = <1>;
#size-cells = <0>;
- poll-interval = <100>;
button@0 {
label = "reset";
};
};
- gpio-keys-polled {
- compatible = "gpio-keys-polled";
+ gpio-keys {
+ compatible = "gpio-keys";
#address-cells = <1>;
#size-cells = <0>;
- poll-interval = <100>;
button@0 {
label = "wps";
/*
* Some ECOFF definitions.
*/
+
+#include <stdint.h>
+
typedef struct filehdr {
- unsigned short f_magic; /* magic number */
- unsigned short f_nscns; /* number of sections */
- long f_timdat; /* time & date stamp */
- long f_symptr; /* file pointer to symbolic header */
- long f_nsyms; /* sizeof(symbolic hdr) */
- unsigned short f_opthdr; /* sizeof(optional hdr) */
- unsigned short f_flags; /* flags */
+ uint16_t f_magic; /* magic number */
+ uint16_t f_nscns; /* number of sections */
+ int32_t f_timdat; /* time & date stamp */
+ int32_t f_symptr; /* file pointer to symbolic header */
+ int32_t f_nsyms; /* sizeof(symbolic hdr) */
+ uint16_t f_opthdr; /* sizeof(optional hdr) */
+ uint16_t f_flags; /* flags */
} FILHDR;
#define FILHSZ sizeof(FILHDR)
typedef struct scnhdr {
char s_name[8]; /* section name */
- long s_paddr; /* physical address, aliased s_nlib */
- long s_vaddr; /* virtual address */
- long s_size; /* section size */
- long s_scnptr; /* file ptr to raw data for section */
- long s_relptr; /* file ptr to relocation */
- long s_lnnoptr; /* file ptr to gp histogram */
- unsigned short s_nreloc; /* number of relocation entries */
- unsigned short s_nlnno; /* number of gp histogram entries */
- long s_flags; /* flags */
+ int32_t s_paddr; /* physical address, aliased s_nlib */
+ int32_t s_vaddr; /* virtual address */
+ int32_t s_size; /* section size */
+ int32_t s_scnptr; /* file ptr to raw data for section */
+ int32_t s_relptr; /* file ptr to relocation */
+ int32_t s_lnnoptr; /* file ptr to gp histogram */
+ uint16_t s_nreloc; /* number of relocation entries */
+ uint16_t s_nlnno; /* number of gp histogram entries */
+ int32_t s_flags; /* flags */
} SCNHDR;
#define SCNHSZ sizeof(SCNHDR)
-#define SCNROUND ((long)16)
+#define SCNROUND ((int32_t)16)
typedef struct aouthdr {
- short magic; /* see above */
- short vstamp; /* version stamp */
- long tsize; /* text size in bytes, padded to DW bdry*/
- long dsize; /* initialized data " " */
- long bsize; /* uninitialized data " " */
- long entry; /* entry pt. */
- long text_start; /* base of text used for this file */
- long data_start; /* base of data used for this file */
- long bss_start; /* base of bss used for this file */
- long gprmask; /* general purpose register mask */
- long cprmask[4]; /* co-processor register masks */
- long gp_value; /* the gp value used for this object */
+ int16_t magic; /* see above */
+ int16_t vstamp; /* version stamp */
+ int32_t tsize; /* text size in bytes, padded to DW bdry*/
+ int32_t dsize; /* initialized data " " */
+ int32_t bsize; /* uninitialized data " " */
+ int32_t entry; /* entry pt. */
+ int32_t text_start; /* base of text used for this file */
+ int32_t data_start; /* base of data used for this file */
+ int32_t bss_start; /* base of bss used for this file */
+ int32_t gprmask; /* general purpose register mask */
+ int32_t cprmask[4]; /* co-processor register masks */
+ int32_t gp_value; /* the gp value used for this object */
} AOUTHDR;
#define AOUTHSZ sizeof(AOUTHDR)
#include <limits.h>
#include <netinet/in.h>
#include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
#include "ecoff.h"
/* -------------------------------------------------------------------- */
struct sect {
- unsigned long vaddr;
- unsigned long len;
+ uint32_t vaddr;
+ uint32_t len;
};
int *symTypeTable;
}
#define swab16(x) \
- ((unsigned short)( \
- (((unsigned short)(x) & (unsigned short)0x00ffU) << 8) | \
- (((unsigned short)(x) & (unsigned short)0xff00U) >> 8) ))
+ ((uint16_t)( \
+ (((uint16_t)(x) & (uint16_t)0x00ffU) << 8) | \
+ (((uint16_t)(x) & (uint16_t)0xff00U) >> 8) ))
#define swab32(x) \
((unsigned int)( \
- (((unsigned int)(x) & (unsigned int)0x000000ffUL) << 24) | \
- (((unsigned int)(x) & (unsigned int)0x0000ff00UL) << 8) | \
- (((unsigned int)(x) & (unsigned int)0x00ff0000UL) >> 8) | \
- (((unsigned int)(x) & (unsigned int)0xff000000UL) >> 24) ))
+ (((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \
+ (((uint32_t)(x) & (uint32_t)0x0000ff00UL) << 8) | \
+ (((uint32_t)(x) & (uint32_t)0x00ff0000UL) >> 8) | \
+ (((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24) ))
static void convert_elf_hdr(Elf32_Ehdr * e)
{
struct aouthdr eah;
struct scnhdr esecs[6];
int infile, outfile;
- unsigned long cur_vma = ULONG_MAX;
+ uint32_t cur_vma = UINT32_MAX;
int addflag = 0;
int nosecs;
for (i = 0; i < nosecs; i++) {
printf
- ("Section %d: %s phys %lx size %lx file offset %lx\n",
+ ("Section %d: %s phys %"PRIx32" size %"PRIx32"\t file offset %"PRIx32"\n",
i, esecs[i].s_name, esecs[i].s_paddr,
esecs[i].s_size, esecs[i].s_scnptr);
}
the section can be loaded before copying. */
if (ph[i].p_type == PT_LOAD && ph[i].p_filesz) {
if (cur_vma != ph[i].p_vaddr) {
- unsigned long gap =
- ph[i].p_vaddr - cur_vma;
+ uint32_t gap = ph[i].p_vaddr - cur_vma;
char obuf[1024];
if (gap > 65536) {
fprintf(stderr,
- "Intersegment gap (%ld bytes) too large.\n",
+ "Intersegment gap (%"PRId32" bytes) too large.\n",
gap);
exit(1);
}
fprintf(stderr,
- "Warning: %ld byte intersegment gap.\n",
+ "Warning: %d byte intersegment gap.\n",
gap);
memset(obuf, 0, sizeof obuf);
while (gap) {
* Copyright (C) 2010 Cavium Networks, Inc.
*/
#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
#include <linux/bootmem.h>
-#include <linux/export.h>
#include <linux/swiotlb.h>
#include <linux/types.h>
#include <linux/init.h>
#include <asm/octeon/octeon.h>
#ifdef CONFIG_PCI
+#include <linux/pci.h>
#include <asm/octeon/pci-octeon.h>
#include <asm/octeon/cvmx-npi-defs.h>
#include <asm/octeon/cvmx-pci-defs.h>
+struct octeon_dma_map_ops {
+ dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
+ phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
+};
+
static dma_addr_t octeon_hole_phys_to_dma(phys_addr_t paddr)
{
if (paddr >= CVMX_PCIE_BAR1_PHYS_BASE && paddr < (CVMX_PCIE_BAR1_PHYS_BASE + CVMX_PCIE_BAR1_PHYS_SIZE))
return daddr;
}
+static const struct octeon_dma_map_ops octeon_gen1_ops = {
+ .phys_to_dma = octeon_gen1_phys_to_dma,
+ .dma_to_phys = octeon_gen1_dma_to_phys,
+};
+
static dma_addr_t octeon_gen2_phys_to_dma(struct device *dev, phys_addr_t paddr)
{
return octeon_hole_phys_to_dma(paddr);
return octeon_hole_dma_to_phys(daddr);
}
+static const struct octeon_dma_map_ops octeon_gen2_ops = {
+ .phys_to_dma = octeon_gen2_phys_to_dma,
+ .dma_to_phys = octeon_gen2_dma_to_phys,
+};
+
static dma_addr_t octeon_big_phys_to_dma(struct device *dev, phys_addr_t paddr)
{
if (paddr >= 0x410000000ull && paddr < 0x420000000ull)
return daddr;
}
+static const struct octeon_dma_map_ops octeon_big_ops = {
+ .phys_to_dma = octeon_big_phys_to_dma,
+ .dma_to_phys = octeon_big_dma_to_phys,
+};
+
static dma_addr_t octeon_small_phys_to_dma(struct device *dev,
phys_addr_t paddr)
{
return daddr;
}
-#endif /* CONFIG_PCI */
-
-static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction direction,
- unsigned long attrs)
-{
- dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
- direction, attrs);
- mb();
-
- return daddr;
-}
-
-static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction, unsigned long attrs)
-{
- int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs);
- mb();
- return r;
-}
-
-static void octeon_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
- swiotlb_sync_single_for_device(dev, dma_handle, size, direction);
- mb();
-}
-
-static void octeon_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nelems, enum dma_data_direction direction)
-{
- swiotlb_sync_sg_for_device(dev, sg, nelems, direction);
- mb();
-}
-
-static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
- void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
- mb();
+static const struct octeon_dma_map_ops octeon_small_ops = {
+ .phys_to_dma = octeon_small_phys_to_dma,
+ .dma_to_phys = octeon_small_dma_to_phys,
+};
- return ret;
-}
+static const struct octeon_dma_map_ops *octeon_pci_dma_ops;
-static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
- return paddr;
-}
-
-static phys_addr_t octeon_unity_dma_to_phys(struct device *dev, dma_addr_t daddr)
+void __init octeon_pci_dma_init(void)
{
- return daddr;
+ switch (octeon_dma_bar_type) {
+ case OCTEON_DMA_BAR_TYPE_PCIE:
+ octeon_pci_dma_ops = &octeon_gen1_ops;
+ break;
+ case OCTEON_DMA_BAR_TYPE_PCIE2:
+ octeon_pci_dma_ops = &octeon_gen2_ops;
+ break;
+ case OCTEON_DMA_BAR_TYPE_BIG:
+ octeon_pci_dma_ops = &octeon_big_ops;
+ break;
+ case OCTEON_DMA_BAR_TYPE_SMALL:
+ octeon_pci_dma_ops = &octeon_small_ops;
+ break;
+ default:
+ BUG();
+ }
}
-
-struct octeon_dma_map_ops {
- const struct dma_map_ops dma_map_ops;
- dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
- phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
-};
+#endif /* CONFIG_PCI */
dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
{
- struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
- struct octeon_dma_map_ops,
- dma_map_ops);
-
- return ops->phys_to_dma(dev, paddr);
+#ifdef CONFIG_PCI
+ if (dev && dev_is_pci(dev))
+ return octeon_pci_dma_ops->phys_to_dma(dev, paddr);
+#endif
+ return paddr;
}
-EXPORT_SYMBOL(__phys_to_dma);
phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
{
- struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
- struct octeon_dma_map_ops,
- dma_map_ops);
-
- return ops->dma_to_phys(dev, daddr);
+#ifdef CONFIG_PCI
+ if (dev && dev_is_pci(dev))
+ return octeon_pci_dma_ops->dma_to_phys(dev, daddr);
+#endif
+ return daddr;
}
-EXPORT_SYMBOL(__dma_to_phys);
-
-static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
- .dma_map_ops = {
- .alloc = octeon_dma_alloc_coherent,
- .free = swiotlb_free,
- .map_page = octeon_dma_map_page,
- .unmap_page = swiotlb_unmap_page,
- .map_sg = octeon_dma_map_sg,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = octeon_dma_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = octeon_dma_sync_sg_for_device,
- .mapping_error = swiotlb_dma_mapping_error,
- .dma_supported = swiotlb_dma_supported
- },
- .phys_to_dma = octeon_unity_phys_to_dma,
- .dma_to_phys = octeon_unity_dma_to_phys
-};
char *octeon_swiotlb;
if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
panic("Cannot allocate SWIOTLB buffer");
-
- mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops;
}
-
-#ifdef CONFIG_PCI
-static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
- .dma_map_ops = {
- .alloc = octeon_dma_alloc_coherent,
- .free = swiotlb_free,
- .map_page = octeon_dma_map_page,
- .unmap_page = swiotlb_unmap_page,
- .map_sg = octeon_dma_map_sg,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = octeon_dma_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = octeon_dma_sync_sg_for_device,
- .mapping_error = swiotlb_dma_mapping_error,
- .dma_supported = swiotlb_dma_supported
- },
-};
-
-const struct dma_map_ops *octeon_pci_dma_map_ops;
-
-void __init octeon_pci_dma_init(void)
-{
- switch (octeon_dma_bar_type) {
- case OCTEON_DMA_BAR_TYPE_PCIE2:
- _octeon_pci_dma_map_ops.phys_to_dma = octeon_gen2_phys_to_dma;
- _octeon_pci_dma_map_ops.dma_to_phys = octeon_gen2_dma_to_phys;
- break;
- case OCTEON_DMA_BAR_TYPE_PCIE:
- _octeon_pci_dma_map_ops.phys_to_dma = octeon_gen1_phys_to_dma;
- _octeon_pci_dma_map_ops.dma_to_phys = octeon_gen1_dma_to_phys;
- break;
- case OCTEON_DMA_BAR_TYPE_BIG:
- _octeon_pci_dma_map_ops.phys_to_dma = octeon_big_phys_to_dma;
- _octeon_pci_dma_map_ops.dma_to_phys = octeon_big_dma_to_phys;
- break;
- case OCTEON_DMA_BAR_TYPE_SMALL:
- _octeon_pci_dma_map_ops.phys_to_dma = octeon_small_phys_to_dma;
- _octeon_pci_dma_map_ops.dma_to_phys = octeon_small_dma_to_phys;
- break;
- default:
- BUG();
- }
- octeon_pci_dma_map_ops = &_octeon_pci_dma_map_ops.dma_map_ops;
-}
-#endif /* CONFIG_PCI */
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#include <asm/octeon/cvmx-asxx-defs.h>
#include <asm/octeon/cvmx-dbg-defs.h>
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_asxx_enable(int block);
-
/**
* Probe RGMII ports and determine the number present
*
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#include <asm/octeon/cvmx-gmxx-defs.h>
#include <asm/octeon/cvmx-pcsx-defs.h>
-
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+#include <asm/octeon/cvmx-pcsxx-defs.h>
/**
* Perform initialization required only once for an SGMII port.
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
* Contact Cavium Networks for more information
***********************license end**************************************/
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_spxx_int_msk_enable(int index);
-void __cvmx_interrupt_stxx_int_msk_enable(int index);
-
/*
* Functions for SPI initialization, configuration,
* and monitoring.
#include <asm/octeon/cvmx-pip-defs.h>
#include <asm/octeon/cvmx-pko-defs.h>
+#include <asm/octeon/cvmx-spxx-defs.h>
+#include <asm/octeon/cvmx-stxx-defs.h>
/*
* CVMX_HELPER_SPI_TIMEOUT is used to determine how long the SPI
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#include <asm/octeon/cvmx-pko-defs.h>
#include <asm/octeon/cvmx-gmxx-defs.h>
+#include <asm/octeon/cvmx-pcsx-defs.h>
#include <asm/octeon/cvmx-pcsxx-defs.h>
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
-
int __cvmx_helper_xaui_enumerate(int interface)
{
union cvmx_gmxx_hg2_control gmx_hg2_control;
pen = &per_cpu(octeon_irq_ciu1_en_mirror, cpu);
if (cpumask_test_cpu(cpu, dest) && enable_one) {
- enable_one = 0;
+ enable_one = false;
__set_bit(cd->bit, pen);
} else {
__clear_bit(cd->bit, pen);
return 0;
pd = of_find_device_by_node(ehci_node);
+ of_node_put(ehci_node);
if (!pd)
return 0;
return 0;
pd = of_find_device_by_node(ohci_node);
+ of_node_put(ohci_node);
if (!pd)
return 0;
static int __init octeon_publish_devices(void)
{
- return of_platform_bus_probe(NULL, octeon_ids, NULL);
+ return of_platform_populate(NULL, octeon_ids, NULL, NULL);
}
arch_initcall(octeon_publish_devices);
#include <asm/mipsregs.h>
#include <asm/bootinfo.h>
#include <asm/sections.h>
+#include <asm/setup.h>
#include <asm/time.h>
#include <asm/octeon/octeon.h>
* Emit one character to the boot UART. Exported for use by the
* watchdog timer.
*/
-int prom_putchar(char c)
+void prom_putchar(char c)
{
uint64_t lsrval;
/* Write the byte */
cvmx_write_csr(CVMX_MIO_UARTX_THR(octeon_uart), c & 0xffull);
- return 1;
}
EXPORT_SYMBOL(prom_putchar);
}
void __init octeon_fill_mac_addresses(void);
-int octeon_prune_device_tree(void);
-extern const char __appended_dtb;
-extern const char __dtb_octeon_3xxx_begin;
-extern const char __dtb_octeon_68xx_begin;
void __init device_tree_init(void)
{
const void *fdt;
# CONFIG_HW_RANDOM is not set
CONFIG_I2C=y
CONFIG_I2C_JZ4780=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
CONFIG_GPIO_SYSFS=y
CONFIG_GPIO_INGENIC=y
# CONFIG_HWMON is not set
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_SCSI=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_HW_RANDOM=y
# CONFIG_HWMON is not set
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
#include <linux/init.h>
#include <linux/console.h>
#include <linux/fs.h>
+#include <asm/setup.h>
#include <asm/sgialib.h>
static void prom_console_write(struct console *co, const char *s,
#include <linux/kernel.h>
#include <asm/sgialib.h>
#include <asm/bcache.h>
+#include <asm/setup.h>
/*
* IP22 boardcache is not compatible with board caches. Thus we disable it
#include <asm/mipsprom.h>
#include <asm/mipsregs.h>
#include <asm/bootinfo.h>
+#include <asm/setup.h>
/* special SNI prom calls */
/*
depends on LEGACY_BOARD_SEAD3=n
select LEGACY_BOARDS
select MSCC_OCELOT
+ select SYS_HAS_EARLY_PRINTK
+ select USE_GENERIC_EARLY_PRINTK_8250
config MSCC_OCELOT
bool
select GPIOLIB
select MSCC_OCELOT_IRQ
- select SYS_HAS_EARLY_PRINTK
- select USE_GENERIC_EARLY_PRINTK_8250
comment "FIT/UHI Boards"
Enable this to include the FDT for the MIPSfpga platform
from Imagination Technologies in the FIT kernel image.
+config FIT_IMAGE_FDT_OCELOT_PCB123
+ bool "Include FDT for Microsemi Ocelot PCB123"
+ select MSCC_OCELOT
+ help
+ Enable this to include the FDT for the Ocelot PCB123 platform
+ from Microsemi in the FIT kernel image.
+ This requires u-boot on the platform.
+
config VIRT_BOARD_RANCHU
bool "Support Ranchu platform for Android emulator"
help
its-y := vmlinux.its.S
its-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += board-boston.its.S
its-$(CONFIG_FIT_IMAGE_FDT_NI169445) += board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_OCELOT_PCB123) += board-ocelot_pcb123.its.S
its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += board-xilfpga.its.S
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/ {
+ images {
+ fdt@ocelot_pcb123 {
+ description = "MSCC Ocelot PCB123 Device Tree";
+ data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb");
+ type = "flat_dt";
+ arch = "mips";
+ compression = "none";
+ hash@0 {
+ algo = "sha1";
+ };
+ };
+ };
+
+ configurations {
+ conf@ocelot_pcb123 {
+ description = "Ocelot Linux kernel";
+ kernel = "kernel@0";
+ fdt = "fdt@ocelot_pcb123";
+ };
+ };
+};
#include <linux/init.h>
#include <linux/irqchip.h>
#include <linux/of_fdt.h>
-#include <linux/of_platform.h>
#include <asm/bootinfo.h>
#include <asm/fw/fw.h>
"mti,cpu-interrupt-controller");
if (!cpu_has_veic && !intc_node)
mips_cpu_irq_init();
+ of_node_put(intc_node);
irqchip_init();
}
-static int __init publish_devices(void)
-{
- if (!of_have_populated_dt())
- panic("Device-tree not present");
-
- if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
- panic("Failed to populate DT");
-
- return 0;
-}
-arch_initcall(publish_devices);
-
void __init prom_free_prom_memory(void)
{
}
/* find or add chosen node */
chosen_off = fdt_path_offset(fdt, "/chosen");
- if (chosen_off == -FDT_ERR_NOTFOUND)
- chosen_off = fdt_path_offset(fdt, "/chosen@0");
if (chosen_off == -FDT_ERR_NOTFOUND)
chosen_off = fdt_add_subnode(fdt, 0, "chosen");
if (chosen_off < 0) {
/* find or add chosen node */
chosen_off = fdt_path_offset(fdt, "/chosen");
- if (chosen_off == -FDT_ERR_NOTFOUND)
- chosen_off = fdt_path_offset(fdt, "/chosen@0");
if (chosen_off == -FDT_ERR_NOTFOUND)
chosen_off = fdt_add_subnode(fdt, 0, "chosen");
if (chosen_off < 0) {
generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
+generic-y += msi.h
generic-y += parport.h
generic-y += percpu.h
generic-y += preempt.h
#include <asm/cmpxchg.h>
#include <asm/war.h>
+/*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+#if R10000_LLSC_WAR
+# define __scbeqz "beqzl"
+#else
+# define __scbeqz "beqz"
+#endif
+
#define ATOMIC_INIT(i) { (i) }
/*
#define ATOMIC_OP(op, c_op, asm_op) \
static __inline__ void atomic_##op(int i, atomic_t * v) \
{ \
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %0, %1 # atomic_" #op " \n" \
" " #asm_op " %0, %2 \n" \
" sc %0, %1 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" .set mips0 \n" \
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %0, %1 # atomic_" #op "\n" \
- " " #asm_op " %0, %2 \n" \
- " sc %0, %1 \n" \
- " .set mips0 \n" \
- : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!temp)); \
} else { \
unsigned long flags; \
\
{ \
int result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %1, %2 # atomic_" #op "_return \n" \
" " #asm_op " %0, %1, %3 \n" \
" sc %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" " #asm_op " %0, %1, %3 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %1, %2 # atomic_" #op "_return \n" \
- " " #asm_op " %0, %1, %3 \n" \
- " sc %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!result)); \
- \
- result = temp; result c_op i; \
} else { \
unsigned long flags; \
\
{ \
int result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %1, %2 # atomic_fetch_" #op " \n" \
" " #asm_op " %0, %1, %3 \n" \
" sc %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" move %0, %1 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %1, %2 # atomic_fetch_" #op " \n" \
- " " #asm_op " %0, %1, %3 \n" \
- " sc %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!result)); \
- \
- result = temp; \
} else { \
unsigned long flags; \
\
smp_mb__before_llsc();
- if (kernel_uses_llsc && R10000_LLSC_WAR) {
- int temp;
-
- __asm__ __volatile__(
- " .set arch=r4000 \n"
- "1: ll %1, %2 # atomic_sub_if_positive\n"
- " subu %0, %1, %3 \n"
- " bltz %0, 1f \n"
- " sc %0, %2 \n"
- " .set noreorder \n"
- " beqzl %0, 1b \n"
- " subu %0, %1, %3 \n"
- " .set reorder \n"
- "1: \n"
- " .set mips0 \n"
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
- : "memory");
- } else if (kernel_uses_llsc) {
+ if (kernel_uses_llsc) {
int temp;
__asm__ __volatile__(
" .set "MIPS_ISA_LEVEL" \n"
"1: ll %1, %2 # atomic_sub_if_positive\n"
" subu %0, %1, %3 \n"
+ " move %1, %0 \n"
" bltz %0, 1f \n"
- " sc %0, %2 \n"
- " .set noreorder \n"
- " beqz %0, 1b \n"
- " subu %0, %1, %3 \n"
- " .set reorder \n"
+ " sc %1, %2 \n"
+ "\t" __scbeqz " %1, 1b \n"
"1: \n"
" .set mips0 \n"
: "=&r" (result), "=&r" (temp),
#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
/*
* atomic_dec_if_positive - decrement by 1 if old value positive
* @v: pointer of type atomic_t
*/
#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
#ifdef CONFIG_64BIT
#define ATOMIC64_INIT(i) { (i) }
#define ATOMIC64_OP(op, c_op, asm_op) \
static __inline__ void atomic64_##op(long i, atomic64_t * v) \
{ \
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %0, %1 # atomic64_" #op " \n" \
" " #asm_op " %0, %2 \n" \
" scd %0, %1 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" .set mips0 \n" \
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %0, %1 # atomic64_" #op "\n" \
- " " #asm_op " %0, %2 \n" \
- " scd %0, %1 \n" \
- " .set mips0 \n" \
- : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!temp)); \
} else { \
unsigned long flags; \
\
{ \
long result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %1, %2 # atomic64_" #op "_return\n" \
" " #asm_op " %0, %1, %3 \n" \
" scd %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" " #asm_op " %0, %1, %3 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %1, %2 # atomic64_" #op "_return\n" \
- " " #asm_op " %0, %1, %3 \n" \
- " scd %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "=" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \
- : "memory"); \
- } while (unlikely(!result)); \
- \
- result = temp; result c_op i; \
} else { \
unsigned long flags; \
\
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %1, %2 # atomic64_fetch_" #op "\n" \
" " #asm_op " %0, %1, %3 \n" \
" scd %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" move %0, %1 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %1, %2 # atomic64_fetch_" #op "\n" \
- " " #asm_op " %0, %1, %3 \n" \
- " scd %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "=" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \
- : "memory"); \
- } while (unlikely(!result)); \
- \
- result = temp; \
} else { \
unsigned long flags; \
\
smp_mb__before_llsc();
- if (kernel_uses_llsc && R10000_LLSC_WAR) {
- long temp;
-
- __asm__ __volatile__(
- " .set arch=r4000 \n"
- "1: lld %1, %2 # atomic64_sub_if_positive\n"
- " dsubu %0, %1, %3 \n"
- " bltz %0, 1f \n"
- " scd %0, %2 \n"
- " .set noreorder \n"
- " beqzl %0, 1b \n"
- " dsubu %0, %1, %3 \n"
- " .set reorder \n"
- "1: \n"
- " .set mips0 \n"
- : "=&r" (result), "=&r" (temp),
- "=" GCC_OFF_SMALL_ASM() (v->counter)
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
- : "memory");
- } else if (kernel_uses_llsc) {
+ if (kernel_uses_llsc) {
long temp;
__asm__ __volatile__(
" .set "MIPS_ISA_LEVEL" \n"
"1: lld %1, %2 # atomic64_sub_if_positive\n"
" dsubu %0, %1, %3 \n"
+ " move %1, %0 \n"
" bltz %0, 1f \n"
- " scd %0, %2 \n"
- " .set noreorder \n"
- " beqz %0, 1b \n"
- " dsubu %0, %1, %3 \n"
- " .set reorder \n"
+ " scd %1, %2 \n"
+ "\t" __scbeqz " %1, 1b \n"
"1: \n"
" .set mips0 \n"
: "=&r" (result), "=&r" (temp),
((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
#define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
/*
* atomic64_dec_if_positive - decrement by 1 if old value positive
* @v: pointer of type atomic64_t
*/
#define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v)
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
#endif /* CONFIG_64BIT */
#endif /* _ASM_ATOMIC_H */
barrier();
}
-static inline void bmips_post_dma_flush(struct device *dev)
-{
- void __iomem *cbr = BMIPS_GET_CBR();
- u32 cfg;
-
- if (boot_cpu_type() != CPU_BMIPS3300 &&
- boot_cpu_type() != CPU_BMIPS4350 &&
- boot_cpu_type() != CPU_BMIPS4380)
- return;
-
- /* Flush stale data out of the readahead cache */
- cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
- __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
- __raw_readl(cbr + BMIPS_RAC_CONFIG);
-}
-
#endif /* !defined(__ASSEMBLY__) */
#endif /* _ASM_BMIPS_H */
#include <asm/isa-rev.h>
#include <cpu-feature-overrides.h>
+#define __ase(ase) (cpu_data[0].ases & (ase))
+#define __opt(opt) (cpu_data[0].options & (opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * Note that these should only be used in cases where a kernel built for an
+ * older ISA *cannot* run on a CPU which supports the feature in question. For
+ * example this may be used for features introduced with MIPSr6, since a kernel
+ * built for an older ISA cannot run on a MIPSr6 CPU. This should not be used
+ * for MIPSr2 features however, since a MIPSr1 or earlier kernel might run on a
+ * MIPSr2 CPU.
+ */
+#define __isa_ge_and_ase(isa, ase) ((MIPS_ISA_REV >= (isa)) && __ase(ase))
+#define __isa_ge_and_opt(isa, opt) ((MIPS_ISA_REV >= (isa)) && __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *or* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & then become required.
+ */
+#define __isa_ge_or_ase(isa, ase) ((MIPS_ISA_REV >= (isa)) || __ase(ase))
+#define __isa_ge_or_opt(isa, opt) ((MIPS_ISA_REV >= (isa)) || __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is < isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & are then removed - ie. no longer present in any CPU implementing
+ * the given ISA revision.
+ */
+#define __isa_lt_and_ase(isa, ase) ((MIPS_ISA_REV < (isa)) && __ase(ase))
+#define __isa_lt_and_opt(isa, opt) ((MIPS_ISA_REV < (isa)) && __opt(opt))
+
/*
* SMP assumption: Options of CPU 0 are a superset of all processors.
* This is true for all known MIPS systems.
*/
#ifndef cpu_has_tlb
-#define cpu_has_tlb (cpu_data[0].options & MIPS_CPU_TLB)
+#define cpu_has_tlb __opt(MIPS_CPU_TLB)
#endif
#ifndef cpu_has_ftlb
-#define cpu_has_ftlb (cpu_data[0].options & MIPS_CPU_FTLB)
+#define cpu_has_ftlb __opt(MIPS_CPU_FTLB)
#endif
#ifndef cpu_has_tlbinv
-#define cpu_has_tlbinv (cpu_data[0].options & MIPS_CPU_TLBINV)
+#define cpu_has_tlbinv __opt(MIPS_CPU_TLBINV)
#endif
#ifndef cpu_has_segments
-#define cpu_has_segments (cpu_data[0].options & MIPS_CPU_SEGMENTS)
+#define cpu_has_segments __opt(MIPS_CPU_SEGMENTS)
#endif
#ifndef cpu_has_eva
-#define cpu_has_eva (cpu_data[0].options & MIPS_CPU_EVA)
+#define cpu_has_eva __opt(MIPS_CPU_EVA)
#endif
#ifndef cpu_has_htw
-#define cpu_has_htw (cpu_data[0].options & MIPS_CPU_HTW)
+#define cpu_has_htw __opt(MIPS_CPU_HTW)
#endif
#ifndef cpu_has_ldpte
-#define cpu_has_ldpte (cpu_data[0].options & MIPS_CPU_LDPTE)
+#define cpu_has_ldpte __opt(MIPS_CPU_LDPTE)
#endif
#ifndef cpu_has_rixiex
-#define cpu_has_rixiex (cpu_data[0].options & MIPS_CPU_RIXIEX)
+#define cpu_has_rixiex __isa_ge_or_opt(6, MIPS_CPU_RIXIEX)
#endif
#ifndef cpu_has_maar
-#define cpu_has_maar (cpu_data[0].options & MIPS_CPU_MAAR)
+#define cpu_has_maar __opt(MIPS_CPU_MAAR)
#endif
#ifndef cpu_has_rw_llb
-#define cpu_has_rw_llb (cpu_data[0].options & MIPS_CPU_RW_LLB)
+#define cpu_has_rw_llb __isa_ge_or_opt(6, MIPS_CPU_RW_LLB)
#endif
/*
#define cpu_has_3kex (!cpu_has_4kex)
#endif
#ifndef cpu_has_4kex
-#define cpu_has_4kex (cpu_data[0].options & MIPS_CPU_4KEX)
+#define cpu_has_4kex __isa_ge_or_opt(1, MIPS_CPU_4KEX)
#endif
#ifndef cpu_has_3k_cache
-#define cpu_has_3k_cache (cpu_data[0].options & MIPS_CPU_3K_CACHE)
+#define cpu_has_3k_cache __isa_lt_and_opt(1, MIPS_CPU_3K_CACHE)
#endif
#define cpu_has_6k_cache 0
#define cpu_has_8k_cache 0
#ifndef cpu_has_4k_cache
-#define cpu_has_4k_cache (cpu_data[0].options & MIPS_CPU_4K_CACHE)
+#define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE)
#endif
#ifndef cpu_has_tx39_cache
-#define cpu_has_tx39_cache (cpu_data[0].options & MIPS_CPU_TX39_CACHE)
+#define cpu_has_tx39_cache __opt(MIPS_CPU_TX39_CACHE)
#endif
#ifndef cpu_has_octeon_cache
#define cpu_has_octeon_cache 0
#define raw_cpu_has_fpu cpu_has_fpu
#endif
#ifndef cpu_has_32fpr
-#define cpu_has_32fpr (cpu_data[0].options & MIPS_CPU_32FPR)
+#define cpu_has_32fpr __isa_ge_or_opt(1, MIPS_CPU_32FPR)
#endif
#ifndef cpu_has_counter
-#define cpu_has_counter (cpu_data[0].options & MIPS_CPU_COUNTER)
+#define cpu_has_counter __opt(MIPS_CPU_COUNTER)
#endif
#ifndef cpu_has_watch
-#define cpu_has_watch (cpu_data[0].options & MIPS_CPU_WATCH)
+#define cpu_has_watch __opt(MIPS_CPU_WATCH)
#endif
#ifndef cpu_has_divec
-#define cpu_has_divec (cpu_data[0].options & MIPS_CPU_DIVEC)
+#define cpu_has_divec __isa_ge_or_opt(1, MIPS_CPU_DIVEC)
#endif
#ifndef cpu_has_vce
-#define cpu_has_vce (cpu_data[0].options & MIPS_CPU_VCE)
+#define cpu_has_vce __opt(MIPS_CPU_VCE)
#endif
#ifndef cpu_has_cache_cdex_p
-#define cpu_has_cache_cdex_p (cpu_data[0].options & MIPS_CPU_CACHE_CDEX_P)
+#define cpu_has_cache_cdex_p __opt(MIPS_CPU_CACHE_CDEX_P)
#endif
#ifndef cpu_has_cache_cdex_s
-#define cpu_has_cache_cdex_s (cpu_data[0].options & MIPS_CPU_CACHE_CDEX_S)
+#define cpu_has_cache_cdex_s __opt(MIPS_CPU_CACHE_CDEX_S)
#endif
#ifndef cpu_has_prefetch
-#define cpu_has_prefetch (cpu_data[0].options & MIPS_CPU_PREFETCH)
+#define cpu_has_prefetch __isa_ge_or_opt(1, MIPS_CPU_PREFETCH)
#endif
#ifndef cpu_has_mcheck
-#define cpu_has_mcheck (cpu_data[0].options & MIPS_CPU_MCHECK)
+#define cpu_has_mcheck __isa_ge_or_opt(1, MIPS_CPU_MCHECK)
#endif
#ifndef cpu_has_ejtag
-#define cpu_has_ejtag (cpu_data[0].options & MIPS_CPU_EJTAG)
+#define cpu_has_ejtag __opt(MIPS_CPU_EJTAG)
#endif
#ifndef cpu_has_llsc
-#define cpu_has_llsc (cpu_data[0].options & MIPS_CPU_LLSC)
+#define cpu_has_llsc __isa_ge_or_opt(1, MIPS_CPU_LLSC)
#endif
#ifndef cpu_has_bp_ghist
-#define cpu_has_bp_ghist (cpu_data[0].options & MIPS_CPU_BP_GHIST)
+#define cpu_has_bp_ghist __opt(MIPS_CPU_BP_GHIST)
#endif
#ifndef kernel_uses_llsc
#define kernel_uses_llsc cpu_has_llsc
#endif
#ifndef cpu_has_guestctl0ext
-#define cpu_has_guestctl0ext (cpu_data[0].options & MIPS_CPU_GUESTCTL0EXT)
+#define cpu_has_guestctl0ext __opt(MIPS_CPU_GUESTCTL0EXT)
#endif
#ifndef cpu_has_guestctl1
-#define cpu_has_guestctl1 (cpu_data[0].options & MIPS_CPU_GUESTCTL1)
+#define cpu_has_guestctl1 __opt(MIPS_CPU_GUESTCTL1)
#endif
#ifndef cpu_has_guestctl2
-#define cpu_has_guestctl2 (cpu_data[0].options & MIPS_CPU_GUESTCTL2)
+#define cpu_has_guestctl2 __opt(MIPS_CPU_GUESTCTL2)
#endif
#ifndef cpu_has_guestid
-#define cpu_has_guestid (cpu_data[0].options & MIPS_CPU_GUESTID)
+#define cpu_has_guestid __opt(MIPS_CPU_GUESTID)
#endif
#ifndef cpu_has_drg
-#define cpu_has_drg (cpu_data[0].options & MIPS_CPU_DRG)
+#define cpu_has_drg __opt(MIPS_CPU_DRG)
#endif
#ifndef cpu_has_mips16
-#define cpu_has_mips16 (cpu_data[0].ases & MIPS_ASE_MIPS16)
+#define cpu_has_mips16 __isa_lt_and_ase(6, MIPS_ASE_MIPS16)
#endif
#ifndef cpu_has_mips16e2
-#define cpu_has_mips16e2 (cpu_data[0].ases & MIPS_ASE_MIPS16E2)
+#define cpu_has_mips16e2 __isa_lt_and_ase(6, MIPS_ASE_MIPS16E2)
#endif
#ifndef cpu_has_mdmx
-#define cpu_has_mdmx (cpu_data[0].ases & MIPS_ASE_MDMX)
+#define cpu_has_mdmx __isa_lt_and_ase(6, MIPS_ASE_MDMX)
#endif
#ifndef cpu_has_mips3d
-#define cpu_has_mips3d (cpu_data[0].ases & MIPS_ASE_MIPS3D)
+#define cpu_has_mips3d __isa_lt_and_ase(6, MIPS_ASE_MIPS3D)
#endif
#ifndef cpu_has_smartmips
-#define cpu_has_smartmips (cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
+#define cpu_has_smartmips __isa_lt_and_ase(6, MIPS_ASE_SMARTMIPS)
#endif
#ifndef cpu_has_rixi
-#define cpu_has_rixi (cpu_data[0].options & MIPS_CPU_RIXI)
+#define cpu_has_rixi __isa_ge_or_opt(6, MIPS_CPU_RIXI)
#endif
#ifndef cpu_has_mmips
# ifdef CONFIG_SYS_SUPPORTS_MICROMIPS
-# define cpu_has_mmips (cpu_data[0].options & MIPS_CPU_MICROMIPS)
+# define cpu_has_mmips __opt(MIPS_CPU_MICROMIPS)
# else
# define cpu_has_mmips 0
# endif
#endif
#ifndef cpu_has_lpa
-#define cpu_has_lpa (cpu_data[0].options & MIPS_CPU_LPA)
+#define cpu_has_lpa __opt(MIPS_CPU_LPA)
#endif
#ifndef cpu_has_mvh
-#define cpu_has_mvh (cpu_data[0].options & MIPS_CPU_MVH)
+#define cpu_has_mvh __opt(MIPS_CPU_MVH)
#endif
#ifndef cpu_has_xpa
#define cpu_has_xpa (cpu_has_lpa && cpu_has_mvh)
#endif
#ifndef cpu_has_dsp
-#define cpu_has_dsp (cpu_data[0].ases & MIPS_ASE_DSP)
+#define cpu_has_dsp __ase(MIPS_ASE_DSP)
#endif
#ifndef cpu_has_dsp2
-#define cpu_has_dsp2 (cpu_data[0].ases & MIPS_ASE_DSP2P)
+#define cpu_has_dsp2 __ase(MIPS_ASE_DSP2P)
#endif
#ifndef cpu_has_dsp3
-#define cpu_has_dsp3 (cpu_data[0].ases & MIPS_ASE_DSP3)
+#define cpu_has_dsp3 __ase(MIPS_ASE_DSP3)
#endif
#ifndef cpu_has_mipsmt
-#define cpu_has_mipsmt (cpu_data[0].ases & MIPS_ASE_MIPSMT)
+#define cpu_has_mipsmt __isa_lt_and_ase(6, MIPS_ASE_MIPSMT)
#endif
#ifndef cpu_has_vp
-#define cpu_has_vp (cpu_data[0].options & MIPS_CPU_VP)
+#define cpu_has_vp __isa_ge_and_opt(6, MIPS_CPU_VP)
#endif
#ifndef cpu_has_userlocal
-#define cpu_has_userlocal (cpu_data[0].options & MIPS_CPU_ULRI)
+#define cpu_has_userlocal __isa_ge_or_opt(6, MIPS_CPU_ULRI)
#endif
#ifdef CONFIG_32BIT
# ifndef cpu_has_nofpuex
-# define cpu_has_nofpuex (cpu_data[0].options & MIPS_CPU_NOFPUEX)
+# define cpu_has_nofpuex __isa_lt_and_opt(1, MIPS_CPU_NOFPUEX)
# endif
# ifndef cpu_has_64bits
# define cpu_has_64bits (cpu_data[0].isa_level & MIPS_CPU_ISA_64BIT)
#endif
#if defined(CONFIG_CPU_MIPSR2_IRQ_VI) && !defined(cpu_has_vint)
-# define cpu_has_vint (cpu_data[0].options & MIPS_CPU_VINT)
+# define cpu_has_vint __opt(MIPS_CPU_VINT)
#elif !defined(cpu_has_vint)
# define cpu_has_vint 0
#endif
#if defined(CONFIG_CPU_MIPSR2_IRQ_EI) && !defined(cpu_has_veic)
-# define cpu_has_veic (cpu_data[0].options & MIPS_CPU_VEIC)
+# define cpu_has_veic __opt(MIPS_CPU_VEIC)
#elif !defined(cpu_has_veic)
# define cpu_has_veic 0
#endif
#ifndef cpu_has_inclusive_pcaches
-#define cpu_has_inclusive_pcaches (cpu_data[0].options & MIPS_CPU_INCLUSIVE_CACHES)
+#define cpu_has_inclusive_pcaches __opt(MIPS_CPU_INCLUSIVE_CACHES)
#endif
#ifndef cpu_dcache_line_size
#endif
#ifndef cpu_has_perf_cntr_intr_bit
-#define cpu_has_perf_cntr_intr_bit (cpu_data[0].options & MIPS_CPU_PCI)
+#define cpu_has_perf_cntr_intr_bit __opt(MIPS_CPU_PCI)
#endif
#ifndef cpu_has_vz
-#define cpu_has_vz (cpu_data[0].ases & MIPS_ASE_VZ)
+#define cpu_has_vz __ase(MIPS_ASE_VZ)
#endif
#if defined(CONFIG_CPU_HAS_MSA) && !defined(cpu_has_msa)
-# define cpu_has_msa (cpu_data[0].ases & MIPS_ASE_MSA)
+# define cpu_has_msa __ase(MIPS_ASE_MSA)
#elif !defined(cpu_has_msa)
# define cpu_has_msa 0
#endif
#ifndef cpu_has_ufr
-# define cpu_has_ufr (cpu_data[0].options & MIPS_CPU_UFR)
+# define cpu_has_ufr __opt(MIPS_CPU_UFR)
#endif
#ifndef cpu_has_fre
-# define cpu_has_fre (cpu_data[0].options & MIPS_CPU_FRE)
+# define cpu_has_fre __opt(MIPS_CPU_FRE)
#endif
#ifndef cpu_has_cdmm
-# define cpu_has_cdmm (cpu_data[0].options & MIPS_CPU_CDMM)
+# define cpu_has_cdmm __opt(MIPS_CPU_CDMM)
#endif
#ifndef cpu_has_small_pages
-# define cpu_has_small_pages (cpu_data[0].options & MIPS_CPU_SP)
+# define cpu_has_small_pages __opt(MIPS_CPU_SP)
#endif
#ifndef cpu_has_nan_legacy
-#define cpu_has_nan_legacy (cpu_data[0].options & MIPS_CPU_NAN_LEGACY)
+#define cpu_has_nan_legacy __isa_lt_and_opt(6, MIPS_CPU_NAN_LEGACY)
#endif
#ifndef cpu_has_nan_2008
-#define cpu_has_nan_2008 (cpu_data[0].options & MIPS_CPU_NAN_2008)
+#define cpu_has_nan_2008 __isa_ge_or_opt(6, MIPS_CPU_NAN_2008)
#endif
#ifndef cpu_has_ebase_wg
-# define cpu_has_ebase_wg (cpu_data[0].options & MIPS_CPU_EBASE_WG)
+# define cpu_has_ebase_wg __opt(MIPS_CPU_EBASE_WG)
#endif
#ifndef cpu_has_badinstr
-# define cpu_has_badinstr (cpu_data[0].options & MIPS_CPU_BADINSTR)
+# define cpu_has_badinstr __isa_ge_or_opt(6, MIPS_CPU_BADINSTR)
#endif
#ifndef cpu_has_badinstrp
-# define cpu_has_badinstrp (cpu_data[0].options & MIPS_CPU_BADINSTRP)
+# define cpu_has_badinstrp __isa_ge_or_opt(6, MIPS_CPU_BADINSTRP)
#endif
#ifndef cpu_has_contextconfig
-# define cpu_has_contextconfig (cpu_data[0].options & MIPS_CPU_CTXTC)
+# define cpu_has_contextconfig __opt(MIPS_CPU_CTXTC)
#endif
#ifndef cpu_has_perf
-# define cpu_has_perf (cpu_data[0].options & MIPS_CPU_PERF)
+# define cpu_has_perf __opt(MIPS_CPU_PERF)
#endif
-#if defined(CONFIG_SMP) && (MIPS_ISA_REV >= 6)
+#ifdef CONFIG_SMP
/*
* Some systems share FTLB RAMs between threads within a core (siblings in
* kernel parlance). This means that FTLB entries may become invalid at almost
*/
# ifndef cpu_has_shared_ftlb_ram
# define cpu_has_shared_ftlb_ram \
- (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM)
+ __isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_RAM)
# endif
/*
*/
# ifndef cpu_has_shared_ftlb_entries
# define cpu_has_shared_ftlb_entries \
- (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES)
+ __isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_ENTRIES)
# endif
-#endif /* SMP && MIPS_ISA_REV >= 6 */
+#endif /* SMP */
#ifndef cpu_has_shared_ftlb_ram
# define cpu_has_shared_ftlb_ram 0
#ifdef CONFIG_MIPS_MT_SMP
# define cpu_has_mipsmt_pertccounters \
- (cpu_data[0].options & MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
+ __isa_lt_and_opt(6, MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
#else
# define cpu_has_mipsmt_pertccounters 0
#endif /* CONFIG_MIPS_MT_SMP */
* Definitions for 7:0 on legacy processors
*/
-#define PRID_REV_TX4927 0x0022
-#define PRID_REV_TX4937 0x0030
-#define PRID_REV_R4400 0x0040
-#define PRID_REV_R3000A 0x0030
-#define PRID_REV_R3000 0x0020
-#define PRID_REV_R2000A 0x0010
-#define PRID_REV_TX3912 0x0010
-#define PRID_REV_TX3922 0x0030
-#define PRID_REV_TX3927 0x0040
-#define PRID_REV_VR4111 0x0050
-#define PRID_REV_VR4181 0x0050 /* Same as VR4111 */
-#define PRID_REV_VR4121 0x0060
-#define PRID_REV_VR4122 0x0070
-#define PRID_REV_VR4181A 0x0070 /* Same as VR4122 */
-#define PRID_REV_VR4130 0x0080
-#define PRID_REV_34K_V1_0_2 0x0022
-#define PRID_REV_LOONGSON1B 0x0020
-#define PRID_REV_LOONGSON1C 0x0020 /* Same as Loongson-1B */
-#define PRID_REV_LOONGSON2E 0x0002
-#define PRID_REV_LOONGSON2F 0x0003
-#define PRID_REV_LOONGSON3A_R1 0x0005
-#define PRID_REV_LOONGSON3B_R1 0x0006
-#define PRID_REV_LOONGSON3B_R2 0x0007
-#define PRID_REV_LOONGSON3A_R2 0x0008
-#define PRID_REV_LOONGSON3A_R3 0x0009
+#define PRID_REV_TX4927 0x0022
+#define PRID_REV_TX4937 0x0030
+#define PRID_REV_R4400 0x0040
+#define PRID_REV_R3000A 0x0030
+#define PRID_REV_R3000 0x0020
+#define PRID_REV_R2000A 0x0010
+#define PRID_REV_TX3912 0x0010
+#define PRID_REV_TX3922 0x0030
+#define PRID_REV_TX3927 0x0040
+#define PRID_REV_VR4111 0x0050
+#define PRID_REV_VR4181 0x0050 /* Same as VR4111 */
+#define PRID_REV_VR4121 0x0060
+#define PRID_REV_VR4122 0x0070
+#define PRID_REV_VR4181A 0x0070 /* Same as VR4122 */
+#define PRID_REV_VR4130 0x0080
+#define PRID_REV_34K_V1_0_2 0x0022
+#define PRID_REV_LOONGSON1B 0x0020
+#define PRID_REV_LOONGSON1C 0x0020 /* Same as Loongson-1B */
+#define PRID_REV_LOONGSON2E 0x0002
+#define PRID_REV_LOONGSON2F 0x0003
+#define PRID_REV_LOONGSON3A_R1 0x0005
+#define PRID_REV_LOONGSON3B_R1 0x0006
+#define PRID_REV_LOONGSON3B_R2 0x0007
+#define PRID_REV_LOONGSON3A_R2 0x0008
+#define PRID_REV_LOONGSON3A_R3_0 0x0009
+#define PRID_REV_LOONGSON3A_R3_1 0x000d
/*
* Older processors used to encode processor version and revision in two
extern enum coherent_io_user_state coherentio;
extern int hw_coherentio;
#else
-#ifdef CONFIG_DMA_COHERENT
-#define coherentio IO_COHERENCE_ENABLED
-#else
+#ifdef CONFIG_DMA_NONCOHERENT
#define coherentio IO_COHERENCE_DISABLED
+#else
+#define coherentio IO_COHERENCE_ENABLED
#endif
#define hw_coherentio 0
#endif /* CONFIG_DMA_MAYBE_COHERENT */
-#include <asm/dma-coherence.h>
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MIPS_DMA_DIRECT_H
+#define _MIPS_DMA_DIRECT_H 1
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return false;
+
+ return addr + size - 1 <= *dev->dma_mask;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+#endif /* _MIPS_DMA_DIRECT_H */
#ifndef _ASM_DMA_MAPPING_H
#define _ASM_DMA_MAPPING_H
-#include <linux/scatterlist.h>
-#include <asm/dma-coherence.h>
-#include <asm/cache.h>
+#include <linux/swiotlb.h>
-#ifndef CONFIG_SGI_IP27 /* Kludge to fix 2.6.39 build for IP27 */
-#include <dma-coherence.h>
-#endif
-
-extern const struct dma_map_ops *mips_dma_map_ops;
+extern const struct dma_map_ops jazz_dma_ops;
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- return mips_dma_map_ops;
+#if defined(CONFIG_MACH_JAZZ)
+ return &jazz_dma_ops;
+#elif defined(CONFIG_SWIOTLB)
+ return &swiotlb_dma_ops;
+#elif defined(CONFIG_DMA_NONCOHERENT_OPS)
+ return &dma_noncoherent_ops;
+#else
+ return &dma_direct_ops;
+#endif
}
#define arch_setup_dma_ops arch_setup_dma_ops
#ifndef _ASM_IO_H
#define _ASM_IO_H
+#define ARCH_HAS_IOREMAP_WC
+
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/types.h>
/*
* ISA I/O bus memory addresses are 1:1 with the physical address.
*/
-static inline unsigned long isa_virt_to_bus(volatile void * address)
+static inline unsigned long isa_virt_to_bus(volatile void *address)
{
- return (unsigned long)address - PAGE_OFFSET;
+ return virt_to_phys(address);
}
-static inline void * isa_bus_to_virt(unsigned long address)
+static inline void *isa_bus_to_virt(unsigned long address)
{
- return (void *)(address + PAGE_OFFSET);
+ return phys_to_virt(address);
}
#define isa_page_to_bus page_to_phys
#define ioremap_cache ioremap_cachable
/*
- * These two are MIPS specific ioremap variant. ioremap_cacheable_cow
- * requests a cachable mapping, ioremap_uncached_accelerated requests a
- * mapping using the uncached accelerated mode which isn't supported on
- * all processors.
+ * ioremap_wc - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_wc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * but accelerated by means of write-combining feature. It is specifically
+ * useful for PCIe prefetchable windows, which may vastly improve a
+ * communications performance. If it was determined on boot stage, what
+ * CPU CCA doesn't support UCA, the method shall fall-back to the
+ * _CACHE_UNCACHED option (see cpu_probe() method).
*/
-#define ioremap_cacheable_cow(offset, size) \
- __ioremap_mode((offset), (size), _CACHE_CACHABLE_COW)
-#define ioremap_uncached_accelerated(offset, size) \
- __ioremap_mode((offset), (size), _CACHE_UNCACHED_ACCELERATED)
+#define ioremap_wc(offset, size) \
+ __ioremap_mode((offset), (size), boot_cpu_data.writecombine)
static inline void iounmap(const volatile void __iomem *addr)
{
__val = *__addr; \
slow; \
\
+ /* prevent prefetching of coherent DMA data prematurely */ \
+ rmb(); \
return pfx##ioswab##bwlq(__addr, __val); \
}
*
* This API used to be exported; it now is for arch code internal use only.
*/
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
extern void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
extern void (*_dma_cache_wback)(unsigned long start, unsigned long size);
#define dma_cache_inv(start,size) \
do { (void) (start); (void) (size); } while (0)
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
/*
* Read a 32-bit register that requires a 64-bit read cycle on the bus.
unsigned long saved_epc;
};
-#define MAX_JPROBES_STACK_SIZE 128
-#define MAX_JPROBES_STACK_ADDR \
- (((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs))
-
-#define MIN_JPROBES_STACK_SIZE(ADDR) \
- ((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR) \
- ? MAX_JPROBES_STACK_ADDR - (ADDR) \
- : MAX_JPROBES_STACK_SIZE)
-
-
#define SKIP_DELAYSLOT 0x0001
/* per-cpu kprobe control block */
unsigned long kprobe_old_SR;
unsigned long kprobe_saved_SR;
unsigned long kprobe_saved_epc;
- unsigned long jprobe_saved_sp;
- struct pt_regs jprobe_saved_regs;
/* Per-thread fields, used while emulating branches */
unsigned long flags;
unsigned long target_epc;
- u8 jprobes_stack[MAX_JPROBES_STACK_SIZE];
struct prev_kprobe prev_kprobe;
};
#define PAGE_OFFSET _AC(0x94000000, UL)
#define PHYS_OFFSET _AC(0x14000000, UL)
-#define UNCAC_BASE _AC(0xb4000000, UL) /* 0xa0000000 + PHYS_OFFSET */
-#define IO_BASE UNCAC_BASE
-
#include <asm/mach-generic/spaces.h>
#endif /* __ASM_AR7_SPACES_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
- *
- */
-#ifndef __ASM_MACH_ATH25_DMA_COHERENCE_H
-#define __ASM_MACH_ATH25_DMA_COHERENCE_H
-
-#include <linux/device.h>
-
-/*
- * We need some arbitrary non-zero value to be programmed to the BAR1 register
- * of PCI host controller to enable DMA. The same value should be used as the
- * offset to calculate the physical address of DMA buffer for PCI devices.
- */
-#define AR2315_PCI_HOST_SDRAM_BASEADDR 0x20000000
-
-static inline dma_addr_t ath25_dev_offset(struct device *dev)
-{
-#ifdef CONFIG_PCI
- extern struct bus_type pci_bus_type;
-
- if (dev && dev->bus == &pci_bus_type)
- return AR2315_PCI_HOST_SDRAM_BASEADDR;
-#endif
- return 0;
-}
-
-static inline dma_addr_t
-plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
- return virt_to_phys(addr) + ath25_dev_offset(dev);
-}
-
-static inline dma_addr_t
-plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
- return page_to_phys(page) + ath25_dev_offset(dev);
-}
-
-static inline unsigned long
-plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
-{
- return dma_addr - ath25_dev_offset(dev);
-}
-
-static inline void
-plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, size_t size,
- enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_COHERENT
- return 1;
-#endif
-#ifdef CONFIG_DMA_NONCOHERENT
- return 0;
-#endif
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_ATH25_DMA_COHERENCE_H */
#include <linux/bitops.h>
#define AR71XX_APB_BASE 0x18000000
+#define AR71XX_GE0_BASE 0x19000000
+#define AR71XX_GE0_SIZE 0x10000
+#define AR71XX_GE1_BASE 0x1a000000
+#define AR71XX_GE1_SIZE 0x10000
#define AR71XX_EHCI_BASE 0x1b000000
#define AR71XX_EHCI_SIZE 0x1000
#define AR71XX_OHCI_BASE 0x1c000000
#define AR71XX_PLL_SIZE 0x100
#define AR71XX_RESET_BASE (AR71XX_APB_BASE + 0x00060000)
#define AR71XX_RESET_SIZE 0x100
+#define AR71XX_MII_BASE (AR71XX_APB_BASE + 0x00070000)
+#define AR71XX_MII_SIZE 0x100
#define AR71XX_PCI_MEM_BASE 0x10000000
#define AR71XX_PCI_MEM_SIZE 0x07000000
#define AR933X_UART_BASE (AR71XX_APB_BASE + 0x00020000)
#define AR933X_UART_SIZE 0x14
+#define AR933X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000)
+#define AR933X_GMAC_SIZE 0x04
#define AR933X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000)
#define AR933X_WMAC_SIZE 0x20000
#define AR933X_EHCI_BASE 0x1b000000
#define AR933X_EHCI_SIZE 0x1000
+#define AR934X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000)
+#define AR934X_GMAC_SIZE 0x14
#define AR934X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000)
#define AR934X_WMAC_SIZE 0x20000
#define AR934X_EHCI_BASE 0x1b000000
#define AR934X_EHCI_SIZE 0x200
+#define AR934X_NFC_BASE 0x1b000200
+#define AR934X_NFC_SIZE 0xb8
#define AR934X_SRIF_BASE (AR71XX_APB_BASE + 0x00116000)
#define AR934X_SRIF_SIZE 0x1000
+#define QCA953X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000)
+#define QCA953X_GMAC_SIZE 0x14
+#define QCA953X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000)
+#define QCA953X_WMAC_SIZE 0x20000
+#define QCA953X_EHCI_BASE 0x1b000000
+#define QCA953X_EHCI_SIZE 0x200
+#define QCA953X_SRIF_BASE (AR71XX_APB_BASE + 0x00116000)
+#define QCA953X_SRIF_SIZE 0x1000
+
+#define QCA953X_PCI_CFG_BASE0 0x14000000
+#define QCA953X_PCI_CTRL_BASE0 (AR71XX_APB_BASE + 0x000f0000)
+#define QCA953X_PCI_CRP_BASE0 (AR71XX_APB_BASE + 0x000c0000)
+#define QCA953X_PCI_MEM_BASE0 0x10000000
+#define QCA953X_PCI_MEM_SIZE 0x02000000
+
#define QCA955X_PCI_MEM_BASE0 0x10000000
#define QCA955X_PCI_MEM_BASE1 0x12000000
#define QCA955X_PCI_MEM_SIZE 0x02000000
#define QCA955X_PCI_CTRL_BASE1 (AR71XX_APB_BASE + 0x00280000)
#define QCA955X_PCI_CTRL_SIZE 0x100
+#define QCA955X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000)
+#define QCA955X_GMAC_SIZE 0x40
#define QCA955X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000)
#define QCA955X_WMAC_SIZE 0x20000
#define QCA955X_EHCI0_BASE 0x1b000000
#define QCA955X_EHCI1_BASE 0x1b400000
#define QCA955X_EHCI_SIZE 0x1000
+#define QCA955X_NFC_BASE 0x1b800200
+#define QCA955X_NFC_SIZE 0xb8
+
+#define QCA956X_PCI_MEM_BASE1 0x12000000
+#define QCA956X_PCI_MEM_SIZE 0x02000000
+#define QCA956X_PCI_CFG_BASE1 0x16000000
+#define QCA956X_PCI_CFG_SIZE 0x1000
+#define QCA956X_PCI_CRP_BASE1 (AR71XX_APB_BASE + 0x00250000)
+#define QCA956X_PCI_CRP_SIZE 0x1000
+#define QCA956X_PCI_CTRL_BASE1 (AR71XX_APB_BASE + 0x00280000)
+#define QCA956X_PCI_CTRL_SIZE 0x100
+
+#define QCA956X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000)
+#define QCA956X_WMAC_SIZE 0x20000
+#define QCA956X_EHCI0_BASE 0x1b000000
+#define QCA956X_EHCI1_BASE 0x1b400000
+#define QCA956X_EHCI_SIZE 0x200
+#define QCA956X_GMAC_SGMII_BASE (AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SGMII_SIZE 0x64
+#define QCA956X_PLL_BASE (AR71XX_APB_BASE + 0x00050000)
+#define QCA956X_PLL_SIZE 0x50
+#define QCA956X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SIZE 0x64
+
+/*
+ * Hidden Registers
+ */
+#define QCA956X_MAC_CFG_BASE 0xb9000000
+#define QCA956X_MAC_CFG_SIZE 0x64
+
+#define QCA956X_MAC_CFG1_REG 0x00
+#define QCA956X_MAC_CFG1_SOFT_RST BIT(31)
+#define QCA956X_MAC_CFG1_RX_RST BIT(19)
+#define QCA956X_MAC_CFG1_TX_RST BIT(18)
+#define QCA956X_MAC_CFG1_LOOPBACK BIT(8)
+#define QCA956X_MAC_CFG1_RX_EN BIT(2)
+#define QCA956X_MAC_CFG1_TX_EN BIT(0)
+
+#define QCA956X_MAC_CFG2_REG 0x04
+#define QCA956X_MAC_CFG2_IF_1000 BIT(9)
+#define QCA956X_MAC_CFG2_IF_10_100 BIT(8)
+#define QCA956X_MAC_CFG2_HUGE_FRAME_EN BIT(5)
+#define QCA956X_MAC_CFG2_LEN_CHECK BIT(4)
+#define QCA956X_MAC_CFG2_PAD_CRC_EN BIT(2)
+#define QCA956X_MAC_CFG2_FDX BIT(0)
+
+#define QCA956X_MAC_MII_MGMT_CFG_REG 0x20
+#define QCA956X_MGMT_CFG_CLK_DIV_20 0x07
+
+#define QCA956X_MAC_FIFO_CFG0_REG 0x48
+#define QCA956X_MAC_FIFO_CFG1_REG 0x4c
+#define QCA956X_MAC_FIFO_CFG2_REG 0x50
+#define QCA956X_MAC_FIFO_CFG3_REG 0x54
+#define QCA956X_MAC_FIFO_CFG4_REG 0x58
+#define QCA956X_MAC_FIFO_CFG5_REG 0x5c
+
+#define QCA956X_DAM_RESET_OFFSET 0xb90001bc
+#define QCA956X_DAM_RESET_SIZE 0x4
+#define QCA956X_INLINE_CHKSUM_ENG BIT(27)
/*
* DDR_CTRL block
#define AR934X_DDR_REG_FLUSH_PCIE 0xa8
#define AR934X_DDR_REG_FLUSH_WMAC 0xac
+#define QCA953X_DDR_REG_FLUSH_GE0 0x9c
+#define QCA953X_DDR_REG_FLUSH_GE1 0xa0
+#define QCA953X_DDR_REG_FLUSH_USB 0xa4
+#define QCA953X_DDR_REG_FLUSH_PCIE 0xa8
+#define QCA953X_DDR_REG_FLUSH_WMAC 0xac
+
/*
* PLL block
*/
#define AR71XX_AHB_DIV_SHIFT 20
#define AR71XX_AHB_DIV_MASK 0x7
+#define AR71XX_ETH0_PLL_SHIFT 17
+#define AR71XX_ETH1_PLL_SHIFT 19
+
#define AR724X_PLL_REG_CPU_CONFIG 0x00
#define AR724X_PLL_REG_PCIE_CONFIG 0x10
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS BIT(16)
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET BIT(25)
+
#define AR724X_PLL_FB_SHIFT 0
#define AR724X_PLL_FB_MASK 0x3ff
#define AR724X_PLL_REF_DIV_SHIFT 10
#define AR724X_DDR_DIV_SHIFT 22
#define AR724X_DDR_DIV_MASK 0x3
+#define AR7242_PLL_REG_ETH0_INT_CLOCK 0x2c
+
#define AR913X_PLL_REG_CPU_CONFIG 0x00
#define AR913X_PLL_REG_ETH_CONFIG 0x04
#define AR913X_PLL_REG_ETH0_INT_CLOCK 0x14
#define AR913X_AHB_DIV_SHIFT 19
#define AR913X_AHB_DIV_MASK 0x1
+#define AR913X_ETH0_PLL_SHIFT 20
+#define AR913X_ETH1_PLL_SHIFT 22
+
#define AR933X_PLL_CPU_CONFIG_REG 0x00
#define AR933X_PLL_CLOCK_CTRL_REG 0x08
#define AR934X_PLL_CPU_CONFIG_REG 0x00
#define AR934X_PLL_DDR_CONFIG_REG 0x04
#define AR934X_PLL_CPU_DDR_CLK_CTRL_REG 0x08
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_REG 0x24
+#define AR934X_PLL_ETH_XMII_CONTROL_REG 0x2c
#define AR934X_PLL_CPU_CONFIG_NFRAC_SHIFT 0
#define AR934X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f
#define AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21)
#define AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24)
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL BIT(6)
+
+#define QCA953X_PLL_CPU_CONFIG_REG 0x00
+#define QCA953X_PLL_DDR_CONFIG_REG 0x04
+#define QCA953X_PLL_CLK_CTRL_REG 0x08
+#define QCA953X_PLL_SWITCH_CLOCK_CONTROL_REG 0x24
+#define QCA953X_PLL_ETH_XMII_CONTROL_REG 0x2c
+#define QCA953X_PLL_ETH_SGMII_CONTROL_REG 0x48
+
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT 0
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f
+#define QCA953X_PLL_CPU_CONFIG_NINT_SHIFT 6
+#define QCA953X_PLL_CPU_CONFIG_NINT_MASK 0x3f
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT 12
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_MASK 0x1f
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT 19
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK 0x7
+
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT 0
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_MASK 0x3ff
+#define QCA953X_PLL_DDR_CONFIG_NINT_SHIFT 10
+#define QCA953X_PLL_DDR_CONFIG_NINT_MASK 0x3f
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT 16
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_MASK 0x1f
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT 23
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK 0x7
+
+#define QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS BIT(2)
+#define QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS BIT(3)
+#define QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS BIT(4)
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT 5
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK 0x1f
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT 10
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK 0x1f
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT 15
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK 0x1f
+#define QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL BIT(20)
+#define QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21)
+#define QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24)
+
#define QCA955X_PLL_CPU_CONFIG_REG 0x00
#define QCA955X_PLL_DDR_CONFIG_REG 0x04
#define QCA955X_PLL_CLK_CTRL_REG 0x08
+#define QCA955X_PLL_ETH_XMII_CONTROL_REG 0x28
+#define QCA955X_PLL_ETH_SGMII_CONTROL_REG 0x48
+#define QCA955X_PLL_ETH_SGMII_SERDES_REG 0x4c
#define QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT 0
#define QCA955X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f
#define QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21)
#define QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24)
+#define QCA955X_PLL_ETH_SGMII_SERDES_LOCK_DETECT BIT(2)
+#define QCA955X_PLL_ETH_SGMII_SERDES_PLL_REFCLK BIT(1)
+#define QCA955X_PLL_ETH_SGMII_SERDES_EN_PLL BIT(0)
+
+#define QCA956X_PLL_CPU_CONFIG_REG 0x00
+#define QCA956X_PLL_CPU_CONFIG1_REG 0x04
+#define QCA956X_PLL_DDR_CONFIG_REG 0x08
+#define QCA956X_PLL_DDR_CONFIG1_REG 0x0c
+#define QCA956X_PLL_CLK_CTRL_REG 0x10
+#define QCA956X_PLL_SWITCH_CLOCK_CONTROL_REG 0x28
+#define QCA956X_PLL_ETH_XMII_CONTROL_REG 0x30
+#define QCA956X_PLL_ETH_SGMII_SERDES_REG 0x4c
+
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT 12
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_MASK 0x1f
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT 19
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK 0x7
+
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT 0
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK 0x1f
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT 5
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK 0x1fff
+#define QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT 18
+#define QCA956X_PLL_CPU_CONFIG1_NINT_MASK 0x1ff
+
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT 16
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_MASK 0x1f
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT 23
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK 0x7
+
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT 0
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK 0x1f
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT 5
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK 0x1fff
+#define QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT 18
+#define QCA956X_PLL_DDR_CONFIG1_NINT_MASK 0x1ff
+
+#define QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS BIT(2)
+#define QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS BIT(3)
+#define QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS BIT(4)
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT 5
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK 0x1f
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT 10
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK 0x1f
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT 15
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK 0x1f
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL BIT(20)
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL BIT(21)
+#define QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24)
+
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_I2C_CLK_SELB BIT(5)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_1 BIT(6)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_UART1_CLK_SEL BIT(7)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_SHIFT 8
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_MASK 0xf
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EN_PLL_TOP BIT(12)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_2 BIT(13)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_1 BIT(14)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_2 BIT(15)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCH_FUNC_TST_MODE BIT(16)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EEE_ENABLE BIT(17)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_OEN_CLK125M_PLL BIT(18)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCHCLK_SEL BIT(19)
+
+#define QCA956X_PLL_ETH_XMII_TX_INVERT BIT(1)
+#define QCA956X_PLL_ETH_XMII_GIGE BIT(25)
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_SHIFT 28
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_MASK 0x3
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_SHIFT 26
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_MASK 3
+
+#define QCA956X_PLL_ETH_SGMII_SERDES_LOCK_DETECT BIT(2)
+#define QCA956X_PLL_ETH_SGMII_SERDES_PLL_REFCLK BIT(1)
+#define QCA956X_PLL_ETH_SGMII_SERDES_EN_PLL BIT(0)
+
/*
* USB_CONFIG block
*/
#define AR934X_RESET_REG_BOOTSTRAP 0xb0
#define AR934X_RESET_REG_PCIE_WMAC_INT_STATUS 0xac
+#define QCA953X_RESET_REG_RESET_MODULE 0x1c
+#define QCA953X_RESET_REG_BOOTSTRAP 0xb0
+#define QCA953X_RESET_REG_PCIE_WMAC_INT_STATUS 0xac
+
#define QCA955X_RESET_REG_RESET_MODULE 0x1c
#define QCA955X_RESET_REG_BOOTSTRAP 0xb0
#define QCA955X_RESET_REG_EXT_INT_STATUS 0xac
+#define QCA956X_RESET_REG_RESET_MODULE 0x1c
+#define QCA956X_RESET_REG_BOOTSTRAP 0xb0
+#define QCA956X_RESET_REG_EXT_INT_STATUS 0xac
+
+#define MISC_INT_MIPS_SI_TIMERINT_MASK BIT(28)
#define MISC_INT_ETHSW BIT(12)
#define MISC_INT_TIMER4 BIT(10)
#define MISC_INT_TIMER3 BIT(9)
#define AR913X_RESET_USB_HOST BIT(5)
#define AR913X_RESET_USB_PHY BIT(4)
+#define AR933X_RESET_GE1_MDIO BIT(23)
+#define AR933X_RESET_GE0_MDIO BIT(22)
+#define AR933X_RESET_GE1_MAC BIT(13)
#define AR933X_RESET_WMAC BIT(11)
+#define AR933X_RESET_GE0_MAC BIT(9)
#define AR933X_RESET_USB_HOST BIT(5)
#define AR933X_RESET_USB_PHY BIT(4)
#define AR933X_RESET_USBSUS_OVERRIDE BIT(3)
+#define AR934X_RESET_HOST BIT(31)
+#define AR934X_RESET_SLIC BIT(30)
+#define AR934X_RESET_HDMA BIT(29)
+#define AR934X_RESET_EXTERNAL BIT(28)
+#define AR934X_RESET_RTC BIT(27)
+#define AR934X_RESET_PCIE_EP_INT BIT(26)
+#define AR934X_RESET_CHKSUM_ACC BIT(25)
+#define AR934X_RESET_FULL_CHIP BIT(24)
+#define AR934X_RESET_GE1_MDIO BIT(23)
+#define AR934X_RESET_GE0_MDIO BIT(22)
+#define AR934X_RESET_CPU_NMI BIT(21)
+#define AR934X_RESET_CPU_COLD BIT(20)
+#define AR934X_RESET_HOST_RESET_INT BIT(19)
+#define AR934X_RESET_PCIE_EP BIT(18)
+#define AR934X_RESET_UART1 BIT(17)
+#define AR934X_RESET_DDR BIT(16)
+#define AR934X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define AR934X_RESET_NANDF BIT(14)
+#define AR934X_RESET_GE1_MAC BIT(13)
+#define AR934X_RESET_ETH_SWITCH_ANALOG BIT(12)
#define AR934X_RESET_USB_PHY_ANALOG BIT(11)
+#define AR934X_RESET_HOST_DMA_INT BIT(10)
+#define AR934X_RESET_GE0_MAC BIT(9)
+#define AR934X_RESET_ETH_SWITCH BIT(8)
+#define AR934X_RESET_PCIE_PHY BIT(7)
+#define AR934X_RESET_PCIE BIT(6)
#define AR934X_RESET_USB_HOST BIT(5)
#define AR934X_RESET_USB_PHY BIT(4)
#define AR934X_RESET_USBSUS_OVERRIDE BIT(3)
-
+#define AR934X_RESET_LUT BIT(2)
+#define AR934X_RESET_MBOX BIT(1)
+#define AR934X_RESET_I2S BIT(0)
+
+#define QCA953X_RESET_USB_EXT_PWR BIT(29)
+#define QCA953X_RESET_EXTERNAL BIT(28)
+#define QCA953X_RESET_RTC BIT(27)
+#define QCA953X_RESET_FULL_CHIP BIT(24)
+#define QCA953X_RESET_GE1_MDIO BIT(23)
+#define QCA953X_RESET_GE0_MDIO BIT(22)
+#define QCA953X_RESET_CPU_NMI BIT(21)
+#define QCA953X_RESET_CPU_COLD BIT(20)
+#define QCA953X_RESET_DDR BIT(16)
+#define QCA953X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA953X_RESET_GE1_MAC BIT(13)
+#define QCA953X_RESET_ETH_SWITCH_ANALOG BIT(12)
+#define QCA953X_RESET_USB_PHY_ANALOG BIT(11)
+#define QCA953X_RESET_GE0_MAC BIT(9)
+#define QCA953X_RESET_ETH_SWITCH BIT(8)
+#define QCA953X_RESET_PCIE_PHY BIT(7)
+#define QCA953X_RESET_PCIE BIT(6)
+#define QCA953X_RESET_USB_HOST BIT(5)
+#define QCA953X_RESET_USB_PHY BIT(4)
+#define QCA953X_RESET_USBSUS_OVERRIDE BIT(3)
+
+#define QCA955X_RESET_HOST BIT(31)
+#define QCA955X_RESET_SLIC BIT(30)
+#define QCA955X_RESET_HDMA BIT(29)
+#define QCA955X_RESET_EXTERNAL BIT(28)
+#define QCA955X_RESET_RTC BIT(27)
+#define QCA955X_RESET_PCIE_EP_INT BIT(26)
+#define QCA955X_RESET_CHKSUM_ACC BIT(25)
+#define QCA955X_RESET_FULL_CHIP BIT(24)
+#define QCA955X_RESET_GE1_MDIO BIT(23)
+#define QCA955X_RESET_GE0_MDIO BIT(22)
+#define QCA955X_RESET_CPU_NMI BIT(21)
+#define QCA955X_RESET_CPU_COLD BIT(20)
+#define QCA955X_RESET_HOST_RESET_INT BIT(19)
+#define QCA955X_RESET_PCIE_EP BIT(18)
+#define QCA955X_RESET_UART1 BIT(17)
+#define QCA955X_RESET_DDR BIT(16)
+#define QCA955X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA955X_RESET_NANDF BIT(14)
+#define QCA955X_RESET_GE1_MAC BIT(13)
+#define QCA955X_RESET_SGMII_ANALOG BIT(12)
+#define QCA955X_RESET_USB_PHY_ANALOG BIT(11)
+#define QCA955X_RESET_HOST_DMA_INT BIT(10)
+#define QCA955X_RESET_GE0_MAC BIT(9)
+#define QCA955X_RESET_SGMII BIT(8)
+#define QCA955X_RESET_PCIE_PHY BIT(7)
+#define QCA955X_RESET_PCIE BIT(6)
+#define QCA955X_RESET_USB_HOST BIT(5)
+#define QCA955X_RESET_USB_PHY BIT(4)
+#define QCA955X_RESET_USBSUS_OVERRIDE BIT(3)
+#define QCA955X_RESET_LUT BIT(2)
+#define QCA955X_RESET_MBOX BIT(1)
+#define QCA955X_RESET_I2S BIT(0)
+
+#define QCA956X_RESET_EXTERNAL BIT(28)
+#define QCA956X_RESET_FULL_CHIP BIT(24)
+#define QCA956X_RESET_GE1_MDIO BIT(23)
+#define QCA956X_RESET_GE0_MDIO BIT(22)
+#define QCA956X_RESET_CPU_NMI BIT(21)
+#define QCA956X_RESET_CPU_COLD BIT(20)
+#define QCA956X_RESET_DMA BIT(19)
+#define QCA956X_RESET_DDR BIT(16)
+#define QCA956X_RESET_GE1_MAC BIT(13)
+#define QCA956X_RESET_SGMII_ANALOG BIT(12)
+#define QCA956X_RESET_USB_PHY_ANALOG BIT(11)
+#define QCA956X_RESET_GE0_MAC BIT(9)
+#define QCA956X_RESET_SGMII BIT(8)
+#define QCA956X_RESET_USB_HOST BIT(5)
+#define QCA956X_RESET_USB_PHY BIT(4)
+#define QCA956X_RESET_USBSUS_OVERRIDE BIT(3)
+#define QCA956X_RESET_SWITCH_ANALOG BIT(2)
+#define QCA956X_RESET_SWITCH BIT(0)
+
+#define AR933X_BOOTSTRAP_MDIO_GPIO_EN BIT(18)
+#define AR933X_BOOTSTRAP_EEPBUSY BIT(4)
#define AR933X_BOOTSTRAP_REF_CLK_40 BIT(0)
#define AR934X_BOOTSTRAP_SW_OPTION8 BIT(23)
#define AR934X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
#define AR934X_BOOTSTRAP_DDR1 BIT(0)
+#define QCA953X_BOOTSTRAP_SW_OPTION2 BIT(12)
+#define QCA953X_BOOTSTRAP_SW_OPTION1 BIT(11)
+#define QCA953X_BOOTSTRAP_EJTAG_MODE BIT(5)
+#define QCA953X_BOOTSTRAP_REF_CLK_40 BIT(4)
+#define QCA953X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
+#define QCA953X_BOOTSTRAP_DDR1 BIT(0)
+
#define QCA955X_BOOTSTRAP_REF_CLK_40 BIT(4)
+#define QCA956X_BOOTSTRAP_REF_CLK_40 BIT(2)
+
#define AR934X_PCIE_WMAC_INT_WMAC_MISC BIT(0)
#define AR934X_PCIE_WMAC_INT_WMAC_TX BIT(1)
#define AR934X_PCIE_WMAC_INT_WMAC_RXLP BIT(2)
AR934X_PCIE_WMAC_INT_PCIE_RC1 | AR934X_PCIE_WMAC_INT_PCIE_RC2 | \
AR934X_PCIE_WMAC_INT_PCIE_RC3)
+#define QCA953X_PCIE_WMAC_INT_WMAC_MISC BIT(0)
+#define QCA953X_PCIE_WMAC_INT_WMAC_TX BIT(1)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXLP BIT(2)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXHP BIT(3)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC BIT(4)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC0 BIT(5)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC1 BIT(6)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC2 BIT(7)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC3 BIT(8)
+#define QCA953X_PCIE_WMAC_INT_WMAC_ALL \
+ (QCA953X_PCIE_WMAC_INT_WMAC_MISC | QCA953X_PCIE_WMAC_INT_WMAC_TX | \
+ QCA953X_PCIE_WMAC_INT_WMAC_RXLP | QCA953X_PCIE_WMAC_INT_WMAC_RXHP)
+
+#define QCA953X_PCIE_WMAC_INT_PCIE_ALL \
+ (QCA953X_PCIE_WMAC_INT_PCIE_RC | QCA953X_PCIE_WMAC_INT_PCIE_RC0 | \
+ QCA953X_PCIE_WMAC_INT_PCIE_RC1 | QCA953X_PCIE_WMAC_INT_PCIE_RC2 | \
+ QCA953X_PCIE_WMAC_INT_PCIE_RC3)
+
#define QCA955X_EXT_INT_WMAC_MISC BIT(0)
#define QCA955X_EXT_INT_WMAC_TX BIT(1)
#define QCA955X_EXT_INT_WMAC_RXLP BIT(2)
QCA955X_EXT_INT_PCIE_RC2_INT1 | QCA955X_EXT_INT_PCIE_RC2_INT2 | \
QCA955X_EXT_INT_PCIE_RC2_INT3)
+#define QCA956X_EXT_INT_WMAC_MISC BIT(0)
+#define QCA956X_EXT_INT_WMAC_TX BIT(1)
+#define QCA956X_EXT_INT_WMAC_RXLP BIT(2)
+#define QCA956X_EXT_INT_WMAC_RXHP BIT(3)
+#define QCA956X_EXT_INT_PCIE_RC1 BIT(4)
+#define QCA956X_EXT_INT_PCIE_RC1_INT0 BIT(5)
+#define QCA956X_EXT_INT_PCIE_RC1_INT1 BIT(6)
+#define QCA956X_EXT_INT_PCIE_RC1_INT2 BIT(7)
+#define QCA956X_EXT_INT_PCIE_RC1_INT3 BIT(8)
+#define QCA956X_EXT_INT_PCIE_RC2 BIT(12)
+#define QCA956X_EXT_INT_PCIE_RC2_INT0 BIT(13)
+#define QCA956X_EXT_INT_PCIE_RC2_INT1 BIT(14)
+#define QCA956X_EXT_INT_PCIE_RC2_INT2 BIT(15)
+#define QCA956X_EXT_INT_PCIE_RC2_INT3 BIT(16)
+#define QCA956X_EXT_INT_USB1 BIT(24)
+#define QCA956X_EXT_INT_USB2 BIT(28)
+
+#define QCA956X_EXT_INT_WMAC_ALL \
+ (QCA956X_EXT_INT_WMAC_MISC | QCA956X_EXT_INT_WMAC_TX | \
+ QCA956X_EXT_INT_WMAC_RXLP | QCA956X_EXT_INT_WMAC_RXHP)
+
+#define QCA956X_EXT_INT_PCIE_RC1_ALL \
+ (QCA956X_EXT_INT_PCIE_RC1 | QCA956X_EXT_INT_PCIE_RC1_INT0 | \
+ QCA956X_EXT_INT_PCIE_RC1_INT1 | QCA956X_EXT_INT_PCIE_RC1_INT2 | \
+ QCA956X_EXT_INT_PCIE_RC1_INT3)
+
+#define QCA956X_EXT_INT_PCIE_RC2_ALL \
+ (QCA956X_EXT_INT_PCIE_RC2 | QCA956X_EXT_INT_PCIE_RC2_INT0 | \
+ QCA956X_EXT_INT_PCIE_RC2_INT1 | QCA956X_EXT_INT_PCIE_RC2_INT2 | \
+ QCA956X_EXT_INT_PCIE_RC2_INT3)
+
#define REV_ID_MAJOR_MASK 0xfff0
#define REV_ID_MAJOR_AR71XX 0x00a0
#define REV_ID_MAJOR_AR913X 0x00b0
#define REV_ID_MAJOR_AR9341 0x0120
#define REV_ID_MAJOR_AR9342 0x1120
#define REV_ID_MAJOR_AR9344 0x2120
+#define REV_ID_MAJOR_QCA9533 0x0140
+#define REV_ID_MAJOR_QCA9533_V2 0x0160
#define REV_ID_MAJOR_QCA9556 0x0130
#define REV_ID_MAJOR_QCA9558 0x1130
+#define REV_ID_MAJOR_TP9343 0x0150
+#define REV_ID_MAJOR_QCA956X 0x1150
#define AR71XX_REV_ID_MINOR_MASK 0x3
#define AR71XX_REV_ID_MINOR_AR7130 0x0
#define AR934X_REV_ID_REVISION_MASK 0xf
+#define QCA953X_REV_ID_REVISION_MASK 0xf
+
#define QCA955X_REV_ID_REVISION_MASK 0xf
+#define QCA956X_REV_ID_REVISION_MASK 0xf
+
/*
* SPI block
*/
#define AR71XX_GPIO_REG_INT_ENABLE 0x24
#define AR71XX_GPIO_REG_FUNC 0x28
+#define AR934X_GPIO_REG_OUT_FUNC0 0x2c
+#define AR934X_GPIO_REG_OUT_FUNC1 0x30
+#define AR934X_GPIO_REG_OUT_FUNC2 0x34
+#define AR934X_GPIO_REG_OUT_FUNC3 0x38
+#define AR934X_GPIO_REG_OUT_FUNC4 0x3c
+#define AR934X_GPIO_REG_OUT_FUNC5 0x40
#define AR934X_GPIO_REG_FUNC 0x6c
+#define QCA953X_GPIO_REG_OUT_FUNC0 0x2c
+#define QCA953X_GPIO_REG_OUT_FUNC1 0x30
+#define QCA953X_GPIO_REG_OUT_FUNC2 0x34
+#define QCA953X_GPIO_REG_OUT_FUNC3 0x38
+#define QCA953X_GPIO_REG_OUT_FUNC4 0x3c
+#define QCA953X_GPIO_REG_IN_ENABLE0 0x44
+#define QCA953X_GPIO_REG_FUNC 0x6c
+
+#define QCA953X_GPIO_OUT_MUX_SPI_CS1 10
+#define QCA953X_GPIO_OUT_MUX_SPI_CS2 11
+#define QCA953X_GPIO_OUT_MUX_SPI_CS0 9
+#define QCA953X_GPIO_OUT_MUX_SPI_CLK 8
+#define QCA953X_GPIO_OUT_MUX_SPI_MOSI 12
+#define QCA953X_GPIO_OUT_MUX_LED_LINK1 41
+#define QCA953X_GPIO_OUT_MUX_LED_LINK2 42
+#define QCA953X_GPIO_OUT_MUX_LED_LINK3 43
+#define QCA953X_GPIO_OUT_MUX_LED_LINK4 44
+#define QCA953X_GPIO_OUT_MUX_LED_LINK5 45
+
+#define QCA955X_GPIO_REG_OUT_FUNC0 0x2c
+#define QCA955X_GPIO_REG_OUT_FUNC1 0x30
+#define QCA955X_GPIO_REG_OUT_FUNC2 0x34
+#define QCA955X_GPIO_REG_OUT_FUNC3 0x38
+#define QCA955X_GPIO_REG_OUT_FUNC4 0x3c
+#define QCA955X_GPIO_REG_OUT_FUNC5 0x40
+#define QCA955X_GPIO_REG_FUNC 0x6c
+
+#define QCA956X_GPIO_REG_OUT_FUNC0 0x2c
+#define QCA956X_GPIO_REG_OUT_FUNC1 0x30
+#define QCA956X_GPIO_REG_OUT_FUNC2 0x34
+#define QCA956X_GPIO_REG_OUT_FUNC3 0x38
+#define QCA956X_GPIO_REG_OUT_FUNC4 0x3c
+#define QCA956X_GPIO_REG_OUT_FUNC5 0x40
+#define QCA956X_GPIO_REG_IN_ENABLE0 0x44
+#define QCA956X_GPIO_REG_IN_ENABLE3 0x50
+#define QCA956X_GPIO_REG_FUNC 0x6c
+
+#define QCA956X_GPIO_OUT_MUX_GE0_MDO 32
+#define QCA956X_GPIO_OUT_MUX_GE0_MDC 33
+
#define AR71XX_GPIO_COUNT 16
#define AR7240_GPIO_COUNT 18
#define AR7241_GPIO_COUNT 20
#define AR913X_GPIO_COUNT 22
#define AR933X_GPIO_COUNT 30
#define AR934X_GPIO_COUNT 23
+#define QCA953X_GPIO_COUNT 18
#define QCA955X_GPIO_COUNT 24
+#define QCA956X_GPIO_COUNT 23
/*
* SRIF block
#define AR934X_SRIF_DPLL2_OUTDIV_SHIFT 13
#define AR934X_SRIF_DPLL2_OUTDIV_MASK 0x7
+#define QCA953X_SRIF_CPU_DPLL1_REG 0x1c0
+#define QCA953X_SRIF_CPU_DPLL2_REG 0x1c4
+#define QCA953X_SRIF_CPU_DPLL3_REG 0x1c8
+
+#define QCA953X_SRIF_DDR_DPLL1_REG 0x240
+#define QCA953X_SRIF_DDR_DPLL2_REG 0x244
+#define QCA953X_SRIF_DDR_DPLL3_REG 0x248
+
+#define QCA953X_SRIF_DPLL1_REFDIV_SHIFT 27
+#define QCA953X_SRIF_DPLL1_REFDIV_MASK 0x1f
+#define QCA953X_SRIF_DPLL1_NINT_SHIFT 18
+#define QCA953X_SRIF_DPLL1_NINT_MASK 0x1ff
+#define QCA953X_SRIF_DPLL1_NFRAC_MASK 0x0003ffff
+
+#define QCA953X_SRIF_DPLL2_LOCAL_PLL BIT(30)
+#define QCA953X_SRIF_DPLL2_OUTDIV_SHIFT 13
+#define QCA953X_SRIF_DPLL2_OUTDIV_MASK 0x7
+
+#define AR71XX_GPIO_FUNC_STEREO_EN BIT(17)
+#define AR71XX_GPIO_FUNC_SLIC_EN BIT(16)
+#define AR71XX_GPIO_FUNC_SPI_CS2_EN BIT(13)
+#define AR71XX_GPIO_FUNC_SPI_CS1_EN BIT(12)
+#define AR71XX_GPIO_FUNC_UART_EN BIT(8)
+#define AR71XX_GPIO_FUNC_USB_OC_EN BIT(4)
+#define AR71XX_GPIO_FUNC_USB_CLK_EN BIT(0)
+
+#define AR724X_GPIO_FUNC_GE0_MII_CLK_EN BIT(19)
+#define AR724X_GPIO_FUNC_SPI_EN BIT(18)
+#define AR724X_GPIO_FUNC_SPI_CS_EN2 BIT(14)
+#define AR724X_GPIO_FUNC_SPI_CS_EN1 BIT(13)
+#define AR724X_GPIO_FUNC_CLK_OBS5_EN BIT(12)
+#define AR724X_GPIO_FUNC_CLK_OBS4_EN BIT(11)
+#define AR724X_GPIO_FUNC_CLK_OBS3_EN BIT(10)
+#define AR724X_GPIO_FUNC_CLK_OBS2_EN BIT(9)
+#define AR724X_GPIO_FUNC_CLK_OBS1_EN BIT(8)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED4_EN BIT(7)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED3_EN BIT(6)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED2_EN BIT(5)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED1_EN BIT(4)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED0_EN BIT(3)
+#define AR724X_GPIO_FUNC_UART_RTS_CTS_EN BIT(2)
+#define AR724X_GPIO_FUNC_UART_EN BIT(1)
+#define AR724X_GPIO_FUNC_JTAG_DISABLE BIT(0)
+
+#define AR913X_GPIO_FUNC_WMAC_LED_EN BIT(22)
+#define AR913X_GPIO_FUNC_EXP_PORT_CS_EN BIT(21)
+#define AR913X_GPIO_FUNC_I2S_REFCLKEN BIT(20)
+#define AR913X_GPIO_FUNC_I2S_MCKEN BIT(19)
+#define AR913X_GPIO_FUNC_I2S1_EN BIT(18)
+#define AR913X_GPIO_FUNC_I2S0_EN BIT(17)
+#define AR913X_GPIO_FUNC_SLIC_EN BIT(16)
+#define AR913X_GPIO_FUNC_UART_RTSCTS_EN BIT(9)
+#define AR913X_GPIO_FUNC_UART_EN BIT(8)
+#define AR913X_GPIO_FUNC_USB_CLK_EN BIT(4)
+
+#define AR933X_GPIO_FUNC_SPDIF2TCK BIT(31)
+#define AR933X_GPIO_FUNC_SPDIF_EN BIT(30)
+#define AR933X_GPIO_FUNC_I2SO_22_18_EN BIT(29)
+#define AR933X_GPIO_FUNC_I2S_MCK_EN BIT(27)
+#define AR933X_GPIO_FUNC_I2SO_EN BIT(26)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_DUPL BIT(25)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_COLL BIT(24)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_ACT BIT(23)
+#define AR933X_GPIO_FUNC_SPI_EN BIT(18)
+#define AR933X_GPIO_FUNC_SPI_CS_EN2 BIT(14)
+#define AR933X_GPIO_FUNC_SPI_CS_EN1 BIT(13)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED4_EN BIT(7)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED3_EN BIT(6)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED2_EN BIT(5)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED1_EN BIT(4)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED0_EN BIT(3)
+#define AR933X_GPIO_FUNC_UART_RTS_CTS_EN BIT(2)
+#define AR933X_GPIO_FUNC_UART_EN BIT(1)
+#define AR933X_GPIO_FUNC_JTAG_DISABLE BIT(0)
+
+#define AR934X_GPIO_FUNC_CLK_OBS7_EN BIT(9)
+#define AR934X_GPIO_FUNC_CLK_OBS6_EN BIT(8)
+#define AR934X_GPIO_FUNC_CLK_OBS5_EN BIT(7)
+#define AR934X_GPIO_FUNC_CLK_OBS4_EN BIT(6)
+#define AR934X_GPIO_FUNC_CLK_OBS3_EN BIT(5)
+#define AR934X_GPIO_FUNC_CLK_OBS2_EN BIT(4)
+#define AR934X_GPIO_FUNC_CLK_OBS1_EN BIT(3)
+#define AR934X_GPIO_FUNC_CLK_OBS0_EN BIT(2)
+#define AR934X_GPIO_FUNC_JTAG_DISABLE BIT(1)
+
+#define AR934X_GPIO_OUT_GPIO 0
+#define AR934X_GPIO_OUT_SPI_CS1 7
+#define AR934X_GPIO_OUT_LED_LINK0 41
+#define AR934X_GPIO_OUT_LED_LINK1 42
+#define AR934X_GPIO_OUT_LED_LINK2 43
+#define AR934X_GPIO_OUT_LED_LINK3 44
+#define AR934X_GPIO_OUT_LED_LINK4 45
+#define AR934X_GPIO_OUT_EXT_LNA0 46
+#define AR934X_GPIO_OUT_EXT_LNA1 47
+
+#define QCA955X_GPIO_FUNC_CLK_OBS7_EN BIT(9)
+#define QCA955X_GPIO_FUNC_CLK_OBS6_EN BIT(8)
+#define QCA955X_GPIO_FUNC_CLK_OBS5_EN BIT(7)
+#define QCA955X_GPIO_FUNC_CLK_OBS4_EN BIT(6)
+#define QCA955X_GPIO_FUNC_CLK_OBS3_EN BIT(5)
+#define QCA955X_GPIO_FUNC_CLK_OBS2_EN BIT(4)
+#define QCA955X_GPIO_FUNC_CLK_OBS1_EN BIT(3)
+#define QCA955X_GPIO_FUNC_JTAG_DISABLE BIT(1)
+
+#define QCA955X_GPIO_OUT_GPIO 0
+#define QCA955X_MII_EXT_MDI 1
+#define QCA955X_SLIC_DATA_OUT 3
+#define QCA955X_SLIC_PCM_FS 4
+#define QCA955X_SLIC_PCM_CLK 5
+#define QCA955X_SPI_CLK 8
+#define QCA955X_SPI_CS_0 9
+#define QCA955X_SPI_CS_1 10
+#define QCA955X_SPI_CS_2 11
+#define QCA955X_SPI_MISO 12
+#define QCA955X_I2S_CLK 13
+#define QCA955X_I2S_WS 14
+#define QCA955X_I2S_SD 15
+#define QCA955X_I2S_MCK 16
+#define QCA955X_SPDIF_OUT 17
+#define QCA955X_UART1_TD 18
+#define QCA955X_UART1_RTS 19
+#define QCA955X_UART1_RD 20
+#define QCA955X_UART1_CTS 21
+#define QCA955X_UART0_SOUT 22
+#define QCA955X_SPDIF2_OUT 23
+#define QCA955X_LED_SGMII_SPEED0 24
+#define QCA955X_LED_SGMII_SPEED1 25
+#define QCA955X_LED_SGMII_DUPLEX 26
+#define QCA955X_LED_SGMII_LINK_UP 27
+#define QCA955X_SGMII_SPEED0_INVERT 28
+#define QCA955X_SGMII_SPEED1_INVERT 29
+#define QCA955X_SGMII_DUPLEX_INVERT 30
+#define QCA955X_SGMII_LINK_UP_INVERT 31
+#define QCA955X_GE1_MII_MDO 32
+#define QCA955X_GE1_MII_MDC 33
+#define QCA955X_SWCOM2 38
+#define QCA955X_SWCOM3 39
+#define QCA955X_MAC2_GPIO 40
+#define QCA955X_MAC3_GPIO 41
+#define QCA955X_ATT_LED 42
+#define QCA955X_PWR_LED 43
+#define QCA955X_TX_FRAME 44
+#define QCA955X_RX_CLEAR_EXTERNAL 45
+#define QCA955X_LED_NETWORK_EN 46
+#define QCA955X_LED_POWER_EN 47
+#define QCA955X_WMAC_GLUE_WOW 68
+#define QCA955X_RX_CLEAR_EXTENSION 70
+#define QCA955X_CP_NAND_CS1 73
+#define QCA955X_USB_SUSPEND 74
+#define QCA955X_ETH_TX_ERR 75
+#define QCA955X_DDR_DQ_OE 76
+#define QCA955X_CLKREQ_N_EP 77
+#define QCA955X_CLKREQ_N_RC 78
+#define QCA955X_CLK_OBS0 79
+#define QCA955X_CLK_OBS1 80
+#define QCA955X_CLK_OBS2 81
+#define QCA955X_CLK_OBS3 82
+#define QCA955X_CLK_OBS4 83
+#define QCA955X_CLK_OBS5 84
+
+/*
+ * MII_CTRL block
+ */
+#define AR71XX_MII_REG_MII0_CTRL 0x00
+#define AR71XX_MII_REG_MII1_CTRL 0x04
+
+#define AR71XX_MII_CTRL_IF_MASK 3
+#define AR71XX_MII_CTRL_SPEED_SHIFT 4
+#define AR71XX_MII_CTRL_SPEED_MASK 3
+#define AR71XX_MII_CTRL_SPEED_10 0
+#define AR71XX_MII_CTRL_SPEED_100 1
+#define AR71XX_MII_CTRL_SPEED_1000 2
+
+#define AR71XX_MII0_CTRL_IF_GMII 0
+#define AR71XX_MII0_CTRL_IF_MII 1
+#define AR71XX_MII0_CTRL_IF_RGMII 2
+#define AR71XX_MII0_CTRL_IF_RMII 3
+
+#define AR71XX_MII1_CTRL_IF_RGMII 0
+#define AR71XX_MII1_CTRL_IF_RMII 1
+
+/*
+ * AR933X GMAC interface
+ */
+#define AR933X_GMAC_REG_ETH_CFG 0x00
+
+#define AR933X_ETH_CFG_RGMII_GE0 BIT(0)
+#define AR933X_ETH_CFG_MII_GE0 BIT(1)
+#define AR933X_ETH_CFG_GMII_GE0 BIT(2)
+#define AR933X_ETH_CFG_MII_GE0_MASTER BIT(3)
+#define AR933X_ETH_CFG_MII_GE0_SLAVE BIT(4)
+#define AR933X_ETH_CFG_MII_GE0_ERR_EN BIT(5)
+#define AR933X_ETH_CFG_SW_PHY_SWAP BIT(7)
+#define AR933X_ETH_CFG_SW_PHY_ADDR_SWAP BIT(8)
+#define AR933X_ETH_CFG_RMII_GE0 BIT(9)
+#define AR933X_ETH_CFG_RMII_GE0_SPD_10 0
+#define AR933X_ETH_CFG_RMII_GE0_SPD_100 BIT(10)
+
+/*
+ * AR934X GMAC Interface
+ */
+#define AR934X_GMAC_REG_ETH_CFG 0x00
+
+#define AR934X_ETH_CFG_RGMII_GMAC0 BIT(0)
+#define AR934X_ETH_CFG_MII_GMAC0 BIT(1)
+#define AR934X_ETH_CFG_GMII_GMAC0 BIT(2)
+#define AR934X_ETH_CFG_MII_GMAC0_MASTER BIT(3)
+#define AR934X_ETH_CFG_MII_GMAC0_SLAVE BIT(4)
+#define AR934X_ETH_CFG_MII_GMAC0_ERR_EN BIT(5)
+#define AR934X_ETH_CFG_SW_ONLY_MODE BIT(6)
+#define AR934X_ETH_CFG_SW_PHY_SWAP BIT(7)
+#define AR934X_ETH_CFG_SW_APB_ACCESS BIT(9)
+#define AR934X_ETH_CFG_RMII_GMAC0 BIT(10)
+#define AR933X_ETH_CFG_MII_CNTL_SPEED BIT(11)
+#define AR934X_ETH_CFG_RMII_GMAC0_MASTER BIT(12)
+#define AR933X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13)
+#define AR934X_ETH_CFG_RXD_DELAY BIT(14)
+#define AR934X_ETH_CFG_RXD_DELAY_MASK 0x3
+#define AR934X_ETH_CFG_RXD_DELAY_SHIFT 14
+#define AR934X_ETH_CFG_RDV_DELAY BIT(16)
+#define AR934X_ETH_CFG_RDV_DELAY_MASK 0x3
+#define AR934X_ETH_CFG_RDV_DELAY_SHIFT 16
+
+/*
+ * QCA953X GMAC Interface
+ */
+#define QCA953X_GMAC_REG_ETH_CFG 0x00
+
+#define QCA953X_ETH_CFG_SW_ONLY_MODE BIT(6)
+#define QCA953X_ETH_CFG_SW_PHY_SWAP BIT(7)
+#define QCA953X_ETH_CFG_SW_APB_ACCESS BIT(9)
+#define QCA953X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13)
+
+/*
+ * QCA955X GMAC Interface
+ */
+
+#define QCA955X_GMAC_REG_ETH_CFG 0x00
+#define QCA955X_GMAC_REG_SGMII_SERDES 0x18
+
+#define QCA955X_ETH_CFG_RGMII_EN BIT(0)
+#define QCA955X_ETH_CFG_MII_GE0 BIT(1)
+#define QCA955X_ETH_CFG_GMII_GE0 BIT(2)
+#define QCA955X_ETH_CFG_MII_GE0_MASTER BIT(3)
+#define QCA955X_ETH_CFG_MII_GE0_SLAVE BIT(4)
+#define QCA955X_ETH_CFG_GE0_ERR_EN BIT(5)
+#define QCA955X_ETH_CFG_GE0_SGMII BIT(6)
+#define QCA955X_ETH_CFG_RMII_GE0 BIT(10)
+#define QCA955X_ETH_CFG_MII_CNTL_SPEED BIT(11)
+#define QCA955X_ETH_CFG_RMII_GE0_MASTER BIT(12)
+#define QCA955X_ETH_CFG_RXD_DELAY_MASK 0x3
+#define QCA955X_ETH_CFG_RXD_DELAY_SHIFT 14
+#define QCA955X_ETH_CFG_RDV_DELAY BIT(16)
+#define QCA955X_ETH_CFG_RDV_DELAY_MASK 0x3
+#define QCA955X_ETH_CFG_RDV_DELAY_SHIFT 16
+#define QCA955X_ETH_CFG_TXD_DELAY_MASK 0x3
+#define QCA955X_ETH_CFG_TXD_DELAY_SHIFT 18
+#define QCA955X_ETH_CFG_TXE_DELAY_MASK 0x3
+#define QCA955X_ETH_CFG_TXE_DELAY_SHIFT 20
+
+#define QCA955X_SGMII_SERDES_LOCK_DETECT_STATUS BIT(15)
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+/*
+ * QCA956X GMAC Interface
+ */
+
+#define QCA956X_GMAC_REG_ETH_CFG 0x00
+#define QCA956X_GMAC_REG_SGMII_RESET 0x14
+#define QCA956X_GMAC_REG_SGMII_SERDES 0x18
+#define QCA956X_GMAC_REG_MR_AN_CONTROL 0x1c
+#define QCA956X_GMAC_REG_SGMII_CONFIG 0x34
+#define QCA956X_GMAC_REG_SGMII_DEBUG 0x58
+
+#define QCA956X_ETH_CFG_RGMII_EN BIT(0)
+#define QCA956X_ETH_CFG_GE0_SGMII BIT(6)
+#define QCA956X_ETH_CFG_SW_ONLY_MODE BIT(7)
+#define QCA956X_ETH_CFG_SW_PHY_SWAP BIT(8)
+#define QCA956X_ETH_CFG_SW_PHY_ADDR_SWAP BIT(9)
+#define QCA956X_ETH_CFG_SW_APB_ACCESS BIT(10)
+#define QCA956X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13)
+#define QCA956X_ETH_CFG_RXD_DELAY_MASK 0x3
+#define QCA956X_ETH_CFG_RXD_DELAY_SHIFT 14
+#define QCA956X_ETH_CFG_RDV_DELAY_MASK 0x3
+#define QCA956X_ETH_CFG_RDV_DELAY_SHIFT 16
+
+#define QCA956X_SGMII_RESET_RX_CLK_N_RESET 0x0
+#define QCA956X_SGMII_RESET_RX_CLK_N BIT(0)
+#define QCA956X_SGMII_RESET_TX_CLK_N BIT(1)
+#define QCA956X_SGMII_RESET_RX_125M_N BIT(2)
+#define QCA956X_SGMII_RESET_TX_125M_N BIT(3)
+#define QCA956X_SGMII_RESET_HW_RX_125M_N BIT(4)
+
+#define QCA956X_SGMII_SERDES_CDR_BW_MASK 0x3
+#define QCA956X_SGMII_SERDES_CDR_BW_SHIFT 1
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_MASK 0x7
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_SHIFT 4
+#define QCA956X_SGMII_SERDES_PLL_BW BIT(8)
+#define QCA956X_SGMII_SERDES_VCO_FAST BIT(9)
+#define QCA956X_SGMII_SERDES_VCO_SLOW BIT(10)
+#define QCA956X_SGMII_SERDES_LOCK_DETECT_STATUS BIT(15)
+#define QCA956X_SGMII_SERDES_EN_SIGNAL_DETECT BIT(16)
+#define QCA956X_SGMII_SERDES_FIBER_SDO BIT(17)
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+#define QCA956X_SGMII_SERDES_VCO_REG_SHIFT 27
+#define QCA956X_SGMII_SERDES_VCO_REG_MASK 0xf
+
+#define QCA956X_MR_AN_CONTROL_AN_ENABLE BIT(12)
+#define QCA956X_MR_AN_CONTROL_PHY_RESET BIT(15)
+
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_SHIFT 0
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_MASK 0x7
+
#endif /* __ASM_MACH_AR71XX_REGS_H */
ATH79_SOC_AR9341,
ATH79_SOC_AR9342,
ATH79_SOC_AR9344,
+ ATH79_SOC_QCA9533,
ATH79_SOC_QCA9556,
ATH79_SOC_QCA9558,
+ ATH79_SOC_TP9343,
+ ATH79_SOC_QCA956X,
};
extern enum ath79_soc_type ath79_soc;
return soc_is_ar9341() || soc_is_ar9342() || soc_is_ar9344();
}
+static inline int soc_is_qca9533(void)
+{
+ return ath79_soc == ATH79_SOC_QCA9533;
+}
+
+static inline int soc_is_qca953x(void)
+{
+ return soc_is_qca9533();
+}
+
static inline int soc_is_qca9556(void)
{
return ath79_soc == ATH79_SOC_QCA9556;
return soc_is_qca9556() || soc_is_qca9558();
}
+static inline int soc_is_tp9343(void)
+{
+ return ath79_soc == ATH79_SOC_TP9343;
+}
+
+static inline int soc_is_qca9561(void)
+{
+ return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca9563(void)
+{
+ return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca956x(void)
+{
+ return soc_is_qca9561() || soc_is_qca9563();
+}
+
void ath79_ddr_wb_flush(unsigned int reg);
void ath79_ddr_set_pci_windows(void);
static inline void ath79_reset_wr(unsigned reg, u32 val)
{
__raw_writel(val, ath79_reset_base + reg);
+ (void) __raw_readl(ath79_reset_base + reg); /* flush */
}
static inline u32 ath79_reset_rr(unsigned reg)
#define cpu_has_mdmx 0
#define cpu_has_mips3d 0
#define cpu_has_smartmips 0
+#define cpu_has_rixi 0
#define cpu_has_mips32r1 1
#define cpu_has_mips32r2 1
#define cpu_has_mips64r2 0
#define cpu_has_mipsmt 0
+#define cpu_has_userlocal 0
#define cpu_has_64bits 0
#define cpu_has_64bit_zero_reg 0
#define cpu_dcache_line_size() 32
#define cpu_icache_line_size() 32
+#define cpu_has_vtag_icache 0
+#define cpu_has_dc_aliases 1
+#define cpu_has_ic_fills_f_dc 0
+#define cpu_has_pindexed_dcache 0
#endif /* __ASM_MACH_ATH79_CPU_FEATURE_OVERRIDES_H */
+++ /dev/null
-/*
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2009 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#ifndef __ASM_MACH_BMIPS_DMA_COHERENCE_H
-#define __ASM_MACH_BMIPS_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-#include <asm/cpu-type.h>
-#include <asm/cpu.h>
-
-struct device;
-
-extern dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size);
-extern dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page);
-extern unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr);
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
- return 0;
-}
-
-#define plat_post_dma_flush bmips_post_dma_flush
-
-#endif /* __ASM_MACH_BMIPS_DMA_COHERENCE_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- *
- *
- * Similar to mach-generic/dma-coherence.h except
- * plat_device_is_coherent hard coded to return 1.
- *
- */
-#ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-#define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-
-#include <linux/bug.h>
-
-struct device;
-
-extern void octeon_pci_dma_init(void);
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
- size_t size)
-{
- BUG();
- return 0;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
- BUG();
- return 0;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
- BUG();
- return 0;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
- BUG();
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- BUG();
- return 0;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
- return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
- if (!dev->dma_mask)
- return false;
-
- return addr + size - 1 <= *dev->dma_mask;
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-struct dma_map_ops;
-extern const struct dma_map_ops *octeon_pci_dma_map_ops;
-extern char *octeon_swiotlb;
-
-#endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_GENERIC_DMA_COHERENCE_H
-#define __ASM_MACH_GENERIC_DMA_COHERENCE_H
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
- size_t size)
-{
- return virt_to_phys(addr);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
- return page_to_phys(page);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
- return dma_addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_PERDEV_COHERENT
- return dev->archdata.dma_coherent;
-#else
- switch (coherentio) {
- default:
- case IO_COHERENCE_DEFAULT:
- return hw_coherentio;
- case IO_COHERENCE_ENABLED:
- return 1;
- case IO_COHERENCE_DISABLED:
- return 0;
- }
-#endif
-}
-
-#ifndef plat_post_dma_flush
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-#endif
-
-#endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */
#ifndef __ASM_MACH_GENERIC_KMALLOC_H
#define __ASM_MACH_GENERIC_KMALLOC_H
-
-#ifndef CONFIG_DMA_COHERENT
+#ifdef CONFIG_DMA_NONCOHERENT
/*
* Total overkill for most systems but need as a safe default.
* Set this one if any device in the system might do non-coherent DMA.
/*
* This gives the physical RAM offset.
*/
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET _AC(0, UL)
-#endif
+#ifndef __ASSEMBLY__
+# if defined(CONFIG_MIPS_AUTO_PFN_OFFSET)
+# define PHYS_OFFSET ((unsigned long)PFN_PHYS(ARCH_PFN_OFFSET))
+# elif !defined(PHYS_OFFSET)
+# define PHYS_OFFSET _AC(0, UL)
+# endif
+#endif /* __ASSEMBLY__ */
#ifdef CONFIG_32BIT
#ifdef CONFIG_KVM_GUEST
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP27_DMA_COHERENCE_H
-#define __ASM_MACH_IP27_DMA_COHERENCE_H
-
-#include <asm/pci/bridge.h>
-
-#define pdev_to_baddr(pdev, addr) \
- (BRIDGE_CONTROLLER(pdev->bus)->baddr + (addr))
-#define dev_to_baddr(dev, addr) \
- pdev_to_baddr(to_pci_dev(dev), (addr))
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
- size_t size)
-{
- dma_addr_t pa = dev_to_baddr(dev, virt_to_phys(addr));
-
- return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
- dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page));
-
- return pa;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
- return dma_addr & ~(0xffUL << 56);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
- return 1; /* IP27 non-coherent mode is unsupported */
-}
-
-#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP32_DMA_COHERENCE_H
-#define __ASM_MACH_IP32_DMA_COHERENCE_H
-
-#include <asm/ip32/crime.h>
-
-struct device;
-
-/*
- * Few notes.
- * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
- * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
- * native-endian)
- * 3. All other devices see memory as one big chunk at 0x40000000
- * 4. Non-PCI devices will pass NULL as struct device*
- *
- * Thus we translate differently, depending on device.
- */
-
-#define RAM_OFFSET_MASK 0x3fffffffUL
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
- size_t size)
-{
- dma_addr_t pa = virt_to_phys(addr) & RAM_OFFSET_MASK;
-
- if (dev == NULL)
- pa += CRIME_HI_MEM_BASE;
-
- return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
- dma_addr_t pa;
-
- pa = page_to_phys(page) & RAM_OFFSET_MASK;
-
- if (dev == NULL)
- pa += CRIME_HI_MEM_BASE;
-
- return pa;
-}
-
-/* This is almost certainly wrong but it's what dma-ip32.c used to use */
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
- unsigned long addr = dma_addr & RAM_OFFSET_MASK;
-
- if (dma_addr >= 256*1024*1024)
- addr += CRIME_HI_MEM_BASE;
-
- return addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
- return 0; /* IP32 is non-coherent */
-}
-
-#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MACH_JAZZ_DMA_COHERENCE_H
-#define __ASM_MACH_JAZZ_DMA_COHERENCE_H
-
-#include <asm/jazzdma.h>
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
- return vdma_alloc(virt_to_phys(addr), size);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
- return vdma_alloc(page_to_phys(page), PAGE_SIZE);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
- return vdma_log2phys(dma_addr);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
- vdma_free(dma_addr);
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
- return 0;
-}
-
-#endif /* __ASM_MACH_JAZZ_DMA_COHERENCE_H */
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006, 07 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
- * Author: Fuxin Zhang, zhangfx@lemote.com
- *
- */
-#ifndef __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-#define __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-
-#ifdef CONFIG_SWIOTLB
-#include <linux/swiotlb.h>
-#endif
-
-struct device;
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
- if (!dev->dma_mask)
- return false;
-
- return addr + size - 1 <= *dev->dma_mask;
-}
-
-extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
- size_t size)
-{
-#ifdef CONFIG_CPU_LOONGSON3
- return __phys_to_dma(dev, virt_to_phys(addr));
-#else
- return virt_to_phys(addr) | 0x80000000;
-#endif
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
- struct page *page)
-{
-#ifdef CONFIG_CPU_LOONGSON3
- return __phys_to_dma(dev, page_to_phys(page));
-#else
- return page_to_phys(page) | 0x80000000;
-#endif
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
- dma_addr_t dma_addr)
-{
-#if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
- return __dma_to_phys(dev, dma_addr);
-#elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
- return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
-#else
- return dma_addr & 0x7fffffff;
-#endif
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
- return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_NONCOHERENT
- return 0;
-#else
- return 1;
-#endif /* CONFIG_DMA_NONCOHERENT */
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_LOONGSON64_DMA_COHERENCE_H */
.set push
.set mips64
/* Set LPA on LOONGSON3 config3 */
- mfc0 t0, $16, 3
+ mfc0 t0, CP0_CONFIG3
or t0, (0x1 << 7)
- mtc0 t0, $16, 3
+ mtc0 t0, CP0_CONFIG3
/* Set ELPA on LOONGSON3 pagegrain */
- mfc0 t0, $5, 1
+ mfc0 t0, CP0_PAGEGRAIN
or t0, (0x1 << 29)
- mtc0 t0, $5, 1
+ mtc0 t0, CP0_PAGEGRAIN
#ifdef CONFIG_LOONGSON3_ENHANCEMENT
/* Enable STFill Buffer */
- mfc0 t0, $16, 6
+ mfc0 t0, CP0_CONFIG6
or t0, 0x100
- mtc0 t0, $16, 6
+ mtc0 t0, CP0_CONFIG6
#endif
_ehb
.set pop
.set push
.set mips64
/* Set LPA on LOONGSON3 config3 */
- mfc0 t0, $16, 3
+ mfc0 t0, CP0_CONFIG3
or t0, (0x1 << 7)
- mtc0 t0, $16, 3
+ mtc0 t0, CP0_CONFIG3
/* Set ELPA on LOONGSON3 pagegrain */
- mfc0 t0, $5, 1
+ mfc0 t0, CP0_PAGEGRAIN
or t0, (0x1 << 29)
- mtc0 t0, $5, 1
+ mtc0 t0, CP0_PAGEGRAIN
#ifdef CONFIG_LOONGSON3_ENHANCEMENT
/* Enable STFill Buffer */
- mfc0 t0, $16, 6
+ mfc0 t0, CP0_CONFIG6
or t0, 0x100
- mtc0 t0, $16, 6
+ mtc0 t0, CP0_CONFIG6
#endif
_ehb
.set pop
#ifdef CONFIG_PIC32MZDA
#define PHYS_OFFSET _AC(0x08000000, UL)
-#define UNCAC_BASE _AC(0xa8000000, UL)
#endif
#include <asm/mach-generic/spaces.h>
#include <linux/linkage.h>
#include <linux/types.h>
#include <asm/hazards.h>
+#include <asm/isa-rev.h>
#include <asm/war.h>
/*
#define CP0_GLOBALNUMBER $3, 1
#define CP0_CONTEXT $4
#define CP0_PAGEMASK $5
+#define CP0_PAGEGRAIN $5, 1
#define CP0_SEGCTL0 $5, 2
#define CP0_SEGCTL1 $5, 3
#define CP0_SEGCTL2 $5, 4
#define CP0_CONFIG $16
#define CP0_CONFIG3 $16, 3
#define CP0_CONFIG5 $16, 5
+#define CP0_CONFIG6 $16, 6
#define CP0_LLADDR $17
#define CP0_WATCHLO $18
#define CP0_WATCHHI $19
#define __write_64bit_c0_split(source, sel, val) \
do { \
- unsigned long long __tmp; \
+ unsigned long long __tmp = (val); \
unsigned long __flags; \
\
local_irq_save(__flags); \
- if (sel == 0) \
+ if (MIPS_ISA_REV >= 2) \
+ __asm__ __volatile__( \
+ ".set\tpush\n\t" \
+ ".set\t" MIPS_ISA_LEVEL "\n\t" \
+ "dins\t%L0, %M0, 32, 32\n\t" \
+ "dmtc0\t%L0, " #source ", " #sel "\n\t" \
+ ".set\tpop" \
+ : "+r" (__tmp)); \
+ else if (sel == 0) \
__asm__ __volatile__( \
".set\tmips64\n\t" \
- "dsll\t%L0, %L1, 32\n\t" \
+ "dsll\t%L0, %L0, 32\n\t" \
"dsrl\t%L0, %L0, 32\n\t" \
- "dsll\t%M0, %M1, 32\n\t" \
+ "dsll\t%M0, %M0, 32\n\t" \
"or\t%L0, %L0, %M0\n\t" \
"dmtc0\t%L0, " #source "\n\t" \
".set\tmips0" \
- : "=&r,r" (__tmp) \
- : "r,0" (val)); \
+ : "+r" (__tmp)); \
else \
__asm__ __volatile__( \
".set\tmips64\n\t" \
- "dsll\t%L0, %L1, 32\n\t" \
+ "dsll\t%L0, %L0, 32\n\t" \
"dsrl\t%L0, %L0, 32\n\t" \
- "dsll\t%M0, %M1, 32\n\t" \
+ "dsll\t%M0, %M0, 32\n\t" \
"or\t%L0, %L0, %M0\n\t" \
"dmtc0\t%L0, " #source ", " #sel "\n\t" \
".set\tmips0" \
- : "=&r,r" (__tmp) \
- : "r,0" (val)); \
+ : "+r" (__tmp)); \
local_irq_restore(__flags); \
} while (0)
for_each_possible_cpu(i)
cpu_context(i, mm) = 0;
- atomic_set(&mm->context.fp_mode_switching, 0);
-
mm->context.bd_emupage_allocmap = NULL;
spin_lock_init(&mm->context.bd_emupage_lock);
init_waitqueue_head(&mm->context.bd_emupage_queue);
for (i = 0; i < 8; i++) {
nlm_msgsnd(dest);
status = nlm_read_c2_status0();
- if ((status & 0x2) == 1)
- pr_info("Send pending fail!\n");
if ((status & 0x4) == 0)
return 0;
}
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#define CVMX_ASXX_TX_HI_WATERX(offset, block_id) (CVMX_ADD_IO_SEG(0x00011800B0000080ull) + (((offset) & 3) + ((block_id) & 1) * 0x1000000ull) * 8)
#define CVMX_ASXX_TX_PRT_EN(block_id) (CVMX_ADD_IO_SEG(0x00011800B0000008ull) + ((block_id) & 1) * 0x8000000ull)
+void __cvmx_interrupt_asxx_enable(int block);
+
union cvmx_asxx_gmii_rx_clk_set {
uint64_t u64;
struct cvmx_asxx_gmii_rx_clk_set_s {
-/***********************license start***************
- * Author: Cavium Networks
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Octeon CIU definitions
*
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
+ * Copyright (C) 2003-2018 Cavium, Inc.
+ */
#ifndef __CVMX_CIU_DEFS_H__
#define __CVMX_CIU_DEFS_H__
-#define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull))
-#define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull))
-#define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull))
-#define CVMX_CIU_EN2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x000107000000A600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x000107000000A000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000C800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000A800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x000107000000A200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull))
-#define CVMX_CIU_GSTOP (CVMX_ADD_IO_SEG(0x0001070000000710ull))
-#define CVMX_CIU_INT33_SUM0 (CVMX_ADD_IO_SEG(0x0001070000000110ull))
-#define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN4_0(offset) (CVMX_ADD_IO_SEG(0x0001070000000C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1(offset) (CVMX_ADD_IO_SEG(0x0001070000000C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8)
-#define CVMX_CIU_INTX_SUM4(offset) (CVMX_ADD_IO_SEG(0x0001070000000C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_INT_DBG_SEL (CVMX_ADD_IO_SEG(0x00010700000007D0ull))
-#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
-static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
+#include <asm/bitfield.h>
+
+#define CVMX_CIU_ADDR(addr, coreid, coremask, offset) \
+ (CVMX_ADD_IO_SEG(0x0001070000000000ull + addr##ull) + \
+ (((coreid) & (coremask)) * offset))
+
+#define CVMX_CIU_EN2_PPX_IP4(c) CVMX_CIU_ADDR(0xA400, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1C(c) CVMX_CIU_ADDR(0xCC00, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1S(c) CVMX_CIU_ADDR(0xAC00, c, 0x0F, 8)
+#define CVMX_CIU_FUSE CVMX_CIU_ADDR(0x0728, 0, 0x00, 0)
+#define CVMX_CIU_INT_SUM1 CVMX_CIU_ADDR(0x0108, 0, 0x00, 0)
+#define CVMX_CIU_INTX_EN0(c) CVMX_CIU_ADDR(0x0200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1C(c) CVMX_CIU_ADDR(0x2200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1S(c) CVMX_CIU_ADDR(0x6200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1(c) CVMX_CIU_ADDR(0x0208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1C(c) CVMX_CIU_ADDR(0x2208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1S(c) CVMX_CIU_ADDR(0x6208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_SUM0(c) CVMX_CIU_ADDR(0x0000, c, 0x3F, 8)
+#define CVMX_CIU_NMI CVMX_CIU_ADDR(0x0718, 0, 0x00, 0)
+#define CVMX_CIU_PCI_INTA CVMX_CIU_ADDR(0x0750, 0, 0x00, 0)
+#define CVMX_CIU_PP_BIST_STAT CVMX_CIU_ADDR(0x07E0, 0, 0x00, 0)
+#define CVMX_CIU_PP_DBG CVMX_CIU_ADDR(0x0708, 0, 0x00, 0)
+#define CVMX_CIU_PP_RST CVMX_CIU_ADDR(0x0700, 0, 0x00, 0)
+#define CVMX_CIU_QLM0 CVMX_CIU_ADDR(0x0780, 0, 0x00, 0)
+#define CVMX_CIU_QLM1 CVMX_CIU_ADDR(0x0788, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGC CVMX_CIU_ADDR(0x0768, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGD CVMX_CIU_ADDR(0x0770, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_BIST CVMX_CIU_ADDR(0x0738, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST1 CVMX_CIU_ADDR(0x0758, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST CVMX_CIU_ADDR(0x0748, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_RST CVMX_CIU_ADDR(0x0740, 0, 0x00, 0)
+#define CVMX_CIU_SUM2_PPX_IP4(c) CVMX_CIU_ADDR(0x8C00, c, 0x0F, 8)
+#define CVMX_CIU_TIM_MULTI_CAST CVMX_CIU_ADDR(0xC200, 0, 0x00, 0)
+#define CVMX_CIU_TIMX(c) CVMX_CIU_ADDR(0x0480, c, 0x0F, 8)
+
+static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned int coreid)
{
- switch (cvmx_get_octeon_family()) {
- case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
- case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
- case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070100100600ull) + (offset) * 8;
- }
- return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
+ if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+ return CVMX_CIU_ADDR(0x100100600, coreid, 0x0F, 8);
+ else
+ return CVMX_CIU_ADDR(0x000000680, coreid, 0x0F, 8);
}
-static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset)
+static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned int coreid)
{
- switch (cvmx_get_octeon_family()) {
- case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
- case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
- case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070100100400ull) + (offset) * 8;
- }
- return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
+ if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+ return CVMX_CIU_ADDR(0x100100400, coreid, 0x0F, 8);
+ else
+ return CVMX_CIU_ADDR(0x000000600, coreid, 0x0F, 8);
}
-#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
-#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
-#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
-static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
+static inline uint64_t CVMX_CIU_PP_POKEX(unsigned int coreid)
{
switch (cvmx_get_octeon_family()) {
- case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
- case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
- case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070100100200ull) + (offset) * 8;
+ return CVMX_CIU_ADDR(0x100100200, coreid, 0x0F, 8);
case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001010000030000ull) + (offset) * 8;
+ return CVMX_CIU_ADDR(0x000030000, coreid, 0x0F, 8) -
+ 0x60000000000ull;
+ default:
+ return CVMX_CIU_ADDR(0x000000580, coreid, 0x0F, 8);
}
- return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
}
-#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
-#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
-#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
-#define CVMX_CIU_QLM2 (CVMX_ADD_IO_SEG(0x0001070000000790ull))
-#define CVMX_CIU_QLM3 (CVMX_ADD_IO_SEG(0x0001070000000798ull))
-#define CVMX_CIU_QLM4 (CVMX_ADD_IO_SEG(0x00010700000007A0ull))
-#define CVMX_CIU_QLM_DCOK (CVMX_ADD_IO_SEG(0x0001070000000760ull))
-#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
-#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
-#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
-#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
-#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
-#define CVMX_CIU_SOFT_PRST2 (CVMX_ADD_IO_SEG(0x00010700000007D8ull))
-#define CVMX_CIU_SOFT_PRST3 (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
-#define CVMX_CIU_SUM1_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM1_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008E00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008A00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
-static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
+static inline uint64_t CVMX_CIU_WDOGX(unsigned int coreid)
{
switch (cvmx_get_octeon_family()) {
- case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
- case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
- case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
- case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001070100100000ull) + (offset) * 8;
+ return CVMX_CIU_ADDR(0x100100000, coreid, 0x0F, 8);
case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
- return CVMX_ADD_IO_SEG(0x0001010000020000ull) + (offset) * 8;
+ return CVMX_CIU_ADDR(0x000020000, coreid, 0x0F, 8) -
+ 0x60000000000ull;
+ default:
+ return CVMX_CIU_ADDR(0x000000500, coreid, 0x0F, 8);
}
- return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
}
-union cvmx_ciu_bist {
- uint64_t u64;
- struct cvmx_ciu_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_7_63:57;
- uint64_t bist:7;
-#else
- uint64_t bist:7;
- uint64_t reserved_7_63:57;
-#endif
- } s;
- struct cvmx_ciu_bist_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t bist:4;
-#else
- uint64_t bist:4;
- uint64_t reserved_4_63:60;
-#endif
- } cn30xx;
- struct cvmx_ciu_bist_cn30xx cn31xx;
- struct cvmx_ciu_bist_cn30xx cn38xx;
- struct cvmx_ciu_bist_cn30xx cn38xxp2;
- struct cvmx_ciu_bist_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t bist:2;
-#else
- uint64_t bist:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn50xx;
- struct cvmx_ciu_bist_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_3_63:61;
- uint64_t bist:3;
-#else
- uint64_t bist:3;
- uint64_t reserved_3_63:61;
-#endif
- } cn52xx;
- struct cvmx_ciu_bist_cn52xx cn52xxp1;
- struct cvmx_ciu_bist_cn30xx cn56xx;
- struct cvmx_ciu_bist_cn30xx cn56xxp1;
- struct cvmx_ciu_bist_cn30xx cn58xx;
- struct cvmx_ciu_bist_cn30xx cn58xxp1;
- struct cvmx_ciu_bist_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t bist:6;
-#else
- uint64_t bist:6;
- uint64_t reserved_6_63:58;
-#endif
- } cn61xx;
- struct cvmx_ciu_bist_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_5_63:59;
- uint64_t bist:5;
-#else
- uint64_t bist:5;
- uint64_t reserved_5_63:59;
-#endif
- } cn63xx;
- struct cvmx_ciu_bist_cn63xx cn63xxp1;
- struct cvmx_ciu_bist_cn61xx cn66xx;
- struct cvmx_ciu_bist_s cn68xx;
- struct cvmx_ciu_bist_s cn68xxp1;
- struct cvmx_ciu_bist_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_block_int {
- uint64_t u64;
- struct cvmx_ciu_block_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_62_63:2;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_43_59:17;
- uint64_t ptp:1;
- uint64_t dpi:1;
- uint64_t dfm:1;
- uint64_t reserved_34_39:6;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t reserved_31_31:1;
- uint64_t iob:1;
- uint64_t reserved_29_29:1;
- uint64_t agl:1;
- uint64_t reserved_27_27:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t reserved_24_24:1;
- uint64_t asxpcs1:1;
- uint64_t asxpcs0:1;
- uint64_t reserved_21_21:1;
- uint64_t pip:1;
- uint64_t reserved_18_19:2;
- uint64_t lmc0:1;
- uint64_t l2c:1;
- uint64_t reserved_15_15:1;
- uint64_t rad:1;
- uint64_t usb:1;
- uint64_t pow:1;
- uint64_t tim:1;
- uint64_t pko:1;
- uint64_t ipd:1;
- uint64_t reserved_8_8:1;
- uint64_t zip:1;
- uint64_t dfa:1;
- uint64_t fpa:1;
- uint64_t key:1;
- uint64_t sli:1;
- uint64_t gmx1:1;
- uint64_t gmx0:1;
- uint64_t mio:1;
-#else
- uint64_t mio:1;
- uint64_t gmx0:1;
- uint64_t gmx1:1;
- uint64_t sli:1;
- uint64_t key:1;
- uint64_t fpa:1;
- uint64_t dfa:1;
- uint64_t zip:1;
- uint64_t reserved_8_8:1;
- uint64_t ipd:1;
- uint64_t pko:1;
- uint64_t tim:1;
- uint64_t pow:1;
- uint64_t usb:1;
- uint64_t rad:1;
- uint64_t reserved_15_15:1;
- uint64_t l2c:1;
- uint64_t lmc0:1;
- uint64_t reserved_18_19:2;
- uint64_t pip:1;
- uint64_t reserved_21_21:1;
- uint64_t asxpcs0:1;
- uint64_t asxpcs1:1;
- uint64_t reserved_24_24:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_27_27:1;
- uint64_t agl:1;
- uint64_t reserved_29_29:1;
- uint64_t iob:1;
- uint64_t reserved_31_31:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t reserved_34_39:6;
- uint64_t dfm:1;
- uint64_t dpi:1;
- uint64_t ptp:1;
- uint64_t reserved_43_59:17;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_63:2;
-#endif
- } s;
- struct cvmx_ciu_block_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_43_63:21;
- uint64_t ptp:1;
- uint64_t dpi:1;
- uint64_t reserved_31_40:10;
- uint64_t iob:1;
- uint64_t reserved_29_29:1;
- uint64_t agl:1;
- uint64_t reserved_27_27:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t reserved_24_24:1;
- uint64_t asxpcs1:1;
- uint64_t asxpcs0:1;
- uint64_t reserved_21_21:1;
- uint64_t pip:1;
- uint64_t reserved_18_19:2;
- uint64_t lmc0:1;
- uint64_t l2c:1;
- uint64_t reserved_15_15:1;
- uint64_t rad:1;
- uint64_t usb:1;
- uint64_t pow:1;
- uint64_t tim:1;
- uint64_t pko:1;
- uint64_t ipd:1;
- uint64_t reserved_8_8:1;
- uint64_t zip:1;
- uint64_t dfa:1;
- uint64_t fpa:1;
- uint64_t key:1;
- uint64_t sli:1;
- uint64_t gmx1:1;
- uint64_t gmx0:1;
- uint64_t mio:1;
-#else
- uint64_t mio:1;
- uint64_t gmx0:1;
- uint64_t gmx1:1;
- uint64_t sli:1;
- uint64_t key:1;
- uint64_t fpa:1;
- uint64_t dfa:1;
- uint64_t zip:1;
- uint64_t reserved_8_8:1;
- uint64_t ipd:1;
- uint64_t pko:1;
- uint64_t tim:1;
- uint64_t pow:1;
- uint64_t usb:1;
- uint64_t rad:1;
- uint64_t reserved_15_15:1;
- uint64_t l2c:1;
- uint64_t lmc0:1;
- uint64_t reserved_18_19:2;
- uint64_t pip:1;
- uint64_t reserved_21_21:1;
- uint64_t asxpcs0:1;
- uint64_t asxpcs1:1;
- uint64_t reserved_24_24:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_27_27:1;
- uint64_t agl:1;
- uint64_t reserved_29_29:1;
- uint64_t iob:1;
- uint64_t reserved_31_40:10;
- uint64_t dpi:1;
- uint64_t ptp:1;
- uint64_t reserved_43_63:21;
-#endif
- } cn61xx;
- struct cvmx_ciu_block_int_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_43_63:21;
- uint64_t ptp:1;
- uint64_t dpi:1;
- uint64_t dfm:1;
- uint64_t reserved_34_39:6;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t reserved_31_31:1;
- uint64_t iob:1;
- uint64_t reserved_29_29:1;
- uint64_t agl:1;
- uint64_t reserved_27_27:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t reserved_23_24:2;
- uint64_t asxpcs0:1;
- uint64_t reserved_21_21:1;
- uint64_t pip:1;
- uint64_t reserved_18_19:2;
- uint64_t lmc0:1;
- uint64_t l2c:1;
- uint64_t reserved_15_15:1;
- uint64_t rad:1;
- uint64_t usb:1;
- uint64_t pow:1;
- uint64_t tim:1;
- uint64_t pko:1;
- uint64_t ipd:1;
- uint64_t reserved_8_8:1;
- uint64_t zip:1;
- uint64_t dfa:1;
- uint64_t fpa:1;
- uint64_t key:1;
- uint64_t sli:1;
- uint64_t reserved_2_2:1;
- uint64_t gmx0:1;
- uint64_t mio:1;
-#else
- uint64_t mio:1;
- uint64_t gmx0:1;
- uint64_t reserved_2_2:1;
- uint64_t sli:1;
- uint64_t key:1;
- uint64_t fpa:1;
- uint64_t dfa:1;
- uint64_t zip:1;
- uint64_t reserved_8_8:1;
- uint64_t ipd:1;
- uint64_t pko:1;
- uint64_t tim:1;
- uint64_t pow:1;
- uint64_t usb:1;
- uint64_t rad:1;
- uint64_t reserved_15_15:1;
- uint64_t l2c:1;
- uint64_t lmc0:1;
- uint64_t reserved_18_19:2;
- uint64_t pip:1;
- uint64_t reserved_21_21:1;
- uint64_t asxpcs0:1;
- uint64_t reserved_23_24:2;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_27_27:1;
- uint64_t agl:1;
- uint64_t reserved_29_29:1;
- uint64_t iob:1;
- uint64_t reserved_31_31:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t reserved_34_39:6;
- uint64_t dfm:1;
- uint64_t dpi:1;
- uint64_t ptp:1;
- uint64_t reserved_43_63:21;
-#endif
- } cn63xx;
- struct cvmx_ciu_block_int_cn63xx cn63xxp1;
- struct cvmx_ciu_block_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_62_63:2;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_43_59:17;
- uint64_t ptp:1;
- uint64_t dpi:1;
- uint64_t dfm:1;
- uint64_t reserved_33_39:7;
- uint64_t srio0:1;
- uint64_t reserved_31_31:1;
- uint64_t iob:1;
- uint64_t reserved_29_29:1;
- uint64_t agl:1;
- uint64_t reserved_27_27:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t reserved_24_24:1;
- uint64_t asxpcs1:1;
- uint64_t asxpcs0:1;
- uint64_t reserved_21_21:1;
- uint64_t pip:1;
- uint64_t reserved_18_19:2;
- uint64_t lmc0:1;
- uint64_t l2c:1;
- uint64_t reserved_15_15:1;
- uint64_t rad:1;
- uint64_t usb:1;
- uint64_t pow:1;
- uint64_t tim:1;
- uint64_t pko:1;
- uint64_t ipd:1;
- uint64_t reserved_8_8:1;
- uint64_t zip:1;
- uint64_t dfa:1;
- uint64_t fpa:1;
- uint64_t key:1;
- uint64_t sli:1;
- uint64_t gmx1:1;
- uint64_t gmx0:1;
- uint64_t mio:1;
-#else
- uint64_t mio:1;
- uint64_t gmx0:1;
- uint64_t gmx1:1;
- uint64_t sli:1;
- uint64_t key:1;
- uint64_t fpa:1;
- uint64_t dfa:1;
- uint64_t zip:1;
- uint64_t reserved_8_8:1;
- uint64_t ipd:1;
- uint64_t pko:1;
- uint64_t tim:1;
- uint64_t pow:1;
- uint64_t usb:1;
- uint64_t rad:1;
- uint64_t reserved_15_15:1;
- uint64_t l2c:1;
- uint64_t lmc0:1;
- uint64_t reserved_18_19:2;
- uint64_t pip:1;
- uint64_t reserved_21_21:1;
- uint64_t asxpcs0:1;
- uint64_t asxpcs1:1;
- uint64_t reserved_24_24:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_27_27:1;
- uint64_t agl:1;
- uint64_t reserved_29_29:1;
- uint64_t iob:1;
- uint64_t reserved_31_31:1;
- uint64_t srio0:1;
- uint64_t reserved_33_39:7;
- uint64_t dfm:1;
- uint64_t dpi:1;
- uint64_t ptp:1;
- uint64_t reserved_43_59:17;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_63:2;
-#endif
- } cn66xx;
- struct cvmx_ciu_block_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_43_63:21;
- uint64_t ptp:1;
- uint64_t dpi:1;
- uint64_t reserved_31_40:10;
- uint64_t iob:1;
- uint64_t reserved_27_29:3;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t reserved_23_24:2;
- uint64_t asxpcs0:1;
- uint64_t reserved_21_21:1;
- uint64_t pip:1;
- uint64_t reserved_18_19:2;
- uint64_t lmc0:1;
- uint64_t l2c:1;
- uint64_t reserved_15_15:1;
- uint64_t rad:1;
- uint64_t usb:1;
- uint64_t pow:1;
- uint64_t tim:1;
- uint64_t pko:1;
- uint64_t ipd:1;
- uint64_t reserved_6_8:3;
- uint64_t fpa:1;
- uint64_t key:1;
- uint64_t sli:1;
- uint64_t reserved_2_2:1;
- uint64_t gmx0:1;
- uint64_t mio:1;
-#else
- uint64_t mio:1;
- uint64_t gmx0:1;
- uint64_t reserved_2_2:1;
- uint64_t sli:1;
- uint64_t key:1;
- uint64_t fpa:1;
- uint64_t reserved_6_8:3;
- uint64_t ipd:1;
- uint64_t pko:1;
- uint64_t tim:1;
- uint64_t pow:1;
- uint64_t usb:1;
- uint64_t rad:1;
- uint64_t reserved_15_15:1;
- uint64_t l2c:1;
- uint64_t lmc0:1;
- uint64_t reserved_18_19:2;
- uint64_t pip:1;
- uint64_t reserved_21_21:1;
- uint64_t asxpcs0:1;
- uint64_t reserved_23_24:2;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_27_29:3;
- uint64_t iob:1;
- uint64_t reserved_31_40:10;
- uint64_t dpi:1;
- uint64_t ptp:1;
- uint64_t reserved_43_63:21;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_dint {
- uint64_t u64;
- struct cvmx_ciu_dint_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t dint:32;
-#else
- uint64_t dint:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_dint_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t dint:1;
-#else
- uint64_t dint:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_dint_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t dint:2;
-#else
- uint64_t dint:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_dint_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t dint:16;
-#else
- uint64_t dint:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_dint_cn38xx cn38xxp2;
- struct cvmx_ciu_dint_cn31xx cn50xx;
- struct cvmx_ciu_dint_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t dint:4;
-#else
- uint64_t dint:4;
- uint64_t reserved_4_63:60;
-#endif
- } cn52xx;
- struct cvmx_ciu_dint_cn52xx cn52xxp1;
- struct cvmx_ciu_dint_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t dint:12;
-#else
- uint64_t dint:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_dint_cn56xx cn56xxp1;
- struct cvmx_ciu_dint_cn38xx cn58xx;
- struct cvmx_ciu_dint_cn38xx cn58xxp1;
- struct cvmx_ciu_dint_cn52xx cn61xx;
- struct cvmx_ciu_dint_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t dint:6;
-#else
- uint64_t dint:6;
- uint64_t reserved_6_63:58;
-#endif
- } cn63xx;
- struct cvmx_ciu_dint_cn63xx cn63xxp1;
- struct cvmx_ciu_dint_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t dint:10;
-#else
- uint64_t dint:10;
- uint64_t reserved_10_63:54;
-#endif
- } cn66xx;
- struct cvmx_ciu_dint_s cn68xx;
- struct cvmx_ciu_dint_s cn68xxp1;
- struct cvmx_ciu_dint_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int {
- uint64_t u64;
- struct cvmx_ciu_en2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_iox_int_cn61xx cn66xx;
- struct cvmx_ciu_en2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1c {
- uint64_t u64;
- struct cvmx_ciu_en2_iox_int_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_iox_int_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_iox_int_w1c_cn61xx cn66xx;
- struct cvmx_ciu_en2_iox_int_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1s {
- uint64_t u64;
- struct cvmx_ciu_en2_iox_int_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_iox_int_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_iox_int_w1s_cn61xx cn66xx;
- struct cvmx_ciu_en2_iox_int_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2 {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip2_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1c {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip2_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip2_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1s {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip2_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip2_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3 {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip3_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1c {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip3_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip3_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1s {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip3_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip3_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4 {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip4_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip4_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1c {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip4_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip4_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1s {
- uint64_t u64;
- struct cvmx_ciu_en2_ppx_ip4_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx cn66xx;
- struct cvmx_ciu_en2_ppx_ip4_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_fuse {
- uint64_t u64;
- struct cvmx_ciu_fuse_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t fuse:32;
-#else
- uint64_t fuse:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_fuse_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t fuse:1;
-#else
- uint64_t fuse:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_fuse_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t fuse:2;
-#else
- uint64_t fuse:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_fuse_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t fuse:16;
-#else
- uint64_t fuse:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_fuse_cn38xx cn38xxp2;
- struct cvmx_ciu_fuse_cn31xx cn50xx;
- struct cvmx_ciu_fuse_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t fuse:4;
-#else
- uint64_t fuse:4;
- uint64_t reserved_4_63:60;
-#endif
- } cn52xx;
- struct cvmx_ciu_fuse_cn52xx cn52xxp1;
- struct cvmx_ciu_fuse_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t fuse:12;
-#else
- uint64_t fuse:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_fuse_cn56xx cn56xxp1;
- struct cvmx_ciu_fuse_cn38xx cn58xx;
- struct cvmx_ciu_fuse_cn38xx cn58xxp1;
- struct cvmx_ciu_fuse_cn52xx cn61xx;
- struct cvmx_ciu_fuse_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t fuse:6;
-#else
- uint64_t fuse:6;
- uint64_t reserved_6_63:58;
-#endif
- } cn63xx;
- struct cvmx_ciu_fuse_cn63xx cn63xxp1;
- struct cvmx_ciu_fuse_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t fuse:10;
-#else
- uint64_t fuse:10;
- uint64_t reserved_10_63:54;
-#endif
- } cn66xx;
- struct cvmx_ciu_fuse_s cn68xx;
- struct cvmx_ciu_fuse_s cn68xxp1;
- struct cvmx_ciu_fuse_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_gstop {
- uint64_t u64;
- struct cvmx_ciu_gstop_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t gstop:1;
-#else
- uint64_t gstop:1;
- uint64_t reserved_1_63:63;
-#endif
- } s;
- struct cvmx_ciu_gstop_s cn30xx;
- struct cvmx_ciu_gstop_s cn31xx;
- struct cvmx_ciu_gstop_s cn38xx;
- struct cvmx_ciu_gstop_s cn38xxp2;
- struct cvmx_ciu_gstop_s cn50xx;
- struct cvmx_ciu_gstop_s cn52xx;
- struct cvmx_ciu_gstop_s cn52xxp1;
- struct cvmx_ciu_gstop_s cn56xx;
- struct cvmx_ciu_gstop_s cn56xxp1;
- struct cvmx_ciu_gstop_s cn58xx;
- struct cvmx_ciu_gstop_s cn58xxp1;
- struct cvmx_ciu_gstop_s cn61xx;
- struct cvmx_ciu_gstop_s cn63xx;
- struct cvmx_ciu_gstop_s cn63xxp1;
- struct cvmx_ciu_gstop_s cn66xx;
- struct cvmx_ciu_gstop_s cn68xx;
- struct cvmx_ciu_gstop_s cn68xxp1;
- struct cvmx_ciu_gstop_s cnf71xx;
-};
-
-union cvmx_ciu_intx_en0 {
- uint64_t u64;
- struct cvmx_ciu_intx_en0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_47_47:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t reserved_47_47:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn30xx;
- struct cvmx_ciu_intx_en0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn31xx;
- struct cvmx_ciu_intx_en0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn38xx;
- struct cvmx_ciu_intx_en0_cn38xx cn38xxp2;
- struct cvmx_ciu_intx_en0_cn30xx cn50xx;
- struct cvmx_ciu_intx_en0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en0_cn52xx cn52xxp1;
- struct cvmx_ciu_intx_en0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en0_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_en0_cn38xx cn58xx;
- struct cvmx_ciu_intx_en0_cn38xx cn58xxp1;
- struct cvmx_ciu_intx_en0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en0_cn52xx cn63xx;
- struct cvmx_ciu_intx_en0_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1c {
- uint64_t u64;
- struct cvmx_ciu_intx_en0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xx;
- struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1s {
- uint64_t u64;
- struct cvmx_ciu_intx_en0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xx;
- struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en1 {
- uint64_t u64;
- struct cvmx_ciu_intx_en1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t wdog:1;
-#else
- uint64_t wdog:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_intx_en1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t wdog:2;
-#else
- uint64_t wdog:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_intx_en1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_intx_en1_cn38xx cn38xxp2;
- struct cvmx_ciu_intx_en1_cn31xx cn50xx;
- struct cvmx_ciu_intx_en1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t reserved_19_63:45;
-#endif
- } cn52xxp1;
- struct cvmx_ciu_intx_en1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en1_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_en1_cn38xx cn58xx;
- struct cvmx_ciu_intx_en1_cn38xx cn58xxp1;
- struct cvmx_ciu_intx_en1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en1_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1c {
- uint64_t u64;
- struct cvmx_ciu_intx_en1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en1_w1c_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1s {
- uint64_t u64;
- struct cvmx_ciu_intx_en1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en1_w1s_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0 {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_0_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_47_47:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t reserved_47_47:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn50xx;
- struct cvmx_ciu_intx_en4_0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_0_cn52xx cn52xxp1;
- struct cvmx_ciu_intx_en4_0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_0_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_en4_0_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_0_cn58xx cn58xxp1;
- struct cvmx_ciu_intx_en4_0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_0_cn52xx cn63xx;
- struct cvmx_ciu_intx_en4_0_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en4_0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1c {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xx;
- struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en4_0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1s {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xx;
- struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_en4_0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t reserved_44_44:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t reserved_44_44:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1 {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_1_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t wdog:2;
-#else
- uint64_t wdog:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn50xx;
- struct cvmx_ciu_intx_en4_1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t reserved_19_63:45;
-#endif
- } cn52xxp1;
- struct cvmx_ciu_intx_en4_1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_1_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_en4_1_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_1_cn58xx cn58xxp1;
- struct cvmx_ciu_intx_en4_1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en4_1_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en4_1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1c {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en4_1_w1c_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en4_1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1s {
- uint64_t u64;
- struct cvmx_ciu_intx_en4_1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_intx_en4_1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_en4_1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_en4_1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_en4_1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_en4_1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_intx_en4_1_w1s_cn63xx cn63xxp1;
- struct cvmx_ciu_intx_en4_1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_en4_1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_sum0 {
- uint64_t u64;
- struct cvmx_ciu_intx_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_sum0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_47_47:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t reserved_47_47:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn30xx;
- struct cvmx_ciu_intx_sum0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn31xx;
- struct cvmx_ciu_intx_sum0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn38xx;
- struct cvmx_ciu_intx_sum0_cn38xx cn38xxp2;
- struct cvmx_ciu_intx_sum0_cn30xx cn50xx;
- struct cvmx_ciu_intx_sum0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_sum0_cn52xx cn52xxp1;
- struct cvmx_ciu_intx_sum0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_sum0_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_sum0_cn38xx cn58xx;
- struct cvmx_ciu_intx_sum0_cn38xx cn58xxp1;
- struct cvmx_ciu_intx_sum0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_sum0_cn52xx cn63xx;
- struct cvmx_ciu_intx_sum0_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_intx_sum4 {
- uint64_t u64;
- struct cvmx_ciu_intx_sum4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_intx_sum4_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_59_63:5;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_47_47:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t reserved_47_47:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t reserved_59_63:5;
-#endif
- } cn50xx;
- struct cvmx_ciu_intx_sum4_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_intx_sum4_cn52xx cn52xxp1;
- struct cvmx_ciu_intx_sum4_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_intx_sum4_cn56xx cn56xxp1;
- struct cvmx_ciu_intx_sum4_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_56_63:8;
- uint64_t timer:4;
- uint64_t key_zero:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t key_zero:1;
- uint64_t timer:4;
- uint64_t reserved_56_63:8;
-#endif
- } cn58xx;
- struct cvmx_ciu_intx_sum4_cn58xx cn58xxp1;
- struct cvmx_ciu_intx_sum4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_intx_sum4_cn52xx cn63xx;
- struct cvmx_ciu_intx_sum4_cn52xx cn63xxp1;
- struct cvmx_ciu_intx_sum4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_intx_sum4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_int33_sum0 {
- uint64_t u64;
- struct cvmx_ciu_int33_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } s;
- struct cvmx_ciu_int33_sum0_s cn61xx;
- struct cvmx_ciu_int33_sum0_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t reserved_57_58:2;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t reserved_51_51:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_51_51:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_58:2;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_int33_sum0_cn63xx cn63xxp1;
- struct cvmx_ciu_int33_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t mii:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t reserved_57_57:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t gmx_drp:2;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:2;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t reserved_57_57:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t mii:1;
- uint64_t bootdma:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_int33_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t bootdma:1;
- uint64_t reserved_62_62:1;
- uint64_t ipdppthr:1;
- uint64_t powiq:1;
- uint64_t twsi2:1;
- uint64_t mpi:1;
- uint64_t pcm:1;
- uint64_t usb:1;
- uint64_t timer:4;
- uint64_t sum2:1;
- uint64_t ipd_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t gmx_drp:1;
- uint64_t trace:1;
- uint64_t rml:1;
- uint64_t twsi:1;
- uint64_t wdog_sum:1;
- uint64_t pci_msi:4;
- uint64_t pci_int:4;
- uint64_t uart:2;
- uint64_t mbox:2;
- uint64_t gpio:16;
- uint64_t workq:16;
-#else
- uint64_t workq:16;
- uint64_t gpio:16;
- uint64_t mbox:2;
- uint64_t uart:2;
- uint64_t pci_int:4;
- uint64_t pci_msi:4;
- uint64_t wdog_sum:1;
- uint64_t twsi:1;
- uint64_t rml:1;
- uint64_t trace:1;
- uint64_t gmx_drp:1;
- uint64_t reserved_49_49:1;
- uint64_t ipd_drp:1;
- uint64_t sum2:1;
- uint64_t timer:4;
- uint64_t usb:1;
- uint64_t pcm:1;
- uint64_t mpi:1;
- uint64_t twsi2:1;
- uint64_t powiq:1;
- uint64_t ipdppthr:1;
- uint64_t reserved_62_62:1;
- uint64_t bootdma:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_int_dbg_sel {
- uint64_t u64;
- struct cvmx_ciu_int_dbg_sel_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t sel:3;
- uint64_t reserved_10_15:6;
- uint64_t irq:2;
- uint64_t reserved_5_7:3;
- uint64_t pp:5;
-#else
- uint64_t pp:5;
- uint64_t reserved_5_7:3;
- uint64_t irq:2;
- uint64_t reserved_10_15:6;
- uint64_t sel:3;
- uint64_t reserved_19_63:45;
-#endif
- } s;
- struct cvmx_ciu_int_dbg_sel_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t sel:3;
- uint64_t reserved_10_15:6;
- uint64_t irq:2;
- uint64_t reserved_4_7:4;
- uint64_t pp:4;
-#else
- uint64_t pp:4;
- uint64_t reserved_4_7:4;
- uint64_t irq:2;
- uint64_t reserved_10_15:6;
- uint64_t sel:3;
- uint64_t reserved_19_63:45;
-#endif
- } cn61xx;
- struct cvmx_ciu_int_dbg_sel_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t sel:3;
- uint64_t reserved_10_15:6;
- uint64_t irq:2;
- uint64_t reserved_3_7:5;
- uint64_t pp:3;
-#else
- uint64_t pp:3;
- uint64_t reserved_3_7:5;
- uint64_t irq:2;
- uint64_t reserved_10_15:6;
- uint64_t sel:3;
- uint64_t reserved_19_63:45;
-#endif
- } cn63xx;
- struct cvmx_ciu_int_dbg_sel_cn61xx cn66xx;
- struct cvmx_ciu_int_dbg_sel_s cn68xx;
- struct cvmx_ciu_int_dbg_sel_s cn68xxp1;
- struct cvmx_ciu_int_dbg_sel_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_int_sum1 {
- uint64_t u64;
- struct cvmx_ciu_int_sum1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_int_sum1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t wdog:1;
-#else
- uint64_t wdog:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_int_sum1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t wdog:2;
-#else
- uint64_t wdog:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_int_sum1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t wdog:16;
-#else
- uint64_t wdog:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_int_sum1_cn38xx cn38xxp2;
- struct cvmx_ciu_int_sum1_cn31xx cn50xx;
- struct cvmx_ciu_int_sum1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_20_63:44;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t reserved_20_63:44;
-#endif
- } cn52xx;
- struct cvmx_ciu_int_sum1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_19_63:45;
- uint64_t mii1:1;
- uint64_t usb1:1;
- uint64_t uart2:1;
- uint64_t reserved_4_15:12;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_15:12;
- uint64_t uart2:1;
- uint64_t usb1:1;
- uint64_t mii1:1;
- uint64_t reserved_19_63:45;
-#endif
- } cn52xxp1;
- struct cvmx_ciu_int_sum1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t wdog:12;
-#else
- uint64_t wdog:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_int_sum1_cn56xx cn56xxp1;
- struct cvmx_ciu_int_sum1_cn38xx cn58xx;
- struct cvmx_ciu_int_sum1_cn38xx cn58xxp1;
- struct cvmx_ciu_int_sum1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_int_sum1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_57_62:6;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t srio1:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_37_45:9;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_6_17:12;
- uint64_t wdog:6;
-#else
- uint64_t wdog:6;
- uint64_t reserved_6_17:12;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_45:9;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t srio1:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_62:6;
- uint64_t rst:1;
-#endif
- } cn63xx;
- struct cvmx_ciu_int_sum1_cn63xx cn63xxp1;
- struct cvmx_ciu_int_sum1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_int_sum1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_37_46:10;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_46:10;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_mbox_clrx {
- uint64_t u64;
- struct cvmx_ciu_mbox_clrx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t bits:32;
-#else
- uint64_t bits:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_mbox_clrx_s cn30xx;
- struct cvmx_ciu_mbox_clrx_s cn31xx;
- struct cvmx_ciu_mbox_clrx_s cn38xx;
- struct cvmx_ciu_mbox_clrx_s cn38xxp2;
- struct cvmx_ciu_mbox_clrx_s cn50xx;
- struct cvmx_ciu_mbox_clrx_s cn52xx;
- struct cvmx_ciu_mbox_clrx_s cn52xxp1;
- struct cvmx_ciu_mbox_clrx_s cn56xx;
- struct cvmx_ciu_mbox_clrx_s cn56xxp1;
- struct cvmx_ciu_mbox_clrx_s cn58xx;
- struct cvmx_ciu_mbox_clrx_s cn58xxp1;
- struct cvmx_ciu_mbox_clrx_s cn61xx;
- struct cvmx_ciu_mbox_clrx_s cn63xx;
- struct cvmx_ciu_mbox_clrx_s cn63xxp1;
- struct cvmx_ciu_mbox_clrx_s cn66xx;
- struct cvmx_ciu_mbox_clrx_s cn68xx;
- struct cvmx_ciu_mbox_clrx_s cn68xxp1;
- struct cvmx_ciu_mbox_clrx_s cnf71xx;
-};
-
-union cvmx_ciu_mbox_setx {
- uint64_t u64;
- struct cvmx_ciu_mbox_setx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t bits:32;
-#else
- uint64_t bits:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_mbox_setx_s cn30xx;
- struct cvmx_ciu_mbox_setx_s cn31xx;
- struct cvmx_ciu_mbox_setx_s cn38xx;
- struct cvmx_ciu_mbox_setx_s cn38xxp2;
- struct cvmx_ciu_mbox_setx_s cn50xx;
- struct cvmx_ciu_mbox_setx_s cn52xx;
- struct cvmx_ciu_mbox_setx_s cn52xxp1;
- struct cvmx_ciu_mbox_setx_s cn56xx;
- struct cvmx_ciu_mbox_setx_s cn56xxp1;
- struct cvmx_ciu_mbox_setx_s cn58xx;
- struct cvmx_ciu_mbox_setx_s cn58xxp1;
- struct cvmx_ciu_mbox_setx_s cn61xx;
- struct cvmx_ciu_mbox_setx_s cn63xx;
- struct cvmx_ciu_mbox_setx_s cn63xxp1;
- struct cvmx_ciu_mbox_setx_s cn66xx;
- struct cvmx_ciu_mbox_setx_s cn68xx;
- struct cvmx_ciu_mbox_setx_s cn68xxp1;
- struct cvmx_ciu_mbox_setx_s cnf71xx;
-};
-
-union cvmx_ciu_nmi {
- uint64_t u64;
- struct cvmx_ciu_nmi_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t nmi:32;
-#else
- uint64_t nmi:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_nmi_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t nmi:1;
-#else
- uint64_t nmi:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_nmi_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t nmi:2;
-#else
- uint64_t nmi:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_nmi_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t nmi:16;
-#else
- uint64_t nmi:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_nmi_cn38xx cn38xxp2;
- struct cvmx_ciu_nmi_cn31xx cn50xx;
- struct cvmx_ciu_nmi_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t nmi:4;
-#else
- uint64_t nmi:4;
- uint64_t reserved_4_63:60;
-#endif
- } cn52xx;
- struct cvmx_ciu_nmi_cn52xx cn52xxp1;
- struct cvmx_ciu_nmi_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t nmi:12;
-#else
- uint64_t nmi:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_nmi_cn56xx cn56xxp1;
- struct cvmx_ciu_nmi_cn38xx cn58xx;
- struct cvmx_ciu_nmi_cn38xx cn58xxp1;
- struct cvmx_ciu_nmi_cn52xx cn61xx;
- struct cvmx_ciu_nmi_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t nmi:6;
-#else
- uint64_t nmi:6;
- uint64_t reserved_6_63:58;
-#endif
- } cn63xx;
- struct cvmx_ciu_nmi_cn63xx cn63xxp1;
- struct cvmx_ciu_nmi_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t nmi:10;
-#else
- uint64_t nmi:10;
- uint64_t reserved_10_63:54;
-#endif
- } cn66xx;
- struct cvmx_ciu_nmi_s cn68xx;
- struct cvmx_ciu_nmi_s cn68xxp1;
- struct cvmx_ciu_nmi_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pci_inta {
- uint64_t u64;
- struct cvmx_ciu_pci_inta_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t intr:2;
-#else
- uint64_t intr:2;
- uint64_t reserved_2_63:62;
-#endif
- } s;
- struct cvmx_ciu_pci_inta_s cn30xx;
- struct cvmx_ciu_pci_inta_s cn31xx;
- struct cvmx_ciu_pci_inta_s cn38xx;
- struct cvmx_ciu_pci_inta_s cn38xxp2;
- struct cvmx_ciu_pci_inta_s cn50xx;
- struct cvmx_ciu_pci_inta_s cn52xx;
- struct cvmx_ciu_pci_inta_s cn52xxp1;
- struct cvmx_ciu_pci_inta_s cn56xx;
- struct cvmx_ciu_pci_inta_s cn56xxp1;
- struct cvmx_ciu_pci_inta_s cn58xx;
- struct cvmx_ciu_pci_inta_s cn58xxp1;
- struct cvmx_ciu_pci_inta_s cn61xx;
- struct cvmx_ciu_pci_inta_s cn63xx;
- struct cvmx_ciu_pci_inta_s cn63xxp1;
- struct cvmx_ciu_pci_inta_s cn66xx;
- struct cvmx_ciu_pci_inta_s cn68xx;
- struct cvmx_ciu_pci_inta_s cn68xxp1;
- struct cvmx_ciu_pci_inta_s cnf71xx;
-};
-
-union cvmx_ciu_pp_bist_stat {
- uint64_t u64;
- struct cvmx_ciu_pp_bist_stat_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t pp_bist:32;
-#else
- uint64_t pp_bist:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_pp_bist_stat_s cn68xx;
- struct cvmx_ciu_pp_bist_stat_s cn68xxp1;
-};
-
-union cvmx_ciu_pp_dbg {
- uint64_t u64;
- struct cvmx_ciu_pp_dbg_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t ppdbg:32;
-#else
- uint64_t ppdbg:32;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_pp_dbg_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t ppdbg:1;
-#else
- uint64_t ppdbg:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_pp_dbg_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t ppdbg:2;
-#else
- uint64_t ppdbg:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_pp_dbg_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t ppdbg:16;
-#else
- uint64_t ppdbg:16;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_pp_dbg_cn38xx cn38xxp2;
- struct cvmx_ciu_pp_dbg_cn31xx cn50xx;
- struct cvmx_ciu_pp_dbg_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t ppdbg:4;
-#else
- uint64_t ppdbg:4;
- uint64_t reserved_4_63:60;
-#endif
- } cn52xx;
- struct cvmx_ciu_pp_dbg_cn52xx cn52xxp1;
- struct cvmx_ciu_pp_dbg_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t ppdbg:12;
-#else
- uint64_t ppdbg:12;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_pp_dbg_cn56xx cn56xxp1;
- struct cvmx_ciu_pp_dbg_cn38xx cn58xx;
- struct cvmx_ciu_pp_dbg_cn38xx cn58xxp1;
- struct cvmx_ciu_pp_dbg_cn52xx cn61xx;
- struct cvmx_ciu_pp_dbg_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t ppdbg:6;
-#else
- uint64_t ppdbg:6;
- uint64_t reserved_6_63:58;
-#endif
- } cn63xx;
- struct cvmx_ciu_pp_dbg_cn63xx cn63xxp1;
- struct cvmx_ciu_pp_dbg_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t ppdbg:10;
-#else
- uint64_t ppdbg:10;
- uint64_t reserved_10_63:54;
-#endif
- } cn66xx;
- struct cvmx_ciu_pp_dbg_s cn68xx;
- struct cvmx_ciu_pp_dbg_s cn68xxp1;
- struct cvmx_ciu_pp_dbg_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pp_pokex {
- uint64_t u64;
- struct cvmx_ciu_pp_pokex_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t poke:64;
-#else
- uint64_t poke:64;
-#endif
- } s;
- struct cvmx_ciu_pp_pokex_s cn30xx;
- struct cvmx_ciu_pp_pokex_s cn31xx;
- struct cvmx_ciu_pp_pokex_s cn38xx;
- struct cvmx_ciu_pp_pokex_s cn38xxp2;
- struct cvmx_ciu_pp_pokex_s cn50xx;
- struct cvmx_ciu_pp_pokex_s cn52xx;
- struct cvmx_ciu_pp_pokex_s cn52xxp1;
- struct cvmx_ciu_pp_pokex_s cn56xx;
- struct cvmx_ciu_pp_pokex_s cn56xxp1;
- struct cvmx_ciu_pp_pokex_s cn58xx;
- struct cvmx_ciu_pp_pokex_s cn58xxp1;
- struct cvmx_ciu_pp_pokex_s cn61xx;
- struct cvmx_ciu_pp_pokex_s cn63xx;
- struct cvmx_ciu_pp_pokex_s cn63xxp1;
- struct cvmx_ciu_pp_pokex_s cn66xx;
- struct cvmx_ciu_pp_pokex_s cn68xx;
- struct cvmx_ciu_pp_pokex_s cn68xxp1;
- struct cvmx_ciu_pp_pokex_s cnf71xx;
-};
-
-union cvmx_ciu_pp_rst {
- uint64_t u64;
- struct cvmx_ciu_pp_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t rst:31;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:31;
- uint64_t reserved_32_63:32;
-#endif
- } s;
- struct cvmx_ciu_pp_rst_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn30xx;
- struct cvmx_ciu_pp_rst_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t rst:1;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:1;
- uint64_t reserved_2_63:62;
-#endif
- } cn31xx;
- struct cvmx_ciu_pp_rst_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_16_63:48;
- uint64_t rst:15;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:15;
- uint64_t reserved_16_63:48;
-#endif
- } cn38xx;
- struct cvmx_ciu_pp_rst_cn38xx cn38xxp2;
- struct cvmx_ciu_pp_rst_cn31xx cn50xx;
- struct cvmx_ciu_pp_rst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t rst:3;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:3;
- uint64_t reserved_4_63:60;
-#endif
- } cn52xx;
- struct cvmx_ciu_pp_rst_cn52xx cn52xxp1;
- struct cvmx_ciu_pp_rst_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_12_63:52;
- uint64_t rst:11;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:11;
- uint64_t reserved_12_63:52;
-#endif
- } cn56xx;
- struct cvmx_ciu_pp_rst_cn56xx cn56xxp1;
- struct cvmx_ciu_pp_rst_cn38xx cn58xx;
- struct cvmx_ciu_pp_rst_cn38xx cn58xxp1;
- struct cvmx_ciu_pp_rst_cn52xx cn61xx;
- struct cvmx_ciu_pp_rst_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_6_63:58;
- uint64_t rst:5;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:5;
- uint64_t reserved_6_63:58;
-#endif
- } cn63xx;
- struct cvmx_ciu_pp_rst_cn63xx cn63xxp1;
- struct cvmx_ciu_pp_rst_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t rst:9;
- uint64_t rst0:1;
-#else
- uint64_t rst0:1;
- uint64_t rst:9;
- uint64_t reserved_10_63:54;
-#endif
- } cn66xx;
- struct cvmx_ciu_pp_rst_s cn68xx;
- struct cvmx_ciu_pp_rst_s cn68xxp1;
- struct cvmx_ciu_pp_rst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_qlm0 {
- uint64_t u64;
- struct cvmx_ciu_qlm0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t g2bypass:1;
- uint64_t reserved_53_62:10;
- uint64_t g2deemph:5;
- uint64_t reserved_45_47:3;
- uint64_t g2margin:5;
- uint64_t reserved_32_39:8;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_39:8;
- uint64_t g2margin:5;
- uint64_t reserved_45_47:3;
- uint64_t g2deemph:5;
- uint64_t reserved_53_62:10;
- uint64_t g2bypass:1;
-#endif
- } s;
- struct cvmx_ciu_qlm0_s cn61xx;
- struct cvmx_ciu_qlm0_s cn63xx;
- struct cvmx_ciu_qlm0_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t txbypass:1;
- uint64_t reserved_20_30:11;
- uint64_t txdeemph:4;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:4;
- uint64_t reserved_20_30:11;
- uint64_t txbypass:1;
- uint64_t reserved_32_63:32;
-#endif
- } cn63xxp1;
- struct cvmx_ciu_qlm0_s cn66xx;
- struct cvmx_ciu_qlm0_cn68xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_63:32;
-#endif
- } cn68xx;
- struct cvmx_ciu_qlm0_cn68xx cn68xxp1;
- struct cvmx_ciu_qlm0_s cnf71xx;
-};
-
-union cvmx_ciu_qlm1 {
- uint64_t u64;
- struct cvmx_ciu_qlm1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t g2bypass:1;
- uint64_t reserved_53_62:10;
- uint64_t g2deemph:5;
- uint64_t reserved_45_47:3;
- uint64_t g2margin:5;
- uint64_t reserved_32_39:8;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_39:8;
- uint64_t g2margin:5;
- uint64_t reserved_45_47:3;
- uint64_t g2deemph:5;
- uint64_t reserved_53_62:10;
- uint64_t g2bypass:1;
-#endif
- } s;
- struct cvmx_ciu_qlm1_s cn61xx;
- struct cvmx_ciu_qlm1_s cn63xx;
- struct cvmx_ciu_qlm1_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t txbypass:1;
- uint64_t reserved_20_30:11;
- uint64_t txdeemph:4;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:4;
- uint64_t reserved_20_30:11;
- uint64_t txbypass:1;
- uint64_t reserved_32_63:32;
-#endif
- } cn63xxp1;
- struct cvmx_ciu_qlm1_s cn66xx;
- struct cvmx_ciu_qlm1_s cn68xx;
- struct cvmx_ciu_qlm1_s cn68xxp1;
- struct cvmx_ciu_qlm1_s cnf71xx;
-};
-
-union cvmx_ciu_qlm2 {
- uint64_t u64;
- struct cvmx_ciu_qlm2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t g2bypass:1;
- uint64_t reserved_53_62:10;
- uint64_t g2deemph:5;
- uint64_t reserved_45_47:3;
- uint64_t g2margin:5;
- uint64_t reserved_32_39:8;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_39:8;
- uint64_t g2margin:5;
- uint64_t reserved_45_47:3;
- uint64_t g2deemph:5;
- uint64_t reserved_53_62:10;
- uint64_t g2bypass:1;
-#endif
- } s;
- struct cvmx_ciu_qlm2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_63:32;
-#endif
- } cn61xx;
- struct cvmx_ciu_qlm2_cn61xx cn63xx;
- struct cvmx_ciu_qlm2_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_32_63:32;
- uint64_t txbypass:1;
- uint64_t reserved_20_30:11;
- uint64_t txdeemph:4;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:4;
- uint64_t reserved_20_30:11;
- uint64_t txbypass:1;
- uint64_t reserved_32_63:32;
-#endif
- } cn63xxp1;
- struct cvmx_ciu_qlm2_cn61xx cn66xx;
- struct cvmx_ciu_qlm2_s cn68xx;
- struct cvmx_ciu_qlm2_s cn68xxp1;
- struct cvmx_ciu_qlm2_cn61xx cnf71xx;
-};
-union cvmx_ciu_qlm3 {
+union cvmx_ciu_qlm {
uint64_t u64;
- struct cvmx_ciu_qlm3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t g2bypass:1;
- uint64_t reserved_53_62:10;
- uint64_t g2deemph:5;
- uint64_t reserved_45_47:3;
- uint64_t g2margin:5;
- uint64_t reserved_32_39:8;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_39:8;
- uint64_t g2margin:5;
- uint64_t reserved_45_47:3;
- uint64_t g2deemph:5;
- uint64_t reserved_53_62:10;
- uint64_t g2bypass:1;
-#endif
+ struct cvmx_ciu_qlm_s {
+ __BITFIELD_FIELD(uint64_t g2bypass:1,
+ __BITFIELD_FIELD(uint64_t reserved_53_62:10,
+ __BITFIELD_FIELD(uint64_t g2deemph:5,
+ __BITFIELD_FIELD(uint64_t reserved_45_47:3,
+ __BITFIELD_FIELD(uint64_t g2margin:5,
+ __BITFIELD_FIELD(uint64_t reserved_32_39:8,
+ __BITFIELD_FIELD(uint64_t txbypass:1,
+ __BITFIELD_FIELD(uint64_t reserved_21_30:10,
+ __BITFIELD_FIELD(uint64_t txdeemph:5,
+ __BITFIELD_FIELD(uint64_t reserved_13_15:3,
+ __BITFIELD_FIELD(uint64_t txmargin:5,
+ __BITFIELD_FIELD(uint64_t reserved_4_7:4,
+ __BITFIELD_FIELD(uint64_t lane_en:4,
+ ;)))))))))))))
} s;
- struct cvmx_ciu_qlm3_s cn68xx;
- struct cvmx_ciu_qlm3_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm4 {
- uint64_t u64;
- struct cvmx_ciu_qlm4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t g2bypass:1;
- uint64_t reserved_53_62:10;
- uint64_t g2deemph:5;
- uint64_t reserved_45_47:3;
- uint64_t g2margin:5;
- uint64_t reserved_32_39:8;
- uint64_t txbypass:1;
- uint64_t reserved_21_30:10;
- uint64_t txdeemph:5;
- uint64_t reserved_13_15:3;
- uint64_t txmargin:5;
- uint64_t reserved_4_7:4;
- uint64_t lane_en:4;
-#else
- uint64_t lane_en:4;
- uint64_t reserved_4_7:4;
- uint64_t txmargin:5;
- uint64_t reserved_13_15:3;
- uint64_t txdeemph:5;
- uint64_t reserved_21_30:10;
- uint64_t txbypass:1;
- uint64_t reserved_32_39:8;
- uint64_t g2margin:5;
- uint64_t reserved_45_47:3;
- uint64_t g2deemph:5;
- uint64_t reserved_53_62:10;
- uint64_t g2bypass:1;
-#endif
- } s;
- struct cvmx_ciu_qlm4_s cn68xx;
- struct cvmx_ciu_qlm4_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm_dcok {
- uint64_t u64;
- struct cvmx_ciu_qlm_dcok_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_4_63:60;
- uint64_t qlm_dcok:4;
-#else
- uint64_t qlm_dcok:4;
- uint64_t reserved_4_63:60;
-#endif
- } s;
- struct cvmx_ciu_qlm_dcok_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_2_63:62;
- uint64_t qlm_dcok:2;
-#else
- uint64_t qlm_dcok:2;
- uint64_t reserved_2_63:62;
-#endif
- } cn52xx;
- struct cvmx_ciu_qlm_dcok_cn52xx cn52xxp1;
- struct cvmx_ciu_qlm_dcok_s cn56xx;
- struct cvmx_ciu_qlm_dcok_s cn56xxp1;
};
union cvmx_ciu_qlm_jtgc {
uint64_t u64;
struct cvmx_ciu_qlm_jtgc_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_17_63:47;
- uint64_t bypass_ext:1;
- uint64_t reserved_11_15:5;
- uint64_t clk_div:3;
- uint64_t reserved_7_7:1;
- uint64_t mux_sel:3;
- uint64_t bypass:4;
-#else
- uint64_t bypass:4;
- uint64_t mux_sel:3;
- uint64_t reserved_7_7:1;
- uint64_t clk_div:3;
- uint64_t reserved_11_15:5;
- uint64_t bypass_ext:1;
- uint64_t reserved_17_63:47;
-#endif
+ __BITFIELD_FIELD(uint64_t reserved_17_63:47,
+ __BITFIELD_FIELD(uint64_t bypass_ext:1,
+ __BITFIELD_FIELD(uint64_t reserved_11_15:5,
+ __BITFIELD_FIELD(uint64_t clk_div:3,
+ __BITFIELD_FIELD(uint64_t reserved_7_7:1,
+ __BITFIELD_FIELD(uint64_t mux_sel:3,
+ __BITFIELD_FIELD(uint64_t bypass:4,
+ ;)))))))
} s;
- struct cvmx_ciu_qlm_jtgc_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_11_63:53;
- uint64_t clk_div:3;
- uint64_t reserved_5_7:3;
- uint64_t mux_sel:1;
- uint64_t reserved_2_3:2;
- uint64_t bypass:2;
-#else
- uint64_t bypass:2;
- uint64_t reserved_2_3:2;
- uint64_t mux_sel:1;
- uint64_t reserved_5_7:3;
- uint64_t clk_div:3;
- uint64_t reserved_11_63:53;
-#endif
- } cn52xx;
- struct cvmx_ciu_qlm_jtgc_cn52xx cn52xxp1;
- struct cvmx_ciu_qlm_jtgc_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_11_63:53;
- uint64_t clk_div:3;
- uint64_t reserved_6_7:2;
- uint64_t mux_sel:2;
- uint64_t bypass:4;
-#else
- uint64_t bypass:4;
- uint64_t mux_sel:2;
- uint64_t reserved_6_7:2;
- uint64_t clk_div:3;
- uint64_t reserved_11_63:53;
-#endif
- } cn56xx;
- struct cvmx_ciu_qlm_jtgc_cn56xx cn56xxp1;
- struct cvmx_ciu_qlm_jtgc_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_11_63:53;
- uint64_t clk_div:3;
- uint64_t reserved_6_7:2;
- uint64_t mux_sel:2;
- uint64_t reserved_3_3:1;
- uint64_t bypass:3;
-#else
- uint64_t bypass:3;
- uint64_t reserved_3_3:1;
- uint64_t mux_sel:2;
- uint64_t reserved_6_7:2;
- uint64_t clk_div:3;
- uint64_t reserved_11_63:53;
-#endif
- } cn61xx;
- struct cvmx_ciu_qlm_jtgc_cn61xx cn63xx;
- struct cvmx_ciu_qlm_jtgc_cn61xx cn63xxp1;
- struct cvmx_ciu_qlm_jtgc_cn61xx cn66xx;
- struct cvmx_ciu_qlm_jtgc_s cn68xx;
- struct cvmx_ciu_qlm_jtgc_s cn68xxp1;
- struct cvmx_ciu_qlm_jtgc_cn61xx cnf71xx;
};
union cvmx_ciu_qlm_jtgd {
uint64_t u64;
struct cvmx_ciu_qlm_jtgd_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t capture:1;
- uint64_t shift:1;
- uint64_t update:1;
- uint64_t reserved_45_60:16;
- uint64_t select:5;
- uint64_t reserved_37_39:3;
- uint64_t shft_cnt:5;
- uint64_t shft_reg:32;
-#else
- uint64_t shft_reg:32;
- uint64_t shft_cnt:5;
- uint64_t reserved_37_39:3;
- uint64_t select:5;
- uint64_t reserved_45_60:16;
- uint64_t update:1;
- uint64_t shift:1;
- uint64_t capture:1;
-#endif
- } s;
- struct cvmx_ciu_qlm_jtgd_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t capture:1;
- uint64_t shift:1;
- uint64_t update:1;
- uint64_t reserved_42_60:19;
- uint64_t select:2;
- uint64_t reserved_37_39:3;
- uint64_t shft_cnt:5;
- uint64_t shft_reg:32;
-#else
- uint64_t shft_reg:32;
- uint64_t shft_cnt:5;
- uint64_t reserved_37_39:3;
- uint64_t select:2;
- uint64_t reserved_42_60:19;
- uint64_t update:1;
- uint64_t shift:1;
- uint64_t capture:1;
-#endif
- } cn52xx;
- struct cvmx_ciu_qlm_jtgd_cn52xx cn52xxp1;
- struct cvmx_ciu_qlm_jtgd_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t capture:1;
- uint64_t shift:1;
- uint64_t update:1;
- uint64_t reserved_44_60:17;
- uint64_t select:4;
- uint64_t reserved_37_39:3;
- uint64_t shft_cnt:5;
- uint64_t shft_reg:32;
-#else
- uint64_t shft_reg:32;
- uint64_t shft_cnt:5;
- uint64_t reserved_37_39:3;
- uint64_t select:4;
- uint64_t reserved_44_60:17;
- uint64_t update:1;
- uint64_t shift:1;
- uint64_t capture:1;
-#endif
- } cn56xx;
- struct cvmx_ciu_qlm_jtgd_cn56xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t capture:1;
- uint64_t shift:1;
- uint64_t update:1;
- uint64_t reserved_37_60:24;
- uint64_t shft_cnt:5;
- uint64_t shft_reg:32;
-#else
- uint64_t shft_reg:32;
- uint64_t shft_cnt:5;
- uint64_t reserved_37_60:24;
- uint64_t update:1;
- uint64_t shift:1;
- uint64_t capture:1;
-#endif
- } cn56xxp1;
- struct cvmx_ciu_qlm_jtgd_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t capture:1;
- uint64_t shift:1;
- uint64_t update:1;
- uint64_t reserved_43_60:18;
- uint64_t select:3;
- uint64_t reserved_37_39:3;
- uint64_t shft_cnt:5;
- uint64_t shft_reg:32;
-#else
- uint64_t shft_reg:32;
- uint64_t shft_cnt:5;
- uint64_t reserved_37_39:3;
- uint64_t select:3;
- uint64_t reserved_43_60:18;
- uint64_t update:1;
- uint64_t shift:1;
- uint64_t capture:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_qlm_jtgd_cn61xx cn63xx;
- struct cvmx_ciu_qlm_jtgd_cn61xx cn63xxp1;
- struct cvmx_ciu_qlm_jtgd_cn61xx cn66xx;
- struct cvmx_ciu_qlm_jtgd_s cn68xx;
- struct cvmx_ciu_qlm_jtgd_s cn68xxp1;
- struct cvmx_ciu_qlm_jtgd_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_soft_bist {
- uint64_t u64;
- struct cvmx_ciu_soft_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_bist:1;
-#else
- uint64_t soft_bist:1;
- uint64_t reserved_1_63:63;
-#endif
+ __BITFIELD_FIELD(uint64_t capture:1,
+ __BITFIELD_FIELD(uint64_t shift:1,
+ __BITFIELD_FIELD(uint64_t update:1,
+ __BITFIELD_FIELD(uint64_t reserved_45_60:16,
+ __BITFIELD_FIELD(uint64_t select:5,
+ __BITFIELD_FIELD(uint64_t reserved_37_39:3,
+ __BITFIELD_FIELD(uint64_t shft_cnt:5,
+ __BITFIELD_FIELD(uint64_t shft_reg:32,
+ ;))))))))
} s;
- struct cvmx_ciu_soft_bist_s cn30xx;
- struct cvmx_ciu_soft_bist_s cn31xx;
- struct cvmx_ciu_soft_bist_s cn38xx;
- struct cvmx_ciu_soft_bist_s cn38xxp2;
- struct cvmx_ciu_soft_bist_s cn50xx;
- struct cvmx_ciu_soft_bist_s cn52xx;
- struct cvmx_ciu_soft_bist_s cn52xxp1;
- struct cvmx_ciu_soft_bist_s cn56xx;
- struct cvmx_ciu_soft_bist_s cn56xxp1;
- struct cvmx_ciu_soft_bist_s cn58xx;
- struct cvmx_ciu_soft_bist_s cn58xxp1;
- struct cvmx_ciu_soft_bist_s cn61xx;
- struct cvmx_ciu_soft_bist_s cn63xx;
- struct cvmx_ciu_soft_bist_s cn63xxp1;
- struct cvmx_ciu_soft_bist_s cn66xx;
- struct cvmx_ciu_soft_bist_s cn68xx;
- struct cvmx_ciu_soft_bist_s cn68xxp1;
- struct cvmx_ciu_soft_bist_s cnf71xx;
};
union cvmx_ciu_soft_prst {
uint64_t u64;
struct cvmx_ciu_soft_prst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_3_63:61;
- uint64_t host64:1;
- uint64_t npi:1;
- uint64_t soft_prst:1;
-#else
- uint64_t soft_prst:1;
- uint64_t npi:1;
- uint64_t host64:1;
- uint64_t reserved_3_63:61;
-#endif
- } s;
- struct cvmx_ciu_soft_prst_s cn30xx;
- struct cvmx_ciu_soft_prst_s cn31xx;
- struct cvmx_ciu_soft_prst_s cn38xx;
- struct cvmx_ciu_soft_prst_s cn38xxp2;
- struct cvmx_ciu_soft_prst_s cn50xx;
- struct cvmx_ciu_soft_prst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_prst:1;
-#else
- uint64_t soft_prst:1;
- uint64_t reserved_1_63:63;
-#endif
- } cn52xx;
- struct cvmx_ciu_soft_prst_cn52xx cn52xxp1;
- struct cvmx_ciu_soft_prst_cn52xx cn56xx;
- struct cvmx_ciu_soft_prst_cn52xx cn56xxp1;
- struct cvmx_ciu_soft_prst_s cn58xx;
- struct cvmx_ciu_soft_prst_s cn58xxp1;
- struct cvmx_ciu_soft_prst_cn52xx cn61xx;
- struct cvmx_ciu_soft_prst_cn52xx cn63xx;
- struct cvmx_ciu_soft_prst_cn52xx cn63xxp1;
- struct cvmx_ciu_soft_prst_cn52xx cn66xx;
- struct cvmx_ciu_soft_prst_cn52xx cn68xx;
- struct cvmx_ciu_soft_prst_cn52xx cn68xxp1;
- struct cvmx_ciu_soft_prst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_soft_prst1 {
- uint64_t u64;
- struct cvmx_ciu_soft_prst1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_prst:1;
-#else
- uint64_t soft_prst:1;
- uint64_t reserved_1_63:63;
-#endif
- } s;
- struct cvmx_ciu_soft_prst1_s cn52xx;
- struct cvmx_ciu_soft_prst1_s cn52xxp1;
- struct cvmx_ciu_soft_prst1_s cn56xx;
- struct cvmx_ciu_soft_prst1_s cn56xxp1;
- struct cvmx_ciu_soft_prst1_s cn61xx;
- struct cvmx_ciu_soft_prst1_s cn63xx;
- struct cvmx_ciu_soft_prst1_s cn63xxp1;
- struct cvmx_ciu_soft_prst1_s cn66xx;
- struct cvmx_ciu_soft_prst1_s cn68xx;
- struct cvmx_ciu_soft_prst1_s cn68xxp1;
- struct cvmx_ciu_soft_prst1_s cnf71xx;
-};
-
-union cvmx_ciu_soft_prst2 {
- uint64_t u64;
- struct cvmx_ciu_soft_prst2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_prst:1;
-#else
- uint64_t soft_prst:1;
- uint64_t reserved_1_63:63;
-#endif
- } s;
- struct cvmx_ciu_soft_prst2_s cn66xx;
-};
-
-union cvmx_ciu_soft_prst3 {
- uint64_t u64;
- struct cvmx_ciu_soft_prst3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_prst:1;
-#else
- uint64_t soft_prst:1;
- uint64_t reserved_1_63:63;
-#endif
- } s;
- struct cvmx_ciu_soft_prst3_s cn66xx;
-};
-
-union cvmx_ciu_soft_rst {
- uint64_t u64;
- struct cvmx_ciu_soft_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t soft_rst:1;
-#else
- uint64_t soft_rst:1;
- uint64_t reserved_1_63:63;
-#endif
- } s;
- struct cvmx_ciu_soft_rst_s cn30xx;
- struct cvmx_ciu_soft_rst_s cn31xx;
- struct cvmx_ciu_soft_rst_s cn38xx;
- struct cvmx_ciu_soft_rst_s cn38xxp2;
- struct cvmx_ciu_soft_rst_s cn50xx;
- struct cvmx_ciu_soft_rst_s cn52xx;
- struct cvmx_ciu_soft_rst_s cn52xxp1;
- struct cvmx_ciu_soft_rst_s cn56xx;
- struct cvmx_ciu_soft_rst_s cn56xxp1;
- struct cvmx_ciu_soft_rst_s cn58xx;
- struct cvmx_ciu_soft_rst_s cn58xxp1;
- struct cvmx_ciu_soft_rst_s cn61xx;
- struct cvmx_ciu_soft_rst_s cn63xx;
- struct cvmx_ciu_soft_rst_s cn63xxp1;
- struct cvmx_ciu_soft_rst_s cn66xx;
- struct cvmx_ciu_soft_rst_s cn68xx;
- struct cvmx_ciu_soft_rst_s cn68xxp1;
- struct cvmx_ciu_soft_rst_s cnf71xx;
-};
-
-union cvmx_ciu_sum1_iox_int {
- uint64_t u64;
- struct cvmx_ciu_sum1_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
+ __BITFIELD_FIELD(uint64_t reserved_3_63:61,
+ __BITFIELD_FIELD(uint64_t host64:1,
+ __BITFIELD_FIELD(uint64_t npi:1,
+ __BITFIELD_FIELD(uint64_t soft_prst:1,
+ ;))))
} s;
- struct cvmx_ciu_sum1_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum1_iox_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_sum1_iox_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip2 {
- uint64_t u64;
- struct cvmx_ciu_sum1_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_sum1_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum1_ppx_ip2_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_sum1_ppx_ip2_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip3 {
- uint64_t u64;
- struct cvmx_ciu_sum1_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_sum1_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum1_ppx_ip3_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_sum1_ppx_ip3_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip4 {
- uint64_t u64;
- struct cvmx_ciu_sum1_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } s;
- struct cvmx_ciu_sum1_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_41_45:5;
- uint64_t dpi_dma:1;
- uint64_t reserved_38_39:2;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_4_17:14;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_17:14;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_39:2;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_45:5;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum1_ppx_ip4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_62_62:1;
- uint64_t srio3:1;
- uint64_t srio2:1;
- uint64_t reserved_57_59:3;
- uint64_t dfm:1;
- uint64_t reserved_53_55:3;
- uint64_t lmc0:1;
- uint64_t reserved_51_51:1;
- uint64_t srio0:1;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t agl:1;
- uint64_t reserved_38_45:8;
- uint64_t agx1:1;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t dfa:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t zip:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t mii1:1;
- uint64_t reserved_10_17:8;
- uint64_t wdog:10;
-#else
- uint64_t wdog:10;
- uint64_t reserved_10_17:8;
- uint64_t mii1:1;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t zip:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t dfa:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t agx1:1;
- uint64_t reserved_38_45:8;
- uint64_t agl:1;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t srio0:1;
- uint64_t reserved_51_51:1;
- uint64_t lmc0:1;
- uint64_t reserved_53_55:3;
- uint64_t dfm:1;
- uint64_t reserved_57_59:3;
- uint64_t srio2:1;
- uint64_t srio3:1;
- uint64_t reserved_62_62:1;
- uint64_t rst:1;
-#endif
- } cn66xx;
- struct cvmx_ciu_sum1_ppx_ip4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t rst:1;
- uint64_t reserved_53_62:10;
- uint64_t lmc0:1;
- uint64_t reserved_50_51:2;
- uint64_t pem1:1;
- uint64_t pem0:1;
- uint64_t ptp:1;
- uint64_t reserved_41_46:6;
- uint64_t dpi_dma:1;
- uint64_t reserved_37_39:3;
- uint64_t agx0:1;
- uint64_t dpi:1;
- uint64_t sli:1;
- uint64_t usb:1;
- uint64_t reserved_32_32:1;
- uint64_t key:1;
- uint64_t rad:1;
- uint64_t tim:1;
- uint64_t reserved_28_28:1;
- uint64_t pko:1;
- uint64_t pip:1;
- uint64_t ipd:1;
- uint64_t l2c:1;
- uint64_t pow:1;
- uint64_t fpa:1;
- uint64_t iob:1;
- uint64_t mio:1;
- uint64_t nand:1;
- uint64_t reserved_4_18:15;
- uint64_t wdog:4;
-#else
- uint64_t wdog:4;
- uint64_t reserved_4_18:15;
- uint64_t nand:1;
- uint64_t mio:1;
- uint64_t iob:1;
- uint64_t fpa:1;
- uint64_t pow:1;
- uint64_t l2c:1;
- uint64_t ipd:1;
- uint64_t pip:1;
- uint64_t pko:1;
- uint64_t reserved_28_28:1;
- uint64_t tim:1;
- uint64_t rad:1;
- uint64_t key:1;
- uint64_t reserved_32_32:1;
- uint64_t usb:1;
- uint64_t sli:1;
- uint64_t dpi:1;
- uint64_t agx0:1;
- uint64_t reserved_37_39:3;
- uint64_t dpi_dma:1;
- uint64_t reserved_41_46:6;
- uint64_t ptp:1;
- uint64_t pem0:1;
- uint64_t pem1:1;
- uint64_t reserved_50_51:2;
- uint64_t lmc0:1;
- uint64_t reserved_53_62:10;
- uint64_t rst:1;
-#endif
- } cnf71xx;
-};
-
-union cvmx_ciu_sum2_iox_int {
- uint64_t u64;
- struct cvmx_ciu_sum2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_sum2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum2_iox_int_cn61xx cn66xx;
- struct cvmx_ciu_sum2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip2 {
- uint64_t u64;
- struct cvmx_ciu_sum2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_sum2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum2_ppx_ip2_cn61xx cn66xx;
- struct cvmx_ciu_sum2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip3 {
- uint64_t u64;
- struct cvmx_ciu_sum2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_sum2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum2_ppx_ip3_cn61xx cn66xx;
- struct cvmx_ciu_sum2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip4 {
- uint64_t u64;
- struct cvmx_ciu_sum2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_15_63:49;
- uint64_t endor:2;
- uint64_t eoi:1;
- uint64_t reserved_10_11:2;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_11:2;
- uint64_t eoi:1;
- uint64_t endor:2;
- uint64_t reserved_15_63:49;
-#endif
- } s;
- struct cvmx_ciu_sum2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_10_63:54;
- uint64_t timer:6;
- uint64_t reserved_0_3:4;
-#else
- uint64_t reserved_0_3:4;
- uint64_t timer:6;
- uint64_t reserved_10_63:54;
-#endif
- } cn61xx;
- struct cvmx_ciu_sum2_ppx_ip4_cn61xx cn66xx;
- struct cvmx_ciu_sum2_ppx_ip4_s cnf71xx;
};
union cvmx_ciu_timx {
uint64_t u64;
struct cvmx_ciu_timx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_37_63:27;
- uint64_t one_shot:1;
- uint64_t len:36;
-#else
- uint64_t len:36;
- uint64_t one_shot:1;
- uint64_t reserved_37_63:27;
-#endif
- } s;
- struct cvmx_ciu_timx_s cn30xx;
- struct cvmx_ciu_timx_s cn31xx;
- struct cvmx_ciu_timx_s cn38xx;
- struct cvmx_ciu_timx_s cn38xxp2;
- struct cvmx_ciu_timx_s cn50xx;
- struct cvmx_ciu_timx_s cn52xx;
- struct cvmx_ciu_timx_s cn52xxp1;
- struct cvmx_ciu_timx_s cn56xx;
- struct cvmx_ciu_timx_s cn56xxp1;
- struct cvmx_ciu_timx_s cn58xx;
- struct cvmx_ciu_timx_s cn58xxp1;
- struct cvmx_ciu_timx_s cn61xx;
- struct cvmx_ciu_timx_s cn63xx;
- struct cvmx_ciu_timx_s cn63xxp1;
- struct cvmx_ciu_timx_s cn66xx;
- struct cvmx_ciu_timx_s cn68xx;
- struct cvmx_ciu_timx_s cn68xxp1;
- struct cvmx_ciu_timx_s cnf71xx;
-};
-
-union cvmx_ciu_tim_multi_cast {
- uint64_t u64;
- struct cvmx_ciu_tim_multi_cast_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_1_63:63;
- uint64_t en:1;
-#else
- uint64_t en:1;
- uint64_t reserved_1_63:63;
-#endif
+ __BITFIELD_FIELD(uint64_t reserved_37_63:27,
+ __BITFIELD_FIELD(uint64_t one_shot:1,
+ __BITFIELD_FIELD(uint64_t len:36,
+ ;)))
} s;
- struct cvmx_ciu_tim_multi_cast_s cn61xx;
- struct cvmx_ciu_tim_multi_cast_s cn66xx;
- struct cvmx_ciu_tim_multi_cast_s cnf71xx;
};
union cvmx_ciu_wdogx {
uint64_t u64;
struct cvmx_ciu_wdogx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_46_63:18;
- uint64_t gstopen:1;
- uint64_t dstop:1;
- uint64_t cnt:24;
- uint64_t len:16;
- uint64_t state:2;
- uint64_t mode:2;
-#else
- uint64_t mode:2;
- uint64_t state:2;
- uint64_t len:16;
- uint64_t cnt:24;
- uint64_t dstop:1;
- uint64_t gstopen:1;
- uint64_t reserved_46_63:18;
-#endif
+ __BITFIELD_FIELD(uint64_t reserved_46_63:18,
+ __BITFIELD_FIELD(uint64_t gstopen:1,
+ __BITFIELD_FIELD(uint64_t dstop:1,
+ __BITFIELD_FIELD(uint64_t cnt:24,
+ __BITFIELD_FIELD(uint64_t len:16,
+ __BITFIELD_FIELD(uint64_t state:2,
+ __BITFIELD_FIELD(uint64_t mode:2,
+ ;)))))))
} s;
- struct cvmx_ciu_wdogx_s cn30xx;
- struct cvmx_ciu_wdogx_s cn31xx;
- struct cvmx_ciu_wdogx_s cn38xx;
- struct cvmx_ciu_wdogx_s cn38xxp2;
- struct cvmx_ciu_wdogx_s cn50xx;
- struct cvmx_ciu_wdogx_s cn52xx;
- struct cvmx_ciu_wdogx_s cn52xxp1;
- struct cvmx_ciu_wdogx_s cn56xx;
- struct cvmx_ciu_wdogx_s cn56xxp1;
- struct cvmx_ciu_wdogx_s cn58xx;
- struct cvmx_ciu_wdogx_s cn58xxp1;
- struct cvmx_ciu_wdogx_s cn61xx;
- struct cvmx_ciu_wdogx_s cn63xx;
- struct cvmx_ciu_wdogx_s cn63xxp1;
- struct cvmx_ciu_wdogx_s cn66xx;
- struct cvmx_ciu_wdogx_s cn68xx;
- struct cvmx_ciu_wdogx_s cn68xxp1;
- struct cvmx_ciu_wdogx_s cnf71xx;
};
-#endif
+#endif /* __CVMX_CIU_DEFS_H__ */
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
return CVMX_ADD_IO_SEG(0x0001180008000540ull) + (block_id) * 0x8000000ull;
}
+void __cvmx_interrupt_gmxx_enable(int interface);
+
union cvmx_gmxx_bad_reg {
uint64_t u64;
struct cvmx_gmxx_bad_reg_s {
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
return CVMX_ADD_IO_SEG(0x00011800B0001048ull) + ((offset) + (block_id) * 0x20000ull) * 1024;
}
+void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
+
union cvmx_pcsx_anx_adv_reg {
uint64_t u64;
struct cvmx_pcsx_anx_adv_reg_s {
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
return CVMX_ADD_IO_SEG(0x00011800B0000830ull) + (block_id) * 0x1000000ull;
}
+void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+
union cvmx_pcsxx_10gbx_status_reg {
uint64_t u64;
struct cvmx_pcsxx_10gbx_status_reg_s {
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#define CVMX_SPXX_TPA_SEL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000328ull) + ((block_id) & 1) * 0x8000000ull)
#define CVMX_SPXX_TRN4_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000360ull) + ((block_id) & 1) * 0x8000000ull)
+void __cvmx_interrupt_spxx_int_msk_enable(int index);
+
union cvmx_spxx_bckprs_cnt {
uint64_t u64;
struct cvmx_spxx_bckprs_cnt_s {
* Contact: support@caviumnetworks.com
* This file is part of the OCTEON SDK
*
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
#define CVMX_STXX_STAT_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000638ull) + ((block_id) & 1) * 0x8000000ull)
#define CVMX_STXX_STAT_PKT_XMT(block_id) (CVMX_ADD_IO_SEG(0x0001180090000640ull) + ((block_id) & 1) * 0x8000000ull)
+void __cvmx_interrupt_stxx_int_msk_enable(int index);
+
union cvmx_stxx_arb_ctl {
uint64_t u64;
struct cvmx_stxx_arb_ctl_s {
} s;
};
-extern void octeon_write_lcd(const char *s);
extern void octeon_check_cpu_bist(void);
-extern int octeon_get_boot_uart(void);
-struct uart_port;
-extern unsigned int octeon_serial_in(struct uart_port *, int);
-extern void octeon_serial_out(struct uart_port *, int, int);
+int octeon_prune_device_tree(void);
+extern const char __appended_dtb;
+extern const char __dtb_octeon_3xxx_begin;
+extern const char __dtb_octeon_68xx_begin;
/**
* Write a 32bit value to the Octeon NPI register space
*/
extern enum octeon_dma_bar_type octeon_dma_bar_type;
+void octeon_pci_dma_init(void);
+extern char *octeon_swiotlb;
+
#endif
* used in our early mem init code for all memory models.
* So always define it.
*/
-#define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET)
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+extern unsigned long ARCH_PFN_OFFSET;
+# define ARCH_PFN_OFFSET ARCH_PFN_OFFSET
+#else
+# define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET)
+#endif
extern void clear_page(void * page);
extern void copy_page(void * to, void * from);
((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE)
-#define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET)
+#define UNCAC_ADDR(addr) (UNCAC_BASE + __pa(addr))
+#define CAC_ADDR(addr) ((unsigned long)__va((addr) - UNCAC_BASE))
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
#define NUM_DSP_REGS 6
-typedef __u32 dspreg_t;
+typedef unsigned long dspreg_t;
struct mips_dsp_state {
dspreg_t dspr[NUM_DSP_REGS];
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
#define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
+#ifdef CONFIG_CPU_LOONGSON3
+/*
+ * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
+ * tight read loop is executed, because reads take priority over writes & the
+ * hardware (incorrectly) doesn't ensure that writes will eventually occur.
+ *
+ * Since spin loops of any kind should have a cpu_relax() in them, force an SFB
+ * flush from cpu_relax() such that any pending writes will become visible as
+ * expected.
+ */
+#define cpu_relax() smp_mb()
+#else
#define cpu_relax() barrier()
+#endif
/*
* Return_address is a replacement for __builtin_return_address(count)
#ifndef _MIPS_SETUP_H
#define _MIPS_SETUP_H
+#include <linux/types.h>
#include <uapi/asm/setup.h>
+extern void prom_putchar(char);
extern void setup_early_printk(void);
#ifdef CONFIG_EARLY_PRINTK_8250
#define PROM_FLAG_DONT_FREE_TEMP 4
/* Simple char-by-char console I/O. */
-extern void prom_putchar(char c);
extern char prom_getchar(void);
/* Get next memory descriptor after CURR, returns first descriptor
".end\t__" #symbol "\n\t" \
".size\t__" #symbol",. - __" #symbol)
-#define nabi_no_regargs
-
#endif /* CONFIG_32BIT */
#ifdef CONFIG_64BIT
".end\t__" #symbol "\n\t" \
".size\t__" #symbol",. - __" #symbol)
-#define nabi_no_regargs \
- unsigned long __dummy0, \
- unsigned long __dummy1, \
- unsigned long __dummy2, \
- unsigned long __dummy3, \
- unsigned long __dummy4, \
- unsigned long __dummy5, \
- unsigned long __dummy6, \
- unsigned long __dummy7,
-
#endif /* CONFIG_64BIT */
#endif /* _ASM_SIM_H */
extern cpumask_t cpu_core_map[];
extern cpumask_t cpu_foreign_map[];
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+static inline int raw_smp_processor_id(void)
+{
+#if defined(__VDSO__)
+ extern int vdso_smp_processor_id(void)
+ __compiletime_error("VDSO should not call smp_processor_id()");
+ return vdso_smp_processor_id();
+#else
+ return current_thread_info()->cpu;
+#endif
+}
+#define raw_smp_processor_id raw_smp_processor_id
/* Map from cpu id to sequential logical cpu number. This will only
not be idempotent when cpus failed to come on-line. */
void txx9_ethaddr_init(unsigned int id, unsigned char *ethaddr);
void txx9_sio_init(unsigned long baseaddr, int irq,
unsigned int line, unsigned int sclk, int nocts);
-void prom_putchar(char c);
#ifdef CONFIG_EARLY_PRINTK
extern void (*txx9_prom_putchar)(char c);
void txx9_sio_putchar_init(unsigned long baseaddr);
struct tx4939_le_reg maskext;
};
-struct tx4939_rtc_reg {
- __u32 ctl;
- __u32 adr;
- __u32 dat;
- __u32 tbc;
-};
-
struct tx4939_crypto_reg {
struct tx4939_le_reg csr;
struct tx4939_le_reg idesptr;
#define TX4939_CLKCTR_SIO0RST 0x00000002
#define TX4939_CLKCTR_CYPRST 0x00000001
-/*
- * RTC
- */
-#define TX4939_RTCCTL_ALME 0x00000080
-#define TX4939_RTCCTL_ALMD 0x00000040
-#define TX4939_RTCCTL_BUSY 0x00000020
-
-#define TX4939_RTCCTL_COMMAND 0x00000007
-#define TX4939_RTCCTL_COMMAND_NOP 0x00000000
-#define TX4939_RTCCTL_COMMAND_GETTIME 0x00000001
-#define TX4939_RTCCTL_COMMAND_SETTIME 0x00000002
-#define TX4939_RTCCTL_COMMAND_GETALARM 0x00000003
-#define TX4939_RTCCTL_COMMAND_SETALARM 0x00000004
-
-#define TX4939_RTCTBC_PM 0x00000080
-#define TX4939_RTCTBC_COMP 0x0000007f
-
-#define TX4939_RTC_REG_RAMSIZE 0x00000100
-#define TX4939_RTC_REG_RWBSIZE 0x00000006
-
/*
* CRYPTO
*/
#define tx4939_ccfgptr \
((struct tx4939_ccfg_reg __iomem *)TX4939_CCFG_REG)
#define tx4939_sramcptr tx4938_sramcptr
-#define tx4939_rtcptr \
- ((struct tx4939_rtc_reg __iomem *)TX4939_RTC_REG)
#define tx4939_cryptoptr \
((struct tx4939_crypto_reg __iomem *)TX4939_CRYPTO_REG)
#define tx4939_vpcptr ((struct tx4939_vpc_reg __iomem *)TX4939_VPC_REG)
#define __NR_pkey_alloc (__NR_Linux + 364)
#define __NR_pkey_free (__NR_Linux + 365)
#define __NR_statx (__NR_Linux + 366)
+#define __NR_rseq (__NR_Linux + 367)
+#define __NR_io_pgetevents (__NR_Linux + 368)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 366
+#define __NR_Linux_syscalls 368
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 366
+#define __NR_O32_Linux_syscalls 368
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_pkey_alloc (__NR_Linux + 324)
#define __NR_pkey_free (__NR_Linux + 325)
#define __NR_statx (__NR_Linux + 326)
+#define __NR_rseq (__NR_Linux + 327)
+#define __NR_io_pgetevents (__NR_Linux + 328)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 326
+#define __NR_Linux_syscalls 328
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 326
+#define __NR_64_Linux_syscalls 328
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_pkey_alloc (__NR_Linux + 328)
#define __NR_pkey_free (__NR_Linux + 329)
#define __NR_statx (__NR_Linux + 330)
+#define __NR_rseq (__NR_Linux + 331)
+#define __NR_io_pgetevents (__NR_Linux + 332)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 330
+#define __NR_Linux_syscalls 332
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 330
+#define __NR_N32_Linux_syscalls 332
#endif /* _UAPI_ASM_UNISTD_H */
#include <linux/bootmem.h>
#include <linux/spinlock.h>
#include <linux/gfp.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <asm/mipsregs.h>
#include <asm/jazz.h>
#include <asm/io.h>
printk(KERN_INFO "VDMA: R4030 DMA pagetables initialized.\n");
return 0;
}
+arch_initcall(vdma_init);
/*
* Allocate DMA pagetables using a simple first-fit algorithm
return enable;
}
-arch_initcall(vdma_init);
+static void *jazz_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+ void *ret;
+
+ ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+ if (!ret)
+ return NULL;
+
+ *dma_handle = vdma_alloc(virt_to_phys(ret), size);
+ if (*dma_handle == VDMA_ERROR) {
+ dma_direct_free(dev, size, ret, *dma_handle, attrs);
+ return NULL;
+ }
+
+ if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
+ dma_cache_wback_inv((unsigned long)ret, size);
+ ret = (void *)UNCAC_ADDR(ret);
+ }
+ return ret;
+}
+
+static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle, unsigned long attrs)
+{
+ vdma_free(dma_handle);
+ if (!(attrs & DMA_ATTR_NON_CONSISTENT))
+ vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+ return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+}
+
+static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ phys_addr_t phys = page_to_phys(page) + offset;
+
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(dev, phys, size, dir);
+ return vdma_alloc(phys, size);
+}
+
+static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+ vdma_free(dma_addr);
+}
+
+static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sglist, sg, nents, i) {
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+ dir);
+ sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
+ if (sg->dma_address == VDMA_ERROR)
+ return 0;
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nents;
+}
+
+static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sglist, sg, nents, i) {
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
+ dir);
+ vdma_free(sg->dma_address);
+ }
+}
+
+static void jazz_dma_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void jazz_dma_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr == VDMA_ERROR;
+}
+
+const struct dma_map_ops jazz_dma_ops = {
+ .alloc = jazz_dma_alloc,
+ .free = jazz_dma_free,
+ .mmap = arch_dma_mmap,
+ .map_page = jazz_dma_map_page,
+ .unmap_page = jazz_dma_unmap_page,
+ .map_sg = jazz_dma_map_sg,
+ .unmap_sg = jazz_dma_unmap_sg,
+ .sync_single_for_cpu = jazz_dma_sync_single_for_cpu,
+ .sync_single_for_device = jazz_dma_sync_single_for_device,
+ .sync_sg_for_cpu = jazz_dma_sync_sg_for_cpu,
+ .sync_sg_for_device = jazz_dma_sync_sg_for_device,
+ .dma_supported = dma_direct_supported,
+ .cache_sync = arch_dma_cache_sync,
+ .mapping_error = jazz_dma_mapping_error,
+};
+EXPORT_SYMBOL(jazz_dma_ops);
#include <linux/screen_info.h>
#include <linux/platform_device.h>
#include <linux/serial_8250.h>
+#include <linux/dma-mapping.h>
#include <asm/jazz.h>
#include <asm/jazzdma.h>
}
};
+static u64 jazz_esp_dma_mask = DMA_BIT_MASK(32);
+
static struct platform_device jazz_esp_pdev = {
.name = "jazz_esp",
.num_resources = ARRAY_SIZE(jazz_esp_rsrc),
- .resource = jazz_esp_rsrc
+ .resource = jazz_esp_rsrc,
+ .dev = {
+ .dma_mask = &jazz_esp_dma_mask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ }
};
static struct resource jazz_sonic_rsrc[] = {
}
};
+static u64 jazz_sonic_dma_mask = DMA_BIT_MASK(32);
+
static struct platform_device jazz_sonic_pdev = {
.name = "jazzsonic",
.num_resources = ARRAY_SIZE(jazz_sonic_rsrc),
- .resource = jazz_sonic_rsrc
+ .resource = jazz_sonic_rsrc,
+ .dev = {
+ .dma_mask = &jazz_sonic_dma_mask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ }
};
static struct resource jazz_cmos_rsrc[] = {
platform-$(CONFIG_MACH_INGENIC) += jz4740/
cflags-$(CONFIG_MACH_INGENIC) += -I$(srctree)/arch/mips/include/asm/mach-jz4740
load-$(CONFIG_MACH_INGENIC) += 0xffffffff80010000
-zload-$(CONFIG_MACH_INGENIC) += 0xffffffff80600000
+zload-$(CONFIG_MACH_INGENIC) += 0xffffffff81000000
set_elf_platform(cpu, "loongson3a");
set_isa(c, MIPS_CPU_ISA_M64R2);
break;
- case PRID_REV_LOONGSON3A_R3:
+ case PRID_REV_LOONGSON3A_R3_0:
+ case PRID_REV_LOONGSON3A_R3_1:
c->cputype = CPU_LOONGSON3;
__cpu_name[cpu] = "ICT Loongson-3";
set_elf_platform(cpu, "loongson3a");
#include <asm/setup.h>
-extern void prom_putchar(char);
-
static void early_console_write(struct console *con, const char *s, unsigned n)
{
while (n-- && *s) {
#include <linux/io.h>
#include <linux/serial_core.h>
#include <linux/serial_reg.h>
+#include <asm/setup.h>
static void __iomem *serial8250_base;
static unsigned int serial8250_reg_shift;
jal schedule_tail # a0 = struct task_struct *prev
FEXPORT(syscall_exit)
+#ifdef CONFIG_DEBUG_RSEQ
+ move a0, sp
+ jal rseq_syscall
+#endif
local_irq_disable # make sure need_resched and
# signals dont change between
# sampling and return
j resume_userspace_check
FEXPORT(syscall_exit_partial)
+#ifdef CONFIG_DEBUG_RSEQ
+ move a0, sp
+ jal rseq_syscall
+#endif
local_irq_disable # make sure need_resched doesn't
# change between and return
LONG_L a2, TI_FLAGS($28) # current->work
sll k0, k0, 30 # Check for SDBBP.
bgez k0, ejtag_return
+#ifdef CONFIG_SMP
+1: PTR_LA k0, ejtag_debug_buffer_spinlock
+ ll k0, 0(k0)
+ bnez k0, 1b
+ PTR_LA k0, ejtag_debug_buffer_spinlock
+ sc k0, 0(k0)
+ beqz k0, 1b
+# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+ sync
+# endif
+
+ PTR_LA k0, ejtag_debug_buffer
+ LONG_S k1, 0(k0)
+
+ ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+ PTR_SRL k1, SMP_CPUID_PTRSHIFT
+ PTR_SLL k1, LONGLOG
+ PTR_LA k0, ejtag_debug_buffer_per_cpu
+ PTR_ADDU k0, k1
+
+ PTR_LA k1, ejtag_debug_buffer
+ LONG_L k1, 0(k1)
+ LONG_S k1, 0(k0)
+
+ PTR_LA k0, ejtag_debug_buffer_spinlock
+ sw zero, 0(k0)
+#else
PTR_LA k0, ejtag_debug_buffer
LONG_S k1, 0(k0)
+#endif
+
SAVE_ALL
move a0, sp
jal ejtag_exception_handler
RESTORE_ALL
+
+#ifdef CONFIG_SMP
+ ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+ PTR_SRL k1, SMP_CPUID_PTRSHIFT
+ PTR_SLL k1, LONGLOG
+ PTR_LA k0, ejtag_debug_buffer_per_cpu
+ PTR_ADDU k0, k1
+ LONG_L k1, 0(k0)
+#else
PTR_LA k0, ejtag_debug_buffer
LONG_L k1, 0(k0)
+#endif
ejtag_return:
+ back_to_back_c0_hazard
MFC0 k0, CP0_DESAVE
.set mips32
deret
.data
EXPORT(ejtag_debug_buffer)
.fill LONGSIZE
+#ifdef CONFIG_SMP
+EXPORT(ejtag_debug_buffer_spinlock)
+ .fill LONGSIZE
+EXPORT(ejtag_debug_buffer_per_cpu)
+ .fill LONGSIZE * NR_CPUS
+#endif
.previous
__INIT
void (*cpu_wait)(void);
EXPORT_SYMBOL(cpu_wait);
-static void r3081_wait(void)
+static void __cpuidle r3081_wait(void)
{
unsigned long cfg = read_c0_conf();
write_c0_conf(cfg | R30XX_CONF_HALT);
local_irq_enable();
}
-static void r39xx_wait(void)
+static void __cpuidle r39xx_wait(void)
{
if (!need_resched())
write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
local_irq_enable();
}
-void r4k_wait(void)
+void __cpuidle r4k_wait(void)
{
local_irq_enable();
__r4k_wait();
* interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
* using this version a gamble.
*/
-void r4k_wait_irqoff(void)
+void __cpuidle r4k_wait_irqoff(void)
{
if (!need_resched())
__asm__(
* The RM7000 variant has to handle erratum 38. The workaround is to not
* have any pending stores when the WAIT instruction is executed.
*/
-static void rm7k_wait_irqoff(void)
+static void __cpuidle rm7k_wait_irqoff(void)
{
if (!need_resched())
__asm__(
* since coreclock (and the cp0 counter) stops upon executing it. Only an
* interrupt can wake it, so they must be enabled before entering idle modes.
*/
-static void au1k_wait(void)
+static void __cpuidle au1k_wait(void)
{
unsigned long c0status = read_c0_status() | 1; /* irqs on */
preempt_enable_no_resched();
}
return 1;
- } else {
- if (addr->word != breakpoint_insn.word) {
- /*
- * The breakpoint instruction was removed by
- * another cpu right after we hit, no further
- * handling of this interrupt is appropriate
- */
- ret = 1;
- goto no_kprobe;
- }
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs))
- goto ss_probe;
+ } else if (addr->word != breakpoint_insn.word) {
+ /*
+ * The breakpoint instruction was removed by
+ * another cpu right after we hit, no further
+ * handling of this interrupt is appropriate
+ */
+ ret = 1;
}
goto no_kprobe;
}
if (p->pre_handler && p->pre_handler(p, regs)) {
/* handler has already set things up, so skip ss setup */
+ reset_current_kprobe();
+ preempt_enable_no_resched();
return 1;
}
-ss_probe:
prepare_singlestep(p, regs, kcb);
if (kcb->flags & SKIP_DELAYSLOT) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
return ret;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- kcb->jprobe_saved_regs = *regs;
- kcb->jprobe_saved_sp = regs->regs[29];
-
- memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
- MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-
- regs->cp0_epc = (unsigned long)(jp->entry);
-
- return 1;
-}
-
-/* Defined in the inline asm below. */
-void jprobe_return_end(void);
-
-void __kprobes jprobe_return(void)
-{
- /* Assembler quirk necessitates this '0,code' business. */
- asm volatile(
- "break 0,%0\n\t"
- ".globl jprobe_return_end\n"
- "jprobe_return_end:\n"
- : : "n" (BRK_KPROBE_BP) : "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- if (regs->cp0_epc >= (unsigned long)jprobe_return &&
- regs->cp0_epc <= (unsigned long)jprobe_return_end) {
- *regs = kcb->jprobe_saved_regs;
- memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
- MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
- preempt_enable_no_resched();
-
- return 1;
- }
- return 0;
-}
-
/*
* Function return probe trampoline:
* - init_kprobes() establishes a probepoint here
kretprobe_assert(ri, orig_ret_address, trampoline_address);
instruction_pointer(regs) = orig_ret_address;
- reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
#include <asm/mmu_context.h>
#include <asm/mman.h>
-/* Use this to get at 32-bit user passed pointers. */
-/* A() macro should be used for places where you e.g.
- have some internal variable u32 and just want to get
- rid of a compiler warning. AA() has to be used in
- places where you want to convert a function argument
- to 32bit pointer or when you e.g. access pt_regs
- structure and want to consider 32bit registers only.
- */
-#define A(__x) ((unsigned long)(__x))
-#define AA(__x) ((unsigned long)((int)__x))
-
#ifdef __MIPSEB__
#define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
#endif
#define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
#endif
-SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len,
- unsigned long, prot, unsigned long, flags, unsigned long, fd,
- unsigned long, pgoff)
-{
- if (pgoff & (~PAGE_MASK >> 12))
- return -EINVAL;
- return ksys_mmap_pgoff(addr, len, prot, flags, fd,
- pgoff >> (PAGE_SHIFT-12));
-}
-
-#define RLIM_INFINITY32 0x7fffffff
-#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
-
-struct rlimit32 {
- int rlim_cur;
- int rlim_max;
-};
-
SYSCALL_DEFINE4(32_truncate64, const char __user *, path,
unsigned long, __dummy, unsigned long, a2, unsigned long, a3)
{
EXPORT_SYMBOL(_mcount)
PTR_LA t1, ftrace_stub
PTR_L t2, ftrace_trace_function /* Prepare t2 for (1) */
- bne t1, t2, static_trace
+ beq t1, t2, fgraph_trace
nop
+ MCOUNT_SAVE_REGS
+
+ move a0, ra /* arg1: self return address */
+ jalr t2 /* (1) call *ftrace_trace_function */
+ move a1, AT /* arg2: parent's return address */
+
+ MCOUNT_RESTORE_REGS
+
+fgraph_trace:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ PTR_LA t1, ftrace_stub
PTR_L t3, ftrace_graph_return
bne t1, t3, ftrace_graph_caller
nop
bne t1, t3, ftrace_graph_caller
nop
#endif
- b ftrace_stub
-#ifdef CONFIG_32BIT
- addiu sp, sp, 8
-#else
- nop
-#endif
-static_trace:
- MCOUNT_SAVE_REGS
-
- move a0, ra /* arg1: self return address */
- jalr t2 /* (1) call *ftrace_trace_function */
- move a1, AT /* arg2: parent's return address */
-
- MCOUNT_RESTORE_REGS
#ifdef CONFIG_32BIT
addiu sp, sp, 8
#endif
+
.globl ftrace_stub
ftrace_stub:
RETURN_BACK
#include <linux/kallsyms.h>
#include <linux/random.h>
#include <linux/prctl.h>
+#include <linux/nmi.h>
+#include <linux/cpu.h>
#include <asm/asm.h>
#include <asm/bootinfo.h>
return sp & ALMASK;
}
-static void arch_dump_stack(void *info)
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
+static struct cpumask backtrace_csd_busy;
+
+static void handle_backtrace(void *info)
{
- struct pt_regs *regs;
+ nmi_cpu_backtrace(get_irq_regs());
+ cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
+}
- regs = get_irq_regs();
+static void raise_backtrace(cpumask_t *mask)
+{
+ call_single_data_t *csd;
+ int cpu;
- if (regs)
- show_regs(regs);
+ for_each_cpu(cpu, mask) {
+ /*
+ * If we previously sent an IPI to the target CPU & it hasn't
+ * cleared its bit in the busy cpumask then it didn't handle
+ * our previous IPI & it's not safe for us to reuse the
+ * call_single_data_t.
+ */
+ if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
+ pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
+ cpu);
+ continue;
+ }
- dump_stack();
+ csd = &per_cpu(backtrace_csd, cpu);
+ csd->func = handle_backtrace;
+ smp_call_function_single_async(cpu, csd);
+ }
}
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{
- long this_cpu = get_cpu();
-
- if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
- dump_stack();
-
- smp_call_function_many(mask, arch_dump_stack, NULL, 1);
-
- put_cpu();
+ nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
}
int mips_get_process_fp_mode(struct task_struct *task)
return value;
}
-static void prepare_for_fp_mode_switch(void *info)
+static long prepare_for_fp_mode_switch(void *unused)
{
- struct mm_struct *mm = info;
-
- if (current->mm == mm)
- lose_fpu(1);
+ /*
+ * This is icky, but we use this to simply ensure that all CPUs have
+ * context switched, regardless of whether they were previously running
+ * kernel or user code. This ensures that no CPU currently has its FPU
+ * enabled, or is about to attempt to enable it through any path other
+ * than enable_restore_fp_context() which will wait appropriately for
+ * fp_mode_switching to be zero.
+ */
+ return 0;
}
int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
{
const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
struct task_struct *t;
- int max_users;
+ struct cpumask process_cpus;
+ int cpu;
/* If nothing to change, return right away, successfully. */
if (value == mips_get_process_fp_mode(task))
if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
- /* Proceed with the mode switch */
- preempt_disable();
-
- /* Save FP & vector context, then disable FPU & MSA */
- if (task->signal == current->signal)
- lose_fpu(1);
-
- /* Prevent any threads from obtaining live FP context */
- atomic_set(&task->mm->context.fp_mode_switching, 1);
- smp_mb__after_atomic();
-
- /*
- * If there are multiple online CPUs then force any which are running
- * threads in this process to lose their FPU context, which they can't
- * regain until fp_mode_switching is cleared later.
- */
- if (num_online_cpus() > 1) {
- /* No need to send an IPI for the local CPU */
- max_users = (task->mm == current->mm) ? 1 : 0;
-
- if (atomic_read(¤t->mm->mm_users) > max_users)
- smp_call_function(prepare_for_fp_mode_switch,
- (void *)current->mm, 1);
- }
-
- /*
- * There are now no threads of the process with live FP context, so it
- * is safe to proceed with the FP mode switch.
- */
+ /* Indicate the new FP mode in each thread */
for_each_thread(task, t) {
/* Update desired FP register width */
if (value & PR_FP_MODE_FR) {
clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
}
- /* Allow threads to use FP again */
- atomic_set(&task->mm->context.fp_mode_switching, 0);
- preempt_enable();
+ /*
+ * We need to ensure that all threads in the process have switched mode
+ * before returning, in order to allow userland to not worry about
+ * races. We can do this by forcing all CPUs that any thread in the
+ * process may be running on to schedule something else - in this case
+ * prepare_for_fp_mode_switch().
+ *
+ * We begin by generating a mask of all CPUs that any thread in the
+ * process may be running on.
+ */
+ cpumask_clear(&process_cpus);
+ for_each_thread(task, t)
+ cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+ /*
+ * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+ *
+ * The CPUs may have rescheduled already since we switched mode or
+ * generated the cpumask, but that doesn't matter. If the task in this
+ * process is scheduled out then our scheduling
+ * prepare_for_fp_mode_switch() will simply be redundant. If it's
+ * scheduled in then it will already have picked up the new FP mode
+ * whilst doing so.
+ */
+ get_online_cpus();
+ for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+ work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+ put_online_cpus();
wake_up_var(&task->mm->context.fp_mode_switching);
#include <asm/mipsmtregs.h>
#include <asm/pgtable.h>
#include <asm/page.h>
+#include <asm/processor.h>
#include <asm/syscall.h>
#include <linux/uaccess.h>
#include <asm/bootinfo.h>
return err;
}
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+/*
+ * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer.
+ */
+static int dsp32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ unsigned int start, num_regs, i;
+ u32 dspregs[NUM_DSP_REGS + 1];
+
+ BUG_ON(count % sizeof(u32));
+
+ if (!cpu_has_dsp)
+ return -EIO;
+
+ start = pos / sizeof(u32);
+ num_regs = count / sizeof(u32);
+
+ if (start + num_regs > NUM_DSP_REGS + 1)
+ return -EIO;
+
+ for (i = start; i < num_regs; i++)
+ switch (i) {
+ case 0 ... NUM_DSP_REGS - 1:
+ dspregs[i] = target->thread.dsp.dspr[i];
+ break;
+ case NUM_DSP_REGS:
+ dspregs[i] = target->thread.dsp.dspcontrol;
+ break;
+ }
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+ sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ unsigned int start, num_regs, i;
+ u32 dspregs[NUM_DSP_REGS + 1];
+ int err;
+
+ BUG_ON(count % sizeof(u32));
+
+ if (!cpu_has_dsp)
+ return -EIO;
+
+ start = pos / sizeof(u32);
+ num_regs = count / sizeof(u32);
+
+ if (start + num_regs > NUM_DSP_REGS + 1)
+ return -EIO;
+
+ err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+ sizeof(dspregs));
+ if (err)
+ return err;
+
+ for (i = start; i < num_regs; i++)
+ switch (i) {
+ case 0 ... NUM_DSP_REGS - 1:
+ target->thread.dsp.dspr[i] = (s32)dspregs[i];
+ break;
+ case NUM_DSP_REGS:
+ target->thread.dsp.dspcontrol = (s32)dspregs[i];
+ break;
+ }
+
+ return 0;
+}
+
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer.
+ */
+static int dsp64_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ unsigned int start, num_regs, i;
+ u64 dspregs[NUM_DSP_REGS + 1];
+
+ BUG_ON(count % sizeof(u64));
+
+ if (!cpu_has_dsp)
+ return -EIO;
+
+ start = pos / sizeof(u64);
+ num_regs = count / sizeof(u64);
+
+ if (start + num_regs > NUM_DSP_REGS + 1)
+ return -EIO;
+
+ for (i = start; i < num_regs; i++)
+ switch (i) {
+ case 0 ... NUM_DSP_REGS - 1:
+ dspregs[i] = target->thread.dsp.dspr[i];
+ break;
+ case NUM_DSP_REGS:
+ dspregs[i] = target->thread.dsp.dspcontrol;
+ break;
+ }
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+ sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp64_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ unsigned int start, num_regs, i;
+ u64 dspregs[NUM_DSP_REGS + 1];
+ int err;
+
+ BUG_ON(count % sizeof(u64));
+
+ if (!cpu_has_dsp)
+ return -EIO;
+
+ start = pos / sizeof(u64);
+ num_regs = count / sizeof(u64);
+
+ if (start + num_regs > NUM_DSP_REGS + 1)
+ return -EIO;
+
+ err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+ sizeof(dspregs));
+ if (err)
+ return err;
+
+ for (i = start; i < num_regs; i++)
+ switch (i) {
+ case 0 ... NUM_DSP_REGS - 1:
+ target->thread.dsp.dspr[i] = dspregs[i];
+ break;
+ case NUM_DSP_REGS:
+ target->thread.dsp.dspcontrol = dspregs[i];
+ break;
+ }
+
+ return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
+/*
+ * Determine whether the DSP context is present.
+ */
+static int dsp_active(struct task_struct *target,
+ const struct user_regset *regset)
+{
+ return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV;
+}
+
+/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer. */
+static int fp_mode_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ int fp_mode;
+
+ fp_mode = mips_get_process_fp_mode(target);
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+ sizeof(fp_mode));
+}
+
+/*
+ * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting.
+ *
+ * We optimize for the case where `count % sizeof(int) == 0', which
+ * is supposed to have been guaranteed by the kernel before calling
+ * us, e.g. in `ptrace_regset'. We enforce that requirement, so
+ * that we can safely avoid preinitializing temporaries for partial
+ * mode writes.
+ */
+static int fp_mode_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int fp_mode;
+ int err;
+
+ BUG_ON(count % sizeof(int));
+
+ if (pos + count > sizeof(fp_mode))
+ return -EIO;
+
+ err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+ sizeof(fp_mode));
+ if (err)
+ return err;
+
+ if (count > 0)
+ err = mips_set_process_fp_mode(target, fp_mode);
+
+ return err;
+}
+
enum mips_regset {
REGSET_GPR,
REGSET_FPR,
+ REGSET_DSP,
+ REGSET_FP_MODE,
};
struct pt_regs_offset {
.get = fpr_get,
.set = fpr_set,
},
+ [REGSET_DSP] = {
+ .core_note_type = NT_MIPS_DSP,
+ .n = NUM_DSP_REGS + 1,
+ .size = sizeof(u32),
+ .align = sizeof(u32),
+ .get = dsp32_get,
+ .set = dsp32_set,
+ .active = dsp_active,
+ },
+ [REGSET_FP_MODE] = {
+ .core_note_type = NT_MIPS_FP_MODE,
+ .n = 1,
+ .size = sizeof(int),
+ .align = sizeof(int),
+ .get = fp_mode_get,
+ .set = fp_mode_set,
+ },
};
static const struct user_regset_view user_mips_view = {
.get = fpr_get,
.set = fpr_set,
},
+ [REGSET_DSP] = {
+ .core_note_type = NT_MIPS_DSP,
+ .n = NUM_DSP_REGS + 1,
+ .size = sizeof(u64),
+ .align = sizeof(u64),
+ .get = dsp64_get,
+ .set = dsp64_set,
+ .active = dsp_active,
+ },
+ [REGSET_FP_MODE] = {
+ .core_note_type = NT_MIPS_FP_MODE,
+ .n = 1,
+ .size = sizeof(int),
+ .align = sizeof(int),
+ .get = fp_mode_get,
+ .set = fp_mode_set,
+ },
};
static const struct user_regset_view user_mips64_view = {
goto out;
}
dregs = __get_dsp_regs(child);
- tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+ tmp = dregs[addr - DSP_BASE];
break;
}
case DSP_CONTROL:
goto out;
}
dregs = __get_dsp_regs(child);
- tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+ tmp = dregs[addr - DSP_BASE];
break;
}
case DSP_CONTROL:
#ifdef CONFIG_CPU_CAVIUM_OCTEON
/* We need to flush I-cache before jumping to new kernel.
- * Unfortunatelly, this code is cpu-specific.
+ * Unfortunately, this code is cpu-specific.
*/
.set push
.set noreorder
#endif
/* All parameters to new kernel are passed in registers a0-a3.
- * kexec_args[0..3] are uses to prepare register values.
+ * kexec_args[0..3] are used to prepare register values.
*/
kexec_args:
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
PTR sys_statx
+ PTR sys_rseq
+ PTR sys_io_pgetevents
PTR sys_pkey_alloc
PTR sys_pkey_free /* 5325 */
PTR sys_statx
+ PTR sys_rseq
+ PTR sys_io_pgetevents
.size sys_call_table,.-sys_call_table
PTR sys_pkey_alloc
PTR sys_pkey_free
PTR sys_statx /* 6330 */
+ PTR sys_rseq
+ PTR compat_sys_io_pgetevents
.size sysn32_call_table,.-sysn32_call_table
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
PTR sys_statx
+ PTR sys_rseq
+ PTR compat_sys_io_pgetevents
.size sys32_call_table,.-sys32_call_table
#include <asm/cdmm.h>
#include <asm/cpu.h>
#include <asm/debug.h>
+#include <asm/dma-coherence.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp-ops.h>
static void *detect_magic __initdata = detect_memory_region;
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+unsigned long ARCH_PFN_OFFSET;
+EXPORT_SYMBOL(ARCH_PFN_OFFSET);
+#endif
+
void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
{
int x = boot_mem_map.nr_map;
* If the region reaches the top of the physical address space, adjust
* the size slightly so that (start + size) doesn't overflow
*/
- if (start + size - 1 == (phys_addr_t)ULLONG_MAX)
+ if (start + size - 1 == PHYS_ADDR_MAX)
--size;
/* Sanity check */
unsigned long reserved_end;
unsigned long mapstart = ~0UL;
unsigned long bootmap_size;
- phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX;
+ phys_addr_t ramstart = PHYS_ADDR_MAX;
bool bootmap_valid = false;
int i;
mapstart = max(reserved_end, start);
}
+ if (min_low_pfn >= max_low_pfn)
+ panic("Incorrect memory mapping !!!");
+
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+ ARCH_PFN_OFFSET = PFN_UP(ramstart);
+#else
/*
* Reserve any memory between the start of RAM and PHYS_OFFSET
*/
add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET,
BOOT_MEM_RESERVED);
- if (min_low_pfn >= max_low_pfn)
- panic("Incorrect memory mapping !!!");
if (min_low_pfn > ARCH_PFN_OFFSET) {
pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
(min_low_pfn - ARCH_PFN_OFFSET) * sizeof(struct page),
ARCH_PFN_OFFSET - min_low_pfn);
}
min_low_pfn = ARCH_PFN_OFFSET;
+#endif
/*
* Determine low and high memory ranges
}
arch_initcall(debugfs_mips);
#endif
+
+#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
+/* User defined DMA coherency from command line. */
+enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
+EXPORT_SYMBOL_GPL(coherentio);
+int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */
+
+static int __init setcoherentio(char *str)
+{
+ coherentio = IO_COHERENCE_ENABLED;
+ pr_info("Hardware DMA cache coherency (command line)\n");
+ return 0;
+}
+early_param("coherentio", setcoherentio);
+
+static int __init setnocoherentio(char *str)
+{
+ coherentio = IO_COHERENCE_DISABLED;
+ pr_info("Software DMA cache coherency (command line)\n");
+ return 0;
+}
+early_param("nocoherentio", setnocoherentio);
+#endif
#endif
#ifdef CONFIG_TRAD_SIGNALS
-asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_sigreturn(void)
{
struct sigframe __user *frame;
+ struct pt_regs *regs;
sigset_t blocked;
int sig;
- frame = (struct sigframe __user *) regs.regs[29];
+ regs = current_pt_regs();
+ frame = (struct sigframe __user *)regs->regs[29];
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked)))
set_current_blocked(&blocked);
- sig = restore_sigcontext(®s, &frame->sf_sc);
+ sig = restore_sigcontext(regs, &frame->sf_sc);
if (sig < 0)
goto badframe;
else if (sig)
__asm__ __volatile__(
"move\t$29, %0\n\t"
"j\tsyscall_exit"
- :/* no outputs */
- :"r" (®s));
+ : /* no outputs */
+ : "r" (regs));
/* Unreached */
badframe:
}
#endif /* CONFIG_TRAD_SIGNALS */
-asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_rt_sigreturn(void)
{
struct rt_sigframe __user *frame;
+ struct pt_regs *regs;
sigset_t set;
int sig;
- frame = (struct rt_sigframe __user *) regs.regs[29];
+ regs = current_pt_regs();
+ frame = (struct rt_sigframe __user *)regs->regs[29];
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set)))
set_current_blocked(&set);
- sig = restore_sigcontext(®s, &frame->rs_uc.uc_mcontext);
+ sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
if (sig < 0)
goto badframe;
else if (sig)
__asm__ __volatile__(
"move\t$29, %0\n\t"
"j\tsyscall_exit"
- :/* no outputs */
- :"r" (®s));
+ : /* no outputs */
+ : "r" (regs));
/* Unreached */
badframe:
regs->regs[0] = 0; /* Don't deal with this again. */
}
+ rseq_signal_deliver(ksig, regs);
+
if (sig_uses_siginfo(&ksig->ka, abi))
ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn,
ksig, regs, oldset);
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
user_enter();
struct ucontextn32 rs_uc;
};
-asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sysn32_rt_sigreturn(void)
{
struct rt_sigframe_n32 __user *frame;
+ struct pt_regs *regs;
sigset_t set;
int sig;
- frame = (struct rt_sigframe_n32 __user *) regs.regs[29];
+ regs = current_pt_regs();
+ frame = (struct rt_sigframe_n32 __user *)regs->regs[29];
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
set_current_blocked(&set);
- sig = restore_sigcontext(®s, &frame->rs_uc.uc_mcontext);
+ sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
if (sig < 0)
goto badframe;
else if (sig)
__asm__ __volatile__(
"move\t$29, %0\n\t"
"j\tsyscall_exit"
- :/* no outputs */
- :"r" (®s));
+ : /* no outputs */
+ : "r" (regs));
/* Unreached */
badframe:
return 0;
}
-asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_rt_sigreturn(void)
{
struct rt_sigframe32 __user *frame;
+ struct pt_regs *regs;
sigset_t set;
int sig;
- frame = (struct rt_sigframe32 __user *) regs.regs[29];
+ regs = current_pt_regs();
+ frame = (struct rt_sigframe32 __user *)regs->regs[29];
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
set_current_blocked(&set);
- sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext);
+ sig = restore_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
if (sig < 0)
goto badframe;
else if (sig)
__asm__ __volatile__(
"move\t$29, %0\n\t"
"j\tsyscall_exit"
- :/* no outputs */
- :"r" (®s));
+ : /* no outputs */
+ : "r" (regs));
/* Unreached */
badframe:
};
-asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_sigreturn(void)
{
struct sigframe32 __user *frame;
+ struct pt_regs *regs;
sigset_t blocked;
int sig;
- frame = (struct sigframe32 __user *) regs.regs[29];
+ regs = current_pt_regs();
+ frame = (struct sigframe32 __user *)regs->regs[29];
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
set_current_blocked(&blocked);
- sig = restore_sigcontext32(®s, &frame->sf_sc);
+ sig = restore_sigcontext32(regs, &frame->sf_sc);
if (sig < 0)
goto badframe;
else if (sig)
__asm__ __volatile__(
"move\t$29, %0\n\t"
"j\tsyscall_exit"
- :/* no outputs */
- :"r" (®s));
+ : /* no outputs */
+ : "r" (regs));
/* Unreached */
badframe:
void show_regs(struct pt_regs *regs)
{
__show_regs((struct pt_regs *)regs);
+ dump_stack();
}
void show_registers(struct pt_regs *regs)
{
int err, was_fpu_owner, prior_msa;
- /*
- * If an FP mode switch is currently underway, wait for it to
- * complete before proceeding.
- */
- wait_var_event(¤t->mm->context.fp_mode_switching,
- !atomic_read(¤t->mm->context.fp_mode_switching));
-
if (!used_math()) {
/* First time FP context user. */
preempt_disable();
dvcpu->arch.wait = 0;
if (swq_has_sleeper(&dvcpu->wq))
- swake_up(&dvcpu->wq);
+ swake_up_one(&dvcpu->wq);
return 0;
}
vcpu->arch.wait = 0;
if (swq_has_sleeper(&vcpu->wq))
- swake_up(&vcpu->wq);
+ swake_up_one(&vcpu->wq);
}
/* low level hrtimer wake routine */
#include <linux/cpu.h>
#include <lantiq_soc.h>
+#include <asm/setup.h>
#define ASC_BUF 1024
#define LTQ_ASC_FSTAT ((u32 *)(LTQ_EARLY_ASC + 0x0048))
#include <linux/export.h>
#include <linux/clk.h>
#include <linux/bootmem.h>
-#include <linux/of_platform.h>
#include <linux/of_fdt.h>
#include <asm/bootinfo.h>
panic("failed to register_vsmp_smp_ops()");
#endif
}
-
-int __init plat_of_setup(void)
-{
- return of_platform_default_populate(NULL, NULL, NULL);
-}
-
-arch_initcall(plat_of_setup);
unsigned long flags;
ch->desc = 0;
- ch->desc_base = dma_alloc_coherent(NULL,
+ ch->desc_base = dma_zalloc_coherent(NULL,
LTQ_DESC_NUM * LTQ_DESC_SIZE,
&ch->phys, GFP_ATOMIC);
- memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE);
spin_lock_irqsave(<q_dma_lock, flags);
ltq_dma_w32(ch->nr, LTQ_DMA_CS);
#include <asm/bootinfo.h>
#include <asm/lasat/lasat.h>
#include <asm/cpu.h>
+#include <asm/setup.h>
#include "at93c.h"
#include <asm/lasat/eeprom.h>
#endif
#else
PTR_SUBU t0, $0, a2
+ move a2, zero /* No remaining longs */
PTR_ADDIU t0, 1
STORE_BYTE(0)
STORE_BYTE(1)
#ifdef CONFIG_CPU_MIPSR6
.Lbyte_fixup\@:
- PTR_SUBU a2, $0, t0
+ /*
+ * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
+ * a2 = a2 - t0 + 1
+ */
+ PTR_SUBU a2, t0
jr ra
PTR_ADDIU a2, 1
#endif /* CONFIG_CPU_MIPSR6 */
.Lfirst_fixup\@:
+ /* unset_bytes already in a2 */
jr ra
nop
.Lfwd_fixup\@:
+ /*
+ * unset_bytes = partial_start_addr + #bytes - fault_addr
+ * a2 = t1 + (a2 & 3f) - $28->task->BUADDR
+ */
PTR_L t0, TI_TASK($28)
andi a2, 0x3f
LONG_L t0, THREAD_BUADDR(t0)
LONG_SUBU a2, t0
.Lpartial_fixup\@:
+ /*
+ * unset_bytes = partial_end_addr + #bytes - fault_addr
+ * a2 = a0 + (a2 & STORMASK) - $28->task->BUADDR
+ */
PTR_L t0, TI_TASK($28)
andi a2, STORMASK
LONG_L t0, THREAD_BUADDR(t0)
LONG_SUBU a2, t0
.Llast_fixup\@:
+ /* unset_bytes already in a2 */
jr ra
nop
.Lsmall_fixup\@:
+ /*
+ * unset_bytes = end_addr - current_addr + 1
+ * a2 = t1 - a0 + 1
+ */
PTR_SUBU a2, t1, a0
jr ra
PTR_ADDIU a2, 1
-cflags-$(CONFIG_CPU_LOONGSON1) += \
- $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
- -Wa,-mips32r2 -Wa,--trap
-
+cflags-$(CONFIG_CPU_LOONGSON1) += -march=mips32 -Wa,--trap
platform-$(CONFIG_MACH_LOONGSON32) += loongson32/
cflags-$(CONFIG_MACH_LOONGSON32) += -I$(srctree)/arch/mips/include/asm/mach-loongson32
-load-$(CONFIG_LOONGSON1_LS1B) += 0xffffffff80100000
-load-$(CONFIG_LOONGSON1_LS1C) += 0xffffffff80100000
+load-$(CONFIG_CPU_LOONGSON1) += 0xffffffff80100000
select LOONGSON_MC146818
select ZONE_DMA32
select LEFI_FIRMWARE_INTERFACE
- select PHYS48_TO_HT40
help
Generic Loongson 3 family machines utilize the 3A/3B revision
of Loongson processor and RS780/SBX00 chipset.
default y
depends on EARLY_PRINTK || SERIAL_8250
-config PHYS48_TO_HT40
- bool
- default y if CPU_LOONGSON3
-
config LOONGSON_MC146818
bool
default n
obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
bonito-irq.o mem.o machtype.o platform.o serial.o
obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_CPU_LOONGSON2) += dma.o
#
# Serial port support
#
obj-$(CONFIG_SUSPEND) += pm.o
-
-#
-# Big Memory (SWIOTLB) Support
-#
-obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
break;
case PCI_OHCI_INT_REG:
_rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo);
- if ((lo & 0x00000f00) == CS5536_USB_INTR)
+ if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR)
conf_data = 1;
break;
default:
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/swiotlb.h>
-#include <linux/bootmem.h>
-
-#include <asm/bootinfo.h>
-#include <boot_param.h>
-#include <dma-coherence.h>
-
-static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
- void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
- mb();
- return ret;
-}
-
-static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
- dir, attrs);
- mb();
- return daddr;
-}
-
-static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
- mb();
-
- return r;
-}
-
-static void loongson_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction dir)
-{
- swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
- mb();
-}
-
-static void loongson_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction dir)
-{
- swiotlb_sync_sg_for_device(dev, sg, nents, dir);
- mb();
-}
-
-static int loongson_dma_supported(struct device *dev, u64 mask)
-{
- if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits))
- return 0;
- return swiotlb_dma_supported(dev, mask);
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
- long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
- /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
- * Loongson-3's 48bit address space and embed it into 40bit */
- nid = (paddr >> 44) & 0x3;
- paddr = ((nid << 44) ^ paddr) | (nid << 37);
-#endif
- return paddr;
-}
-
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
- long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
- /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
- * Loongson-3's 48bit address space and embed it into 40bit */
- nid = (daddr >> 37) & 0x3;
- daddr = ((nid << 37) ^ daddr) | (nid << 44);
-#endif
- return daddr;
-}
-
-static const struct dma_map_ops loongson_dma_map_ops = {
- .alloc = loongson_dma_alloc_coherent,
- .free = swiotlb_free,
- .map_page = loongson_dma_map_page,
- .unmap_page = swiotlb_unmap_page,
- .map_sg = loongson_dma_map_sg,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = loongson_dma_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = loongson_dma_sync_sg_for_device,
- .mapping_error = swiotlb_dma_mapping_error,
- .dma_supported = loongson_dma_supported,
-};
-
-void __init plat_swiotlb_setup(void)
-{
- swiotlb_init(1);
- mips_dma_map_ops = &loongson_dma_map_ops;
-}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr | 0x80000000;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
+ if (dma_addr > 0x8fffffff)
+ return dma_addr;
+ return dma_addr & 0x0fffffff;
+#else
+ return dma_addr & 0x7fffffff;
+#endif
+}
* option) any later version.
*/
#include <linux/serial_reg.h>
+#include <asm/setup.h>
#include <loongson.h>
break;
case PRID_REV_LOONGSON3A_R1:
case PRID_REV_LOONGSON3A_R2:
- case PRID_REV_LOONGSON3A_R3:
+ case PRID_REV_LOONGSON3A_R3_0:
+ case PRID_REV_LOONGSON3A_R3_1:
cpu_clock_freq = 900000000;
break;
case PRID_REV_LOONGSON3B_R1:
#
# Makefile for Loongson-3 family machines
#
-obj-y += irq.o cop2-ex.o platform.o acpi_init.o
+obj-y += irq.o cop2-ex.o platform.o acpi_init.o dma.o
obj-$(CONFIG_SMP) += smp.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+#include <linux/init.h>
+#include <linux/swiotlb.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+ * Loongson-3's 48bit address space and embed it into 40bit */
+ long nid = (paddr >> 44) & 0x3;
+ return ((nid << 44) ^ paddr) | (nid << 37);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+ /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+ * Loongson-3's 48bit address space and embed it into 40bit */
+ long nid = (daddr >> 37) & 0x3;
+ return ((nid << 37) ^ daddr) | (nid << 44);
+}
+
+void __init plat_swiotlb_setup(void)
+{
+ swiotlb_init(1);
+}
(void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead);
break;
case PRID_REV_LOONGSON3A_R2:
- case PRID_REV_LOONGSON3A_R3:
+ case PRID_REV_LOONGSON3A_R3_0:
+ case PRID_REV_LOONGSON3A_R3_1:
play_dead_at_ckseg1 =
(void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead);
break;
# Makefile for the Linux/MIPS-specific parts of the memory manager.
#
-obj-y += cache.o dma-default.o extable.o fault.o \
+obj-y += cache.o extable.o fault.o \
gup.o init.o mmap.o page.o page-funcs.o \
pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o
obj-$(CONFIG_64BIT) += pgtable-64.o
obj-$(CONFIG_HIGHMEM) += highmem.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_DMA_NONCOHERENT) += dma-noncoherent.o
obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
obj-$(CONFIG_CPU_R3000) += c-r3k.o tlb-r3k.o
return __r4k_flush_icache_range(start, end, true);
}
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
{
/* Catch bad driver code */
- BUG_ON(size == 0);
+ if (WARN_ON(size == 0))
+ return;
preempt_disable();
if (cpu_has_inclusive_pcaches) {
static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
{
/* Catch bad driver code */
- BUG_ON(size == 0);
+ if (WARN_ON(size == 0))
+ return;
preempt_disable();
if (cpu_has_inclusive_pcaches) {
bc_inv(addr, size);
__sync();
}
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
struct flush_cache_sigtramp_args {
struct mm_struct *mm;
if (c->dcache.flags & MIPS_CACHE_PINDEX)
c->dcache.flags &= ~MIPS_CACHE_ALIASES;
+ /*
+ * In systems with CM the icache fills from L2 or closer caches, and
+ * thus sees remote stores without needing to write them back any
+ * further than that.
+ */
+ if (mips_cm_present())
+ c->icache.flags |= MIPS_IC_SNOOPS_REMOTE;
+
switch (current_cpu_type()) {
case CPU_20KC:
/*
EXPORT_SYMBOL(flush_data_cache_page);
EXPORT_SYMBOL(flush_icache_all);
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
/* DMA cache operations. */
void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
EXPORT_SYMBOL(_dma_cache_wback_inv);
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
/*
* We could optimize the case where the cache argument is not BCACHE but
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000 Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06 Ralf Baechle <ralf@linux-mips.org>
- * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-#include <linux/dma-contiguous.h>
-
-#include <asm/cache.h>
-#include <asm/cpu-type.h>
-#include <asm/io.h>
-
-#include <dma-coherence.h>
-
-#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
-/* User defined DMA coherency from command line. */
-enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
-EXPORT_SYMBOL_GPL(coherentio);
-int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */
-
-static int __init setcoherentio(char *str)
-{
- coherentio = IO_COHERENCE_ENABLED;
- pr_info("Hardware DMA cache coherency (command line)\n");
- return 0;
-}
-early_param("coherentio", setcoherentio);
-
-static int __init setnocoherentio(char *str)
-{
- coherentio = IO_COHERENCE_DISABLED;
- pr_info("Software DMA cache coherency (command line)\n");
- return 0;
-}
-early_param("nocoherentio", setnocoherentio);
-#endif
-
-static inline struct page *dma_addr_to_page(struct device *dev,
- dma_addr_t dma_addr)
-{
- return pfn_to_page(
- plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
-}
-
-/*
- * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
- * speculatively fill random cachelines with stale data at any time,
- * requiring an extra flush post-DMA.
- *
- * Warning on the terminology - Linux calls an uncached area coherent;
- * MIPS terminology calls memory areas with hardware maintained coherency
- * coherent.
- *
- * Note that the R14000 and R16000 should also be checked for in this
- * condition. However this function is only called on non-I/O-coherent
- * systems and only the R10000 and R12000 are used in such systems, the
- * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
- */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
-{
- if (plat_device_is_coherent(dev))
- return false;
-
- switch (boot_cpu_type()) {
- case CPU_R10000:
- case CPU_R12000:
- case CPU_BMIPS5000:
- return true;
-
- default:
- /*
- * Presence of MAARs suggests that the CPU supports
- * speculatively prefetching data, and therefore requires
- * the post-DMA flush/invalidate.
- */
- return cpu_has_maar;
- }
-}
-
-static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
-{
- gfp_t dma_flag;
-
-#ifdef CONFIG_ISA
- if (dev == NULL)
- dma_flag = __GFP_DMA;
- else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
- if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32))
- dma_flag = __GFP_DMA;
- else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
- dma_flag = __GFP_DMA32;
- else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
- if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64))
- dma_flag = __GFP_DMA32;
- else
-#endif
-#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
- if (dev == NULL ||
- dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
- dma_flag = __GFP_DMA;
- else
-#endif
- dma_flag = 0;
-
- /* Don't invoke OOM killer */
- gfp |= __GFP_NORETRY;
-
- return gfp | dma_flag;
-}
-
-static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
- void *ret;
- struct page *page = NULL;
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
- gfp = massage_gfp_flags(dev, gfp);
-
- if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
- page = dma_alloc_from_contiguous(dev, count, get_order(size),
- gfp);
- if (!page)
- page = alloc_pages(gfp, get_order(size));
-
- if (!page)
- return NULL;
-
- ret = page_address(page);
- memset(ret, 0, size);
- *dma_handle = plat_map_dma_mem(dev, ret, size);
- if (!(attrs & DMA_ATTR_NON_CONSISTENT) &&
- !plat_device_is_coherent(dev)) {
- dma_cache_wback_inv((unsigned long) ret, size);
- ret = UNCAC_ADDR(ret);
- }
-
- return ret;
-}
-
-static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- unsigned long addr = (unsigned long) vaddr;
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- struct page *page = NULL;
-
- plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
-
- if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev))
- addr = CAC_ADDR(addr);
-
- page = virt_to_page((void *) addr);
-
- if (!dma_release_from_contiguous(dev, page, count))
- __free_pages(page, get_order(size));
-}
-
-static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs)
-{
- unsigned long user_count = vma_pages(vma);
- unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long addr = (unsigned long)cpu_addr;
- unsigned long off = vma->vm_pgoff;
- unsigned long pfn;
- int ret = -ENXIO;
-
- if (!plat_device_is_coherent(dev))
- addr = CAC_ADDR(addr);
-
- pfn = page_to_pfn(virt_to_page((void *)addr));
-
- if (attrs & DMA_ATTR_WRITE_COMBINE)
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
- else
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
- if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
- return ret;
-
- if (off < count && user_count <= (count - off)) {
- ret = remap_pfn_range(vma, vma->vm_start,
- pfn + off,
- user_count << PAGE_SHIFT,
- vma->vm_page_prot);
- }
-
- return ret;
-}
-
-static inline void __dma_sync_virtual(void *addr, size_t size,
- enum dma_data_direction direction)
-{
- switch (direction) {
- case DMA_TO_DEVICE:
- dma_cache_wback((unsigned long)addr, size);
- break;
-
- case DMA_FROM_DEVICE:
- dma_cache_inv((unsigned long)addr, size);
- break;
-
- case DMA_BIDIRECTIONAL:
- dma_cache_wback_inv((unsigned long)addr, size);
- break;
-
- default:
- BUG();
- }
-}
-
-/*
- * A single sg entry may refer to multiple physically contiguous
- * pages. But we still need to process highmem pages individually.
- * If highmem is not configured then the bulk of this loop gets
- * optimized out.
- */
-static inline void __dma_sync(struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction direction)
-{
- size_t left = size;
-
- do {
- size_t len = left;
-
- if (PageHighMem(page)) {
- void *addr;
-
- if (offset + len > PAGE_SIZE) {
- if (offset >= PAGE_SIZE) {
- page += offset >> PAGE_SHIFT;
- offset &= ~PAGE_MASK;
- }
- len = PAGE_SIZE - offset;
- }
-
- addr = kmap_atomic(page);
- __dma_sync_virtual(addr + offset, len, direction);
- kunmap_atomic(addr);
- } else
- __dma_sync_virtual(page_address(page) + offset,
- size, direction);
- offset = 0;
- page++;
- left -= len;
- } while (left);
-}
-
-static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction direction, unsigned long attrs)
-{
- if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- __dma_sync(dma_addr_to_page(dev, dma_addr),
- dma_addr & ~PAGE_MASK, size, direction);
- plat_post_dma_flush(dev);
- plat_unmap_dma_mem(dev, dma_addr, size, direction);
-}
-
-static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction direction, unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nents, i) {
- if (!plat_device_is_coherent(dev) &&
- !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- __dma_sync(sg_page(sg), sg->offset, sg->length,
- direction);
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
- sg->dma_length = sg->length;
-#endif
- sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) +
- sg->offset;
- }
-
- return nents;
-}
-
-static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction direction,
- unsigned long attrs)
-{
- if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- __dma_sync(page, offset, size, direction);
-
- return plat_map_dma_mem_page(dev, page) + offset;
-}
-
-static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nhwentries, enum dma_data_direction direction,
- unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nhwentries, i) {
- if (!plat_device_is_coherent(dev) &&
- !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
- direction != DMA_TO_DEVICE)
- __dma_sync(sg_page(sg), sg->offset, sg->length,
- direction);
- plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
- }
-}
-
-static void mips_dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
- if (cpu_needs_post_dma_flush(dev))
- __dma_sync(dma_addr_to_page(dev, dma_handle),
- dma_handle & ~PAGE_MASK, size, direction);
- plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
- if (!plat_device_is_coherent(dev))
- __dma_sync(dma_addr_to_page(dev, dma_handle),
- dma_handle & ~PAGE_MASK, size, direction);
-}
-
-static void mips_dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sglist, int nelems,
- enum dma_data_direction direction)
-{
- int i;
- struct scatterlist *sg;
-
- if (cpu_needs_post_dma_flush(dev)) {
- for_each_sg(sglist, sg, nelems, i) {
- __dma_sync(sg_page(sg), sg->offset, sg->length,
- direction);
- }
- }
- plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sglist, int nelems,
- enum dma_data_direction direction)
-{
- int i;
- struct scatterlist *sg;
-
- if (!plat_device_is_coherent(dev)) {
- for_each_sg(sglist, sg, nelems, i) {
- __dma_sync(sg_page(sg), sg->offset, sg->length,
- direction);
- }
- }
-}
-
-static int mips_dma_supported(struct device *dev, u64 mask)
-{
- return plat_dma_supported(dev, mask);
-}
-
-static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
- enum dma_data_direction direction)
-{
- BUG_ON(direction == DMA_NONE);
-
- if (!plat_device_is_coherent(dev))
- __dma_sync_virtual(vaddr, size, direction);
-}
-
-static const struct dma_map_ops mips_default_dma_map_ops = {
- .alloc = mips_dma_alloc_coherent,
- .free = mips_dma_free_coherent,
- .mmap = mips_dma_mmap,
- .map_page = mips_dma_map_page,
- .unmap_page = mips_dma_unmap_page,
- .map_sg = mips_dma_map_sg,
- .unmap_sg = mips_dma_unmap_sg,
- .sync_single_for_cpu = mips_dma_sync_single_for_cpu,
- .sync_single_for_device = mips_dma_sync_single_for_device,
- .sync_sg_for_cpu = mips_dma_sync_sg_for_cpu,
- .sync_sg_for_device = mips_dma_sync_sg_for_device,
- .dma_supported = mips_dma_supported,
- .cache_sync = mips_dma_cache_sync,
-};
-
-const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
-EXPORT_SYMBOL(mips_dma_map_ops);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 Ani Joshi <ajoshi@unixbox.com>
+ * Copyright (C) 2000, 2001, 06 Ralf Baechle <ralf@linux-mips.org>
+ * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/highmem.h>
+
+#include <asm/cache.h>
+#include <asm/cpu-type.h>
+#include <asm/dma-coherence.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+static inline int dev_is_coherent(struct device *dev)
+{
+ return dev->archdata.dma_coherent;
+}
+#else
+static inline int dev_is_coherent(struct device *dev)
+{
+ switch (coherentio) {
+ default:
+ case IO_COHERENCE_DEFAULT:
+ return hw_coherentio;
+ case IO_COHERENCE_ENABLED:
+ return 1;
+ case IO_COHERENCE_DISABLED:
+ return 0;
+ }
+}
+#endif /* CONFIG_DMA_PERDEV_COHERENT */
+
+/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively
+ * fill random cachelines with stale data at any time, requiring an extra
+ * flush post-DMA.
+ *
+ * Warning on the terminology - Linux calls an uncached area coherent; MIPS
+ * terminology calls memory areas with hardware maintained coherency coherent.
+ *
+ * Note that the R14000 and R16000 should also be checked for in this condition.
+ * However this function is only called on non-I/O-coherent systems and only the
+ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
+ * SGI IP32 aka O2.
+ */
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
+{
+ if (dev_is_coherent(dev))
+ return false;
+
+ switch (boot_cpu_type()) {
+ case CPU_R10000:
+ case CPU_R12000:
+ case CPU_BMIPS5000:
+ return true;
+ default:
+ /*
+ * Presence of MAARs suggests that the CPU supports
+ * speculatively prefetching data, and therefore requires
+ * the post-DMA flush/invalidate.
+ */
+ return cpu_has_maar;
+ }
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+ void *ret;
+
+ ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+ if (!ret)
+ return NULL;
+
+ if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+ dma_cache_wback_inv((unsigned long) ret, size);
+ ret = (void *)UNCAC_ADDR(ret);
+ }
+
+ return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev))
+ cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
+ dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long addr = (unsigned long)cpu_addr;
+ unsigned long off = vma->vm_pgoff;
+ unsigned long pfn;
+ int ret = -ENXIO;
+
+ if (!dev_is_coherent(dev))
+ addr = CAC_ADDR(addr);
+
+ pfn = page_to_pfn(virt_to_page((void *)addr));
+
+ if (attrs & DMA_ATTR_WRITE_COMBINE)
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+ else
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (off < count && user_count <= (count - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+
+ return ret;
+}
+
+static inline void dma_sync_virt(void *addr, size_t size,
+ enum dma_data_direction dir)
+{
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ dma_cache_wback((unsigned long)addr, size);
+ break;
+
+ case DMA_FROM_DEVICE:
+ dma_cache_inv((unsigned long)addr, size);
+ break;
+
+ case DMA_BIDIRECTIONAL:
+ dma_cache_wback_inv((unsigned long)addr, size);
+ break;
+
+ default:
+ BUG();
+ }
+}
+
+/*
+ * A single sg entry may refer to multiple physically contiguous pages. But
+ * we still need to process highmem pages individually. If highmem is not
+ * configured then the bulk of this loop gets optimized out.
+ */
+static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir)
+{
+ struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+ unsigned long offset = paddr & ~PAGE_MASK;
+ size_t left = size;
+
+ do {
+ size_t len = left;
+
+ if (PageHighMem(page)) {
+ void *addr;
+
+ if (offset + len > PAGE_SIZE) {
+ if (offset >= PAGE_SIZE) {
+ page += offset >> PAGE_SHIFT;
+ offset &= ~PAGE_MASK;
+ }
+ len = PAGE_SIZE - offset;
+ }
+
+ addr = kmap_atomic(page);
+ dma_sync_virt(addr + offset, len, dir);
+ kunmap_atomic(addr);
+ } else
+ dma_sync_virt(page_address(page) + offset, size, dir);
+ offset = 0;
+ page++;
+ left -= len;
+ } while (left);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ if (!dev_is_coherent(dev))
+ dma_sync_phys(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ if (cpu_needs_post_dma_flush(dev))
+ dma_sync_phys(paddr, size, dir);
+}
+
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+ enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+
+ if (!dev_is_coherent(dev))
+ dma_sync_virt(vaddr, size, direction);
+}
#include <linux/export.h>
#include <asm/addrspace.h>
#include <asm/byteorder.h>
+#include <linux/ioport.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
return error;
}
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+ void *arg)
+{
+ unsigned long i;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (pfn_valid(start_pfn + i) &&
+ !PageReserved(pfn_to_page(start_pfn + i)))
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* Generic mapping function (not visible outside):
*/
void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long flags)
{
+ unsigned long offset, pfn, last_pfn;
struct vm_struct * area;
- unsigned long offset;
phys_addr_t last_addr;
void * addr;
return (void __iomem *) CKSEG1ADDR(phys_addr);
/*
- * Don't allow anybody to remap normal RAM that we're using..
+ * Don't allow anybody to remap RAM that may be allocated by the page
+ * allocator, since that could lead to races & data clobbering.
*/
- if (phys_addr < virt_to_phys(high_memory)) {
- char *t_addr, *t_end;
- struct page *page;
-
- t_addr = __va(phys_addr);
- t_end = t_addr + (size - 1);
-
- for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++)
- if(!PageReserved(page))
- return NULL;
+ pfn = PFN_DOWN(phys_addr);
+ last_pfn = PFN_DOWN(last_addr);
+ if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+ __ioremap_check_ram) == 1) {
+ WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+ &phys_addr, &last_addr);
+ return NULL;
}
/*
u64 pad_b;
} ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
-void sb1_dma_init(void)
-{
- int i;
-
- for (i = 0; i < DM_NUM_CHANNELS; i++) {
- const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
- V_DM_DSCR_BASE_RINGSZ(1);
- void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
- __raw_writeq(base_val, base_reg);
- __raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
- __raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
- }
-}
-
void clear_page(void *page)
{
u64 to_phys = CPHYSADDR((unsigned long)page);
#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
write_c0_pwctl(1 << 6 | psn);
#endif
- write_c0_kpgd(swapper_pg_dir);
+ write_c0_kpgd((long)swapper_pg_dir);
kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
}
#include <asm/inst.h>
#include <asm/elf.h>
#include <asm/bugs.h>
-#define UASM_ISA _UASM_ISA_MICROMIPS
#include <asm/uasm.h>
#define RS_MASK 0x1f
#include <asm/inst.h>
#include <asm/elf.h>
#include <asm/bugs.h>
-#define UASM_ISA _UASM_ISA_CLASSIC
#include <asm/uasm.h>
#define RS_MASK 0x1f
obj-y += malta-int.o
obj-y += malta-memory.o
obj-y += malta-platform.o
-obj-y += malta-reset.o
obj-y += malta-setup.o
obj-y += malta-time.o
obj-$(CONFIG_MIPS_CMP) += malta-amon.o
-obj-$(CONFIG_MIPS_MALTA_PM) += malta-pm.o
CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt
+++ /dev/null
-/*
- * Copyright (C) 2014 Imagination Technologies
- * Author: Paul Burton <paul.burton@mips.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/pci.h>
-
-#include <asm/mach-malta/malta-pm.h>
-
-static struct pci_bus *pm_pci_bus;
-static resource_size_t pm_io_offset;
-
-int mips_pm_suspend(unsigned state)
-{
- int spec_devid;
- u16 sts;
-
- if (!pm_pci_bus || !pm_io_offset)
- return -ENODEV;
-
- /* Ensure the power button status is clear */
- while (1) {
- sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS);
- if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS))
- break;
- outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS);
- }
-
- /* Enable entry to suspend */
- outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN,
- pm_io_offset + PIIX4_FUNC3IO_PMCNTRL);
-
- /* If the special cycle occurs too soon this doesn't work... */
- mdelay(10);
-
- /*
- * The PIIX4 will enter the suspend state only after seeing a special
- * cycle with the correct magic data on the PCI bus. Generate that
- * cycle now.
- */
- spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7));
- pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0,
- PIIX4_SUSPEND_MAGIC);
-
- /* Give the system some time to power down */
- mdelay(1000);
-
- return 0;
-}
-
-static int __init malta_pm_setup(void)
-{
- struct pci_dev *dev;
- int res, io_region = PCI_BRIDGE_RESOURCES;
-
- /* Find a reference to the PCI bus */
- pm_pci_bus = pci_find_next_bus(NULL);
- if (!pm_pci_bus) {
- pr_warn("malta-pm: failed to find reference to PCI bus\n");
- return -ENODEV;
- }
-
- /* Find the PIIX4 PM device */
- dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID,
- PCI_ANY_ID, NULL);
- if (!dev) {
- pr_warn("malta-pm: failed to find PIIX4 PM\n");
- return -ENODEV;
- }
-
- /* Request access to the PIIX4 PM IO registers */
- res = pci_request_region(dev, io_region, "PIIX4 PM IO registers");
- if (res) {
- pr_warn("malta-pm: failed to request PM IO registers (%d)\n",
- res);
- pci_dev_put(dev);
- return -ENODEV;
- }
-
- /* Find the offset to the PIIX4 PM IO registers */
- pm_io_offset = pci_resource_start(dev, io_region);
-
- pci_dev_put(dev);
- return 0;
-}
-
-late_initcall(malta_pm_setup);
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/io.h>
-#include <linux/pm.h>
-#include <linux/reboot.h>
-
-#include <asm/reboot.h>
-#include <asm/mach-malta/malta-pm.h>
-
-static void mips_machine_power_off(void)
-{
- mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
-
- pr_info("Failed to power down, resetting\n");
- machine_restart(NULL);
-}
-
-static int __init mips_reboot_setup(void)
-{
- pm_power_off = mips_machine_power_off;
-
- return 0;
-}
-arch_initcall(mips_reboot_setup);
#include <linux/screen_info.h>
#include <linux/time.h>
+#include <asm/dma-coherence.h>
#include <asm/fw/fw.h>
#include <asm/mach-malta/malta-dtshim.h>
#include <asm/mips-cps.h>
static void __init plat_setup_iocoherency(void)
{
-#ifdef CONFIG_DMA_NONCOHERENT
- /*
- * Kernel has been configured with software coherency
- * but we might choose to turn it off and use hardware
- * coherency instead.
- */
if (plat_enable_iocoherency()) {
if (coherentio == IO_COHERENCE_DISABLED)
pr_info("Hardware DMA cache coherency disabled\n");
else
pr_info("Software DMA cache coherency enabled\n");
}
-#else
- if (!plat_enable_iocoherency())
- panic("Hardware DMA cache coherency not supported!");
-#endif
}
static void __init pci_clock_check(void)
pr_info("Enabled Bonito debug mode\n");
} else
BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE;
-
-#ifdef CONFIG_DMA_COHERENT
- if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
- BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
- pr_info("Enabled Bonito CPU coherency\n");
-
- argptr = fw_getcmdline();
- if (strstr(argptr, "iobcuncached")) {
- BONITO_PCICACHECTRL &= ~BONITO_PCICACHECTRL_IOBCCOH_EN;
- BONITO_PCIMEMBASECFG = BONITO_PCIMEMBASECFG &
- ~(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
- BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
- pr_info("Disabled Bonito IOBC coherency\n");
- } else {
- BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_IOBCCOH_EN;
- BONITO_PCIMEMBASECFG |=
- (BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
- BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
- pr_info("Enabled Bonito IOBC coherency\n");
- }
- } else
- panic("Hardware DMA cache coherency not supported");
-#endif
}
void __init *plat_get_fdt(void)
*/
enable_dma(4);
-#ifdef CONFIG_DMA_COHERENT
- if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO)
- panic("Hardware DMA cache coherency not supported");
-#endif
-
if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO)
bonito_quirks_setup();
#include <linux/serial_reg.h>
#include <asm/mipsregs.h>
+#include <asm/setup.h>
#include <asm/netlogic/haldefs.h>
#include <asm/netlogic/common.h>
{
unflatten_and_copy_device_tree();
}
-
-static struct of_device_id __initdata xlp_ids[] = {
- { .compatible = "simple-bus", },
- {},
-};
-
-int __init xlp8xx_ds_publish_devices(void)
-{
- if (!of_have_populated_dt())
- return 0;
- return of_platform_bus_probe(NULL, xlp_ids, NULL);
-}
-
-device_initcall(xlp8xx_ds_publish_devices);
#include <linux/kernel.h>
#include <linux/virtio_console.h>
#include <linux/kvm_para.h>
+#include <asm/setup.h>
/*
* Emit one character to the boot console.
*/
-int prom_putchar(char c)
+void prom_putchar(char c)
{
kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /* port 0 */,
(unsigned long)&c, 1 /* len == 1 */);
-
- return 1;
}
#ifdef CONFIG_VIRTIO_CONSOLE
static int pci_read_config(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 * value)
{
- if (bus->number > 0)
+ if (!pci_is_root_bus(bus))
return pci_conf1_read_config(bus, devfn, where, size, value);
return pci_conf0_read_config(bus, devfn, where, size, value);
static int pci_write_config(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 value)
{
- if (bus->number > 0)
+ if (!pci_is_root_bus(bus))
return pci_conf1_write_config(bus, devfn, where, size, value);
return pci_conf0_write_config(bus, devfn, where, size, value);
#define AR2315_PCI_HOST_SLOT 3
#define AR2315_PCI_HOST_DEVID ((0xff18 << 16) | PCI_VENDOR_ID_ATHEROS)
+/*
+ * We need some arbitrary non-zero value to be programmed to the BAR1 register
+ * of PCI host controller to enable DMA. The same value should be used as the
+ * offset to calculate the physical address of DMA buffer for PCI devices.
+ */
+#define AR2315_PCI_HOST_SDRAM_BASEADDR 0x20000000
+
/* ??? access BAR */
#define AR2315_PCI_HOST_MBAR0 0x10000000
/* RAM access BAR */
struct resource io_res;
};
+static inline dma_addr_t ar2315_dev_offset(struct device *dev)
+{
+ if (dev && dev_is_pci(dev))
+ return AR2315_PCI_HOST_SDRAM_BASEADDR;
+ return 0;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr + ar2315_dev_offset(dev);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr - ar2315_dev_offset(dev);
+}
+
static inline struct ar2315_pci_ctrl *ar2315_pci_bus_to_apc(struct pci_bus *bus)
{
struct pci_controller *hose = bus->sysdata;
#include <linux/irq.h>
#include <linux/pci.h>
#include <linux/init.h>
+#include <linux/delay.h>
#include <linux/platform_device.h>
#include <asm/mach-ath79/ath79.h>
#include <asm/mach-ath79/ar71xx_regs.h>
+#define AR724X_PCI_REG_APP 0x00
#define AR724X_PCI_REG_RESET 0x18
#define AR724X_PCI_REG_INT_STATUS 0x4c
#define AR724X_PCI_REG_INT_MASK 0x50
+#define AR724X_PCI_APP_LTSSM_ENABLE BIT(0)
+
#define AR724X_PCI_RESET_LINK_UP BIT(0)
#define AR724X_PCI_INT_DEV0 BIT(14)
apc);
}
+static void ar724x_pci_hw_init(struct ar724x_pci_controller *apc)
+{
+ u32 ppl, app;
+ int wait = 0;
+
+ /* deassert PCIe host controller and PCIe PHY reset */
+ ath79_device_reset_clear(AR724X_RESET_PCIE);
+ ath79_device_reset_clear(AR724X_RESET_PCIE_PHY);
+
+ /* remove the reset of the PCIE PLL */
+ ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+ ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET;
+ ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+ /* deassert bypass for the PCIE PLL */
+ ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+ ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS;
+ ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+ /* set PCIE Application Control to ready */
+ app = __raw_readl(apc->ctrl_base + AR724X_PCI_REG_APP);
+ app |= AR724X_PCI_APP_LTSSM_ENABLE;
+ __raw_writel(app, apc->ctrl_base + AR724X_PCI_REG_APP);
+
+ /* wait up to 100ms for PHY link up */
+ do {
+ mdelay(10);
+ wait++;
+ } while (wait < 10 && !ar724x_pci_check_link(apc));
+}
+
static int ar724x_pci_probe(struct platform_device *pdev)
{
struct ar724x_pci_controller *apc;
apc->pci_controller.io_resource = &apc->io_res;
apc->pci_controller.mem_resource = &apc->mem_res;
+ /*
+ * Do the full PCIE Root Complex Initialization Sequence if the PCIe
+ * host controller is in reset.
+ */
+ if (ath79_reset_rr(AR724X_RESET_REG_RESET_MODULE) & AR724X_RESET_PCIE)
+ ar724x_pci_hw_init(apc);
+
apc->link_up = ar724x_pci_check_link(apc);
if (!apc->link_up)
dev_warn(&pdev->dev, "PCIe link is down\n");
#include <linux/export.h>
#include <linux/pci.h>
#include <linux/smp.h>
+#include <linux/dma-direct.h>
#include <asm/sn/arch.h>
#include <asm/pci/bridge.h>
#include <asm/paccess.h>
return 0;
}
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
+
+ return bc->baddr + paddr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr & ~(0xffUL << 56);
+}
+
/*
* Device might live on a subordinate PCI bus. XXX Walk up the chain of buses
* to find the slot number in sense of the bridge device register.
bridge->b_widget.w_tflush; /* Flush */
}
-static inline void pci_enable_swapping(struct pci_dev *dev)
-{
- struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
- bridge_t *bridge = bc->base;
- int slot = PCI_SLOT(dev->devfn);
-
- /* Turn on byte swapping */
- bridge->b_device[slot].reg |= BRIDGE_DEV_SWAP_DIR;
- bridge->b_widget.w_tflush; /* Flush */
-}
-
static void pci_fixup_ioc3(struct pci_dev *d)
{
pci_disable_swapping(d);
#include <asm/octeon/cvmx-pci-defs.h>
#include <asm/octeon/pci-octeon.h>
-#include <dma-coherence.h>
-
#define USE_OCTEON_INTERNAL_ARBITER
/*
pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, dconfig);
}
- dev->dev.dma_ops = octeon_pci_dma_map_ops;
-
return 0;
}
phys_addr_t size = resource_size(rsrc);
*start = fixup_bigphys_addr(rsrc->start, size);
- *end = rsrc->start + size;
+ *end = rsrc->start + size - 1;
}
static int cvmx_pcie_rc_initialize(int pcie_port);
-#include <dma-coherence.h>
-
/**
* Return the Core virtual base address for PCIe IO access. IOs are
* read/written as an offset from this address.
/* CN63XX Pass 1.0 errata G-14395 requires the QLM De-emphasis be programmed */
if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_0)) {
if (pcie_port) {
- union cvmx_ciu_qlm1 ciu_qlm;
+ union cvmx_ciu_qlm ciu_qlm;
ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM1);
ciu_qlm.s.txbypass = 1;
ciu_qlm.s.txdeemph = 5;
ciu_qlm.s.txmargin = 0x17;
cvmx_write_csr(CVMX_CIU_QLM1, ciu_qlm.u64);
} else {
- union cvmx_ciu_qlm0 ciu_qlm;
+ union cvmx_ciu_qlm ciu_qlm;
ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM0);
ciu_qlm.s.txbypass = 1;
ciu_qlm.s.txdeemph = 5;
*/
#include <asm/mach-pic32/pic32.h>
#include <asm/fw/fw.h>
+#include <asm/setup.h>
#include "pic32mzda.h"
#include "early_pin.h"
setup_early_console(port, baud);
}
-int prom_putchar(char c)
+void prom_putchar(char c)
{
if (console_port >= 0) {
while (__raw_readl(
__raw_writel(c, uart_base + U_TXR(console_port));
}
-
- return 1;
}
#include <linux/serial_reg.h>
#include <asm/addrspace.h>
+#include <asm/setup.h>
#ifdef CONFIG_SOC_RT288X
#define EARLY_UART_BASE 0x300c00
}
}
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
{
if (!init_complete) {
find_uart_base();
}
if (IS_ENABLED(CONFIG_SOC_MT7621) || soc_is_mt7628()) {
- uart_w32(ch, UART_TX);
+ uart_w32((unsigned char)ch, UART_TX);
while ((uart_r32(UART_REG_LSR) & UART_LSR_THRE) == 0)
;
} else {
while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
;
- uart_w32(ch, UART_REG_TX);
+ uart_w32((unsigned char)ch, UART_REG_TX);
while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
;
}
*/
#include <asm/page.h>
+#include <asm/setup.h>
#include <asm/sn/addrs.h>
#include <asm/sn/sn0/hub.h>
#include <asm/sn/klconfig.h>
#
obj-y += ip32-berr.o ip32-irq.o ip32-platform.o ip32-setup.o ip32-reset.o \
- crime.o ip32-memory.o
+ crime.o ip32-memory.o ip32-dma.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/dma-direct.h>
+#include <asm/ip32/crime.h>
+
+/*
+ * Few notes.
+ * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
+ * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
+ * native-endian)
+ * 3. All other devices see memory as one big chunk at 0x40000000
+ * 4. Non-PCI devices will pass NULL as struct device*
+ *
+ * Thus we translate differently, depending on device.
+ */
+
+#define RAM_OFFSET_MASK 0x3fffffffUL
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
+
+ if (!dev)
+ dma_addr += CRIME_HI_MEM_BASE;
+ return dma_addr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+ phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
+
+ if (dma_addr >= 256*1024*1024)
+ paddr += CRIME_HI_MEM_BASE;
+ return paddr;
+}
config SIBYTE_SB1xxx_SOC
bool
- select DMA_COHERENT
select IRQ_MIPS_CPU
select SWAP_IO_SPACE
select SYS_SUPPORTS_32BIT_KERNEL
#include <asm/bootinfo.h>
#include <asm/reboot.h>
+#include <asm/setup.h>
#include <asm/sibyte/board.h>
#include <asm/smp-ops.h>
#include <asm/reboot.h>
#include <asm/r4kcache.h>
#include <asm/sections.h>
+#include <asm/setup.h>
#include <asm/txx9/generic.h>
#include <asm/txx9/pci.h>
#include <asm/txx9tmr.h>
$(filter -I%,$(KBUILD_CFLAGS)) \
$(filter -E%,$(KBUILD_CFLAGS)) \
$(filter -mmicromips,$(KBUILD_CFLAGS)) \
- $(filter -march=%,$(KBUILD_CFLAGS))
+ $(filter -march=%,$(KBUILD_CFLAGS)) \
+ -D__VDSO__
+
+ifeq ($(cc-name),clang)
+ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS))
+endif
+
cflags-vdso := $(ccflags-vdso) \
$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
# VDSO linker flags.
VDSO_LDFLAGS := \
-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
+ $(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \
-nostdlib -shared \
$(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
$(call cc-ldoption, -Wl$(comma)--build-id)
ELF(Shdr) *shdr;
char *shstrtab, *name;
uint16_t sh_count, sh_entsize, i;
- unsigned int local_gotno, symtabno, gotsym;
- ELF(Dyn) *dyn = NULL;
shdrs = vdso + FUNC(swap_uint)(ehdr->e_shoff);
sh_count = swap_uint16(ehdr->e_shnum);
"%s: '%s' contains relocation sections\n",
program_name, path);
return false;
- case SHT_DYNAMIC:
- dyn = vdso + FUNC(swap_uint)(shdr->sh_offset);
- break;
}
/* Check for existing sections. */
}
}
- /*
- * Ensure the GOT has no entries other than the standard 2, for the same
- * reason we check that there's no relocation sections above.
- * The standard two entries are:
- * - Lazy resolver
- * - Module pointer
- */
- if (dyn) {
- local_gotno = symtabno = gotsym = 0;
-
- while (FUNC(swap_uint)(dyn->d_tag) != DT_NULL) {
- switch (FUNC(swap_uint)(dyn->d_tag)) {
- /*
- * This member holds the number of local GOT entries.
- */
- case DT_MIPS_LOCAL_GOTNO:
- local_gotno = FUNC(swap_uint)(dyn->d_un.d_val);
- break;
- /*
- * This member holds the number of entries in the
- * .dynsym section.
- */
- case DT_MIPS_SYMTABNO:
- symtabno = FUNC(swap_uint)(dyn->d_un.d_val);
- break;
- /*
- * This member holds the index of the first dynamic
- * symbol table entry that corresponds to an entry in
- * the GOT.
- */
- case DT_MIPS_GOTSYM:
- gotsym = FUNC(swap_uint)(dyn->d_un.d_val);
- break;
- }
-
- dyn++;
- }
-
- if (local_gotno > 2 || symtabno - gotsym) {
- fprintf(stderr,
- "%s: '%s' contains unexpected GOT entries\n",
- program_name, path);
- return false;
- }
- }
-
return true;
}
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/ioport.h>
#define pmu_read(offset) readw(pmu_base + (offset))
#define pmu_write(offset, value) writew((value), pmu_base + (offset))
-static void vr41xx_cpu_wait(void)
+static void __cpuidle vr41xx_cpu_wait(void)
{
local_irq_disable();
if (!need_resched())
select CLONE_BACKWARDS
select COMMON_CLK
select DMA_NONCOHERENT_OPS
- select GENERIC_ASHLDI3
- select GENERIC_ASHRDI3
- select GENERIC_LSHRDI3
- select GENERIC_CMPDI2
- select GENERIC_MULDI3
- select GENERIC_UCMPDI2
select GENERIC_ATOMIC64
select GENERIC_CPU_DEVICES
select GENERIC_CLOCKEVENTS
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_SHOW
+ select GENERIC_LIB_ASHLDI3
+ select GENERIC_LIB_ASHRDI3
+ select GENERIC_LIB_CMPDI2
+ select GENERIC_LIB_LSHRDI3
+ select GENERIC_LIB_MULDI3
+ select GENERIC_LIB_UCMPDI2
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
KBUILD_CFLAGS += $(call cc-option, -EL)
KBUILD_AFLAGS += $(call cc-option, -EL)
LDFLAGS += $(call cc-option, -EL)
+CHECKFLAGS += -D__NDS32_EL__
else
KBUILD_CFLAGS += $(call cc-option, -EB)
KBUILD_AFLAGS += $(call cc-option, -EB)
LDFLAGS += $(call cc-option, -EB)
+CHECKFLAGS += -D__NDS32_EB__
endif
boot := arch/nds32/boot
#define PG_dcache_dirty PG_arch_1
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
#ifdef CONFIG_CPU_CACHE_ALIASING
void flush_cache_mm(struct mm_struct *mm);
void flush_cache_dup_mm(struct mm_struct *mm);
void flush_kernel_dcache_page(struct page *page);
void flush_kernel_vmap_range(void *addr, int size);
void invalidate_kernel_vmap_range(void *addr, int size);
-void flush_icache_range(unsigned long start, unsigned long end);
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages)
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
#else
#include <asm-generic/cacheflush.h>
+#undef flush_icache_range
+#undef flush_icache_page
+#undef flush_icache_user_range
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+ unsigned long addr, int len);
#endif
#endif /* __NDS32_CACHEFLUSH_H__ */
" .popsection\n" \
" .pushsection .fixup,\"ax\"\n" \
"4: move %0, " err_reg "\n" \
- " j 3b\n" \
+ " b 3b\n" \
" .popsection"
#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \
void __init setup_arch(char **cmdline_p)
{
- early_init_devtree( __dtb_start);
+ early_init_devtree(__atags_pointer ? \
+ phys_to_virt(__atags_pointer) : __dtb_start);
setup_cpuinfo();
extern struct cache_info L1_cache_info[2];
-#ifndef CONFIG_CPU_CACHE_ALIASING
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+ unsigned long line_size, flags;
+ line_size = L1_cache_info[DCACHE].line_size;
+ start = start & ~(line_size - 1);
+ end = (end + line_size - 1) & ~(line_size - 1);
+ local_irq_save(flags);
+ cpu_cache_wbinval_range(start, end, 1);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+ unsigned long flags;
+ unsigned long kaddr;
+ local_irq_save(flags);
+ kaddr = (unsigned long)kmap_atomic(page);
+ cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+ kunmap_atomic((void *)kaddr);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_page);
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+ unsigned long addr, int len)
+{
+ unsigned long kaddr;
+ kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK);
+ flush_icache_range(kaddr, kaddr + len);
+ kunmap_atomic((void *)kaddr);
+}
+
void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
pte_t * pte)
{
if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) ||
(vma->vm_flags & VM_EXEC)) {
-
- if (!PageHighMem(page)) {
- cpu_cache_wbinval_page((unsigned long)
- page_address(page),
- vma->vm_flags & VM_EXEC);
- } else {
- unsigned long kaddr = (unsigned long)kmap_atomic(page);
- cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
- kunmap_atomic((void *)kaddr);
- }
+ unsigned long kaddr;
+ local_irq_save(flags);
+ kaddr = (unsigned long)kmap_atomic(page);
+ cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+ kunmap_atomic((void *)kaddr);
+ local_irq_restore(flags);
}
}
-#else
+#ifdef CONFIG_CPU_CACHE_ALIASING
extern pte_t va_present(struct mm_struct *mm, unsigned long addr);
static inline unsigned long aliasing(unsigned long addr, unsigned long page)
local_irq_restore(flags);
}
EXPORT_SYMBOL(invalidate_kernel_vmap_range);
-
-void flush_icache_range(unsigned long start, unsigned long end)
-{
- unsigned long line_size, flags;
- line_size = L1_cache_info[DCACHE].line_size;
- start = start & ~(line_size - 1);
- end = (end + line_size - 1) & ~(line_size - 1);
- local_irq_save(flags);
- cpu_cache_wbinval_range(start, end, 1);
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
- unsigned long flags;
- local_irq_save(flags);
- cpu_cache_wbinval_page((unsigned long)page_address(page),
- vma->vm_flags & VM_EXEC);
- local_irq_restore(flags);
-}
-
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
- pte_t * pte)
-{
- struct page *page;
- unsigned long flags;
- unsigned long pfn = pte_pfn(*pte);
-
- if (!pfn_valid(pfn))
- return;
-
- if (vma->vm_mm == current->active_mm) {
- local_irq_save(flags);
- __nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN);
- __nds32__tlbop_rwr(*pte);
- __nds32__isb();
- local_irq_restore(flags);
- }
-
- page = pfn_to_page(pfn);
- if (test_and_clear_bit(PG_dcache_dirty, &page->flags) ||
- (vma->vm_flags & VM_EXEC)) {
- local_irq_save(flags);
- cpu_dcache_wbinval_page((unsigned long)page_address(page));
- local_irq_restore(flags);
- }
-}
#endif
select GENERIC_STRNLEN_USER
select GENERIC_SMP_IDLE_THREAD
select MODULES_USE_ELF_RELA
- select MULTI_IRQ_HANDLER
select HAVE_DEBUG_STACKOVERFLOW
select OR1K_PIC
select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
select ARCH_USE_QUEUED_RWLOCKS
select OMPIC if SMP
select ARCH_WANT_FRAME_POINTERS
+ select GENERIC_IRQ_MULTI_HANDLER
config CPU_BIG_ENDIAN
def_bool y
config LOCKDEP_SUPPORT
def_bool y
-config MULTI_IRQ_HANDLER
- def_bool y
-
source "init/Kconfig"
source "kernel/Kconfig.freezer"
*
* This is often used through atomic_inc_not_zero()
*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int old, tmp;
return old;
}
-#define __atomic_add_unless __atomic_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
#include <asm-generic/atomic.h>
#ifndef __ASM_OPENRISC_CMPXCHG_H
#define __ASM_OPENRISC_CMPXCHG_H
+#include <linux/bits.h>
+#include <linux/compiler.h>
#include <linux/types.h>
-#include <linux/bitops.h>
#define __HAVE_ARCH_CMPXCHG 1
#define NO_IRQ (-1)
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
#endif /* __ASM_OPENRISC_IRQ_H__ */
__free_page(pte);
}
+#define __pte_free_tlb(tlb, pte, addr) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), (pte)); \
+} while (0)
-#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte))
#define pmd_pgtable(pmd) pmd_page(pmd)
#define check_pgt_cache() do { } while (0)
l.addi r3,r1,0 // pt_regs
/* r4 set be EXCEPTION_HANDLE */ // effective address of fault
- /*
- * __PHX__: TODO
- *
- * all this can be written much simpler. look at
- * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part
- */
#ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX
l.lwz r6,PT_PC(r3) // address of an offending insn
l.lwz r6,0(r6) // instruction that caused pf
#else
- l.lwz r6,PT_SR(r3) // SR
+ l.mfspr r6,r0,SPR_SR // SR
l.andi r6,r6,SPR_SR_DSX // check for delay slot exception
l.sfne r6,r0 // exception happened in delay slot
l.bnf 7f
* r4 - EEAR exception EA
* r10 - current pointing to current_thread_info struct
* r12 - syscall 0, since we didn't come from syscall
- * r13 - temp it actually contains new SR, not needed anymore
- * r31 - handler address of the handler we'll jump to
+ * r30 - handler address of the handler we'll jump to
*
* handler has to save remaining registers to the exception
* ksp frame *before* tainting them!
/* r1 is KSP, r30 is __pa(KSP) */ ;\
tophys (r30,r1) ;\
l.sw PT_GPR12(r30),r12 ;\
+ /* r4 use for tmp before EA */ ;\
l.mfspr r12,r0,SPR_EPCR_BASE ;\
l.sw PT_PC(r30),r12 ;\
l.mfspr r12,r0,SPR_ESR_BASE ;\
/* r12 == 1 if we come from syscall */ ;\
CLEAR_GPR(r12) ;\
/* ----- turn on MMU ----- */ ;\
- l.ori r30,r0,(EXCEPTION_SR) ;\
+ /* Carry DSX into exception SR */ ;\
+ l.mfspr r30,r0,SPR_SR ;\
+ l.andi r30,r30,SPR_SR_DSX ;\
+ l.ori r30,r30,(EXCEPTION_SR) ;\
l.mtspr r0,r30,SPR_ESR_BASE ;\
/* r30: EA address of handler */ ;\
LOAD_SYMBOL_2_GPR(r30,handler) ;\
irqchip_init();
}
-static void (*handle_arch_irq)(struct pt_regs *);
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
- handle_arch_irq = handle_irq;
-}
-
void __irq_entry do_IRQ(struct pt_regs *regs)
{
handle_arch_irq(regs);
return 0;
}
#else
- return regs->sr & SPR_SR_DSX;
+ return mfspr(SPR_SR) & SPR_SR_DSX;
#endif
}
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_UBSAN_SANITIZE_ALL
- select ARCH_WANTS_UBSAN_NO_NULL
select ARCH_SUPPORTS_MEMORY_FAILURE
select RTC_CLASS
select RTC_DRV_GENERIC
select HAVE_ARCH_HASH
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
+ select HAVE_REGS_AND_STACK_ACCESS_API
select GENERIC_SCHED_CLOCK
select HAVE_UNSTABLE_SCHED_CLOCK if SMP
select GENERIC_CLOCKEVENTS
config PA11
def_bool y
depends on PA7000 || PA7100LC || PA7200 || PA7300LC
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select DMA_NONCOHERENT_OPS
+ select DMA_NONCOHERENT_CACHE_SYNC
config PREFETCH
def_bool y
config MLONGCALLS
bool "Enable the -mlong-calls compiler option for big kernels"
- def_bool y if (!MODULES)
+ default y
depends on PA8X00
help
If you configure the kernel to include many drivers built-in instead
config PARISC_PAGE_SIZE_16KB
bool "16KB"
- depends on PA8X00
+ depends on PA8X00 && BROKEN
config PARISC_PAGE_SIZE_64KB
bool "64KB"
- depends on PA8X00
+ depends on PA8X00 && BROKEN
endchoice
machines, but will use only one CPU of a multiprocessor machine.
On a uniprocessor machine, the kernel will run faster if you say N.
- See also <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO
+ See also <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO
available at <http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
int "Maximum number of CPUs (2-32)"
range 2 32
depends on SMP
- default "32"
+ default "4"
endmenu
# kernel.
cflags-y += -mdisable-fpregs
-# Without this, "ld -r" results in .text sections that are too big
-# (> 0x40000) for branches to reach stubs.
-cflags-y += -ffunction-sections
-
# Use long jumps instead of long branches (needed if your linker fails to
# link a too big vmlinux executable). Not enabled for building modules.
ifdef CONFIG_MLONGCALLS
#define RP_OFFSET 16
#define FRAME_SIZE 128
#define CALLEE_REG_FRAME_SIZE 144
+#define REG_SZ 8
#define ASM_ULONG_INSN .dword
#else /* CONFIG_64BIT */
#define LDREG ldw
#define RP_OFFSET 20
#define FRAME_SIZE 64
#define CALLEE_REG_FRAME_SIZE 128
+#define REG_SZ 4
#define ASM_ULONG_INSN .word
#endif
#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
#define ATOMIC_OP(op, c_op) \
static __inline__ void atomic_##op(int i, atomic_t *v) \
{ \
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-#define atomic_inc(v) (atomic_add( 1,(v)))
-#define atomic_dec(v) (atomic_add( -1,(v)))
-
-#define atomic_inc_return(v) (atomic_add_return( 1,(v)))
-#define atomic_dec_return(v) (atomic_add_return( -1,(v)))
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
#define ATOMIC_INIT(i) { (i) }
#ifdef CONFIG_64BIT
return READ_ONCE((v)->counter);
}
-#define atomic64_inc(v) (atomic64_add( 1,(v)))
-#define atomic64_dec(v) (atomic64_add( -1,(v)))
-
-#define atomic64_inc_return(v) (atomic64_add_return( 1,(v)))
-#define atomic64_dec_return(v) (atomic64_add_return( -1,(v)))
-
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i),(v)) == 0)
-
/* exported interface */
#define atomic64_cmpxchg(v, o, n) \
((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
- long c, old, dec;
- c = atomic64_read(v);
- for (;;) {
- dec = c - 1;
- if (unlikely(dec < 0))
- break;
- old = atomic64_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
- return dec;
-}
-
#endif /* !CONFIG_64BIT */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+ which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb() do { synchronize_caches(); } while (0)
+#define rmb() mb()
+#define wmb() mb()
+#define dma_rmb() mb()
+#define dma_wmb() mb()
+#else
+#define mb() barrier()
+#define rmb() barrier()
+#define wmb() barrier()
+#define dma_rmb() barrier()
+#define dma_wmb() barrier()
+#endif
+
+#define __smp_mb() mb()
+#define __smp_rmb() mb()
+#define __smp_wmb() mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
** flush/purge and allocate "regular" cacheable pages for everything.
*/
-#ifdef CONFIG_PA11
-extern const struct dma_map_ops pcxl_dma_ops;
-extern const struct dma_map_ops pcx_dma_ops;
-#endif
-
extern const struct dma_map_ops *hppa_dma_ops;
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
#ifdef __ASSEMBLY__
#define ENTRY(name) \
- .export name !\
- ALIGN !\
-name:
+ ALIGN !\
+name: ASM_NL\
+ .export name
#ifdef CONFIG_64BIT
#define ENDPROC(name) \
END(name)
#endif
-#define ENTRY_CFI(name) \
+#define ENTRY_CFI(name, ...) \
ENTRY(name) ASM_NL\
+ .proc ASM_NL\
+ .callinfo __VA_ARGS__ ASM_NL\
+ .entry ASM_NL\
CFI_STARTPROC
#define ENDPROC_CFI(name) \
- ENDPROC(name) ASM_NL\
- CFI_ENDPROC
+ CFI_ENDPROC ASM_NL\
+ .exit ASM_NL\
+ .procend ASM_NL\
+ ENDPROC(name)
#endif /* __ASSEMBLY__ */
return regs->gr[20];
}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->iaoq[0] = val;
+}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ipsw))
+
#endif
unsigned long sig[_NSIG_WORDS];
} sigset_t;
-#ifndef __KERNEL__
-struct sigaction {
- __sighandler_t sa_handler;
- unsigned long sa_flags;
- sigset_t sa_mask; /* mask last for extensibility */
-};
-#endif
-
#include <asm/sigcontext.h>
#endif /* !__ASSEMBLY */
{
volatile unsigned int *a;
- mb();
a = __ldcw_align(x);
while (__ldcw(a) == 0)
while (*a == 0)
local_irq_disable();
} else
cpu_relax();
- mb();
}
#define arch_spin_lock_flags arch_spin_lock_flags
static inline void arch_spin_unlock(arch_spinlock_t *x)
{
volatile unsigned int *a;
- mb();
+
a = __ldcw_align(x);
- *a = 1;
mb();
+ *a = 1;
}
static inline int arch_spin_trylock(arch_spinlock_t *x)
volatile unsigned int *a;
int ret;
- mb();
a = __ldcw_align(x);
ret = __ldcw(a) != 0;
- mb();
return ret;
}
#include <linux/list.h>
+/* Max number of levels to backtrace */
+#define MAX_UNWIND_ENTRIES 30
+
/* From ABI specifications */
struct unwind_table_entry {
unsigned int region_start;
#define ELOOP 249 /* Too many symbolic links encountered */
#define ENOSYS 251 /* Function not implemented */
-#define ENOTSUP 252 /* Function not implemented (POSIX.4 / HPUX) */
#define ECANCELLED 253 /* aio request was canceled before complete (POSIX.4 / HPUX) */
#define ECANCELED ECANCELLED /* SuSv3 and Solaris wants one 'L' */
#define __NR_preadv2 (__NR_Linux + 347)
#define __NR_pwritev2 (__NR_Linux + 348)
#define __NR_statx (__NR_Linux + 349)
+#define __NR_io_pgetevents (__NR_Linux + 350)
-#define __NR_Linux_syscalls (__NR_statx + 1)
+#define __NR_Linux_syscalls (__NR_io_pgetevents + 1)
#define __IGNORE_select /* newselect */
{
/* FIXME: we need this because apparently the sti
* driver can be registered twice */
- if(driver->drv.name) {
- printk(KERN_WARNING
- "BUG: skipping previously registered driver %s\n",
- driver->name);
+ if (driver->drv.name) {
+ pr_warn("BUG: skipping previously registered driver %s\n",
+ driver->name);
return 1;
}
if (!driver->probe) {
- printk(KERN_WARNING
- "BUG: driver %s has no probe routine\n",
- driver->name);
+ pr_warn("BUG: driver %s has no probe routine\n", driver->name);
return 1;
}
dev = create_parisc_device(mod_path);
if (dev->id.hw_type != HPHW_FAULTY) {
- printk(KERN_ERR "Two devices have hardware path [%s]. "
- "IODC data for second device: "
- "%02x%02x%02x%02x%02x%02x\n"
- "Rearranging GSC cards sometimes helps\n",
- parisc_pathname(dev), iodc_data[0], iodc_data[1],
- iodc_data[3], iodc_data[4], iodc_data[5], iodc_data[6]);
+ pr_err("Two devices have hardware path [%s]. IODC data for second device: %7phN\n"
+ "Rearranging GSC cards sometimes helps\n",
+ parisc_pathname(dev), iodc_data);
return NULL;
}
* the keyboard controller
*/
if ((hpa & 0xfff) == 0 && insert_resource(&iomem_resource, &dev->hpa))
- printk("Unable to claim HPA %lx for device %s\n",
- hpa, name);
+ pr_warn("Unable to claim HPA %lx for device %s\n", hpa, name);
return dev;
}
static int count;
print_pa_hwpath(dev, hw_path);
- printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+ pr_info("%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
/* Release pa_tlb_lock lock without reloading lock address. */
.macro tlb_unlock0 spc,tmp
#ifdef CONFIG_SMP
+ or,COND(=) %r0,\spc,%r0
+ sync
or,COND(=) %r0,\spc,%r0
stw \spc,0(\tmp)
#endif
#endif
/* Fault vector is separately protected and *must* be on its own page */
.align PAGE_SIZE
-ENTRY(end_fault_vector)
.import handle_interruption,code
.import do_cpu_irq_mask,code
*/
ENTRY_CFI(ret_from_kernel_thread)
-
/* Call schedule_tail first though */
BL schedule_tail, %r2
nop
LDREG TASK_THREAD_INFO(%r25), %r25
bv %r0(%r2)
mtctl %r25,%cr30
+ENDPROC_CFI(_switch_to)
-_switch_to_ret:
+ENTRY_CFI(_switch_to_ret)
mtctl %r0, %cr0 /* Needed for single stepping */
callee_rest
callee_rest_float
LDREG -RP_OFFSET(%r30), %r2
bv %r0(%r2)
copy %r26, %r28
-ENDPROC_CFI(_switch_to)
+ENDPROC_CFI(_switch_to_ret)
/*
* Common rfi return path for interruptions, kernel execve, and
STREG %r19,PT_SR5(%r16)
STREG %r19,PT_SR6(%r16)
STREG %r19,PT_SR7(%r16)
+ENDPROC_CFI(syscall_exit_rfi)
-intr_return:
+ENTRY_CFI(intr_return)
/* check for reschedule */
mfctl %cr30,%r1
LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */
bb,<,n %r19,31-TIF_NEED_RESCHED,intr_do_resched /* forward */
+ENDPROC_CFI(intr_return)
.import do_notify_resume,code
intr_check_sig:
b do_cpu_irq_mask
ldo R%intr_return(%r2), %r2 /* return to intr_return, not here */
-ENDPROC_CFI(syscall_exit_rfi)
/* Generic interruptions (illegal insn, unaligned, page fault, etc) */
.align L1_CACHE_BYTES
.globl mcount
.type mcount, @function
-ENTRY(mcount)
+ENTRY_CFI(mcount, caller)
_mcount:
.export _mcount,data
- .proc
- .callinfo caller,frame=0
- .entry
/*
* The 64bit mcount() function pointer needs 4 dwords, of which the
* first two are free. We optimize it here and put 2 instructions for
.dword mcount
.dword 0 /* code in head.S puts value of global gp here */
#endif
- .exit
- .procend
-ENDPROC(mcount)
+ENDPROC_CFI(mcount)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.align 8
.globl return_to_handler
.type return_to_handler, @function
-ENTRY_CFI(return_to_handler)
- .proc
- .callinfo caller,frame=FRAME_SIZE
- .entry
+ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE)
.export parisc_return_to_handler,data
parisc_return_to_handler:
copy %r3,%r1
bv %r0(%rp)
#endif
LDREGM -FRAME_SIZE(%sp),%r3
- .exit
- .procend
ENDPROC_CFI(return_to_handler)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#ifdef CONFIG_IRQSTACKS
/* void call_on_stack(unsigned long param1, void *func,
unsigned long new_stack) */
-ENTRY_CFI(call_on_stack)
+ENTRY_CFI(call_on_stack, FRAME=2*FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP)
copy %sp, %r1
/* Regarding the HPPA calling conventions for function pointers,
we assume the PIC register is not changed across call. For
CONFIG_64BIT, the argument pointer is left to point at the
argument region allocated for the call to call_on_stack. */
+
+ /* Switch to new stack. We allocate two frames. */
+ ldo 2*FRAME_SIZE(%arg2), %sp
# ifdef CONFIG_64BIT
- /* Switch to new stack. We allocate two 128 byte frames. */
- ldo 256(%arg2), %sp
/* Save previous stack pointer and return pointer in frame marker */
- STREG %rp, -144(%sp)
+ STREG %rp, -FRAME_SIZE-RP_OFFSET(%sp)
/* Calls always use function descriptor */
LDREG 16(%arg1), %arg1
bve,l (%arg1), %rp
- STREG %r1, -136(%sp)
- LDREG -144(%sp), %rp
+ STREG %r1, -FRAME_SIZE-REG_SZ(%sp)
+ LDREG -FRAME_SIZE-RP_OFFSET(%sp), %rp
bve (%rp)
- LDREG -136(%sp), %sp
+ LDREG -FRAME_SIZE-REG_SZ(%sp), %sp
# else
- /* Switch to new stack. We allocate two 64 byte frames. */
- ldo 128(%arg2), %sp
/* Save previous stack pointer and return pointer in frame marker */
- STREG %r1, -68(%sp)
- STREG %rp, -84(%sp)
+ STREG %r1, -FRAME_SIZE-REG_SZ(%sp)
+ STREG %rp, -FRAME_SIZE-RP_OFFSET(%sp)
/* Calls use function descriptor if PLABEL bit is set */
bb,>=,n %arg1, 30, 1f
depwi 0,31,2, %arg1
1:
be,l 0(%sr4,%arg1), %sr0, %r31
copy %r31, %rp
- LDREG -84(%sp), %rp
+ LDREG -FRAME_SIZE-RP_OFFSET(%sp), %rp
bv (%rp)
- LDREG -68(%sp), %sp
+ LDREG -FRAME_SIZE-REG_SZ(%sp), %sp
# endif /* CONFIG_64BIT */
ENDPROC_CFI(call_on_stack)
#endif /* CONFIG_IRQSTACKS */
.align 16
ENTRY_CFI(flush_tlb_all_local)
- .proc
- .callinfo NO_CALLS
- .entry
-
/*
* The pitlbe and pdtlbe instructions should only be used to
* flush the entire tlb. Also, there needs to be no intervening
2: bv %r0(%r2)
nop
-
- .exit
- .procend
ENDPROC_CFI(flush_tlb_all_local)
.import cache_info,data
ENTRY_CFI(flush_instruction_cache_local)
- .proc
- .callinfo NO_CALLS
- .entry
-
load32 cache_info, %r1
/* Flush Instruction Cache */
mtsm %r22 /* restore I-bit */
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_instruction_cache_local)
.import cache_info, data
ENTRY_CFI(flush_data_cache_local)
- .proc
- .callinfo NO_CALLS
- .entry
-
load32 cache_info, %r1
/* Flush Data Cache */
mtsm %r22 /* restore I-bit */
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_data_cache_local)
/* Macros to serialize TLB purge operations on SMP. */
.macro tlb_unlock la,flags,tmp
#ifdef CONFIG_SMP
ldi 1,\tmp
+ sync
stw \tmp,0(\la)
mtsm \flags
#endif
/* Clear page using kernel mapping. */
ENTRY_CFI(clear_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
#ifdef CONFIG_64BIT
/* Unroll the loop. */
#endif
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(clear_page_asm)
/* Copy page using kernel mapping. */
ENTRY_CFI(copy_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
#ifdef CONFIG_64BIT
/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
* Unroll the loop by hand and arrange insn appropriately.
#endif
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(copy_page_asm)
/*
*/
ENTRY_CFI(copy_user_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
/* Convert virtual `to' and `from' addresses to physical addresses.
Move `from' physical address to non shadowed register. */
ldil L%(__PAGE_OFFSET), %r1
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(copy_user_page_asm)
ENTRY_CFI(clear_user_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
tophys_r1 %r26
ldil L%(TMPALIAS_MAP_START), %r28
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(clear_user_page_asm)
ENTRY_CFI(flush_dcache_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%(TMPALIAS_MAP_START), %r28
#ifdef CONFIG_64BIT
#if (TMPALIAS_MAP_START >= 0x80000000)
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_dcache_page_asm)
ENTRY_CFI(flush_icache_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%(TMPALIAS_MAP_START), %r28
#ifdef CONFIG_64BIT
#if (TMPALIAS_MAP_START >= 0x80000000)
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_icache_page_asm)
ENTRY_CFI(flush_kernel_dcache_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%dcache_stride, %r1
ldw R%dcache_stride(%r1), %r23
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_kernel_dcache_page_asm)
ENTRY_CFI(purge_kernel_dcache_page_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%dcache_stride, %r1
ldw R%dcache_stride(%r1), %r23
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(purge_kernel_dcache_page_asm)
ENTRY_CFI(flush_user_dcache_range_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%dcache_stride, %r1
ldw R%dcache_stride(%r1), %r23
ldo -1(%r23), %r21
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_user_dcache_range_asm)
ENTRY_CFI(flush_kernel_dcache_range_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%dcache_stride, %r1
ldw R%dcache_stride(%r1), %r23
ldo -1(%r23), %r21
syncdma
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_kernel_dcache_range_asm)
ENTRY_CFI(purge_kernel_dcache_range_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%dcache_stride, %r1
ldw R%dcache_stride(%r1), %r23
ldo -1(%r23), %r21
syncdma
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(purge_kernel_dcache_range_asm)
ENTRY_CFI(flush_user_icache_range_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%icache_stride, %r1
ldw R%icache_stride(%r1), %r23
ldo -1(%r23), %r21
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_user_icache_range_asm)
ENTRY_CFI(flush_kernel_icache_page)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%icache_stride, %r1
ldw R%icache_stride(%r1), %r23
sync
bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(flush_kernel_icache_page)
ENTRY_CFI(flush_kernel_icache_range_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
ldil L%icache_stride, %r1
ldw R%icache_stride(%r1), %r23
ldo -1(%r23), %r21
sync
bv %r0(%r2)
nop
- .exit
- .procend
ENDPROC_CFI(flush_kernel_icache_range_asm)
__INIT
*/
.align 256
ENTRY_CFI(disable_sr_hashing_asm)
- .proc
- .callinfo NO_CALLS
- .entry
-
/*
* Switch to real mode
*/
2: bv %r0(%r2)
nop
- .exit
-
- .procend
ENDPROC_CFI(disable_sr_hashing_asm)
.end
#include <linux/init.h>
#include <linux/gfp.h>
#include <linux/mm.h>
-#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <asm/cacheflush.h>
#include <asm/dma.h> /* for DMA_CHUNK_SIZE */
__initcall(pcxl_dma_init);
-static void *pa11_dma_alloc(struct device *dev, size_t size,
+static void *pcxl_dma_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
{
unsigned long vaddr;
return (void *)vaddr;
}
-static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
+static void *pcx_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
{
- int order;
-
- order = get_order(size);
- size = 1 << (order + PAGE_SHIFT);
- unmap_uncached_pages((unsigned long)vaddr, size);
- pcxl_free_range((unsigned long)vaddr, size);
- free_pages((unsigned long)__va(dma_handle), order);
-}
+ void *addr;
-static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction, unsigned long attrs)
-{
- void *addr = page_address(page) + offset;
- BUG_ON(direction == DMA_NONE);
+ if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
+ return NULL;
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- flush_kernel_dcache_range((unsigned long) addr, size);
+ addr = (void *)__get_free_pages(flag, get_order(size));
+ if (addr)
+ *dma_handle = (dma_addr_t)virt_to_phys(addr);
- return virt_to_phys(addr);
+ return addr;
}
-static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
- size_t size, enum dma_data_direction direction,
- unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
- BUG_ON(direction == DMA_NONE);
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- return;
- if (direction == DMA_TO_DEVICE)
- return;
-
- /*
- * For PCI_DMA_FROMDEVICE this flush is not necessary for the
- * simple map/unmap case. However, it IS necessary if if
- * pci_dma_sync_single_* has been called and the buffer reused.
- */
-
- flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
+ if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl)
+ return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs);
+ else
+ return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
}
-static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction direction,
- unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle, unsigned long attrs)
{
- int i;
- struct scatterlist *sg;
-
- BUG_ON(direction == DMA_NONE);
+ int order = get_order(size);
- for_each_sg(sglist, sg, nents, i) {
- unsigned long vaddr = (unsigned long)sg_virt(sg);
+ if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
+ size = 1 << (order + PAGE_SHIFT);
+ unmap_uncached_pages((unsigned long)vaddr, size);
+ pcxl_free_range((unsigned long)vaddr, size);
- sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
- sg_dma_len(sg) = sg->length;
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- continue;
-
- flush_kernel_dcache_range(vaddr, sg->length);
+ vaddr = __va(dma_handle);
}
- return nents;
-}
-
-static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction direction,
- unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- BUG_ON(direction == DMA_NONE);
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- return;
-
- if (direction == DMA_TO_DEVICE)
- return;
-
- /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
- for_each_sg(sglist, sg, nents, i)
- flush_kernel_vmap_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- BUG_ON(direction == DMA_NONE);
-
- flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
- size);
-}
-
-static void pa11_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- BUG_ON(direction == DMA_NONE);
-
- flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
- size);
+ free_pages((unsigned long)vaddr, get_order(size));
}
-static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- int i;
- struct scatterlist *sg;
-
- /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
- for_each_sg(sglist, sg, nents, i)
- flush_kernel_vmap_range(sg_virt(sg), sg->length);
+ flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
}
-static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- int i;
- struct scatterlist *sg;
-
- /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
- for_each_sg(sglist, sg, nents, i)
- flush_kernel_vmap_range(sg_virt(sg), sg->length);
+ flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
}
-static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
enum dma_data_direction direction)
{
flush_kernel_dcache_range((unsigned long)vaddr, size);
}
-
-const struct dma_map_ops pcxl_dma_ops = {
- .alloc = pa11_dma_alloc,
- .free = pa11_dma_free,
- .map_page = pa11_dma_map_page,
- .unmap_page = pa11_dma_unmap_page,
- .map_sg = pa11_dma_map_sg,
- .unmap_sg = pa11_dma_unmap_sg,
- .sync_single_for_cpu = pa11_dma_sync_single_for_cpu,
- .sync_single_for_device = pa11_dma_sync_single_for_device,
- .sync_sg_for_cpu = pa11_dma_sync_sg_for_cpu,
- .sync_sg_for_device = pa11_dma_sync_sg_for_device,
- .cache_sync = pa11_dma_cache_sync,
-};
-
-static void *pcx_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
- void *addr;
-
- if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
- return NULL;
-
- addr = (void *)__get_free_pages(flag, get_order(size));
- if (addr)
- *dma_handle = (dma_addr_t)virt_to_phys(addr);
-
- return addr;
-}
-
-static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t iova, unsigned long attrs)
-{
- free_pages((unsigned long)vaddr, get_order(size));
- return;
-}
-
-const struct dma_map_ops pcx_dma_ops = {
- .alloc = pcx_dma_alloc,
- .free = pcx_dma_free,
- .map_page = pa11_dma_map_page,
- .unmap_page = pa11_dma_unmap_page,
- .map_sg = pa11_dma_map_sg,
- .unmap_sg = pa11_dma_unmap_sg,
- .sync_single_for_cpu = pa11_dma_sync_single_for_cpu,
- .sync_single_for_device = pa11_dma_sync_single_for_device,
- .sync_sg_for_cpu = pa11_dma_sync_sg_for_cpu,
- .sync_sg_for_device = pa11_dma_sync_sg_for_device,
- .cache_sync = pa11_dma_cache_sync,
-};
ip = info.ip;
if (!in_sched_functions(ip))
return ip;
- } while (count++ < 16);
+ } while (count++ < MAX_UNWIND_ENTRIES);
return 0;
}
#endif
return &user_parisc_native_view;
}
+
+
+/* HAVE_REGS_AND_STACK_ACCESS_API feature */
+
+struct pt_regs_offset {
+ const char *name;
+ int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_INDEX(r,i) {.name = #r#i, .offset = offsetof(struct pt_regs, r[i])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+ REG_OFFSET_INDEX(gr,0),
+ REG_OFFSET_INDEX(gr,1),
+ REG_OFFSET_INDEX(gr,2),
+ REG_OFFSET_INDEX(gr,3),
+ REG_OFFSET_INDEX(gr,4),
+ REG_OFFSET_INDEX(gr,5),
+ REG_OFFSET_INDEX(gr,6),
+ REG_OFFSET_INDEX(gr,7),
+ REG_OFFSET_INDEX(gr,8),
+ REG_OFFSET_INDEX(gr,9),
+ REG_OFFSET_INDEX(gr,10),
+ REG_OFFSET_INDEX(gr,11),
+ REG_OFFSET_INDEX(gr,12),
+ REG_OFFSET_INDEX(gr,13),
+ REG_OFFSET_INDEX(gr,14),
+ REG_OFFSET_INDEX(gr,15),
+ REG_OFFSET_INDEX(gr,16),
+ REG_OFFSET_INDEX(gr,17),
+ REG_OFFSET_INDEX(gr,18),
+ REG_OFFSET_INDEX(gr,19),
+ REG_OFFSET_INDEX(gr,20),
+ REG_OFFSET_INDEX(gr,21),
+ REG_OFFSET_INDEX(gr,22),
+ REG_OFFSET_INDEX(gr,23),
+ REG_OFFSET_INDEX(gr,24),
+ REG_OFFSET_INDEX(gr,25),
+ REG_OFFSET_INDEX(gr,26),
+ REG_OFFSET_INDEX(gr,27),
+ REG_OFFSET_INDEX(gr,28),
+ REG_OFFSET_INDEX(gr,29),
+ REG_OFFSET_INDEX(gr,30),
+ REG_OFFSET_INDEX(gr,31),
+ REG_OFFSET_INDEX(sr,0),
+ REG_OFFSET_INDEX(sr,1),
+ REG_OFFSET_INDEX(sr,2),
+ REG_OFFSET_INDEX(sr,3),
+ REG_OFFSET_INDEX(sr,4),
+ REG_OFFSET_INDEX(sr,5),
+ REG_OFFSET_INDEX(sr,6),
+ REG_OFFSET_INDEX(sr,7),
+ REG_OFFSET_INDEX(iasq,0),
+ REG_OFFSET_INDEX(iasq,1),
+ REG_OFFSET_INDEX(iaoq,0),
+ REG_OFFSET_INDEX(iaoq,1),
+ REG_OFFSET_NAME(cr27),
+ REG_OFFSET_NAME(ksp),
+ REG_OFFSET_NAME(kpc),
+ REG_OFFSET_NAME(sar),
+ REG_OFFSET_NAME(iir),
+ REG_OFFSET_NAME(isr),
+ REG_OFFSET_NAME(ior),
+ REG_OFFSET_NAME(ipsw),
+ REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name: the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->offset;
+ return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset: the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (roff->offset == offset)
+ return roff->name;
+ return NULL;
+}
real64_stack:
.block 8192
-#ifdef CONFIG_64BIT
-# define REG_SZ 8
-#else
-# define REG_SZ 4
-#endif
-
#define N_SAVED_REGS 9
save_cr_space:
panic( "PA-RISC Linux currently only supports machines that conform to\n"
"the PA-RISC 1.1 or 2.0 architecture specification.\n");
- case pcxs:
- case pcxt:
- hppa_dma_ops = &pcx_dma_ops;
- break;
case pcxl2:
pa7300lc_init();
case pcxl: /* falls through */
- hppa_dma_ops = &pcxl_dma_ops;
+ case pcxs:
+ case pcxt:
+ hppa_dma_ops = &dma_noncoherent_ops;
break;
default:
break;
stw %r1, 4(%sr2,%r20)
#endif
/* The load and store could fail */
-1: ldw,ma 0(%r26), %r28
+1: ldw 0(%r26), %r28
sub,<> %r28, %r25, %r0
-2: stw,ma %r24, 0(%r26)
+2: stw %r24, 0(%r26)
/* Free lock */
- stw,ma %r20, 0(%sr2,%r20)
+ sync
+ stw %r20, 0(%sr2,%r20)
#if ENABLE_LWS_DEBUG
/* Clear thread register indicator */
stw %r0, 4(%sr2,%r20)
3:
/* Error occurred on load or store */
/* Free lock */
+ sync
stw %r20, 0(%sr2,%r20)
#if ENABLE_LWS_DEBUG
stw %r0, 4(%sr2,%r20)
ldo 1(%r0),%r28
/* 8bit CAS */
-13: ldb,ma 0(%r26), %r29
+13: ldb 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-14: stb,ma %r24, 0(%r26)
+14: stb %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
nop
/* 16bit CAS */
-15: ldh,ma 0(%r26), %r29
+15: ldh 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-16: sth,ma %r24, 0(%r26)
+16: sth %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
nop
/* 32bit CAS */
-17: ldw,ma 0(%r26), %r29
+17: ldw 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-18: stw,ma %r24, 0(%r26)
+18: stw %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
/* 64bit CAS */
#ifdef CONFIG_64BIT
-19: ldd,ma 0(%r26), %r29
+19: ldd 0(%r26), %r29
sub,*= %r29, %r25, %r0
b,n cas2_end
-20: std,ma %r24, 0(%r26)
+20: std %r24, 0(%r26)
copy %r0, %r28
#else
/* Compare first word */
cas2_end:
/* Free lock */
- stw,ma %r20, 0(%sr2,%r20)
+ sync
+ stw %r20, 0(%sr2,%r20)
/* Enable interrupts */
ssm PSW_SM_I, %r0
/* Return to userspace, set no error */
22:
/* Error occurred on load or store */
/* Free lock */
+ sync
stw %r20, 0(%sr2,%r20)
ssm PSW_SM_I, %r0
ldo 1(%r0),%r28
ENTRY_COMP(preadv2)
ENTRY_COMP(pwritev2)
ENTRY_SAME(statx)
+ ENTRY_COMP(io_pgetevents) /* 350 */
.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
int i = 1;
printk(KERN_CRIT "Backtrace:\n");
- while (i <= 16) {
+ while (i <= MAX_UNWIND_ENTRIES) {
if (unwind_once(info) < 0 || info->ip == 0)
break;
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
-#include <linux/kallsyms.h>
#include <linux/sort.h>
#include <linux/uaccess.h>
/* #define DEBUG 1 */
#ifdef DEBUG
-#define dbg(x...) printk(x)
+#define dbg(x...) pr_debug(x)
#else
#define dbg(x...)
#endif
for (; start <= end; start++) {
if (start < end &&
start->region_end > (start+1)->region_start) {
- printk("WARNING: Out of order unwind entry! %p and %p\n", start, start+1);
+ pr_warn("Out of order unwind entry! %px and %px\n",
+ start, start+1);
}
start->region_start += base_addr;
start = (long)&__start___unwind[0];
stop = (long)&__stop___unwind[0];
- printk("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n",
+ dbg("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n",
start, stop,
(stop - start) / sizeof(struct unwind_table_entry));
return 0;
}
-#ifdef CONFIG_64BIT
-#define get_func_addr(fptr) fptr[2]
-#else
-#define get_func_addr(fptr) fptr[0]
-#endif
-
static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int frame_size)
{
- extern void handle_interruption(int, struct pt_regs *);
- static unsigned long *hi = (unsigned long *)&handle_interruption;
-
- if (pc == get_func_addr(hi)) {
+ /*
+ * We have to use void * instead of a function pointer, because
+ * function pointers aren't a pointer to the function on 64-bit.
+ * Make them const so the compiler knows they live in .text
+ */
+ extern void * const handle_interruption;
+ extern void * const ret_from_kernel_thread;
+ extern void * const syscall_exit;
+ extern void * const intr_return;
+ extern void * const _switch_to_ret;
+#ifdef CONFIG_IRQSTACKS
+ extern void * const call_on_stack;
+#endif /* CONFIG_IRQSTACKS */
+
+ if (pc == (unsigned long) &handle_interruption) {
struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
dbg("Unwinding through handle_interruption()\n");
info->prev_sp = regs->gr[30];
info->prev_ip = regs->iaoq[0];
+ return 1;
+ }
+
+ if (pc == (unsigned long) &ret_from_kernel_thread ||
+ pc == (unsigned long) &syscall_exit) {
+ info->prev_sp = info->prev_ip = 0;
+ return 1;
+ }
+
+ if (pc == (unsigned long) &intr_return) {
+ struct pt_regs *regs;
+
+ dbg("Found intr_return()\n");
+ regs = (struct pt_regs *)(info->sp - PT_SZ_ALGN);
+ info->prev_sp = regs->gr[30];
+ info->prev_ip = regs->iaoq[0];
+ info->rp = regs->gr[2];
+ return 1;
+ }
+
+ if (pc == (unsigned long) &_switch_to_ret) {
+ info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
+ info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+ return 1;
+ }
+#ifdef CONFIG_IRQSTACKS
+ if (pc == (unsigned long) &call_on_stack) {
+ info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
+ info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
return 1;
}
+#endif
return 0;
}
if (e == NULL) {
unsigned long sp;
- dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip);
-
-#ifdef CONFIG_KALLSYMS
- /* Handle some frequent special cases.... */
- {
- char symname[KSYM_NAME_LEN];
- char *modname;
-
- kallsyms_lookup(info->ip, NULL, NULL, &modname,
- symname);
-
- dbg("info->ip = 0x%lx, name = %s\n", info->ip, symname);
-
- if (strcmp(symname, "_switch_to_ret") == 0) {
- info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
- info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
- dbg("_switch_to_ret @ %lx - setting "
- "prev_sp=%lx prev_ip=%lx\n",
- info->ip, info->prev_sp,
- info->prev_ip);
- return;
- } else if (strcmp(symname, "ret_from_kernel_thread") == 0 ||
- strcmp(symname, "syscall_exit") == 0) {
- info->prev_ip = info->prev_sp = 0;
- return;
- }
- }
-#endif
+ dbg("Cannot find unwind entry for %pS; forced unwinding\n",
+ (void *) info->ip);
/* Since we are doing the unwinding blind, we don't know if
we are adjusting the stack correctly or extracting the rp
/* initialize unwind info */
asm volatile ("copy %%r30, %0" : "=r"(sp));
memset(&r, 0, sizeof(struct pt_regs));
- r.iaoq[0] = (unsigned long) current_text_addr();
- r.gr[2] = (unsigned long) __builtin_return_address(0);
+ r.iaoq[0] = _THIS_IP_;
+ r.gr[2] = _RET_IP_;
r.gr[30] = sp;
unwind_frame_init(&info, current, &r);
*/
ENTRY_CFI(lclear_user)
- .proc
- .callinfo NO_CALLS
- .entry
comib,=,n 0,%r25,$lclu_done
get_sr
$lclu_loop:
ldo 1(%r25),%r25
ASM_EXCEPTIONTABLE_ENTRY(1b,2b)
-
- .exit
ENDPROC_CFI(lclear_user)
- .procend
-
/*
* long lstrnlen_user(char *s, long n)
*
*/
ENTRY_CFI(lstrnlen_user)
- .proc
- .callinfo NO_CALLS
- .entry
comib,= 0,%r25,$lslen_nzero
copy %r26,%r24
get_sr
$lslen_done:
bv %r0(%r2)
sub %r26,%r24,%r28
- .exit
$lslen_nzero:
b $lslen_done
ENDPROC_CFI(lstrnlen_user)
- .procend
-
-
/*
* unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
save_len = r31
ENTRY_CFI(pa_memcpy)
- .proc
- .callinfo NO_CALLS
- .entry
-
/* Last destination address */
add dst,len,end
b .Lcopy_done
10: stw,ma t1,4(dstspc,dst)
ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
-
- .exit
ENDPROC_CFI(pa_memcpy)
- .procend
.end
#include <linux/gfp.h>
#include <linux/delay.h>
#include <linux/init.h>
-#include <linux/pci.h> /* for hppa_dma_ops and pcxl_dma_ops */
#include <linux/initrd.h>
#include <linux/swap.h>
#include <linux/unistd.h>
free_all_bootmem();
#ifdef CONFIG_PA11
- if (hppa_dma_ops == &pcxl_dma_ops) {
+ if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START);
parisc_vmalloc_start = SET_MAP_OFFSET(pcxl_dma_start
+ PCXL_DMA_MAP_SIZE);
- } else {
- pcxl_dma_start = 0;
- parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
- }
-#else
- parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
+ } else
#endif
+ parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
mem_init_print_info(NULL);
cpu-as-$(CONFIG_4xx) += -Wa,-m405
cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec)
cpu-as-$(CONFIG_E200) += -Wa,-me200
+cpu-as-$(CONFIG_E500) += -Wa,-me500
cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4
+cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc)
KBUILD_AFLAGS += $(cpu-as-y)
KBUILD_CFLAGS += $(cpu-as-y)
void pnv_power9_force_smt4_catch(void);
void pnv_power9_force_smt4_release(void);
+/* Transaction memory related */
void tm_enable(void);
void tm_disable(void);
void tm_abort(uint8_t cause);
+
+struct kvm_vcpu;
+void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+
#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
* a "bne-" instruction at the end, so an isync is enough as a acquire barrier
* on the platform without lwsync.
*/
-#define __atomic_op_acquire(op, args...) \
-({ \
- typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \
- __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \
- __ret; \
-})
-
-#define __atomic_op_release(op, args...) \
-({ \
- __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \
- op##_relaxed(args); \
-})
+#define __atomic_acquire_fence() \
+ __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence() \
+ __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
static __inline__ int atomic_read(const atomic_t *v)
{
#undef ATOMIC_OP_RETURN_RELAXED
#undef ATOMIC_OP
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-
static __inline__ void atomic_inc(atomic_t *v)
{
int t;
: "r" (&v->counter)
: "cc", "xer");
}
+#define atomic_inc atomic_inc
static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
{
return t;
}
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
static __inline__ void atomic_dec(atomic_t *v)
{
int t;
: "r" (&v->counter)
: "cc", "xer");
}
+#define atomic_dec atomic_dec
static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
{
#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
/**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
* Atomically adds @a to @v, so long as it was not @u.
* Returns the old value of @v.
*/
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int t;
__asm__ __volatile__ (
PPC_ATOMIC_ENTRY_BARRIER
-"1: lwarx %0,0,%1 # __atomic_add_unless\n\
+"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\
cmpw 0,%0,%3 \n\
beq 2f \n\
add %0,%2,%0 \n"
return t;
}
+#define atomic_fetch_add_unless atomic_fetch_add_unless
/**
* atomic_inc_not_zero - increment unless the number is zero
}
#define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
-#define atomic_sub_and_test(a, v) (atomic_sub_return((a), (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_dec_return((v)) == 0)
-
/*
* Atomically test *v and decrement if it is greater than 0.
* The function returns the old value of *v minus 1, even if
#undef ATOMIC64_OP_RETURN_RELAXED
#undef ATOMIC64_OP
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
static __inline__ void atomic64_inc(atomic64_t *v)
{
long t;
: "r" (&v->counter)
: "cc", "xer");
}
+#define atomic64_inc atomic64_inc
static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
{
return t;
}
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
static __inline__ void atomic64_dec(atomic64_t *v)
{
long t;
: "r" (&v->counter)
: "cc", "xer");
}
+#define atomic64_dec atomic64_dec
static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
{
#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
-#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
-
/*
* Atomically test *v and decrement if it is greater than 0.
* The function returns the old value of *v minus 1.
return t;
}
+#define atomic64_dec_if_positive atomic64_dec_if_positive
#define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
#define atomic64_cmpxchg_relaxed(v, o, n) \
#define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
/**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
* Atomically adds @a to @v, so long as it was not @u.
* Returns the old value of @v.
*/
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
{
long t;
__asm__ __volatile__ (
PPC_ATOMIC_ENTRY_BARRIER
-"1: ldarx %0,0,%1 # __atomic_add_unless\n\
+"1: ldarx %0,0,%1 # atomic64_fetch_add_unless\n\
cmpd 0,%0,%3 \n\
beq 2f \n\
add %0,%2,%0 \n"
: "r" (&v->counter), "r" (a), "r" (u)
: "cc", "memory");
- return t != u;
+ return t;
}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
/**
* atomic_inc64_not_zero - increment unless the number is zero
return t1 != 0;
}
+#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v))
#endif /* __powerpc64__ */
}
#define check_pgt_cache() do { } while (0)
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- pgtable_page_dtor(table);
pgtable_free_tlb(tlb, page_address(table), 0);
}
#endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */
}
#define is_hugepd(hpd) (hugepd_ok(hpd))
+/*
+ * 16M and 16G huge page directory tables are allocated from slab cache
+ *
+ */
+#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
+#define H_16G_CACHE_INDEX \
+ (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
+
+static inline int get_hugepd_cache_index(int index)
+{
+ switch (index) {
+ case H_16M_CACHE_INDEX:
+ return HTLB_16M_INDEX;
+ case H_16G_CACHE_INDEX:
+ return HTLB_16G_INDEX;
+ default:
+ BUG();
+ }
+ /* should not reach */
+}
+
#else /* !CONFIG_HUGETLB_PAGE */
static inline int pmd_huge(pmd_t pmd) { return 0; }
static inline int pud_huge(pud_t pud) { return 0; }
{
return 0;
}
+
#define is_hugepd(pdep) 0
+/*
+ * This should never get called
+ */
+static inline int get_hugepd_cache_index(int index)
+{
+ BUG();
+}
+
#else /* !CONFIG_HUGETLB_PAGE */
static inline int pmd_huge(pmd_t pmd) { return 0; }
static inline int pud_huge(pud_t pud) { return 0; }
PMD_INDEX,
PUD_INDEX,
PGD_INDEX,
+ /*
+ * Below are used with 4k page size and hugetlb
+ */
+ HTLB_16M_INDEX,
+ HTLB_16G_INDEX,
};
extern unsigned long __vmalloc_start;
#include <asm/reg.h>
#include <asm/debug.h>
+struct perf_event_attr;
struct perf_event;
struct pmu;
struct perf_sample_data;
extern int hw_breakpoint_slots(int type);
extern int arch_bp_generic_fields(int type, int *gen_bp_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
int arch_install_hw_breakpoint(struct perf_event *bp);
struct kprobe_ctlblk {
unsigned long kprobe_status;
unsigned long kprobe_saved_msr;
- struct pt_regs jprobe_saved_regs;
struct prev_kprobe prev_kprobe;
};
extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
extern int kprobe_handler(struct pt_regs *regs);
extern int kprobe_post_handler(struct pt_regs *regs);
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int __is_active_jprobe(unsigned long addr);
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
-{
- return 0;
-}
-#endif
#else
static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
ulong vtb; /* virtual timebase */
ulong conferring_threads;
unsigned int halt_poll_ns;
+ atomic_t online_count;
};
struct kvmppc_vcpu_book3s {
extern void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
unsigned int vec);
extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags);
+extern void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac);
extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
bool upper, u32 val);
extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd);
extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu);
extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu);
+void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu);
+void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu);
+void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu);
+#else
+static inline void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
+#endif
+
+void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
+
extern int kvm_irq_bypass;
static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
{
- vcpu->arch.gpr[num] = val;
+ vcpu->arch.regs.gpr[num] = val;
}
static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
{
- return vcpu->arch.gpr[num];
+ return vcpu->arch.regs.gpr[num];
}
static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.xer = val;
+ vcpu->arch.regs.xer = val;
}
static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.xer;
+ return vcpu->arch.regs.xer;
}
static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.ctr = val;
+ vcpu->arch.regs.ctr = val;
}
static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.ctr;
+ return vcpu->arch.regs.ctr;
}
static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.lr = val;
+ vcpu->arch.regs.link = val;
}
static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.lr;
+ return vcpu->arch.regs.link;
}
static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.pc = val;
+ vcpu->arch.regs.nip = val;
}
static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.pc;
+ return vcpu->arch.regs.nip;
}
static inline u64 kvmppc_get_msr(struct kvm_vcpu *vcpu);
static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
{
vcpu->arch.cr = vcpu->arch.cr_tm;
- vcpu->arch.xer = vcpu->arch.xer_tm;
- vcpu->arch.lr = vcpu->arch.lr_tm;
- vcpu->arch.ctr = vcpu->arch.ctr_tm;
+ vcpu->arch.regs.xer = vcpu->arch.xer_tm;
+ vcpu->arch.regs.link = vcpu->arch.lr_tm;
+ vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
vcpu->arch.amr = vcpu->arch.amr_tm;
vcpu->arch.ppr = vcpu->arch.ppr_tm;
vcpu->arch.dscr = vcpu->arch.dscr_tm;
vcpu->arch.tar = vcpu->arch.tar_tm;
- memcpy(vcpu->arch.gpr, vcpu->arch.gpr_tm,
- sizeof(vcpu->arch.gpr));
+ memcpy(vcpu->arch.regs.gpr, vcpu->arch.gpr_tm,
+ sizeof(vcpu->arch.regs.gpr));
vcpu->arch.fp = vcpu->arch.fp_tm;
vcpu->arch.vr = vcpu->arch.vr_tm;
vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
{
vcpu->arch.cr_tm = vcpu->arch.cr;
- vcpu->arch.xer_tm = vcpu->arch.xer;
- vcpu->arch.lr_tm = vcpu->arch.lr;
- vcpu->arch.ctr_tm = vcpu->arch.ctr;
+ vcpu->arch.xer_tm = vcpu->arch.regs.xer;
+ vcpu->arch.lr_tm = vcpu->arch.regs.link;
+ vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
vcpu->arch.amr_tm = vcpu->arch.amr;
vcpu->arch.ppr_tm = vcpu->arch.ppr;
vcpu->arch.dscr_tm = vcpu->arch.dscr;
vcpu->arch.tar_tm = vcpu->arch.tar;
- memcpy(vcpu->arch.gpr_tm, vcpu->arch.gpr,
- sizeof(vcpu->arch.gpr));
+ memcpy(vcpu->arch.gpr_tm, vcpu->arch.regs.gpr,
+ sizeof(vcpu->arch.regs.gpr));
vcpu->arch.fp_tm = vcpu->arch.fp;
vcpu->arch.vr_tm = vcpu->arch.vr;
vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
{
- vcpu->arch.gpr[num] = val;
+ vcpu->arch.regs.gpr[num] = val;
}
static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
{
- return vcpu->arch.gpr[num];
+ return vcpu->arch.regs.gpr[num];
}
static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.xer = val;
+ vcpu->arch.regs.xer = val;
}
static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.xer;
+ return vcpu->arch.regs.xer;
}
static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.ctr = val;
+ vcpu->arch.regs.ctr = val;
}
static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.ctr;
+ return vcpu->arch.regs.ctr;
}
static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.lr = val;
+ vcpu->arch.regs.link = val;
}
static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.lr;
+ return vcpu->arch.regs.link;
}
static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
{
- vcpu->arch.pc = val;
+ vcpu->arch.regs.nip = val;
}
static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.pc;
+ return vcpu->arch.regs.nip;
}
static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
unsigned long host_lpcr;
unsigned long sdr1;
unsigned long host_sdr1;
- int tlbie_lock;
unsigned long lpcr;
unsigned long vrma_slb_v;
int mmu_ready;
#define KVMPPC_VSX_COPY_WORD 1
#define KVMPPC_VSX_COPY_DWORD 2
#define KVMPPC_VSX_COPY_DWORD_LOAD_DUMP 3
+#define KVMPPC_VSX_COPY_WORD_LOAD_DUMP 4
+
+#define KVMPPC_VMX_COPY_BYTE 8
+#define KVMPPC_VMX_COPY_HWORD 9
+#define KVMPPC_VMX_COPY_WORD 10
+#define KVMPPC_VMX_COPY_DWORD 11
struct openpic;
struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
#endif
- ulong gpr[32];
+ struct pt_regs regs;
struct thread_fp_state fp;
u32 qpr[32];
#endif
- ulong pc;
- ulong ctr;
- ulong lr;
#ifdef CONFIG_PPC_BOOK3S
ulong tar;
#endif
- ulong xer;
u32 cr;
#ifdef CONFIG_PPC_BOOK3S
struct thread_vr_state vr_tm;
u32 vrsave_tm; /* also USPRG0 */
-
#endif
#ifdef CONFIG_KVM_EXIT_TIMING
* Number of simulations for vsx.
* If we use 2*8bytes to simulate 1*16bytes,
* then the number should be 2 and
- * mmio_vsx_copy_type=KVMPPC_VSX_COPY_DWORD.
+ * mmio_copy_type=KVMPPC_VSX_COPY_DWORD.
* If we use 4*4bytes to simulate 1*16bytes,
* the number should be 4 and
* mmio_vsx_copy_type=KVMPPC_VSX_COPY_WORD.
*/
u8 mmio_vsx_copy_nums;
u8 mmio_vsx_offset;
- u8 mmio_vsx_copy_type;
u8 mmio_vsx_tx_sx_enabled;
u8 mmio_vmx_copy_nums;
+ u8 mmio_vmx_offset;
+ u8 mmio_copy_type;
u8 osi_needed;
u8 osi_enabled;
u8 papr_enabled;
u64 busy_preempt;
u32 emul_inst;
+
+ u32 online;
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
EMULATE_EXIT_USER, /* emulation requires exit to user-space */
};
-enum instruction_type {
+enum instruction_fetch_type {
INST_GENERIC,
INST_SC, /* system call */
};
extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian, int mmio_sign_extend);
-extern int kvmppc_handle_load128_by2x64(struct kvm_run *run,
- struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian);
-extern int kvmppc_handle_store128_by2x64(struct kvm_run *run,
- struct kvm_vcpu *vcpu, unsigned int rs, int is_default_endian);
+extern int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, unsigned int bytes, int is_default_endian);
+extern int kvmppc_handle_vmx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rs, unsigned int bytes, int is_default_endian);
extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
u64 val, unsigned int bytes,
int is_default_endian);
int is_default_endian);
extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
- enum instruction_type type, u32 *inst);
+ enum instruction_fetch_type type, u32 *inst);
extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
bool data);
vector128 vval;
u64 vsxval[2];
u32 vsx32val[4];
+ u16 vsx16val[8];
+ u8 vsx8val[16];
struct {
u64 addr;
u64 length;
int (*get_rmmu_info)(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
int (*set_smt_mode)(struct kvm *kvm, unsigned long mode,
unsigned long flags);
+ void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr);
};
extern struct kvmppc_ops *kvmppc_hv_ops;
extern struct kvmppc_ops *kvmppc_pr_ops;
static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu,
- enum instruction_type type, u32 *inst)
+ enum instruction_fetch_type type, u32 *inst)
{
int ret = EMULATE_DONE;
u32 fetched_inst;
extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
unsigned long ua, unsigned long entries);
extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa);
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa);
extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa);
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa);
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
#endif
{
int c;
- c = atomic_dec_if_positive(&mm->context.copros);
-
- /* Detect imbalance between add and remove */
- WARN_ON(c < 0);
-
/*
- * Need to broadcast a global flush of the full mm before
- * decrementing active_cpus count, as the next TLBI may be
- * local and the nMMU and/or PSL need to be cleaned up.
- * Should be rare enough so that it's acceptable.
+ * When removing the last copro, we need to broadcast a global
+ * flush of the full mm, as the next TLBI may be local and the
+ * nMMU and/or PSL need to be cleaned up.
+ *
+ * Both the 'copros' and 'active_cpus' counts are looked at in
+ * flush_all_mm() to determine the scope (local/global) of the
+ * TLBIs, so we need to flush first before decrementing
+ * 'copros'. If this API is used by several callers for the
+ * same context, it can lead to over-flushing. It's hopefully
+ * not common enough to be a problem.
*
* Skip on hash, as we don't know how to do the proper flush
* for the time being. Invalidations will remain global if
- * used on hash.
+ * used on hash. Note that we can't drop 'copros' either, as
+ * it could make some invalidations local with no flush
+ * in-between.
*/
- if (c == 0 && radix_enabled()) {
+ if (radix_enabled()) {
flush_all_mm(mm);
- dec_mm_active_cpus(mm);
+
+ c = atomic_dec_if_positive(&mm->context.copros);
+ /* Detect imbalance between add and remove */
+ WARN_ON(c < 0);
+
+ if (c == 0)
+ dec_mm_active_cpus(mm);
}
}
#else
static inline void arch_touch_nmi_watchdog(void) {}
#endif
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE)
+#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE)
extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
}
#define check_pgt_cache() do { } while (0)
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
unsigned long address)
{
tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(table);
pgtable_free_tlb(tlb, page_address(table), 0);
}
#endif /* _ASM_POWERPC_PGALLOC_32_H */
}
}
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
{
#define SPRN_PSSCR 0x357 /* Processor Stop Status and Control Register (ISA 3.0) */
#define SPRN_PSSCR_PR 0x337 /* PSSCR ISA 3.0, privileged mode access */
#define SPRN_PMCR 0x374 /* Power Management Control Register */
+#define SPRN_RWMR 0x375 /* Region-Weighting Mode Register */
/* HFSCR and FSCR bit numbers are the same */
#define FSCR_SCV_LG 12 /* Enable System Call Vectored */
SYSCALL(pkey_free)
SYSCALL(pkey_mprotect)
SYSCALL(rseq)
+COMPAT_SYS(io_pgetevents)
#include <uapi/asm/unistd.h>
-#define NR_syscalls 388
+#define NR_syscalls 389
#define __NR__exit __NR_exit
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
#define __NR_rseq 387
+#define __NR_io_pgetevents 388
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
OFFSET(VCPU_HOST_STACK, kvm_vcpu, arch.host_stack);
OFFSET(VCPU_HOST_PID, kvm_vcpu, arch.host_pid);
OFFSET(VCPU_GUEST_PID, kvm_vcpu, arch.pid);
- OFFSET(VCPU_GPRS, kvm_vcpu, arch.gpr);
+ OFFSET(VCPU_GPRS, kvm_vcpu, arch.regs.gpr);
OFFSET(VCPU_VRSAVE, kvm_vcpu, arch.vrsave);
OFFSET(VCPU_FPRS, kvm_vcpu, arch.fp.fpr);
#ifdef CONFIG_ALTIVEC
OFFSET(VCPU_VRS, kvm_vcpu, arch.vr.vr);
#endif
- OFFSET(VCPU_XER, kvm_vcpu, arch.xer);
- OFFSET(VCPU_CTR, kvm_vcpu, arch.ctr);
- OFFSET(VCPU_LR, kvm_vcpu, arch.lr);
+ OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+ OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+ OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
#ifdef CONFIG_PPC_BOOK3S
OFFSET(VCPU_TAR, kvm_vcpu, arch.tar);
#endif
OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
- OFFSET(VCPU_PC, kvm_vcpu, arch.pc);
+ OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
OFFSET(VCPU_MSR, kvm_vcpu, arch.shregs.msr);
OFFSET(VCPU_SRR0, kvm_vcpu, arch.shregs.srr0);
#else /* CONFIG_PPC_BOOK3S */
OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
- OFFSET(VCPU_XER, kvm_vcpu, arch.xer);
- OFFSET(VCPU_LR, kvm_vcpu, arch.lr);
- OFFSET(VCPU_CTR, kvm_vcpu, arch.ctr);
- OFFSET(VCPU_PC, kvm_vcpu, arch.pc);
+ OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+ OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
+ OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+ OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
OFFSET(VCPU_SPRG9, kvm_vcpu, arch.sprg9);
OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst);
OFFSET(VCPU_FAULT_DEAR, kvm_vcpu, arch.fault_dear);
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
- } else /* DD2.1 and up have DD2_1 */
+ } else if ((version & 0xffff0000) == 0x004e0000)
+ /* DD2.1 and up have DD2_1 */
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
if ((version & 0xffff0000) == 0x004e0000) {
/*
* Check for virtual address in kernel space.
*/
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
- return is_kernel_addr(info->address);
+ return is_kernel_addr(hw->address);
}
int arch_bp_generic_fields(int type, int *gen_bp_type)
/*
* Validate the arch-specific HW Breakpoint register settings
*/
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
int ret = -EINVAL, length_max;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
if (!bp)
return ret;
- info->type = HW_BRK_TYPE_TRANSLATE;
- if (bp->attr.bp_type & HW_BREAKPOINT_R)
- info->type |= HW_BRK_TYPE_READ;
- if (bp->attr.bp_type & HW_BREAKPOINT_W)
- info->type |= HW_BRK_TYPE_WRITE;
- if (info->type == HW_BRK_TYPE_TRANSLATE)
+ hw->type = HW_BRK_TYPE_TRANSLATE;
+ if (attr->bp_type & HW_BREAKPOINT_R)
+ hw->type |= HW_BRK_TYPE_READ;
+ if (attr->bp_type & HW_BREAKPOINT_W)
+ hw->type |= HW_BRK_TYPE_WRITE;
+ if (hw->type == HW_BRK_TYPE_TRANSLATE)
/* must set alteast read or write */
return ret;
- if (!(bp->attr.exclude_user))
- info->type |= HW_BRK_TYPE_USER;
- if (!(bp->attr.exclude_kernel))
- info->type |= HW_BRK_TYPE_KERNEL;
- if (!(bp->attr.exclude_hv))
- info->type |= HW_BRK_TYPE_HYP;
- info->address = bp->attr.bp_addr;
- info->len = bp->attr.bp_len;
+ if (!attr->exclude_user)
+ hw->type |= HW_BRK_TYPE_USER;
+ if (!attr->exclude_kernel)
+ hw->type |= HW_BRK_TYPE_KERNEL;
+ if (!attr->exclude_hv)
+ hw->type |= HW_BRK_TYPE_HYP;
+ hw->address = attr->bp_addr;
+ hw->len = attr->bp_len;
/*
* Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
if (cpu_has_feature(CPU_FTR_DAWR)) {
length_max = 512 ; /* 64 doublewords */
/* DAWR region can't cross 512 boundary */
- if ((bp->attr.bp_addr >> 9) !=
- ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9))
+ if ((attr->bp_addr >> 9) !=
+ ((attr->bp_addr + attr->bp_len - 1) >> 9))
return -EINVAL;
}
- if (info->len >
- (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
+ if (hw->len >
+ (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
return -EINVAL;
return 0;
}
mtspr SPRN_MMCR1, r4
ld r3, STOP_MMCR2(r13)
+ ld r4, PACA_SPRG_VDSO(r13)
mtspr SPRN_MMCR2, r3
+ mtspr SPRN_SPRG3, r4
blr
/*
#include <linux/preempt.h>
#include <linux/ftrace.h>
-/*
- * This is called from ftrace code after invoking registered handlers to
- * disambiguate regs->nip changes done by jprobes and livepatch. We check if
- * there is an active jprobe at the provided address (mcount location).
- */
-int __is_active_jprobe(unsigned long addr)
-{
- if (!preemptible()) {
- struct kprobe *p = raw_cpu_read(current_kprobe);
- return (p && (unsigned long)p->addr == addr) ? 1 : 0;
- }
-
- return 0;
-}
-
-static nokprobe_inline
-int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb, unsigned long orig_nip)
-{
- /*
- * Emulate singlestep (and also recover regs->nip)
- * as if there is a nop
- */
- regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
- if (unlikely(p->post_handler)) {
- kcb->kprobe_status = KPROBE_HIT_SSDONE;
- p->post_handler(p, regs, 0);
- }
- __this_cpu_write(current_kprobe, NULL);
- if (orig_nip)
- regs->nip = orig_nip;
- return 1;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
-{
- if (kprobe_ftrace(p))
- return __skip_singlestep(p, regs, kcb, 0);
- else
- return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
/* Ftrace callback handler for kprobes */
void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
struct ftrace_ops *ops, struct pt_regs *regs)
struct kprobe *p;
struct kprobe_ctlblk *kcb;
- preempt_disable();
-
p = get_kprobe((kprobe_opcode_t *)nip);
if (unlikely(!p) || kprobe_disabled(p))
- goto end;
+ return;
kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(p);
} else {
- unsigned long orig_nip = regs->nip;
-
/*
* On powerpc, NIP is *before* this instruction for the
* pre handler
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (!p->pre_handler || !p->pre_handler(p, regs))
- __skip_singlestep(p, regs, kcb, orig_nip);
- else {
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
/*
- * If pre_handler returns !0, it sets regs->nip and
- * resets current kprobe. In this case, we should not
- * re-enable preemption.
+ * Emulate singlestep (and also recover regs->nip)
+ * as if there is a nop
*/
- return;
+ regs->nip += MCOUNT_INSN_SIZE;
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
}
+ /*
+ * If pre_handler returns !0, it changes regs->nip. We have to
+ * skip emulating post_handler.
+ */
+ __this_cpu_write(current_kprobe, NULL);
}
-end:
- preempt_enable_no_resched();
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
}
prepare_singlestep(p, regs);
return 1;
- } else {
- if (*addr != BREAKPOINT_INSTRUCTION) {
- /* If trap variant, then it belongs not to us */
- kprobe_opcode_t cur_insn = *addr;
- if (is_trap(cur_insn))
- goto no_kprobe;
- /* The breakpoint instruction was removed by
- * another cpu right after we hit, no further
- * handling of this interrupt is appropriate
- */
- ret = 1;
+ } else if (*addr != BREAKPOINT_INSTRUCTION) {
+ /* If trap variant, then it belongs not to us */
+ kprobe_opcode_t cur_insn = *addr;
+
+ if (is_trap(cur_insn))
goto no_kprobe;
- }
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- if (!skip_singlestep(p, regs, kcb))
- goto ss_probe;
- ret = 1;
- }
+ /* The breakpoint instruction was removed by
+ * another cpu right after we hit, no further
+ * handling of this interrupt is appropriate
+ */
+ ret = 1;
}
goto no_kprobe;
}
*/
kprobe_opcode_t cur_insn = *addr;
if (is_trap(cur_insn))
- goto no_kprobe;
+ goto no_kprobe;
/*
* The breakpoint instruction was removed right
* after we hit it. Another cpu has removed
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
set_current_kprobe(p, regs, kcb);
- if (p->pre_handler && p->pre_handler(p, regs))
- /* handler has already set things up, so skip ss setup */
+ if (p->pre_handler && p->pre_handler(p, regs)) {
+ /* handler changed execution path, so skip ss setup */
+ reset_current_kprobe();
+ preempt_enable_no_resched();
return 1;
+ }
-ss_probe:
if (p->ainsn.boostable >= 0) {
ret = try_to_emulate(p, regs);
}
NOKPROBE_SYMBOL(arch_deref_entry_point);
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
- /* setup return addr to the jprobe handler routine */
- regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef PPC64_ELF_ABI_v2
- regs->gpr[12] = (unsigned long)jp->entry;
-#elif defined(PPC64_ELF_ABI_v1)
- regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
-#endif
-
- /*
- * jprobes use jprobe_return() which skips the normal return
- * path of the function, and this messes up the accounting of the
- * function graph tracer.
- *
- * Pause function graph tracing while performing the jprobe function.
- */
- pause_graph_tracing();
-
- return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void __used jprobe_return(void)
-{
- asm volatile("jprobe_return_trap:\n"
- "trap\n"
- ::: "memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) {
- pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n",
- regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap"));
- return 0;
- }
-
- memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
- /* It's OK to start function graph tracing again */
- unpause_graph_tracing();
- preempt_enable_no_resched();
- return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
#include <asm/ppc-pci.h>
#include <asm/eeh.h>
+#include "../../../drivers/pci/pci.h"
+
/* hose_spinlock protects accesses to the the phb_bitmap. */
static DEFINE_SPINLOCK(hose_spinlock);
LIST_HEAD(hose_list);
/* Cardbus can call us to add new devices to a bus, so ignore
* those who are already fully discovered
*/
- if (dev->is_added)
+ if (pci_dev_is_added(dev))
continue;
pcibios_setup_device(dev);
* Note that the returned IO or memory base is a physical address
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(pciconfig_iobase, long, which,
unsigned long, bus, unsigned long, devfn)
{
return result;
}
-#pragma GCC diagnostic pop
#define IOBASE_ISA_IO 3
#define IOBASE_ISA_MEM 4
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus,
unsigned long, in_devfn)
{
return -EOPNOTSUPP;
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_NUMA
int pcibus_to_node(struct pci_bus *bus)
}
/* We assume to be passed big endian arguments */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
{
struct rtas_args args;
return 0;
}
-#pragma GCC diagnostic pop
/*
* Call early during boot, before mem init, to retrieve the RTAS
static int ppc_panic_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
+ /*
+ * panic does a local_irq_disable, but we really
+ * want interrupts to be hard disabled.
+ */
+ hard_irq_disable();
+
/*
* If firmware-assisted dump has been registered then trigger
* firmware-assisted dump and let firmware handle everything else.
*/
crash_fadump(NULL, ptr);
- ppc_md.panic(ptr); /* May not return */
+ if (ppc_md.panic)
+ ppc_md.panic(ptr); /* May not return */
return NOTIFY_DONE;
}
void __init setup_panic(void)
{
- if (!ppc_md.panic)
+ /* PPC64 always does a hard irq disable in its panic handler */
+ if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
return;
atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
}
#endif /* CONFIG_SMP */
+void panic_smp_self_stop(void)
+{
+ hard_irq_disable();
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
static bool use_spinloop(void)
{
/* Re-enable the breakpoints for the signal stack */
thread_change_pc(tsk, tsk->thread.regs);
- rseq_signal_deliver(tsk->thread.regs);
+ rseq_signal_deliver(&ksig, tsk->thread.regs);
if (is32) {
if (ksig.ka.sa.sa_flags & SA_SIGINFO)
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
user_enter();
}
#endif
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, int, ctx_size)
set_thread_flag(TIF_RESTOREALL);
return 0;
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
return 0;
}
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
#ifdef CONFIG_PPC32
SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
int, ndbg, struct sig_dbg_op __user *, dbg)
return 0;
}
#endif
-#pragma GCC diagnostic pop
/*
* OK, we're invoking a handler
/*
* Handle {get,set,swap}_context operations
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, long, ctx_size)
{
set_thread_flag(TIF_RESTOREALL);
return 0;
}
-#pragma GCC diagnostic pop
/*
nmi_ipi_busy_count--;
nmi_ipi_unlock();
- /* Remove this CPU */
- set_cpu_online(smp_processor_id(), false);
-
spin_begin();
while (1)
spin_cpu_relax();
static void stop_this_cpu(void *dummy)
{
- /* Remove this CPU */
- set_cpu_online(smp_processor_id(), false);
-
hard_irq_disable();
spin_begin();
while (1)
EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable);
#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-#ifdef CONFIG_PPC_BOOK3S_64
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
static void handle_backtrace_ipi(struct pt_regs *regs)
{
nmi_cpu_backtrace(regs);
{
nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
}
-#endif /* CONFIG_PPC64 */
+#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */
return ret;
}
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, pgoff)
{
return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_PPC32
/*
bl ftrace_stub
nop
- /* Load the possibly modified NIP */
- ld r15, _NIP(r1)
-
+ /* Load ctr with the possibly modified NIP */
+ ld r3, _NIP(r1)
+ mtctr r3
#ifdef CONFIG_LIVEPATCH
- cmpd r14, r15 /* has NIP been altered? */
+ cmpd r14, r3 /* has NIP been altered? */
#endif
-#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
- /* NIP has not been altered, skip over further checks */
- beq 1f
-
- /* Check if there is an active jprobe on us */
- subi r3, r14, 4
- bl __is_active_jprobe
- nop
-
- /*
- * If r3 == 1, then this is a kprobe/jprobe.
- * else, this is livepatched function.
- *
- * The conditional branch for livepatch_handler below will use the
- * result of this comparison. For kprobe/jprobe, we just need to branch to
- * the new NIP, not call livepatch_handler. The branch below is bne, so we
- * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
- * CR0[EQ] = (r3 == 1).
- */
- cmpdi r3, 1
-1:
-#endif
-
- /* Load CTR with the possibly modified NIP */
- mtctr r15
-
/* Restore gprs */
REST_GPR(0,r1)
REST_10GPRS(2,r1)
addi r1, r1, SWITCH_FRAME_SIZE
#ifdef CONFIG_LIVEPATCH
- /*
- * Based on the cmpd or cmpdi above, if the NIP was altered and we're
- * not on a kprobe/jprobe, then handle livepatch.
- */
+ /* Based on the cmpd above, if the NIP was altered handle livepatch */
bne- livepatch_handler
#endif
book3s_64_mmu.o \
book3s_32_mmu.o
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+ tm.o
+
ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_rmhandlers.o
{
kvmppc_unfixup_split_real(vcpu);
kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
- kvmppc_set_srr1(vcpu, kvmppc_get_msr(vcpu) | flags);
+ kvmppc_set_srr1(vcpu, (kvmppc_get_msr(vcpu) & ~0x783f0000ul) | flags);
kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec);
vcpu->arch.mmu.reset_msr(vcpu);
}
{
kvmppc_set_dar(vcpu, dar);
kvmppc_set_dsisr(vcpu, flags);
- kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
}
-EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage); /* used by kvm_hv */
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage);
void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags)
{
- u64 msr = kvmppc_get_msr(vcpu);
- msr &= ~(SRR1_ISI_NOPT | SRR1_ISI_N_OR_G | SRR1_ISI_PROT);
- msr |= flags & (SRR1_ISI_NOPT | SRR1_ISI_N_OR_G | SRR1_ISI_PROT);
- kvmppc_set_msr_fast(vcpu, msr);
- kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, flags);
}
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_inst_storage);
static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
unsigned int priority)
return r;
}
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
- u32 *inst)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+ enum instruction_fetch_type type, u32 *inst)
{
ulong pc = kvmppc_get_pc(vcpu);
int r;
{
int i;
- vcpu_load(vcpu);
-
regs->pc = kvmppc_get_pc(vcpu);
regs->cr = kvmppc_get_cr(vcpu);
regs->ctr = kvmppc_get_ctr(vcpu);
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
- vcpu_put(vcpu);
return 0;
}
{
int i;
- vcpu_load(vcpu);
-
kvmppc_set_pc(vcpu, regs->pc);
kvmppc_set_cr(vcpu, regs->cr);
kvmppc_set_ctr(vcpu, regs->ctr);
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
- vcpu_put(vcpu);
return 0;
}
extern int kvmppc_book3s_init_pr(void);
extern void kvmppc_book3s_exit_pr(void);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val);
+#else
+static inline void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val) {}
+#endif
+
#endif
static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
{
#ifdef DEBUG_MMU_PTE_IP
- return vcpu->arch.pc == DEBUG_MMU_PTE_IP;
+ return vcpu->arch.regs.nip == DEBUG_MMU_PTE_IP;
#else
return true;
#endif
static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
{
- kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
+ unsigned long msr = vcpu->arch.intr_msr;
+ unsigned long cur_msr = kvmppc_get_msr(vcpu);
+
+ /* If transactional, change to suspend mode on IRQ delivery */
+ if (MSR_TM_TRANSACTIONAL(cur_msr))
+ msr |= MSR_TS_S;
+ else
+ msr |= cur_msr & MSR_TS_MASK;
+
+ kvmppc_set_msr(vcpu, msr);
}
static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
if (!cpu_has_feature(CPU_FTR_HVMODE))
return -EINVAL;
+ if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
+ return -EINVAL;
+
/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
host_lpid = mfspr(SPRN_LPID);
rsvd_lpid = LPID_RSVD;
return 0;
}
-#ifdef CONFIG_PPC_64K_PAGES
-#define MMU_BASE_PSIZE MMU_PAGE_64K
-#else
-#define MMU_BASE_PSIZE MMU_PAGE_4K
-#endif
-
static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
unsigned int pshift)
{
- int psize = MMU_BASE_PSIZE;
-
- if (pshift >= PUD_SHIFT)
- psize = MMU_PAGE_1G;
- else if (pshift >= PMD_SHIFT)
- psize = MMU_PAGE_2M;
- addr &= ~0xfffUL;
- addr |= mmu_psize_defs[psize].ap << 5;
- asm volatile("ptesync": : :"memory");
- asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
- : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
- if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
- asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
- : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
- asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
+ unsigned long psize = PAGE_SIZE;
+
+ if (pshift)
+ psize = 1UL << pshift;
+
+ addr &= ~(psize - 1);
+ radix__flush_tlb_lpid_page(kvm->arch.lpid, addr, psize);
}
-static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm)
{
- unsigned long rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
-
- asm volatile("ptesync": : :"memory");
- /* RIC=1 PRS=0 R=1 IS=2 */
- asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
- : : "r" (rb), "r" (kvm->arch.lpid) : "memory");
- asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
+ radix__flush_pwc_lpid(kvm->arch.lpid);
}
-unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
+static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
unsigned long clr, unsigned long set,
unsigned long addr, unsigned int shift)
{
kmem_cache_free(kvm_pmd_cache, pmdp);
}
+static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
+ unsigned long gpa, unsigned int shift)
+
+{
+ unsigned long page_size = 1ul << shift;
+ unsigned long old;
+
+ old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
+ kvmppc_radix_tlbie_page(kvm, gpa, shift);
+ if (old & _PAGE_DIRTY) {
+ unsigned long gfn = gpa >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot;
+
+ memslot = gfn_to_memslot(kvm, gfn);
+ if (memslot && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot, gfn, page_size);
+ }
+}
+
+/*
+ * kvmppc_free_p?d are used to free existing page tables, and recursively
+ * descend and clear and free children.
+ * Callers are responsible for flushing the PWC.
+ *
+ * When page tables are being unmapped/freed as part of page fault path
+ * (full == false), ptes are not expected. There is code to unmap them
+ * and emit a warning if encountered, but there may already be data
+ * corruption due to the unexpected mappings.
+ */
+static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
+{
+ if (full) {
+ memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
+ } else {
+ pte_t *p = pte;
+ unsigned long it;
+
+ for (it = 0; it < PTRS_PER_PTE; ++it, ++p) {
+ if (pte_val(*p) == 0)
+ continue;
+ WARN_ON_ONCE(1);
+ kvmppc_unmap_pte(kvm, p,
+ pte_pfn(*p) << PAGE_SHIFT,
+ PAGE_SHIFT);
+ }
+ }
+
+ kvmppc_pte_free(pte);
+}
+
+static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
+{
+ unsigned long im;
+ pmd_t *p = pmd;
+
+ for (im = 0; im < PTRS_PER_PMD; ++im, ++p) {
+ if (!pmd_present(*p))
+ continue;
+ if (pmd_is_leaf(*p)) {
+ if (full) {
+ pmd_clear(p);
+ } else {
+ WARN_ON_ONCE(1);
+ kvmppc_unmap_pte(kvm, (pte_t *)p,
+ pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
+ PMD_SHIFT);
+ }
+ } else {
+ pte_t *pte;
+
+ pte = pte_offset_map(p, 0);
+ kvmppc_unmap_free_pte(kvm, pte, full);
+ pmd_clear(p);
+ }
+ }
+ kvmppc_pmd_free(pmd);
+}
+
+static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
+{
+ unsigned long iu;
+ pud_t *p = pud;
+
+ for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
+ if (!pud_present(*p))
+ continue;
+ if (pud_huge(*p)) {
+ pud_clear(p);
+ } else {
+ pmd_t *pmd;
+
+ pmd = pmd_offset(p, 0);
+ kvmppc_unmap_free_pmd(kvm, pmd, true);
+ pud_clear(p);
+ }
+ }
+ pud_free(kvm->mm, pud);
+}
+
+void kvmppc_free_radix(struct kvm *kvm)
+{
+ unsigned long ig;
+ pgd_t *pgd;
+
+ if (!kvm->arch.pgtable)
+ return;
+ pgd = kvm->arch.pgtable;
+ for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
+ pud_t *pud;
+
+ if (!pgd_present(*pgd))
+ continue;
+ pud = pud_offset(pgd, 0);
+ kvmppc_unmap_free_pud(kvm, pud);
+ pgd_clear(pgd);
+ }
+ pgd_free(kvm->mm, kvm->arch.pgtable);
+ kvm->arch.pgtable = NULL;
+}
+
+static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
+ unsigned long gpa)
+{
+ pte_t *pte = pte_offset_kernel(pmd, 0);
+
+ /*
+ * Clearing the pmd entry then flushing the PWC ensures that the pte
+ * page no longer be cached by the MMU, so can be freed without
+ * flushing the PWC again.
+ */
+ pmd_clear(pmd);
+ kvmppc_radix_flush_pwc(kvm);
+
+ kvmppc_unmap_free_pte(kvm, pte, false);
+}
+
+static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
+ unsigned long gpa)
+{
+ pmd_t *pmd = pmd_offset(pud, 0);
+
+ /*
+ * Clearing the pud entry then flushing the PWC ensures that the pmd
+ * page and any children pte pages will no longer be cached by the MMU,
+ * so can be freed without flushing the PWC again.
+ */
+ pud_clear(pud);
+ kvmppc_radix_flush_pwc(kvm);
+
+ kvmppc_unmap_free_pmd(kvm, pmd, false);
+}
+
+/*
+ * There are a number of bits which may differ between different faults to
+ * the same partition scope entry. RC bits, in the course of cleaning and
+ * aging. And the write bit can change, either the access could have been
+ * upgraded, or a read fault could happen concurrently with a write fault
+ * that sets those bits first.
+ */
+#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
+
static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
unsigned int level, unsigned long mmu_seq)
{
pud_t *pud, *new_pud = NULL;
pmd_t *pmd, *new_pmd = NULL;
pte_t *ptep, *new_ptep = NULL;
- unsigned long old;
int ret;
/* Traverse the guest's 2nd-level tree, allocate new levels needed */
if (pud_huge(*pud)) {
unsigned long hgpa = gpa & PUD_MASK;
+ /* Check if we raced and someone else has set the same thing */
+ if (level == 2) {
+ if (pud_raw(*pud) == pte_raw(pte)) {
+ ret = 0;
+ goto out_unlock;
+ }
+ /* Valid 1GB page here already, add our extra bits */
+ WARN_ON_ONCE((pud_val(*pud) ^ pte_val(pte)) &
+ PTE_BITS_MUST_MATCH);
+ kvmppc_radix_update_pte(kvm, (pte_t *)pud,
+ 0, pte_val(pte), hgpa, PUD_SHIFT);
+ ret = 0;
+ goto out_unlock;
+ }
/*
* If we raced with another CPU which has just put
* a 1GB pte in after we saw a pmd page, try again.
*/
- if (level <= 1 && !new_pmd) {
+ if (!new_pmd) {
ret = -EAGAIN;
goto out_unlock;
}
- /* Check if we raced and someone else has set the same thing */
- if (level == 2 && pud_raw(*pud) == pte_raw(pte)) {
- ret = 0;
- goto out_unlock;
- }
/* Valid 1GB page here already, remove it */
- old = kvmppc_radix_update_pte(kvm, (pte_t *)pud,
- ~0UL, 0, hgpa, PUD_SHIFT);
- kvmppc_radix_tlbie_page(kvm, hgpa, PUD_SHIFT);
- if (old & _PAGE_DIRTY) {
- unsigned long gfn = hgpa >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot;
- memslot = gfn_to_memslot(kvm, gfn);
- if (memslot && memslot->dirty_bitmap)
- kvmppc_update_dirty_map(memslot,
- gfn, PUD_SIZE);
- }
+ kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT);
}
if (level == 2) {
if (!pud_none(*pud)) {
/*
* There's a page table page here, but we wanted to
* install a large page, so remove and free the page
- * table page. new_pmd will be NULL since level == 2.
+ * table page.
*/
- new_pmd = pmd_offset(pud, 0);
- pud_clear(pud);
- kvmppc_radix_flush_pwc(kvm, gpa);
+ kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa);
}
kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
ret = 0;
if (pmd_is_leaf(*pmd)) {
unsigned long lgpa = gpa & PMD_MASK;
+ /* Check if we raced and someone else has set the same thing */
+ if (level == 1) {
+ if (pmd_raw(*pmd) == pte_raw(pte)) {
+ ret = 0;
+ goto out_unlock;
+ }
+ /* Valid 2MB page here already, add our extra bits */
+ WARN_ON_ONCE((pmd_val(*pmd) ^ pte_val(pte)) &
+ PTE_BITS_MUST_MATCH);
+ kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
+ 0, pte_val(pte), lgpa, PMD_SHIFT);
+ ret = 0;
+ goto out_unlock;
+ }
+
/*
* If we raced with another CPU which has just put
* a 2MB pte in after we saw a pte page, try again.
*/
- if (level == 0 && !new_ptep) {
+ if (!new_ptep) {
ret = -EAGAIN;
goto out_unlock;
}
- /* Check if we raced and someone else has set the same thing */
- if (level == 1 && pmd_raw(*pmd) == pte_raw(pte)) {
- ret = 0;
- goto out_unlock;
- }
/* Valid 2MB page here already, remove it */
- old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
- ~0UL, 0, lgpa, PMD_SHIFT);
- kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
- if (old & _PAGE_DIRTY) {
- unsigned long gfn = lgpa >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot;
- memslot = gfn_to_memslot(kvm, gfn);
- if (memslot && memslot->dirty_bitmap)
- kvmppc_update_dirty_map(memslot,
- gfn, PMD_SIZE);
- }
+ kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT);
}
if (level == 1) {
if (!pmd_none(*pmd)) {
/*
* There's a page table page here, but we wanted to
* install a large page, so remove and free the page
- * table page. new_ptep will be NULL since level == 1.
+ * table page.
*/
- new_ptep = pte_offset_kernel(pmd, 0);
- pmd_clear(pmd);
- kvmppc_radix_flush_pwc(kvm, gpa);
+ kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa);
}
kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
ret = 0;
ret = 0;
goto out_unlock;
}
- /* PTE was previously valid, so invalidate it */
- old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
- 0, gpa, 0);
- kvmppc_radix_tlbie_page(kvm, gpa, 0);
- if (old & _PAGE_DIRTY)
- mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+ /* Valid page here already, add our extra bits */
+ WARN_ON_ONCE((pte_val(*ptep) ^ pte_val(pte)) &
+ PTE_BITS_MUST_MATCH);
+ kvmppc_radix_update_pte(kvm, ptep, 0, pte_val(pte), gpa, 0);
+ ret = 0;
+ goto out_unlock;
}
kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
ret = 0;
unsigned long mask = (1ul << shift) - PAGE_SIZE;
pte = __pte(pte_val(pte) | (hva & mask));
}
- if (!(writing || upgrade_write))
- pte = __pte(pte_val(pte) & ~ _PAGE_WRITE);
- pte = __pte(pte_val(pte) | _PAGE_EXEC);
+ pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
+ if (writing || upgrade_write) {
+ if (pte_val(pte) & _PAGE_WRITE)
+ pte = __pte(pte_val(pte) | _PAGE_DIRTY);
+ } else {
+ pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ }
}
/* Allocate space in the tree and write the PTE */
return 0;
}
-void kvmppc_free_radix(struct kvm *kvm)
-{
- unsigned long ig, iu, im;
- pte_t *pte;
- pmd_t *pmd;
- pud_t *pud;
- pgd_t *pgd;
-
- if (!kvm->arch.pgtable)
- return;
- pgd = kvm->arch.pgtable;
- for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
- if (!pgd_present(*pgd))
- continue;
- pud = pud_offset(pgd, 0);
- for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++pud) {
- if (!pud_present(*pud))
- continue;
- if (pud_huge(*pud)) {
- pud_clear(pud);
- continue;
- }
- pmd = pmd_offset(pud, 0);
- for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
- if (pmd_is_leaf(*pmd)) {
- pmd_clear(pmd);
- continue;
- }
- if (!pmd_present(*pmd))
- continue;
- pte = pte_offset_map(pmd, 0);
- memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
- kvmppc_pte_free(pte);
- pmd_clear(pmd);
- }
- kvmppc_pmd_free(pmd_offset(pud, 0));
- pud_clear(pud);
- }
- pud_free(kvm->mm, pud_offset(pgd, 0));
- pgd_clear(pgd);
- }
- pgd_free(kvm->mm, kvm->arch.pgtable);
- kvm->arch.pgtable = NULL;
-}
-
static void pte_ctor(void *addr)
{
memset(addr, 0, RADIX_PTE_TABLE_SIZE);
if (!tbltmp)
continue;
- /*
- * Make sure hardware table parameters are exactly the same;
- * this is used in the TCE handlers where boundary checks
- * use only the first attached table.
- */
- if ((tbltmp->it_page_shift == stt->page_shift) &&
- (tbltmp->it_offset == stt->offset) &&
- (tbltmp->it_size == stt->size)) {
+ /* Make sure hardware table parameters are compatible */
+ if ((tbltmp->it_page_shift <= stt->page_shift) &&
+ (tbltmp->it_offset << tbltmp->it_page_shift ==
+ stt->offset << stt->page_shift) &&
+ (tbltmp->it_size << tbltmp->it_page_shift ==
+ stt->size << stt->page_shift)) {
/*
* Reference the table to avoid races with
* add/remove DMA windows.
kfree(stt);
}
-static int kvm_spapr_tce_fault(struct vm_fault *vmf)
+static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
{
struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
struct page *page;
int ret = -ENOMEM;
int i;
- if (!args->size)
+ if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
+ (args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
return -EINVAL;
size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
return H_SUCCESS;
}
-static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm,
struct iommu_table *tbl, unsigned long entry)
{
enum dma_data_direction dir = DMA_NONE;
return ret;
}
-long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+ struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+ unsigned long entry)
+{
+ unsigned long i, ret = H_SUCCESS;
+ unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+ unsigned long io_entry = entry * subpages;
+
+ for (i = 0; i < subpages; ++i) {
+ ret = kvmppc_tce_iommu_do_unmap(kvm, tbl, io_entry + i);
+ if (ret != H_SUCCESS)
+ break;
+ }
+
+ return ret;
+}
+
+long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
unsigned long entry, unsigned long ua,
enum dma_data_direction dir)
{
/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
return H_TOO_HARD;
- if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+ if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
return H_HARDWARE;
if (mm_iommu_mapped_inc(mem))
return 0;
}
+static long kvmppc_tce_iommu_map(struct kvm *kvm,
+ struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ unsigned long i, pgoff, ret = H_SUCCESS;
+ unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+ unsigned long io_entry = entry * subpages;
+
+ for (i = 0, pgoff = 0; i < subpages;
+ ++i, pgoff += IOMMU_PAGE_SIZE(tbl)) {
+
+ ret = kvmppc_tce_iommu_do_map(kvm, tbl,
+ io_entry + i, ua + pgoff, dir);
+ if (ret != H_SUCCESS)
+ break;
+ }
+
+ return ret;
+}
+
long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
if (dir == DMA_NONE)
- ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stt,
stit->tbl, entry);
else
- ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl,
entry, ua, dir);
if (ret == H_SUCCESS)
return H_PARAMETER;
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
- ret = kvmppc_tce_iommu_map(vcpu->kvm,
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, stt,
stit->tbl, entry + i, ua,
iommu_tce_direction(tce));
return H_PARAMETER;
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
- unsigned long entry = ioba >> stit->tbl->it_page_shift;
+ unsigned long entry = ioba >> stt->page_shift;
for (i = 0; i < npages; ++i) {
- ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stt,
stit->tbl, entry + i);
if (ret == H_SUCCESS)
return H_SUCCESS;
}
-static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
struct iommu_table *tbl, unsigned long entry)
{
enum dma_data_direction dir = DMA_NONE;
return ret;
}
-static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+ struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+ unsigned long entry)
+{
+ unsigned long i, ret = H_SUCCESS;
+ unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+ unsigned long io_entry = entry * subpages;
+
+ for (i = 0; i < subpages; ++i) {
+ ret = kvmppc_rm_tce_iommu_do_unmap(kvm, tbl, io_entry + i);
+ if (ret != H_SUCCESS)
+ break;
+ }
+
+ return ret;
+}
+
+static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
unsigned long entry, unsigned long ua,
enum dma_data_direction dir)
{
if (!mem)
return H_TOO_HARD;
- if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+ if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+ &hpa)))
return H_HARDWARE;
pua = (void *) vmalloc_to_phys(pua);
return 0;
}
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm,
+ struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ unsigned long i, pgoff, ret = H_SUCCESS;
+ unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
+ unsigned long io_entry = entry * subpages;
+
+ for (i = 0, pgoff = 0; i < subpages;
+ ++i, pgoff += IOMMU_PAGE_SIZE(tbl)) {
+
+ ret = kvmppc_rm_tce_iommu_do_map(kvm, tbl,
+ io_entry + i, ua + pgoff, dir);
+ if (ret != H_SUCCESS)
+ break;
+ }
+
+ return ret;
+}
+
long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
if (dir == DMA_NONE)
- ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
stit->tbl, entry);
else
- ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
stit->tbl, entry, ua, dir);
if (ret == H_SUCCESS)
mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
if (mem)
- prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+ prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+ IOMMU_PAGE_SHIFT_4K, &tces) == 0;
}
if (!prereg) {
return H_PARAMETER;
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
- ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
stit->tbl, entry + i, ua,
iommu_tce_direction(tce));
return H_PARAMETER;
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
- unsigned long entry = ioba >> stit->tbl->it_page_shift;
+ unsigned long entry = ioba >> stt->page_shift;
for (i = 0; i < npages; ++i) {
- ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
stit->tbl, entry + i);
if (ret == H_SUCCESS)
page = stt->pages[idx / TCES_PER_PAGE];
tbl = (u64 *)page_address(page);
- vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+ vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
return H_SUCCESS;
}
#include <asm/reg.h>
#include <asm/switch_to.h>
#include <asm/time.h>
+#include <asm/tm.h>
#include "book3s.h"
+#include <asm/asm-prototypes.h>
#define OP_19_XOP_RFID 18
#define OP_19_XOP_RFI 50
#define OP_31_XOP_EIOIO 854
#define OP_31_XOP_SLBMFEE 915
+#define OP_31_XOP_TBEGIN 654
+#define OP_31_XOP_TABORT 910
+
+#define OP_31_XOP_TRECLAIM 942
+#define OP_31_XOP_TRCHKPT 1006
+
/* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */
#define OP_31_XOP_DCBZ 1010
return true;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline void kvmppc_copyto_vcpu_tm(struct kvm_vcpu *vcpu)
+{
+ memcpy(&vcpu->arch.gpr_tm[0], &vcpu->arch.regs.gpr[0],
+ sizeof(vcpu->arch.gpr_tm));
+ memcpy(&vcpu->arch.fp_tm, &vcpu->arch.fp,
+ sizeof(struct thread_fp_state));
+ memcpy(&vcpu->arch.vr_tm, &vcpu->arch.vr,
+ sizeof(struct thread_vr_state));
+ vcpu->arch.ppr_tm = vcpu->arch.ppr;
+ vcpu->arch.dscr_tm = vcpu->arch.dscr;
+ vcpu->arch.amr_tm = vcpu->arch.amr;
+ vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
+ vcpu->arch.tar_tm = vcpu->arch.tar;
+ vcpu->arch.lr_tm = vcpu->arch.regs.link;
+ vcpu->arch.cr_tm = vcpu->arch.cr;
+ vcpu->arch.xer_tm = vcpu->arch.regs.xer;
+ vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
+}
+
+static inline void kvmppc_copyfrom_vcpu_tm(struct kvm_vcpu *vcpu)
+{
+ memcpy(&vcpu->arch.regs.gpr[0], &vcpu->arch.gpr_tm[0],
+ sizeof(vcpu->arch.regs.gpr));
+ memcpy(&vcpu->arch.fp, &vcpu->arch.fp_tm,
+ sizeof(struct thread_fp_state));
+ memcpy(&vcpu->arch.vr, &vcpu->arch.vr_tm,
+ sizeof(struct thread_vr_state));
+ vcpu->arch.ppr = vcpu->arch.ppr_tm;
+ vcpu->arch.dscr = vcpu->arch.dscr_tm;
+ vcpu->arch.amr = vcpu->arch.amr_tm;
+ vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
+ vcpu->arch.tar = vcpu->arch.tar_tm;
+ vcpu->arch.regs.link = vcpu->arch.lr_tm;
+ vcpu->arch.cr = vcpu->arch.cr_tm;
+ vcpu->arch.regs.xer = vcpu->arch.xer_tm;
+ vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
+}
+
+static void kvmppc_emulate_treclaim(struct kvm_vcpu *vcpu, int ra_val)
+{
+ unsigned long guest_msr = kvmppc_get_msr(vcpu);
+ int fc_val = ra_val ? ra_val : 1;
+ uint64_t texasr;
+
+ /* CR0 = 0 | MSR[TS] | 0 */
+ vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+ (((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
+ << CR0_SHIFT);
+
+ preempt_disable();
+ tm_enable();
+ texasr = mfspr(SPRN_TEXASR);
+ kvmppc_save_tm_pr(vcpu);
+ kvmppc_copyfrom_vcpu_tm(vcpu);
+
+ /* failure recording depends on Failure Summary bit */
+ if (!(texasr & TEXASR_FS)) {
+ texasr &= ~TEXASR_FC;
+ texasr |= ((u64)fc_val << TEXASR_FC_LG) | TEXASR_FS;
+
+ texasr &= ~(TEXASR_PR | TEXASR_HV);
+ if (kvmppc_get_msr(vcpu) & MSR_PR)
+ texasr |= TEXASR_PR;
+
+ if (kvmppc_get_msr(vcpu) & MSR_HV)
+ texasr |= TEXASR_HV;
+
+ vcpu->arch.texasr = texasr;
+ vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+ mtspr(SPRN_TEXASR, texasr);
+ mtspr(SPRN_TFIAR, vcpu->arch.tfiar);
+ }
+ tm_disable();
+ /*
+ * treclaim need quit to non-transactional state.
+ */
+ guest_msr &= ~(MSR_TS_MASK);
+ kvmppc_set_msr(vcpu, guest_msr);
+ preempt_enable();
+
+ if (vcpu->arch.shadow_fscr & FSCR_TAR)
+ mtspr(SPRN_TAR, vcpu->arch.tar);
+}
+
+static void kvmppc_emulate_trchkpt(struct kvm_vcpu *vcpu)
+{
+ unsigned long guest_msr = kvmppc_get_msr(vcpu);
+
+ preempt_disable();
+ /*
+ * need flush FP/VEC/VSX to vcpu save area before
+ * copy.
+ */
+ kvmppc_giveup_ext(vcpu, MSR_VSX);
+ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+ kvmppc_copyto_vcpu_tm(vcpu);
+ kvmppc_save_tm_sprs(vcpu);
+
+ /*
+ * as a result of trecheckpoint. set TS to suspended.
+ */
+ guest_msr &= ~(MSR_TS_MASK);
+ guest_msr |= MSR_TS_S;
+ kvmppc_set_msr(vcpu, guest_msr);
+ kvmppc_restore_tm_pr(vcpu);
+ preempt_enable();
+}
+
+/* emulate tabort. at guest privilege state */
+void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val)
+{
+ /* currently we only emulate tabort. but no emulation of other
+ * tabort variants since there is no kernel usage of them at
+ * present.
+ */
+ unsigned long guest_msr = kvmppc_get_msr(vcpu);
+ uint64_t org_texasr;
+
+ preempt_disable();
+ tm_enable();
+ org_texasr = mfspr(SPRN_TEXASR);
+ tm_abort(ra_val);
+
+ /* CR0 = 0 | MSR[TS] | 0 */
+ vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+ (((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
+ << CR0_SHIFT);
+
+ vcpu->arch.texasr = mfspr(SPRN_TEXASR);
+ /* failure recording depends on Failure Summary bit,
+ * and tabort will be treated as nops in non-transactional
+ * state.
+ */
+ if (!(org_texasr & TEXASR_FS) &&
+ MSR_TM_ACTIVE(guest_msr)) {
+ vcpu->arch.texasr &= ~(TEXASR_PR | TEXASR_HV);
+ if (guest_msr & MSR_PR)
+ vcpu->arch.texasr |= TEXASR_PR;
+
+ if (guest_msr & MSR_HV)
+ vcpu->arch.texasr |= TEXASR_HV;
+
+ vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+ }
+ tm_disable();
+ preempt_enable();
+}
+
+#endif
+
int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int inst, int *advance)
{
case 19:
switch (get_xop(inst)) {
case OP_19_XOP_RFID:
- case OP_19_XOP_RFI:
+ case OP_19_XOP_RFI: {
+ unsigned long srr1 = kvmppc_get_srr1(vcpu);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ unsigned long cur_msr = kvmppc_get_msr(vcpu);
+
+ /*
+ * add rules to fit in ISA specification regarding TM
+ * state transistion in TM disable/Suspended state,
+ * and target TM state is TM inactive(00) state. (the
+ * change should be suppressed).
+ */
+ if (((cur_msr & MSR_TM) == 0) &&
+ ((srr1 & MSR_TM) == 0) &&
+ MSR_TM_SUSPENDED(cur_msr) &&
+ !MSR_TM_ACTIVE(srr1))
+ srr1 |= MSR_TS_S;
+#endif
kvmppc_set_pc(vcpu, kvmppc_get_srr0(vcpu));
- kvmppc_set_msr(vcpu, kvmppc_get_srr1(vcpu));
+ kvmppc_set_msr(vcpu, srr1);
*advance = 0;
break;
+ }
default:
emulated = EMULATE_FAIL;
break;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case OP_31_XOP_TBEGIN:
+ {
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_PR)) {
+ preempt_disable();
+ vcpu->arch.cr = (CR0_TBEGIN_FAILURE |
+ (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)));
+
+ vcpu->arch.texasr = (TEXASR_FS | TEXASR_EXACT |
+ (((u64)(TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+ << TEXASR_FC_LG));
+
+ if ((inst >> 21) & 0x1)
+ vcpu->arch.texasr |= TEXASR_ROT;
+
+ if (kvmppc_get_msr(vcpu) & MSR_HV)
+ vcpu->arch.texasr |= TEXASR_HV;
+
+ vcpu->arch.tfhar = kvmppc_get_pc(vcpu) + 4;
+ vcpu->arch.tfiar = kvmppc_get_pc(vcpu);
+
+ kvmppc_restore_tm_sprs(vcpu);
+ preempt_enable();
+ } else
+ emulated = EMULATE_FAIL;
+ break;
+ }
+ case OP_31_XOP_TABORT:
+ {
+ ulong guest_msr = kvmppc_get_msr(vcpu);
+ unsigned long ra_val = 0;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ /* only emulate for privilege guest, since problem state
+ * guest can run with TM enabled and we don't expect to
+ * trap at here for that case.
+ */
+ WARN_ON(guest_msr & MSR_PR);
+
+ if (ra)
+ ra_val = kvmppc_get_gpr(vcpu, ra);
+
+ kvmppc_emulate_tabort(vcpu, ra_val);
+ break;
+ }
+ case OP_31_XOP_TRECLAIM:
+ {
+ ulong guest_msr = kvmppc_get_msr(vcpu);
+ unsigned long ra_val = 0;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ /* generate interrupts based on priorities */
+ if (guest_msr & MSR_PR) {
+ /* Privileged Instruction type Program Interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ if (!MSR_TM_ACTIVE(guest_msr)) {
+ /* TM bad thing interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ if (ra)
+ ra_val = kvmppc_get_gpr(vcpu, ra);
+ kvmppc_emulate_treclaim(vcpu, ra_val);
+ break;
+ }
+ case OP_31_XOP_TRCHKPT:
+ {
+ ulong guest_msr = kvmppc_get_msr(vcpu);
+ unsigned long texasr;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ /* generate interrupt based on priorities */
+ if (guest_msr & MSR_PR) {
+ /* Privileged Instruction type Program Intr */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ tm_enable();
+ texasr = mfspr(SPRN_TEXASR);
+ tm_disable();
+
+ if (MSR_TM_ACTIVE(guest_msr) ||
+ !(texasr & (TEXASR_FS))) {
+ /* TM bad thing interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ kvmppc_emulate_trchkpt(vcpu);
+ break;
+ }
+#endif
default:
emulated = EMULATE_FAIL;
}
break;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case SPRN_TFHAR:
- vcpu->arch.tfhar = spr_val;
- break;
case SPRN_TEXASR:
- vcpu->arch.texasr = spr_val;
- break;
case SPRN_TFIAR:
- vcpu->arch.tfiar = spr_val;
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ if (MSR_TM_ACTIVE(kvmppc_get_msr(vcpu)) &&
+ !((MSR_TM_SUSPENDED(kvmppc_get_msr(vcpu))) &&
+ (sprn == SPRN_TFHAR))) {
+ /* it is illegal to mtspr() TM regs in
+ * other than non-transactional state, with
+ * the exception of TFHAR in suspend state.
+ */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ tm_enable();
+ if (sprn == SPRN_TFHAR)
+ mtspr(SPRN_TFHAR, spr_val);
+ else if (sprn == SPRN_TEXASR)
+ mtspr(SPRN_TEXASR, spr_val);
+ else
+ mtspr(SPRN_TFIAR, spr_val);
+ tm_disable();
+
break;
#endif
#endif
break;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case SPRN_TFHAR:
- *spr_val = vcpu->arch.tfhar;
- break;
case SPRN_TEXASR:
- *spr_val = vcpu->arch.texasr;
- break;
case SPRN_TFIAR:
- *spr_val = vcpu->arch.tfiar;
+ if (!cpu_has_feature(CPU_FTR_TM))
+ break;
+
+ if (!(kvmppc_get_msr(vcpu) & MSR_TM)) {
+ kvmppc_trigger_fac_interrupt(vcpu, FSCR_TM_LG);
+ emulated = EMULATE_AGAIN;
+ break;
+ }
+
+ tm_enable();
+ if (sprn == SPRN_TFHAR)
+ *spr_val = mfspr(SPRN_TFHAR);
+ else if (sprn == SPRN_TEXASR)
+ *spr_val = mfspr(SPRN_TEXASR);
+ else if (sprn == SPRN_TFIAR)
+ *spr_val = mfspr(SPRN_TFIAR);
+ tm_disable();
break;
#endif
#endif
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
+/*
+ * RWMR values for POWER8. These control the rate at which PURR
+ * and SPURR count and should be set according to the number of
+ * online threads in the vcore being run.
+ */
+#define RWMR_RPA_P8_1THREAD 0x164520C62609AECA
+#define RWMR_RPA_P8_2THREAD 0x7FFF2908450D8DA9
+#define RWMR_RPA_P8_3THREAD 0x164520C62609AECA
+#define RWMR_RPA_P8_4THREAD 0x199A421245058DA9
+#define RWMR_RPA_P8_5THREAD 0x164520C62609AECA
+#define RWMR_RPA_P8_6THREAD 0x164520C62609AECA
+#define RWMR_RPA_P8_7THREAD 0x164520C62609AECA
+#define RWMR_RPA_P8_8THREAD 0x164520C62609AECA
+
+static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = {
+ RWMR_RPA_P8_1THREAD,
+ RWMR_RPA_P8_1THREAD,
+ RWMR_RPA_P8_2THREAD,
+ RWMR_RPA_P8_3THREAD,
+ RWMR_RPA_P8_4THREAD,
+ RWMR_RPA_P8_5THREAD,
+ RWMR_RPA_P8_6THREAD,
+ RWMR_RPA_P8_7THREAD,
+ RWMR_RPA_P8_8THREAD,
+};
+
static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
int *ip)
{
wqp = kvm_arch_vcpu_wq(vcpu);
if (swq_has_sleeper(wqp)) {
- swake_up(wqp);
+ swake_up_one(wqp);
++vcpu->stat.halt_wakeup;
}
pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
pr_err("pc = %.16lx msr = %.16llx trap = %x\n",
- vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap);
+ vcpu->arch.regs.nip, vcpu->arch.shregs.msr, vcpu->arch.trap);
for (r = 0; r < 16; ++r)
pr_err("r%2d = %.16lx r%d = %.16lx\n",
r, kvmppc_get_gpr(vcpu, r),
r+16, kvmppc_get_gpr(vcpu, r+16));
pr_err("ctr = %.16lx lr = %.16lx\n",
- vcpu->arch.ctr, vcpu->arch.lr);
+ vcpu->arch.regs.ctr, vcpu->arch.regs.link);
pr_err("srr0 = %.16llx srr1 = %.16llx\n",
vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
pr_err("cr = %.8x xer = %.16lx dsisr = %.8x\n",
- vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr);
+ vcpu->arch.cr, vcpu->arch.regs.xer, vcpu->arch.shregs.dsisr);
pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
pr_err("fault dar = %.16lx dsisr = %.8x\n",
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
*val = get_reg_val(id, vcpu->arch.dec_expires +
vcpu->arch.vcore->tb_offset);
break;
+ case KVM_REG_PPC_ONLINE:
+ *val = get_reg_val(id, vcpu->arch.online);
+ break;
default:
r = -EINVAL;
break;
vcpu->arch.dec_expires = set_reg_val(id, *val) -
vcpu->arch.vcore->tb_offset;
break;
+ case KVM_REG_PPC_ONLINE:
+ i = set_reg_val(id, *val);
+ if (i && !vcpu->arch.online)
+ atomic_inc(&vcpu->arch.vcore->online_count);
+ else if (!i && vcpu->arch.online)
+ atomic_dec(&vcpu->arch.vcore->online_count);
+ vcpu->arch.online = i;
+ break;
default:
r = -EINVAL;
break;
}
}
+ /*
+ * On POWER8, set RWMR register.
+ * Since it only affects PURR and SPURR, it doesn't affect
+ * the host, so we don't save/restore the host value.
+ */
+ if (is_power8) {
+ unsigned long rwmr_val = RWMR_RPA_P8_8THREAD;
+ int n_online = atomic_read(&vc->online_count);
+
+ /*
+ * Use the 8-thread value if we're doing split-core
+ * or if the vcore's online count looks bogus.
+ */
+ if (split == 1 && threads_per_subcore == MAX_SMT_THREADS &&
+ n_online >= 1 && n_online <= MAX_SMT_THREADS)
+ rwmr_val = p8_rwmr_values[n_online];
+ mtspr(SPRN_RWMR, rwmr_val);
+ }
+
/* Start all the threads */
active = 0;
for (sub = 0; sub < core_info.n_subcores; ++sub) {
for (sub = 0; sub < core_info.n_subcores; ++sub)
spin_unlock(&core_info.vc[sub]->lock);
+ if (kvm_is_radix(vc->kvm)) {
+ int tmp = pcpu;
+
+ /*
+ * Do we need to flush the process scoped TLB for the LPAR?
+ *
+ * On POWER9, individual threads can come in here, but the
+ * TLB is shared between the 4 threads in a core, hence
+ * invalidating on one thread invalidates for all.
+ * Thus we make all 4 threads use the same bit here.
+ *
+ * Hash must be flushed in realmode in order to use tlbiel.
+ */
+ mtspr(SPRN_LPID, vc->kvm->arch.lpid);
+ isync();
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ tmp &= ~0x3UL;
+
+ if (cpumask_test_cpu(tmp, &vc->kvm->arch.need_tlb_flush)) {
+ radix__local_flush_tlb_lpid_guest(vc->kvm->arch.lpid);
+ /* Clear the bit after the TLB flush */
+ cpumask_clear_cpu(tmp, &vc->kvm->arch.need_tlb_flush);
+ }
+ }
+
/*
* Interrupts will be enabled once we get into the guest,
* so tell lockdep that we're about to enable interrupts.
}
}
- prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
if (kvmppc_vcore_check_block(vc)) {
finish_swait(&vc->wq, &wait);
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
- swake_up(&vc->wq);
+ swake_up_one(&vc->wq);
}
}
}
#endif
+ /*
+ * Force online to 1 for the sake of old userspace which doesn't
+ * set it.
+ */
+ if (!vcpu->arch.online) {
+ atomic_inc(&vcpu->arch.vcore->online_count);
+ vcpu->arch.online = 1;
+ }
+
kvmppc_core_prepare_to_enter(vcpu);
/* No need to go into the guest when all we'll do is come back out */
#include <linux/cma.h>
#include <linux/bitops.h>
+#include <asm/asm-prototypes.h>
#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
/* Only need to do the expensive mfmsr() on radix */
if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
- r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+ r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]);
else
- r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+ r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]);
if (r)
return H_SUCCESS;
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
- vcpu->arch.gpr[5] = get_tb();
+ vcpu->arch.regs.gpr[5] = get_tb();
if (xive_enabled()) {
if (is_rm())
return xive_rm_h_xirr(vcpu);
void kvmppc_bad_interrupt(struct pt_regs *regs)
{
- die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+ /*
+ * 100 could happen at any time, 200 can happen due to invalid real
+ * address access for example (or any time due to a hardware problem).
+ */
+ if (TRAP(regs) == 0x100) {
+ get_paca()->in_nmi++;
+ system_reset_exception(regs);
+ get_paca()->in_nmi--;
+ } else if (TRAP(regs) == 0x200) {
+ machine_check_exception(regs);
+ } else {
+ die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+ }
panic("Bad KVM trap");
}
/*
* We return here in virtual mode after the guest exits
* with something that we can't handle in real mode.
- * Interrupts are enabled again at this point.
+ * Interrupts are still hard-disabled.
*/
/*
long pte_index, unsigned long pteh, unsigned long ptel)
{
return kvmppc_do_h_enter(vcpu->kvm, flags, pte_index, pteh, ptel,
- vcpu->arch.pgdir, true, &vcpu->arch.gpr[4]);
+ vcpu->arch.pgdir, true,
+ &vcpu->arch.regs.gpr[4]);
}
#ifdef __BIG_ENDIAN__
(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
}
-static inline int try_lock_tlbie(unsigned int *lock)
-{
- unsigned int tmp, old;
- unsigned int token = LOCK_TOKEN;
-
- asm volatile("1:lwarx %1,0,%2\n"
- " cmpwi cr0,%1,0\n"
- " bne 2f\n"
- " stwcx. %3,0,%2\n"
- " bne- 1b\n"
- " isync\n"
- "2:"
- : "=&r" (tmp), "=&r" (old)
- : "r" (lock), "r" (token)
- : "cc", "memory");
- return old == 0;
-}
-
static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
long npages, int global, bool need_sync)
{
* the RS field, this is backwards-compatible with P7 and P8.
*/
if (global) {
- while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
- cpu_relax();
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i) {
}
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
- kvm->arch.tlbie_lock = 0;
} else {
if (need_sync)
asm volatile("ptesync" : : : "memory");
unsigned long pte_index, unsigned long avpn)
{
return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
- &vcpu->arch.gpr[4]);
+ &vcpu->arch.regs.gpr[4]);
}
long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long *args = &vcpu->arch.gpr[4];
+ unsigned long *args = &vcpu->arch.regs.gpr[4];
__be64 *hp, *hptes[4];
unsigned long tlbrb[4];
long int i, j, k, n, found, indexes[4];
r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
r &= ~HPTE_GR_RESERVED;
}
- vcpu->arch.gpr[4 + i * 2] = v;
- vcpu->arch.gpr[5 + i * 2] = r;
+ vcpu->arch.regs.gpr[4 + i * 2] = v;
+ vcpu->arch.regs.gpr[5 + i * 2] = r;
}
return H_SUCCESS;
}
}
}
}
- vcpu->arch.gpr[4] = gr;
+ vcpu->arch.regs.gpr[4] = gr;
ret = H_SUCCESS;
out:
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
kvmppc_set_dirty_from_hpte(kvm, v, gr);
}
}
- vcpu->arch.gpr[4] = gr;
+ vcpu->arch.regs.gpr[4] = gr;
ret = H_SUCCESS;
out:
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
} while (!icp_rm_try_update(icp, old_state, new_state));
/* Return the result in GPR4 */
- vcpu->arch.gpr[4] = xirr;
+ vcpu->arch.regs.gpr[4] = xirr;
return check_too_hard(xics, icp);
}
extsw reg, reg; \
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
-
/* Values in HSTATE_NAPPING(r13) */
#define NAPPING_CEDE 1
#define NAPPING_NOVCPU 2
/* Primary thread switches to guest partition. */
cmpwi r6,0
bne 10f
+
+ /* Radix has already switched LPID and flushed core TLB */
+ bne cr7, 22f
+
lwz r7,KVM_LPID(r9)
BEGIN_FTR_SECTION
ld r6,KVM_SDR1(r9)
mtspr SPRN_LPID,r7
isync
- /* See if we need to flush the TLB */
+ /* See if we need to flush the TLB. Hash has to be done in RM */
lhz r6,PACAPACAINDEX(r13) /* test_bit(cpu, need_tlb_flush) */
BEGIN_FTR_SECTION
/*
li r7,0x800 /* IS field = 0b10 */
ptesync
li r0,0 /* RS for P9 version of tlbiel */
- bne cr7, 29f
28: tlbiel r7 /* On P9, rs=0, RIC=0, PRS=0, R=0 */
addi r7,r7,0x1000
bdnz 28b
- b 30f
-29: PPC_TLBIEL(7,0,2,1,1) /* for radix, RIC=2, PRS=1, R=1 */
- addi r7,r7,0x1000
- bdnz 29b
-30: ptesync
+ ptesync
23: ldarx r7,0,r6 /* clear the bit after TLB flushed */
andc r7,r7,r8
stdcx. r7,0,r6
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
- bl kvmppc_restore_tm
+ mr r3, r4
+ ld r4, VCPU_MSR(r3)
+ bl kvmppc_restore_tm_hv
+ ld r4, HSTATE_KVM_VCPU(r13)
91:
#endif
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
- bl kvmppc_save_tm
+ mr r3, r9
+ ld r4, VCPU_MSR(r3)
+ bl kvmppc_save_tm_hv
+ ld r9, HSTATE_KVM_VCPU(r13)
91:
#endif
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
- ld r9, HSTATE_KVM_VCPU(r13)
- bl kvmppc_save_tm
+ ld r3, HSTATE_KVM_VCPU(r13)
+ ld r4, VCPU_MSR(r3)
+ bl kvmppc_save_tm_hv
91:
#endif
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
- bl kvmppc_restore_tm
+ mr r3, r4
+ ld r4, VCPU_MSR(r3)
+ bl kvmppc_restore_tm_hv
+ ld r4, HSTATE_KVM_VCPU(r13)
91:
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* Save transactional state and TM-related registers.
- * Called with r9 pointing to the vcpu struct.
+ * Called with r3 pointing to the vcpu struct and r4 containing
+ * the guest MSR value.
* This can modify all checkpointed registers, but
- * restores r1, r2 and r9 (vcpu pointer) before exit.
+ * restores r1 and r2 before exit.
*/
-kvmppc_save_tm:
+kvmppc_save_tm_hv:
+ /* See if we need to handle fake suspend mode */
+BEGIN_FTR_SECTION
+ b __kvmppc_save_tm
+END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
+
+ lbz r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
+ cmpwi r0, 0
+ beq __kvmppc_save_tm
+
+ /* The following code handles the fake_suspend = 1 case */
mflr r0
std r0, PPC_LR_STKOFF(r1)
stdu r1, -PPC_MIN_STKFRM(r1)
rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r8
- ld r5, VCPU_MSR(r9)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
- beq 1f /* TM not active in guest. */
-
- std r1, HSTATE_HOST_R1(r13)
- li r3, TM_CAUSE_KVM_RESCHED
-
-BEGIN_FTR_SECTION
- lbz r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
- cmpwi r0, 0
- beq 3f
rldicl. r8, r8, 64 - MSR_TS_S_LG, 62 /* Did we actually hrfid? */
beq 4f
-BEGIN_FTR_SECTION_NESTED(96)
+BEGIN_FTR_SECTION
bl pnv_power9_force_smt4_catch
-END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
nop
- b 6f
-3:
- /* Emulation of the treclaim instruction needs TEXASR before treclaim */
- mfspr r6, SPRN_TEXASR
- std r6, VCPU_ORIG_TEXASR(r9)
-6:
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ std r1, HSTATE_HOST_R1(r13)
+
+ /* Clear the MSR RI since r1, r13 may be foobar. */
li r5, 0
mtmsrd r5, 1
- /* All GPRs are volatile at this point. */
+ /* We have to treclaim here because that's the only way to do S->N */
+ li r3, TM_CAUSE_KVM_RESCHED
TRECLAIM(R3)
- /* Temporarily store r13 and r9 so we have some regs to play with */
- SET_SCRATCH0(r13)
- GET_PACA(r13)
- std r9, PACATMSCRATCH(r13)
-
- /* If doing TM emulation on POWER9 DD2.2, check for fake suspend mode */
-BEGIN_FTR_SECTION
- lbz r9, HSTATE_FAKE_SUSPEND(r13)
- cmpwi r9, 0
- beq 2f
/*
* We were in fake suspend, so we are not going to save the
* register state as the guest checkpointed state (since
* we already have it), therefore we can now use any volatile GPR.
*/
- /* Reload stack pointer and TOC. */
+ /* Reload PACA pointer, stack pointer and TOC. */
+ GET_PACA(r13)
ld r1, HSTATE_HOST_R1(r13)
ld r2, PACATOC(r13)
+
/* Set MSR RI now we have r1 and r13 back. */
li r5, MSR_RI
mtmsrd r5, 1
+
HMT_MEDIUM
ld r6, HSTATE_DSCR(r13)
mtspr SPRN_DSCR, r6
li r0, PSSCR_FAKE_SUSPEND
andc r3, r3, r0
mtspr SPRN_PSSCR, r3
- ld r9, HSTATE_KVM_VCPU(r13)
- /* Don't save TEXASR, use value from last exit in real suspend state */
- b 11f
-2:
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+ /* Don't save TEXASR, use value from last exit in real suspend state */
ld r9, HSTATE_KVM_VCPU(r13)
-
- /* Get a few more GPRs free. */
- std r29, VCPU_GPRS_TM(29)(r9)
- std r30, VCPU_GPRS_TM(30)(r9)
- std r31, VCPU_GPRS_TM(31)(r9)
-
- /* Save away PPR and DSCR soon so don't run with user values. */
- mfspr r31, SPRN_PPR
- HMT_MEDIUM
- mfspr r30, SPRN_DSCR
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
-
- /* Save all but r9, r13 & r29-r31 */
- reg = 0
- .rept 29
- .if (reg != 9) && (reg != 13)
- std reg, VCPU_GPRS_TM(reg)(r9)
- .endif
- reg = reg + 1
- .endr
- /* ... now save r13 */
- GET_SCRATCH0(r4)
- std r4, VCPU_GPRS_TM(13)(r9)
- /* ... and save r9 */
- ld r4, PACATMSCRATCH(r13)
- std r4, VCPU_GPRS_TM(9)(r9)
-
- /* Reload stack pointer and TOC. */
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATOC(r13)
-
- /* Set MSR RI now we have r1 and r13 back. */
- li r5, MSR_RI
- mtmsrd r5, 1
-
- /* Save away checkpinted SPRs. */
- std r31, VCPU_PPR_TM(r9)
- std r30, VCPU_DSCR_TM(r9)
- mflr r5
- mfcr r6
- mfctr r7
- mfspr r8, SPRN_AMR
- mfspr r10, SPRN_TAR
- mfxer r11
- std r5, VCPU_LR_TM(r9)
- stw r6, VCPU_CR_TM(r9)
- std r7, VCPU_CTR_TM(r9)
- std r8, VCPU_AMR_TM(r9)
- std r10, VCPU_TAR_TM(r9)
- std r11, VCPU_XER_TM(r9)
-
- /* Restore r12 as trap number. */
- lwz r12, VCPU_TRAP(r9)
-
- /* Save FP/VSX. */
- addi r3, r9, VCPU_FPRS_TM
- bl store_fp_state
- addi r3, r9, VCPU_VRS_TM
- bl store_vr_state
- mfspr r6, SPRN_VRSAVE
- stw r6, VCPU_VRSAVE_TM(r9)
-1:
- /*
- * We need to save these SPRs after the treclaim so that the software
- * error code is recorded correctly in the TEXASR. Also the user may
- * change these outside of a transaction, so they must always be
- * context switched.
- */
- mfspr r7, SPRN_TEXASR
- std r7, VCPU_TEXASR(r9)
-11:
mfspr r5, SPRN_TFHAR
mfspr r6, SPRN_TFIAR
std r5, VCPU_TFHAR(r9)
/*
* Restore transactional state and TM-related registers.
- * Called with r4 pointing to the vcpu struct.
+ * Called with r3 pointing to the vcpu struct
+ * and r4 containing the guest MSR value.
* This potentially modifies all checkpointed registers.
- * It restores r1, r2, r4 from the PACA.
+ * It restores r1 and r2 from the PACA.
*/
-kvmppc_restore_tm:
+kvmppc_restore_tm_hv:
+ /*
+ * If we are doing TM emulation for the guest on a POWER9 DD2,
+ * then we don't actually do a trechkpt -- we either set up
+ * fake-suspend mode, or emulate a TM rollback.
+ */
+BEGIN_FTR_SECTION
+ b __kvmppc_restore_tm
+END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
mflr r0
std r0, PPC_LR_STKOFF(r1)
- /* Turn on TM/FP/VSX/VMX so we can restore them. */
+ li r0, 0
+ stb r0, HSTATE_FAKE_SUSPEND(r13)
+
+ /* Turn on TM so we can restore TM SPRs */
mfmsr r5
- li r6, MSR_TM >> 32
- sldi r6, r6, 32
- or r5, r5, r6
- ori r5, r5, MSR_FP
- oris r5, r5, (MSR_VEC | MSR_VSX)@h
+ li r0, 1
+ rldimi r5, r0, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r5
/*
* The user may change these outside of a transaction, so they must
* always be context switched.
*/
- ld r5, VCPU_TFHAR(r4)
- ld r6, VCPU_TFIAR(r4)
- ld r7, VCPU_TEXASR(r4)
+ ld r5, VCPU_TFHAR(r3)
+ ld r6, VCPU_TFIAR(r3)
+ ld r7, VCPU_TEXASR(r3)
mtspr SPRN_TFHAR, r5
mtspr SPRN_TFIAR, r6
mtspr SPRN_TEXASR, r7
- li r0, 0
- stb r0, HSTATE_FAKE_SUSPEND(r13)
- ld r5, VCPU_MSR(r4)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ rldicl. r5, r4, 64 - MSR_TS_S_LG, 62
beqlr /* TM not active in guest */
- std r1, HSTATE_HOST_R1(r13)
- /* Make sure the failure summary is set, otherwise we'll program check
- * when we trechkpt. It's possible that this might have been not set
- * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
- * host.
- */
+ /* Make sure the failure summary is set */
oris r7, r7, (TEXASR_FS)@h
mtspr SPRN_TEXASR, r7
- /*
- * If we are doing TM emulation for the guest on a POWER9 DD2,
- * then we don't actually do a trechkpt -- we either set up
- * fake-suspend mode, or emulate a TM rollback.
- */
-BEGIN_FTR_SECTION
- b .Ldo_tm_fake_load
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
-
- /*
- * We need to load up the checkpointed state for the guest.
- * We need to do this early as it will blow away any GPRs, VSRs and
- * some SPRs.
- */
-
- mr r31, r4
- addi r3, r31, VCPU_FPRS_TM
- bl load_fp_state
- addi r3, r31, VCPU_VRS_TM
- bl load_vr_state
- mr r4, r31
- lwz r7, VCPU_VRSAVE_TM(r4)
- mtspr SPRN_VRSAVE, r7
-
- ld r5, VCPU_LR_TM(r4)
- lwz r6, VCPU_CR_TM(r4)
- ld r7, VCPU_CTR_TM(r4)
- ld r8, VCPU_AMR_TM(r4)
- ld r9, VCPU_TAR_TM(r4)
- ld r10, VCPU_XER_TM(r4)
- mtlr r5
- mtcr r6
- mtctr r7
- mtspr SPRN_AMR, r8
- mtspr SPRN_TAR, r9
- mtxer r10
-
- /*
- * Load up PPR and DSCR values but don't put them in the actual SPRs
- * till the last moment to avoid running with userspace PPR and DSCR for
- * too long.
- */
- ld r29, VCPU_DSCR_TM(r4)
- ld r30, VCPU_PPR_TM(r4)
-
- std r2, PACATMSCRATCH(r13) /* Save TOC */
-
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
- li r5, 0
- mtmsrd r5, 1
-
- /* Load GPRs r0-r28 */
- reg = 0
- .rept 29
- ld reg, VCPU_GPRS_TM(reg)(r31)
- reg = reg + 1
- .endr
-
- mtspr SPRN_DSCR, r29
- mtspr SPRN_PPR, r30
-
- /* Load final GPRs */
- ld 29, VCPU_GPRS_TM(29)(r31)
- ld 30, VCPU_GPRS_TM(30)(r31)
- ld 31, VCPU_GPRS_TM(31)(r31)
-
- /* TM checkpointed state is now setup. All GPRs are now volatile. */
- TRECHKPT
-
- /* Now let's get back the state we need. */
- HMT_MEDIUM
- GET_PACA(r13)
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
- ld r4, HSTATE_KVM_VCPU(r13)
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATMSCRATCH(r13)
-
- /* Set the MSR RI since we have our registers back. */
- li r5, MSR_RI
- mtmsrd r5, 1
-9:
- ld r0, PPC_LR_STKOFF(r1)
- mtlr r0
- blr
-
-.Ldo_tm_fake_load:
cmpwi r5, 1 /* check for suspended state */
bgt 10f
stb r5, HSTATE_FAKE_SUSPEND(r13)
- b 9b /* and return */
+ b 9f /* and return */
10: stdu r1, -PPC_MIN_STKFRM(r1)
/* guest is in transactional state, so simulate rollback */
- mr r3, r4
bl kvmhv_emulate_tm_rollback
nop
- ld r4, HSTATE_KVM_VCPU(r13) /* our vcpu pointer has been trashed */
addi r1, r1, PPC_MIN_STKFRM
- b 9b
-#endif
+9: ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
/*
* We come here if we get any exception or interrupt while we are
bcl 20, 31, .+4
5: mflr r3
addi r3, r3, 9f - 5b
+ li r4, -1
+ rldimi r3, r4, 62, 0 /* ensure 0xc000000000000000 bits are set */
ld r4, PACAKMSR(r13)
mtspr SPRN_SRR0, r3
mtspr SPRN_SRR1, r4
u64 texasr, tfiar;
u64 msr = vcpu->arch.shregs.msr;
- tfiar = vcpu->arch.pc & ~0x3ull;
+ tfiar = vcpu->arch.regs.nip & ~0x3ull;
texasr = (failure_cause << 56) | TEXASR_ABORT | TEXASR_FS | TEXASR_EXACT;
if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr))
texasr |= TEXASR_SUSP;
(newmsr & MSR_TM)));
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
- vcpu->arch.cfar = vcpu->arch.pc - 4;
- vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
return RESUME_GUEST;
case PPC_INST_RFEBB:
vcpu->arch.bescr = bescr;
msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
vcpu->arch.shregs.msr = msr;
- vcpu->arch.cfar = vcpu->arch.pc - 4;
- vcpu->arch.pc = vcpu->arch.ebbrr;
+ vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.regs.nip = vcpu->arch.ebbrr;
return RESUME_GUEST;
case PPC_INST_MTMSRD:
return 0;
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
- vcpu->arch.cfar = vcpu->arch.pc - 4;
- vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
return 1;
case PPC_INST_RFEBB:
mtspr(SPRN_BESCR, bescr);
msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
vcpu->arch.shregs.msr = msr;
- vcpu->arch.cfar = vcpu->arch.pc - 4;
- vcpu->arch.pc = mfspr(SPRN_EBBRR);
+ vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.regs.nip = mfspr(SPRN_EBBRR);
return 1;
case PPC_INST_MTMSRD:
void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
{
vcpu->arch.shregs.msr &= ~MSR_TS_MASK; /* go to N state */
- vcpu->arch.pc = vcpu->arch.tfhar;
+ vcpu->arch.regs.nip = vcpu->arch.tfhar;
copy_from_checkpoint(vcpu);
vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
}
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/miscdevice.h>
+#include <asm/asm-prototypes.h>
+#include <asm/tm.h>
#include "book3s.h"
static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
ulong msr);
-static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
+#ifdef CONFIG_PPC_BOOK3S_64
+static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac);
+#endif
/* Some compatibility defines */
#ifdef CONFIG_PPC_BOOK3S_32
if (kvmppc_is_split_real(vcpu))
kvmppc_fixup_split_real(vcpu);
+
+ kvmppc_restore_tm_pr(vcpu);
}
static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+ kvmppc_save_tm_pr(vcpu);
/* Enable AIL if supported */
if (cpu_has_feature(CPU_FTR_HVMODE) &&
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
- svcpu->gpr[0] = vcpu->arch.gpr[0];
- svcpu->gpr[1] = vcpu->arch.gpr[1];
- svcpu->gpr[2] = vcpu->arch.gpr[2];
- svcpu->gpr[3] = vcpu->arch.gpr[3];
- svcpu->gpr[4] = vcpu->arch.gpr[4];
- svcpu->gpr[5] = vcpu->arch.gpr[5];
- svcpu->gpr[6] = vcpu->arch.gpr[6];
- svcpu->gpr[7] = vcpu->arch.gpr[7];
- svcpu->gpr[8] = vcpu->arch.gpr[8];
- svcpu->gpr[9] = vcpu->arch.gpr[9];
- svcpu->gpr[10] = vcpu->arch.gpr[10];
- svcpu->gpr[11] = vcpu->arch.gpr[11];
- svcpu->gpr[12] = vcpu->arch.gpr[12];
- svcpu->gpr[13] = vcpu->arch.gpr[13];
+ svcpu->gpr[0] = vcpu->arch.regs.gpr[0];
+ svcpu->gpr[1] = vcpu->arch.regs.gpr[1];
+ svcpu->gpr[2] = vcpu->arch.regs.gpr[2];
+ svcpu->gpr[3] = vcpu->arch.regs.gpr[3];
+ svcpu->gpr[4] = vcpu->arch.regs.gpr[4];
+ svcpu->gpr[5] = vcpu->arch.regs.gpr[5];
+ svcpu->gpr[6] = vcpu->arch.regs.gpr[6];
+ svcpu->gpr[7] = vcpu->arch.regs.gpr[7];
+ svcpu->gpr[8] = vcpu->arch.regs.gpr[8];
+ svcpu->gpr[9] = vcpu->arch.regs.gpr[9];
+ svcpu->gpr[10] = vcpu->arch.regs.gpr[10];
+ svcpu->gpr[11] = vcpu->arch.regs.gpr[11];
+ svcpu->gpr[12] = vcpu->arch.regs.gpr[12];
+ svcpu->gpr[13] = vcpu->arch.regs.gpr[13];
svcpu->cr = vcpu->arch.cr;
- svcpu->xer = vcpu->arch.xer;
- svcpu->ctr = vcpu->arch.ctr;
- svcpu->lr = vcpu->arch.lr;
- svcpu->pc = vcpu->arch.pc;
+ svcpu->xer = vcpu->arch.regs.xer;
+ svcpu->ctr = vcpu->arch.regs.ctr;
+ svcpu->lr = vcpu->arch.regs.link;
+ svcpu->pc = vcpu->arch.regs.nip;
#ifdef CONFIG_PPC_BOOK3S_64
svcpu->shadow_fscr = vcpu->arch.shadow_fscr;
#endif
svcpu_put(svcpu);
}
+static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
+{
+ ulong guest_msr = kvmppc_get_msr(vcpu);
+ ulong smsr = guest_msr;
+
+ /* Guest MSR values */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE |
+ MSR_TM | MSR_TS_MASK;
+#else
+ smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE;
+#endif
+ /* Process MSR values */
+ smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
+ /* External providers the guest reserved */
+ smsr |= (guest_msr & vcpu->arch.guest_owned_ext);
+ /* 64-bit Process MSR values */
+#ifdef CONFIG_PPC_BOOK3S_64
+ smsr |= MSR_ISF | MSR_HV;
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * in guest privileged state, we want to fail all TM transactions.
+ * So disable MSR TM bit so that all tbegin. will be able to be
+ * trapped into host.
+ */
+ if (!(guest_msr & MSR_PR))
+ smsr &= ~MSR_TM;
+#endif
+ vcpu->arch.shadow_msr = smsr;
+}
+
/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu)
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ ulong old_msr;
+#endif
/*
* Maybe we were already preempted and synced the svcpu from
if (!svcpu->in_use)
goto out;
- vcpu->arch.gpr[0] = svcpu->gpr[0];
- vcpu->arch.gpr[1] = svcpu->gpr[1];
- vcpu->arch.gpr[2] = svcpu->gpr[2];
- vcpu->arch.gpr[3] = svcpu->gpr[3];
- vcpu->arch.gpr[4] = svcpu->gpr[4];
- vcpu->arch.gpr[5] = svcpu->gpr[5];
- vcpu->arch.gpr[6] = svcpu->gpr[6];
- vcpu->arch.gpr[7] = svcpu->gpr[7];
- vcpu->arch.gpr[8] = svcpu->gpr[8];
- vcpu->arch.gpr[9] = svcpu->gpr[9];
- vcpu->arch.gpr[10] = svcpu->gpr[10];
- vcpu->arch.gpr[11] = svcpu->gpr[11];
- vcpu->arch.gpr[12] = svcpu->gpr[12];
- vcpu->arch.gpr[13] = svcpu->gpr[13];
+ vcpu->arch.regs.gpr[0] = svcpu->gpr[0];
+ vcpu->arch.regs.gpr[1] = svcpu->gpr[1];
+ vcpu->arch.regs.gpr[2] = svcpu->gpr[2];
+ vcpu->arch.regs.gpr[3] = svcpu->gpr[3];
+ vcpu->arch.regs.gpr[4] = svcpu->gpr[4];
+ vcpu->arch.regs.gpr[5] = svcpu->gpr[5];
+ vcpu->arch.regs.gpr[6] = svcpu->gpr[6];
+ vcpu->arch.regs.gpr[7] = svcpu->gpr[7];
+ vcpu->arch.regs.gpr[8] = svcpu->gpr[8];
+ vcpu->arch.regs.gpr[9] = svcpu->gpr[9];
+ vcpu->arch.regs.gpr[10] = svcpu->gpr[10];
+ vcpu->arch.regs.gpr[11] = svcpu->gpr[11];
+ vcpu->arch.regs.gpr[12] = svcpu->gpr[12];
+ vcpu->arch.regs.gpr[13] = svcpu->gpr[13];
vcpu->arch.cr = svcpu->cr;
- vcpu->arch.xer = svcpu->xer;
- vcpu->arch.ctr = svcpu->ctr;
- vcpu->arch.lr = svcpu->lr;
- vcpu->arch.pc = svcpu->pc;
+ vcpu->arch.regs.xer = svcpu->xer;
+ vcpu->arch.regs.ctr = svcpu->ctr;
+ vcpu->arch.regs.link = svcpu->lr;
+ vcpu->arch.regs.nip = svcpu->pc;
vcpu->arch.shadow_srr1 = svcpu->shadow_srr1;
vcpu->arch.fault_dar = svcpu->fault_dar;
vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
to_book3s(vcpu)->vtb += get_vtb() - vcpu->arch.entry_vtb;
if (cpu_has_feature(CPU_FTR_ARCH_207S))
vcpu->arch.ic += mfspr(SPRN_IC) - vcpu->arch.entry_ic;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * Unlike other MSR bits, MSR[TS]bits can be changed at guest without
+ * notifying host:
+ * modified by unprivileged instructions like "tbegin"/"tend"/
+ * "tresume"/"tsuspend" in PR KVM guest.
+ *
+ * It is necessary to sync here to calculate a correct shadow_msr.
+ *
+ * privileged guest's tbegin will be failed at present. So we
+ * only take care of problem state guest.
+ */
+ old_msr = kvmppc_get_msr(vcpu);
+ if (unlikely((old_msr & MSR_PR) &&
+ (vcpu->arch.shadow_srr1 & (MSR_TS_MASK)) !=
+ (old_msr & (MSR_TS_MASK)))) {
+ old_msr &= ~(MSR_TS_MASK);
+ old_msr |= (vcpu->arch.shadow_srr1 & (MSR_TS_MASK));
+ kvmppc_set_msr_fast(vcpu, old_msr);
+ kvmppc_recalc_shadow_msr(vcpu);
+ }
+#endif
+
svcpu->in_use = false;
out:
svcpu_put(svcpu);
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu)
+{
+ tm_enable();
+ vcpu->arch.tfhar = mfspr(SPRN_TFHAR);
+ vcpu->arch.texasr = mfspr(SPRN_TEXASR);
+ vcpu->arch.tfiar = mfspr(SPRN_TFIAR);
+ tm_disable();
+}
+
+void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu)
+{
+ tm_enable();
+ mtspr(SPRN_TFHAR, vcpu->arch.tfhar);
+ mtspr(SPRN_TEXASR, vcpu->arch.texasr);
+ mtspr(SPRN_TFIAR, vcpu->arch.tfiar);
+ tm_disable();
+}
+
+/* loadup math bits which is enabled at kvmppc_get_msr() but not enabled at
+ * hardware.
+ */
+static void kvmppc_handle_lost_math_exts(struct kvm_vcpu *vcpu)
+{
+ ulong exit_nr;
+ ulong ext_diff = (kvmppc_get_msr(vcpu) & ~vcpu->arch.guest_owned_ext) &
+ (MSR_FP | MSR_VEC | MSR_VSX);
+
+ if (!ext_diff)
+ return;
+
+ if (ext_diff == MSR_FP)
+ exit_nr = BOOK3S_INTERRUPT_FP_UNAVAIL;
+ else if (ext_diff == MSR_VEC)
+ exit_nr = BOOK3S_INTERRUPT_ALTIVEC;
+ else
+ exit_nr = BOOK3S_INTERRUPT_VSX;
+
+ kvmppc_handle_ext(vcpu, exit_nr, ext_diff);
+}
+
+void kvmppc_save_tm_pr(struct kvm_vcpu *vcpu)
+{
+ if (!(MSR_TM_ACTIVE(kvmppc_get_msr(vcpu)))) {
+ kvmppc_save_tm_sprs(vcpu);
+ return;
+ }
+
+ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+ kvmppc_giveup_ext(vcpu, MSR_VSX);
+
+ preempt_disable();
+ _kvmppc_save_tm_pr(vcpu, mfmsr());
+ preempt_enable();
+}
+
+void kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu)
+{
+ if (!MSR_TM_ACTIVE(kvmppc_get_msr(vcpu))) {
+ kvmppc_restore_tm_sprs(vcpu);
+ if (kvmppc_get_msr(vcpu) & MSR_TM) {
+ kvmppc_handle_lost_math_exts(vcpu);
+ if (vcpu->arch.fscr & FSCR_TAR)
+ kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+ }
+ return;
+ }
+
+ preempt_disable();
+ _kvmppc_restore_tm_pr(vcpu, kvmppc_get_msr(vcpu));
+ preempt_enable();
+
+ if (kvmppc_get_msr(vcpu) & MSR_TM) {
+ kvmppc_handle_lost_math_exts(vcpu);
+ if (vcpu->arch.fscr & FSCR_TAR)
+ kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+ }
+}
+#endif
+
static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
{
int r = 1; /* Indicate we want to get back into the guest */
/*****************************************/
-static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
-{
- ulong guest_msr = kvmppc_get_msr(vcpu);
- ulong smsr = guest_msr;
-
- /* Guest MSR values */
- smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE;
- /* Process MSR values */
- smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
- /* External providers the guest reserved */
- smsr |= (guest_msr & vcpu->arch.guest_owned_ext);
- /* 64-bit Process MSR values */
-#ifdef CONFIG_PPC_BOOK3S_64
- smsr |= MSR_ISF | MSR_HV;
-#endif
- vcpu->arch.shadow_msr = smsr;
-}
-
static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
{
- ulong old_msr = kvmppc_get_msr(vcpu);
+ ulong old_msr;
+
+ /* For PAPR guest, make sure MSR reflects guest mode */
+ if (vcpu->arch.papr_enabled)
+ msr = (msr & ~MSR_HV) | MSR_ME;
#ifdef EXIT_DEBUG
printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* We should never target guest MSR to TS=10 && PR=0,
+ * since we always fail transaction for guest privilege
+ * state.
+ */
+ if (!(msr & MSR_PR) && MSR_TM_TRANSACTIONAL(msr))
+ kvmppc_emulate_tabort(vcpu,
+ TM_CAUSE_KVM_FAC_UNAV | TM_CAUSE_PERSISTENT);
+#endif
+
+ old_msr = kvmppc_get_msr(vcpu);
msr &= to_book3s(vcpu)->msr_mask;
kvmppc_set_msr_fast(vcpu, msr);
kvmppc_recalc_shadow_msr(vcpu);
/* Preload FPU if it's enabled */
if (kvmppc_get_msr(vcpu) & MSR_FP)
kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (kvmppc_get_msr(vcpu) & MSR_TM)
+ kvmppc_handle_lost_math_exts(vcpu);
+#endif
}
void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
pte.may_execute = !data;
}
- if (page_found == -ENOENT) {
- /* Page not found in guest PTE entries */
- u64 ssrr1 = vcpu->arch.shadow_srr1;
- u64 msr = kvmppc_get_msr(vcpu);
- kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
- kvmppc_set_dsisr(vcpu, vcpu->arch.fault_dsisr);
- kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
- kvmppc_book3s_queue_irqprio(vcpu, vec);
- } else if (page_found == -EPERM) {
- /* Storage protection */
- u32 dsisr = vcpu->arch.fault_dsisr;
- u64 ssrr1 = vcpu->arch.shadow_srr1;
- u64 msr = kvmppc_get_msr(vcpu);
- kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
- dsisr = (dsisr & ~DSISR_NOHPTE) | DSISR_PROTFAULT;
- kvmppc_set_dsisr(vcpu, dsisr);
- kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
- kvmppc_book3s_queue_irqprio(vcpu, vec);
+ if (page_found == -ENOENT || page_found == -EPERM) {
+ /* Page not found in guest PTE entries, or protection fault */
+ u64 flags;
+
+ if (page_found == -EPERM)
+ flags = DSISR_PROTFAULT;
+ else
+ flags = DSISR_NOHPTE;
+ if (data) {
+ flags |= vcpu->arch.fault_dsisr & DSISR_ISSTORE;
+ kvmppc_core_queue_data_storage(vcpu, eaddr, flags);
+ } else {
+ kvmppc_core_queue_inst_storage(vcpu, flags);
+ }
} else if (page_found == -EINVAL) {
/* Page not found in guest SLB */
kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
}
/* Give up facility (TAR / EBB / DSCR) */
-static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac)
+void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac)
{
#ifdef CONFIG_PPC_BOOK3S_64
if (!(vcpu->arch.shadow_fscr & (1ULL << fac))) {
#ifdef CONFIG_PPC_BOOK3S_64
-static void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac)
+void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac)
{
/* Inject the Interrupt Cause field and trigger a guest interrupt */
vcpu->arch.fscr &= ~(0xffULL << 56);
break;
}
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* Since we disabled MSR_TM at privilege state, the mfspr instruction
+ * for TM spr can trigger TM fac unavailable. In this case, the
+ * emulation is handled by kvmppc_emulate_fac(), which invokes
+ * kvmppc_emulate_mfspr() finally. But note the mfspr can include
+ * RT for NV registers. So it need to restore those NV reg to reflect
+ * the update.
+ */
+ if ((fac == FSCR_TM_LG) && !(kvmppc_get_msr(vcpu) & MSR_PR))
+ return RESUME_GUEST_NV;
+#endif
+
return RESUME_GUEST;
}
if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) {
/* TAR got dropped, drop it in shadow too */
kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+ } else if (!(vcpu->arch.fscr & FSCR_TAR) && (fscr & FSCR_TAR)) {
+ vcpu->arch.fscr = fscr;
+ kvmppc_handle_fac(vcpu, FSCR_TAR_LG);
+ return;
}
+
vcpu->arch.fscr = fscr;
}
#endif
kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
r = RESUME_GUEST;
} else {
- u64 msr = kvmppc_get_msr(vcpu);
- msr |= shadow_srr1 & 0x58000000;
- kvmppc_set_msr_fast(vcpu, msr);
- kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+ kvmppc_core_queue_inst_storage(vcpu,
+ shadow_srr1 & 0x58000000);
r = RESUME_GUEST;
}
break;
r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
} else {
- kvmppc_set_dar(vcpu, dar);
- kvmppc_set_dsisr(vcpu, fault_dsisr);
- kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+ kvmppc_core_queue_data_storage(vcpu, dar, fault_dsisr);
r = RESUME_GUEST;
}
break;
case BOOK3S_INTERRUPT_EXTERNAL:
case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
case BOOK3S_INTERRUPT_EXTERNAL_HV:
+ case BOOK3S_INTERRUPT_H_VIRT:
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
+ case BOOK3S_INTERRUPT_HMI:
case BOOK3S_INTERRUPT_PERFMON:
+ case BOOK3S_INTERRUPT_SYSTEM_RESET:
r = RESUME_GUEST;
break;
case BOOK3S_INTERRUPT_PROGRAM:
}
#ifdef CONFIG_PPC_BOOK3S_64
case BOOK3S_INTERRUPT_FAC_UNAVAIL:
- kvmppc_handle_fac(vcpu, vcpu->arch.shadow_fscr >> 56);
- r = RESUME_GUEST;
+ r = kvmppc_handle_fac(vcpu, vcpu->arch.shadow_fscr >> 56);
break;
#endif
case BOOK3S_INTERRUPT_MACHINE_CHECK:
else
*val = get_reg_val(id, 0);
break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case KVM_REG_PPC_TFHAR:
+ *val = get_reg_val(id, vcpu->arch.tfhar);
+ break;
+ case KVM_REG_PPC_TFIAR:
+ *val = get_reg_val(id, vcpu->arch.tfiar);
+ break;
+ case KVM_REG_PPC_TEXASR:
+ *val = get_reg_val(id, vcpu->arch.texasr);
+ break;
+ case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+ *val = get_reg_val(id,
+ vcpu->arch.gpr_tm[id-KVM_REG_PPC_TM_GPR0]);
+ break;
+ case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+ {
+ int i, j;
+
+ i = id - KVM_REG_PPC_TM_VSR0;
+ if (i < 32)
+ for (j = 0; j < TS_FPRWIDTH; j++)
+ val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
+ else {
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ val->vval = vcpu->arch.vr_tm.vr[i-32];
+ else
+ r = -ENXIO;
+ }
+ break;
+ }
+ case KVM_REG_PPC_TM_CR:
+ *val = get_reg_val(id, vcpu->arch.cr_tm);
+ break;
+ case KVM_REG_PPC_TM_XER:
+ *val = get_reg_val(id, vcpu->arch.xer_tm);
+ break;
+ case KVM_REG_PPC_TM_LR:
+ *val = get_reg_val(id, vcpu->arch.lr_tm);
+ break;
+ case KVM_REG_PPC_TM_CTR:
+ *val = get_reg_val(id, vcpu->arch.ctr_tm);
+ break;
+ case KVM_REG_PPC_TM_FPSCR:
+ *val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
+ break;
+ case KVM_REG_PPC_TM_AMR:
+ *val = get_reg_val(id, vcpu->arch.amr_tm);
+ break;
+ case KVM_REG_PPC_TM_PPR:
+ *val = get_reg_val(id, vcpu->arch.ppr_tm);
+ break;
+ case KVM_REG_PPC_TM_VRSAVE:
+ *val = get_reg_val(id, vcpu->arch.vrsave_tm);
+ break;
+ case KVM_REG_PPC_TM_VSCR:
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ *val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
+ else
+ r = -ENXIO;
+ break;
+ case KVM_REG_PPC_TM_DSCR:
+ *val = get_reg_val(id, vcpu->arch.dscr_tm);
+ break;
+ case KVM_REG_PPC_TM_TAR:
+ *val = get_reg_val(id, vcpu->arch.tar_tm);
+ break;
+#endif
default:
r = -EINVAL;
break;
case KVM_REG_PPC_LPCR_64:
kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val));
break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case KVM_REG_PPC_TFHAR:
+ vcpu->arch.tfhar = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TFIAR:
+ vcpu->arch.tfiar = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TEXASR:
+ vcpu->arch.texasr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+ vcpu->arch.gpr_tm[id - KVM_REG_PPC_TM_GPR0] =
+ set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+ {
+ int i, j;
+
+ i = id - KVM_REG_PPC_TM_VSR0;
+ if (i < 32)
+ for (j = 0; j < TS_FPRWIDTH; j++)
+ vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
+ else
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ vcpu->arch.vr_tm.vr[i-32] = val->vval;
+ else
+ r = -ENXIO;
+ break;
+ }
+ case KVM_REG_PPC_TM_CR:
+ vcpu->arch.cr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_XER:
+ vcpu->arch.xer_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_LR:
+ vcpu->arch.lr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_CTR:
+ vcpu->arch.ctr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_FPSCR:
+ vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_AMR:
+ vcpu->arch.amr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_PPR:
+ vcpu->arch.ppr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_VRSAVE:
+ vcpu->arch.vrsave_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_VSCR:
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
+ else
+ r = -ENXIO;
+ break;
+ case KVM_REG_PPC_TM_DSCR:
+ vcpu->arch.dscr_tm = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TM_TAR:
+ vcpu->arch.tar_tm = set_reg_val(id, *val);
+ break;
+#endif
default:
r = -EINVAL;
break;
return 0;
}
+
+static int kvm_configure_mmu_pr(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return -ENODEV;
+ /* Require flags and process table base and size to all be zero. */
+ if (cfg->flags || cfg->process_table)
+ return -EINVAL;
+ return 0;
+}
+
#else
static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
struct kvm_ppc_smmu_info *info)
static int kvmppc_core_check_processor_compat_pr(void)
{
/*
- * Disable KVM for Power9 untill the required bits merged.
+ * PR KVM can work on POWER9 inside a guest partition
+ * running in HPT mode. It can't work if we are using
+ * radix translation (because radix provides no way for
+ * a process to have unique translations in quadrant 3).
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
return -EIO;
return 0;
}
.arch_vm_ioctl = kvm_arch_vm_ioctl_pr,
#ifdef CONFIG_PPC_BOOK3S_64
.hcall_implemented = kvmppc_hcall_impl_pr,
+ .configure_mmu = kvm_configure_mmu_pr,
#endif
+ .giveup_ext = kvmppc_giveup_ext,
};
*/
PPC_LL r6, HSTATE_HOST_MSR(r13)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * We don't want to change MSR[TS] bits via rfi here.
+ * The actual TM handling logic will be in host with
+ * recovered DR/IR bits after HSTATE_VMHANDLER.
+ * And MSR_TM can be enabled in HOST_MSR so rfid may
+ * not suppress this change and can lead to exception.
+ * Manually set MSR to prevent TS state change here.
+ */
+ mfmsr r7
+ rldicl r7, r7, 64 - MSR_TS_S_LG, 62
+ rldimi r6, r7, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+#endif
PPC_LL r8, HSTATE_VMHANDLER(r13)
#ifdef CONFIG_PPC64
*/
/* Return interrupt and old CPPR in GPR4 */
- vcpu->arch.gpr[4] = hirq | (old_cppr << 24);
+ vcpu->arch.regs.gpr[4] = hirq | (old_cppr << 24);
return H_SUCCESS;
}
hirq = GLUE(X_PFX,scan_interrupts)(xc, pending, scan_poll);
/* Return interrupt and old CPPR in GPR4 */
- vcpu->arch.gpr[4] = hirq | (xc->cppr << 24);
+ vcpu->arch.regs.gpr[4] = hirq | (xc->cppr << 24);
return H_SUCCESS;
}
{
int i;
- printk("pc: %08lx msr: %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
- printk("lr: %08lx ctr: %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
+ printk("pc: %08lx msr: %08llx\n", vcpu->arch.regs.nip,
+ vcpu->arch.shared->msr);
+ printk("lr: %08lx ctr: %08lx\n", vcpu->arch.regs.link,
+ vcpu->arch.regs.ctr);
printk("srr0: %08llx srr1: %08llx\n", vcpu->arch.shared->srr0,
vcpu->arch.shared->srr1);
if (allowed) {
switch (int_class) {
case INT_CLASS_NONCRIT:
- set_guest_srr(vcpu, vcpu->arch.pc,
+ set_guest_srr(vcpu, vcpu->arch.regs.nip,
vcpu->arch.shared->msr);
break;
case INT_CLASS_CRIT:
- set_guest_csrr(vcpu, vcpu->arch.pc,
+ set_guest_csrr(vcpu, vcpu->arch.regs.nip,
vcpu->arch.shared->msr);
break;
case INT_CLASS_DBG:
- set_guest_dsrr(vcpu, vcpu->arch.pc,
+ set_guest_dsrr(vcpu, vcpu->arch.regs.nip,
vcpu->arch.shared->msr);
break;
case INT_CLASS_MC:
- set_guest_mcsrr(vcpu, vcpu->arch.pc,
+ set_guest_mcsrr(vcpu, vcpu->arch.regs.nip,
vcpu->arch.shared->msr);
break;
}
- vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
+ vcpu->arch.regs.nip = vcpu->arch.ivpr |
+ vcpu->arch.ivor[priority];
if (update_esr == true)
kvmppc_set_esr(vcpu, vcpu->arch.queued_esr);
if (update_dear == true)
case EMULATE_FAIL:
printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
- __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+ __func__, vcpu->arch.regs.nip, vcpu->arch.last_inst);
/* For debugging, encode the failing instruction and
* report it to userspace. */
run->hw.hardware_exit_reason = ~0ULL << 32;
*/
vcpu->arch.dbsr = 0;
run->debug.arch.status = 0;
- run->debug.arch.address = vcpu->arch.pc;
+ run->debug.arch.address = vcpu->arch.regs.nip;
if (dbsr & (DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4)) {
run->debug.arch.status |= KVMPPC_DEBUG_BREAKPOINT;
case EMULATE_FAIL:
pr_debug("%s: load instruction from guest address %lx failed\n",
- __func__, vcpu->arch.pc);
+ __func__, vcpu->arch.regs.nip);
/* For debugging, encode the failing instruction and
* report it to userspace. */
run->hw.hardware_exit_reason = ~0ULL << 32;
case BOOKE_INTERRUPT_SPE_FP_DATA:
case BOOKE_INTERRUPT_SPE_FP_ROUND:
printk(KERN_CRIT "%s: unexpected SPE interrupt %u at %08lx\n",
- __func__, exit_nr, vcpu->arch.pc);
+ __func__, exit_nr, vcpu->arch.regs.nip);
run->hw.hardware_exit_reason = exit_nr;
r = RESUME_HOST;
break;
}
case BOOKE_INTERRUPT_ITLB_MISS: {
- unsigned long eaddr = vcpu->arch.pc;
+ unsigned long eaddr = vcpu->arch.regs.nip;
gpa_t gpaddr;
gfn_t gfn;
int gtlb_index;
int i;
int r;
- vcpu->arch.pc = 0;
+ vcpu->arch.regs.nip = 0;
vcpu->arch.shared->pir = vcpu->vcpu_id;
kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
kvmppc_set_msr(vcpu, 0);
vcpu_load(vcpu);
- regs->pc = vcpu->arch.pc;
+ regs->pc = vcpu->arch.regs.nip;
regs->cr = kvmppc_get_cr(vcpu);
- regs->ctr = vcpu->arch.ctr;
- regs->lr = vcpu->arch.lr;
+ regs->ctr = vcpu->arch.regs.ctr;
+ regs->lr = vcpu->arch.regs.link;
regs->xer = kvmppc_get_xer(vcpu);
regs->msr = vcpu->arch.shared->msr;
regs->srr0 = kvmppc_get_srr0(vcpu);
vcpu_load(vcpu);
- vcpu->arch.pc = regs->pc;
+ vcpu->arch.regs.nip = regs->pc;
kvmppc_set_cr(vcpu, regs->cr);
- vcpu->arch.ctr = regs->ctr;
- vcpu->arch.lr = regs->lr;
+ vcpu->arch.regs.ctr = regs->ctr;
+ vcpu->arch.regs.link = regs->lr;
kvmppc_set_xer(vcpu, regs->xer);
kvmppc_set_msr(vcpu, regs->msr);
kvmppc_set_srr0(vcpu, regs->srr0);
static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pc = vcpu->arch.shared->srr0;
+ vcpu->arch.regs.nip = vcpu->arch.shared->srr0;
kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
}
static void kvmppc_emul_rfdi(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pc = vcpu->arch.dsrr0;
+ vcpu->arch.regs.nip = vcpu->arch.dsrr0;
kvmppc_set_msr(vcpu, vcpu->arch.dsrr1);
}
static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pc = vcpu->arch.csrr0;
+ vcpu->arch.regs.nip = vcpu->arch.csrr0;
kvmppc_set_msr(vcpu, vcpu->arch.csrr1);
}
static int kvmppc_e500_emul_msgclr(struct kvm_vcpu *vcpu, int rb)
{
- ulong param = vcpu->arch.gpr[rb];
+ ulong param = vcpu->arch.regs.gpr[rb];
int prio = dbell2prio(param);
if (prio < 0)
static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb)
{
- ulong param = vcpu->arch.gpr[rb];
+ ulong param = vcpu->arch.regs.gpr[rb];
int prio = dbell2prio(rb);
int pir = param & PPC_DBELL_PIR_MASK;
int i;
switch (get_oc(inst)) {
case EHPRIV_OC_DEBUG:
run->exit_reason = KVM_EXIT_DEBUG;
- run->debug.arch.address = vcpu->arch.pc;
+ run->debug.arch.address = vcpu->arch.regs.nip;
run->debug.arch.status = 0;
kvmppc_account_exit(vcpu, DEBUG_EXITS);
emulated = EMULATE_EXIT_USER;
{
unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
- kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
+ kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.regs.nip, as);
}
void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
}
#ifdef CONFIG_KVM_BOOKE_HV
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
- u32 *instr)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+ enum instruction_fetch_type type, u32 *instr)
{
gva_t geaddr;
hpa_t addr;
return EMULATE_DONE;
}
#else
-int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
- u32 *instr)
+int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
+ enum instruction_fetch_type type, u32 *instr)
{
return EMULATE_AGAIN;
}
#include <asm/kvm_ppc.h>
#include <asm/disassemble.h>
#include <asm/ppc-opcode.h>
+#include <asm/sstep.h>
#include "timing.h"
#include "trace.h"
struct kvm_run *run = vcpu->run;
u32 inst;
int ra, rs, rt;
- enum emulation_result emulated;
+ enum emulation_result emulated = EMULATE_FAIL;
int advance = 1;
+ struct instruction_op op;
/* this default type might be overwritten by subcategories */
kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst);
vcpu->arch.mmio_vsx_copy_nums = 0;
vcpu->arch.mmio_vsx_offset = 0;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE;
+ vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
vcpu->arch.mmio_sp64_extend = 0;
vcpu->arch.mmio_sign_extend = 0;
vcpu->arch.mmio_vmx_copy_nums = 0;
+ vcpu->arch.mmio_vmx_offset = 0;
+ vcpu->arch.mmio_host_swabbed = 0;
- switch (get_op(inst)) {
- case 31:
- switch (get_xop(inst)) {
- case OP_31_XOP_LWZX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
- break;
-
- case OP_31_XOP_LWZUX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
+ emulated = EMULATE_FAIL;
+ vcpu->arch.regs.msr = vcpu->arch.shared->msr;
+ vcpu->arch.regs.ccr = vcpu->arch.cr;
+ if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
+ int type = op.type & INSTR_TYPE_MASK;
+ int size = GETSIZE(op.type);
- case OP_31_XOP_LBZX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
- break;
-
- case OP_31_XOP_LBZUX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
+ switch (type) {
+ case LOAD: {
+ int instr_byte_swap = op.type & BYTEREV;
- case OP_31_XOP_STDX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 8, 1);
- break;
+ if (op.type & SIGNEXT)
+ emulated = kvmppc_handle_loads(run, vcpu,
+ op.reg, size, !instr_byte_swap);
+ else
+ emulated = kvmppc_handle_load(run, vcpu,
+ op.reg, size, !instr_byte_swap);
- case OP_31_XOP_STDUX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
+ if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+ kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
- case OP_31_XOP_STWX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 4, 1);
- break;
-
- case OP_31_XOP_STWUX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_STBX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 1, 1);
- break;
-
- case OP_31_XOP_STBUX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 1, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_LHAX:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
- break;
-
- case OP_31_XOP_LHAUX:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_LHZX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
- break;
-
- case OP_31_XOP_LHZUX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_STHX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 2, 1);
- break;
-
- case OP_31_XOP_STHUX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_DCBST:
- case OP_31_XOP_DCBF:
- case OP_31_XOP_DCBI:
- /* Do nothing. The guest is performing dcbi because
- * hardware DMA is not snooped by the dcache, but
- * emulated DMA either goes through the dcache as
- * normal writes, or the host kernel has handled dcache
- * coherence. */
- break;
-
- case OP_31_XOP_LWBRX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
- break;
-
- case OP_31_XOP_STWBRX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 4, 0);
break;
-
- case OP_31_XOP_LHBRX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
- break;
-
- case OP_31_XOP_STHBRX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 2, 0);
- break;
-
- case OP_31_XOP_LDBRX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 0);
- break;
-
- case OP_31_XOP_STDBRX:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 8, 0);
- break;
-
- case OP_31_XOP_LDX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
- break;
-
- case OP_31_XOP_LDUX:
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_LWAX:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
- break;
-
- case OP_31_XOP_LWAUX:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
+ }
#ifdef CONFIG_PPC_FPU
- case OP_31_XOP_LFSX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- break;
-
- case OP_31_XOP_LFSUX:
+ case LOAD_FP:
if (kvmppc_check_fp_disabled(vcpu))
return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
- case OP_31_XOP_LFDX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 8, 1);
- break;
+ if (op.type & FPCONV)
+ vcpu->arch.mmio_sp64_extend = 1;
- case OP_31_XOP_LFDUX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_LFIWAX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_loads(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- break;
+ if (op.type & SIGNEXT)
+ emulated = kvmppc_handle_loads(run, vcpu,
+ KVM_MMIO_REG_FPR|op.reg, size, 1);
+ else
+ emulated = kvmppc_handle_load(run, vcpu,
+ KVM_MMIO_REG_FPR|op.reg, size, 1);
- case OP_31_XOP_LFIWZX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- break;
+ if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+ kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
- case OP_31_XOP_STFSX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs), 4, 1);
break;
-
- case OP_31_XOP_STFSUX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs), 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_31_XOP_STFDX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs), 8, 1);
- break;
-
- case OP_31_XOP_STFDUX:
- if (kvmppc_check_fp_disabled(vcpu))
+#endif
+#ifdef CONFIG_ALTIVEC
+ case LOAD_VMX:
+ if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs), 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
- case OP_31_XOP_STFIWX:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs), 4, 1);
+ /* Hardware enforces alignment of VMX accesses */
+ vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
+ vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
+
+ if (size == 16) { /* lvx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_DWORD;
+ } else if (size == 4) { /* lvewx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_WORD;
+ } else if (size == 2) { /* lvehx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_HWORD;
+ } else if (size == 1) { /* lvebx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_BYTE;
+ } else
+ break;
+
+ vcpu->arch.mmio_vmx_offset =
+ (vcpu->arch.vaddr_accessed & 0xf)/size;
+
+ if (size == 16) {
+ vcpu->arch.mmio_vmx_copy_nums = 2;
+ emulated = kvmppc_handle_vmx_load(run,
+ vcpu, KVM_MMIO_REG_VMX|op.reg,
+ 8, 1);
+ } else {
+ vcpu->arch.mmio_vmx_copy_nums = 1;
+ emulated = kvmppc_handle_vmx_load(run, vcpu,
+ KVM_MMIO_REG_VMX|op.reg,
+ size, 1);
+ }
break;
#endif
-
#ifdef CONFIG_VSX
- case OP_31_XOP_LXSDX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 8, 1, 0);
- break;
-
- case OP_31_XOP_LXSSPX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 4, 1, 0);
- break;
+ case LOAD_VSX: {
+ int io_size_each;
+
+ if (op.vsx_flags & VSX_CHECK_VEC) {
+ if (kvmppc_check_altivec_disabled(vcpu))
+ return EMULATE_DONE;
+ } else {
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ }
+
+ if (op.vsx_flags & VSX_FPCONV)
+ vcpu->arch.mmio_sp64_extend = 1;
+
+ if (op.element_size == 8) {
+ if (op.vsx_flags & VSX_SPLAT)
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
+ else
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_DWORD;
+ } else if (op.element_size == 4) {
+ if (op.vsx_flags & VSX_SPLAT)
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_WORD_LOAD_DUMP;
+ else
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_WORD;
+ } else
+ break;
+
+ if (size < op.element_size) {
+ /* precision convert case: lxsspx, etc */
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ io_size_each = size;
+ } else { /* lxvw4x, lxvd2x, etc */
+ vcpu->arch.mmio_vsx_copy_nums =
+ size/op.element_size;
+ io_size_each = op.element_size;
+ }
- case OP_31_XOP_LXSIWAX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 4, 1, 1);
- break;
-
- case OP_31_XOP_LXSIWZX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 4, 1, 0);
+ KVM_MMIO_REG_VSX | (op.reg & 0x1f),
+ io_size_each, 1, op.type & SIGNEXT);
break;
+ }
+#endif
+ case STORE:
+ /* if need byte reverse, op.val has been reversed by
+ * analyse_instr().
+ */
+ emulated = kvmppc_handle_store(run, vcpu, op.val,
+ size, 1);
- case OP_31_XOP_LXVD2X:
- /*
- * In this case, the official load/store process is like this:
- * Step1, exit from vm by page fault isr, then kvm save vsr.
- * Please see guest_exit_cont->store_fp_state->SAVE_32VSRS
- * as reference.
- *
- * Step2, copy data between memory and VCPU
- * Notice: for LXVD2X/STXVD2X/LXVW4X/STXVW4X, we use
- * 2copies*8bytes or 4copies*4bytes
- * to simulate one copy of 16bytes.
- * Also there is an endian issue here, we should notice the
- * layout of memory.
- * Please see MARCO of LXVD2X_ROT/STXVD2X_ROT as more reference.
- * If host is little-endian, kvm will call XXSWAPD for
- * LXVD2X_ROT/STXVD2X_ROT.
- * So, if host is little-endian,
- * the postion of memeory should be swapped.
- *
- * Step3, return to guest, kvm reset register.
- * Please see kvmppc_hv_entry->load_fp_state->REST_32VSRS
- * as reference.
- */
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 2;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 8, 1, 0);
- break;
+ if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+ kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
- case OP_31_XOP_LXVW4X:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 4;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 4, 1, 0);
break;
-
- case OP_31_XOP_LXVDSX:
- if (kvmppc_check_vsx_disabled(vcpu))
+#ifdef CONFIG_PPC_FPU
+ case STORE_FP:
+ if (kvmppc_check_fp_disabled(vcpu))
return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type =
- KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
- emulated = kvmppc_handle_vsx_load(run, vcpu,
- KVM_MMIO_REG_VSX|rt, 8, 1, 0);
- break;
- case OP_31_XOP_STXSDX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- emulated = kvmppc_handle_vsx_store(run, vcpu,
- rs, 8, 1);
- break;
+ /* The FP registers need to be flushed so that
+ * kvmppc_handle_store() can read actual FP vals
+ * from vcpu->arch.
+ */
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+ MSR_FP);
- case OP_31_XOP_STXSSPX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_vsx_store(run, vcpu,
- rs, 4, 1);
- break;
+ if (op.type & FPCONV)
+ vcpu->arch.mmio_sp64_extend = 1;
- case OP_31_XOP_STXSIWX:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_offset = 1;
- vcpu->arch.mmio_vsx_copy_nums = 1;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
- emulated = kvmppc_handle_vsx_store(run, vcpu,
- rs, 4, 1);
- break;
+ emulated = kvmppc_handle_store(run, vcpu,
+ VCPU_FPR(vcpu, op.reg), size, 1);
- case OP_31_XOP_STXVD2X:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 2;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD;
- emulated = kvmppc_handle_vsx_store(run, vcpu,
- rs, 8, 1);
- break;
+ if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
+ kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
- case OP_31_XOP_STXVW4X:
- if (kvmppc_check_vsx_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_vsx_copy_nums = 4;
- vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD;
- emulated = kvmppc_handle_vsx_store(run, vcpu,
- rs, 4, 1);
break;
-#endif /* CONFIG_VSX */
-
+#endif
#ifdef CONFIG_ALTIVEC
- case OP_31_XOP_LVX:
+ case STORE_VMX:
if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
- vcpu->arch.vaddr_accessed &= ~0xFULL;
- vcpu->arch.paddr_accessed &= ~0xFULL;
- vcpu->arch.mmio_vmx_copy_nums = 2;
- emulated = kvmppc_handle_load128_by2x64(run, vcpu,
- KVM_MMIO_REG_VMX|rt, 1);
- break;
- case OP_31_XOP_STVX:
- if (kvmppc_check_altivec_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.vaddr_accessed &= ~0xFULL;
- vcpu->arch.paddr_accessed &= ~0xFULL;
- vcpu->arch.mmio_vmx_copy_nums = 2;
- emulated = kvmppc_handle_store128_by2x64(run, vcpu,
- rs, 1);
- break;
-#endif /* CONFIG_ALTIVEC */
+ /* Hardware enforces alignment of VMX accesses. */
+ vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
+ vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
+
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+ MSR_VEC);
+ if (size == 16) { /* stvx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_DWORD;
+ } else if (size == 4) { /* stvewx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_WORD;
+ } else if (size == 2) { /* stvehx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_HWORD;
+ } else if (size == 1) { /* stvebx */
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VMX_COPY_BYTE;
+ } else
+ break;
+
+ vcpu->arch.mmio_vmx_offset =
+ (vcpu->arch.vaddr_accessed & 0xf)/size;
+
+ if (size == 16) {
+ vcpu->arch.mmio_vmx_copy_nums = 2;
+ emulated = kvmppc_handle_vmx_store(run,
+ vcpu, op.reg, 8, 1);
+ } else {
+ vcpu->arch.mmio_vmx_copy_nums = 1;
+ emulated = kvmppc_handle_vmx_store(run,
+ vcpu, op.reg, size, 1);
+ }
- default:
- emulated = EMULATE_FAIL;
break;
- }
- break;
-
- case OP_LWZ:
- emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
- break;
-
-#ifdef CONFIG_PPC_FPU
- case OP_STFS:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs),
- 4, 1);
- break;
-
- case OP_STFSU:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs),
- 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_STFD:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs),
- 8, 1);
- break;
-
- case OP_STFDU:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_store(run, vcpu,
- VCPU_FPR(vcpu, rs),
- 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
#endif
+#ifdef CONFIG_VSX
+ case STORE_VSX: {
+ int io_size_each;
+
+ if (op.vsx_flags & VSX_CHECK_VEC) {
+ if (kvmppc_check_altivec_disabled(vcpu))
+ return EMULATE_DONE;
+ } else {
+ if (kvmppc_check_vsx_disabled(vcpu))
+ return EMULATE_DONE;
+ }
+
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
+ MSR_VSX);
+
+ if (op.vsx_flags & VSX_FPCONV)
+ vcpu->arch.mmio_sp64_extend = 1;
+
+ if (op.element_size == 8)
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_DWORD;
+ else if (op.element_size == 4)
+ vcpu->arch.mmio_copy_type =
+ KVMPPC_VSX_COPY_WORD;
+ else
+ break;
+
+ if (size < op.element_size) {
+ /* precise conversion case, like stxsspx */
+ vcpu->arch.mmio_vsx_copy_nums = 1;
+ io_size_each = size;
+ } else { /* stxvw4x, stxvd2x, etc */
+ vcpu->arch.mmio_vsx_copy_nums =
+ size/op.element_size;
+ io_size_each = op.element_size;
+ }
- case OP_LD:
- rt = get_rt(inst);
- switch (inst & 3) {
- case 0: /* ld */
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
- break;
- case 1: /* ldu */
- emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
- case 2: /* lwa */
- emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1);
+ emulated = kvmppc_handle_vsx_store(run, vcpu,
+ op.reg & 0x1f, io_size_each, 1);
break;
- default:
- emulated = EMULATE_FAIL;
}
- break;
-
- case OP_LWZU:
- emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_LBZ:
- emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
- break;
-
- case OP_LBZU:
- emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_STW:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs),
- 4, 1);
- break;
-
- case OP_STD:
- rs = get_rs(inst);
- switch (inst & 3) {
- case 0: /* std */
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 8, 1);
- break;
- case 1: /* stdu */
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
+#endif
+ case CACHEOP:
+ /* Do nothing. The guest is performing dcbi because
+ * hardware DMA is not snooped by the dcache, but
+ * emulated DMA either goes through the dcache as
+ * normal writes, or the host kernel has handled dcache
+ * coherence.
+ */
+ emulated = EMULATE_DONE;
break;
default:
- emulated = EMULATE_FAIL;
+ break;
}
- break;
-
- case OP_STWU:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_STB:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 1, 1);
- break;
-
- case OP_STBU:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 1, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_LHZ:
- emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
- break;
-
- case OP_LHZU:
- emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_LHA:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
- break;
-
- case OP_LHAU:
- emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_STH:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 2, 1);
- break;
-
- case OP_STHU:
- emulated = kvmppc_handle_store(run, vcpu,
- kvmppc_get_gpr(vcpu, rs), 2, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
-#ifdef CONFIG_PPC_FPU
- case OP_LFS:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- break;
-
- case OP_LFSU:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- vcpu->arch.mmio_sp64_extend = 1;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 4, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-
- case OP_LFD:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 8, 1);
- break;
-
- case OP_LFDU:
- if (kvmppc_check_fp_disabled(vcpu))
- return EMULATE_DONE;
- emulated = kvmppc_handle_load(run, vcpu,
- KVM_MMIO_REG_FPR|rt, 8, 1);
- kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
- break;
-#endif
-
- default:
- emulated = EMULATE_FAIL;
- break;
}
if (emulated == EMULATE_FAIL) {
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case KVM_CAP_PPC_HTM:
- r = hv_enabled &&
- (!!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
- cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
+ r = !!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
+ (hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
break;
#endif
default:
}
}
+static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
+ u32 gpr)
+{
+ union kvmppc_one_reg val;
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+ if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+ val.vsx32val[0] = gpr;
+ val.vsx32val[1] = gpr;
+ val.vsx32val[2] = gpr;
+ val.vsx32val[3] = gpr;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+ } else {
+ val.vsx32val[0] = gpr;
+ val.vsx32val[1] = gpr;
+ VCPU_VSX_FPR(vcpu, index, 0) = val.vsxval[0];
+ VCPU_VSX_FPR(vcpu, index, 1) = val.vsxval[0];
+ }
+}
+
static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
u32 gpr32)
{
#endif /* CONFIG_VSX */
#ifdef CONFIG_ALTIVEC
+static inline int kvmppc_get_vmx_offset_generic(struct kvm_vcpu *vcpu,
+ int index, int element_size)
+{
+ int offset;
+ int elts = sizeof(vector128)/element_size;
+
+ if ((index < 0) || (index >= elts))
+ return -1;
+
+ if (kvmppc_need_byteswap(vcpu))
+ offset = elts - index - 1;
+ else
+ offset = index;
+
+ return offset;
+}
+
+static inline int kvmppc_get_vmx_dword_offset(struct kvm_vcpu *vcpu,
+ int index)
+{
+ return kvmppc_get_vmx_offset_generic(vcpu, index, 8);
+}
+
+static inline int kvmppc_get_vmx_word_offset(struct kvm_vcpu *vcpu,
+ int index)
+{
+ return kvmppc_get_vmx_offset_generic(vcpu, index, 4);
+}
+
+static inline int kvmppc_get_vmx_hword_offset(struct kvm_vcpu *vcpu,
+ int index)
+{
+ return kvmppc_get_vmx_offset_generic(vcpu, index, 2);
+}
+
+static inline int kvmppc_get_vmx_byte_offset(struct kvm_vcpu *vcpu,
+ int index)
+{
+ return kvmppc_get_vmx_offset_generic(vcpu, index, 1);
+}
+
+
static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu,
- u64 gpr)
+ u64 gpr)
{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vmx_dword_offset(vcpu,
+ vcpu->arch.mmio_vmx_offset);
int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
- u32 hi, lo;
- u32 di;
-#ifdef __BIG_ENDIAN
- hi = gpr >> 32;
- lo = gpr & 0xffffffff;
-#else
- lo = gpr >> 32;
- hi = gpr & 0xffffffff;
-#endif
+ if (offset == -1)
+ return;
+
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsxval[offset] = gpr;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu,
+ u32 gpr32)
+{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vmx_word_offset(vcpu,
+ vcpu->arch.mmio_vmx_offset);
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
- di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */
- if (di > 1)
+ if (offset == -1)
return;
- if (vcpu->arch.mmio_host_swabbed)
- di = 1 - di;
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsx32val[offset] = gpr32;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu,
+ u16 gpr16)
+{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vmx_hword_offset(vcpu,
+ vcpu->arch.mmio_vmx_offset);
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+ if (offset == -1)
+ return;
+
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsx16val[offset] = gpr16;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
+}
+
+static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu,
+ u8 gpr8)
+{
+ union kvmppc_one_reg val;
+ int offset = kvmppc_get_vmx_byte_offset(vcpu,
+ vcpu->arch.mmio_vmx_offset);
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+
+ if (offset == -1)
+ return;
- VCPU_VSX_VR(vcpu, index).u[di * 2] = hi;
- VCPU_VSX_VR(vcpu, index).u[di * 2 + 1] = lo;
+ val.vval = VCPU_VSX_VR(vcpu, index);
+ val.vsx8val[offset] = gpr8;
+ VCPU_VSX_VR(vcpu, index) = val.vval;
}
#endif /* CONFIG_ALTIVEC */
kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
break;
case KVM_MMIO_REG_FPR:
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_FP);
+
VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
break;
#ifdef CONFIG_PPC_BOOK3S
#endif
#ifdef CONFIG_VSX
case KVM_MMIO_REG_VSX:
- if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_DWORD)
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_VSX);
+
+ if (vcpu->arch.mmio_copy_type == KVMPPC_VSX_COPY_DWORD)
kvmppc_set_vsr_dword(vcpu, gpr);
- else if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_WORD)
+ else if (vcpu->arch.mmio_copy_type == KVMPPC_VSX_COPY_WORD)
kvmppc_set_vsr_word(vcpu, gpr);
- else if (vcpu->arch.mmio_vsx_copy_type ==
+ else if (vcpu->arch.mmio_copy_type ==
KVMPPC_VSX_COPY_DWORD_LOAD_DUMP)
kvmppc_set_vsr_dword_dump(vcpu, gpr);
+ else if (vcpu->arch.mmio_copy_type ==
+ KVMPPC_VSX_COPY_WORD_LOAD_DUMP)
+ kvmppc_set_vsr_word_dump(vcpu, gpr);
break;
#endif
#ifdef CONFIG_ALTIVEC
case KVM_MMIO_REG_VMX:
- kvmppc_set_vmx_dword(vcpu, gpr);
+ if (vcpu->kvm->arch.kvm_ops->giveup_ext)
+ vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_VEC);
+
+ if (vcpu->arch.mmio_copy_type == KVMPPC_VMX_COPY_DWORD)
+ kvmppc_set_vmx_dword(vcpu, gpr);
+ else if (vcpu->arch.mmio_copy_type == KVMPPC_VMX_COPY_WORD)
+ kvmppc_set_vmx_word(vcpu, gpr);
+ else if (vcpu->arch.mmio_copy_type ==
+ KVMPPC_VMX_COPY_HWORD)
+ kvmppc_set_vmx_hword(vcpu, gpr);
+ else if (vcpu->arch.mmio_copy_type ==
+ KVMPPC_VMX_COPY_BYTE)
+ kvmppc_set_vmx_byte(vcpu, gpr);
break;
#endif
default:
u32 dword_offset, word_offset;
union kvmppc_one_reg reg;
int vsx_offset = 0;
- int copy_type = vcpu->arch.mmio_vsx_copy_type;
+ int copy_type = vcpu->arch.mmio_copy_type;
int result = 0;
switch (copy_type) {
#endif /* CONFIG_VSX */
#ifdef CONFIG_ALTIVEC
-/* handle quadword load access in two halves */
-int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
- unsigned int rt, int is_default_endian)
+int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, unsigned int bytes, int is_default_endian)
{
enum emulation_result emulated = EMULATE_DONE;
+ if (vcpu->arch.mmio_vsx_copy_nums > 2)
+ return EMULATE_FAIL;
+
while (vcpu->arch.mmio_vmx_copy_nums) {
- emulated = __kvmppc_handle_load(run, vcpu, rt, 8,
+ emulated = __kvmppc_handle_load(run, vcpu, rt, bytes,
is_default_endian, 0);
if (emulated != EMULATE_DONE)
vcpu->arch.paddr_accessed += run->mmio.len;
vcpu->arch.mmio_vmx_copy_nums--;
+ vcpu->arch.mmio_vmx_offset++;
}
return emulated;
}
-static inline int kvmppc_get_vmx_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
+int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val)
{
- vector128 vrs = VCPU_VSX_VR(vcpu, rs);
- u32 di;
- u64 w0, w1;
+ union kvmppc_one_reg reg;
+ int vmx_offset = 0;
+ int result = 0;
- di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */
- if (di > 1)
+ vmx_offset =
+ kvmppc_get_vmx_dword_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+ if (vmx_offset == -1)
return -1;
- if (vcpu->arch.mmio_host_swabbed)
- di = 1 - di;
+ reg.vval = VCPU_VSX_VR(vcpu, index);
+ *val = reg.vsxval[vmx_offset];
- w0 = vrs.u[di * 2];
- w1 = vrs.u[di * 2 + 1];
+ return result;
+}
-#ifdef __BIG_ENDIAN
- *val = (w0 << 32) | w1;
-#else
- *val = (w1 << 32) | w0;
-#endif
- return 0;
+int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+ union kvmppc_one_reg reg;
+ int vmx_offset = 0;
+ int result = 0;
+
+ vmx_offset =
+ kvmppc_get_vmx_word_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+ if (vmx_offset == -1)
+ return -1;
+
+ reg.vval = VCPU_VSX_VR(vcpu, index);
+ *val = reg.vsx32val[vmx_offset];
+
+ return result;
+}
+
+int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+ union kvmppc_one_reg reg;
+ int vmx_offset = 0;
+ int result = 0;
+
+ vmx_offset =
+ kvmppc_get_vmx_hword_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+ if (vmx_offset == -1)
+ return -1;
+
+ reg.vval = VCPU_VSX_VR(vcpu, index);
+ *val = reg.vsx16val[vmx_offset];
+
+ return result;
}
-/* handle quadword store in two halves */
-int kvmppc_handle_store128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
- unsigned int rs, int is_default_endian)
+int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val)
+{
+ union kvmppc_one_reg reg;
+ int vmx_offset = 0;
+ int result = 0;
+
+ vmx_offset =
+ kvmppc_get_vmx_byte_offset(vcpu, vcpu->arch.mmio_vmx_offset);
+
+ if (vmx_offset == -1)
+ return -1;
+
+ reg.vval = VCPU_VSX_VR(vcpu, index);
+ *val = reg.vsx8val[vmx_offset];
+
+ return result;
+}
+
+int kvmppc_handle_vmx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rs, unsigned int bytes, int is_default_endian)
{
u64 val = 0;
+ unsigned int index = rs & KVM_MMIO_REG_MASK;
enum emulation_result emulated = EMULATE_DONE;
+ if (vcpu->arch.mmio_vsx_copy_nums > 2)
+ return EMULATE_FAIL;
+
vcpu->arch.io_gpr = rs;
while (vcpu->arch.mmio_vmx_copy_nums) {
- if (kvmppc_get_vmx_data(vcpu, rs, &val) == -1)
+ switch (vcpu->arch.mmio_copy_type) {
+ case KVMPPC_VMX_COPY_DWORD:
+ if (kvmppc_get_vmx_dword(vcpu, index, &val) == -1)
+ return EMULATE_FAIL;
+
+ break;
+ case KVMPPC_VMX_COPY_WORD:
+ if (kvmppc_get_vmx_word(vcpu, index, &val) == -1)
+ return EMULATE_FAIL;
+ break;
+ case KVMPPC_VMX_COPY_HWORD:
+ if (kvmppc_get_vmx_hword(vcpu, index, &val) == -1)
+ return EMULATE_FAIL;
+ break;
+ case KVMPPC_VMX_COPY_BYTE:
+ if (kvmppc_get_vmx_byte(vcpu, index, &val) == -1)
+ return EMULATE_FAIL;
+ break;
+ default:
return EMULATE_FAIL;
+ }
- emulated = kvmppc_handle_store(run, vcpu, val, 8,
+ emulated = kvmppc_handle_store(run, vcpu, val, bytes,
is_default_endian);
if (emulated != EMULATE_DONE)
break;
vcpu->arch.paddr_accessed += run->mmio.len;
vcpu->arch.mmio_vmx_copy_nums--;
+ vcpu->arch.mmio_vmx_offset++;
}
return emulated;
vcpu->arch.paddr_accessed += run->mmio.len;
if (!vcpu->mmio_is_write) {
- emulated = kvmppc_handle_load128_by2x64(run, vcpu,
- vcpu->arch.io_gpr, 1);
+ emulated = kvmppc_handle_vmx_load(run, vcpu,
+ vcpu->arch.io_gpr, run->mmio.len, 1);
} else {
- emulated = kvmppc_handle_store128_by2x64(run, vcpu,
- vcpu->arch.io_gpr, 1);
+ emulated = kvmppc_handle_vmx_store(run, vcpu,
+ vcpu->arch.io_gpr, run->mmio.len, 1);
}
switch (emulated) {
}
#endif
#ifdef CONFIG_ALTIVEC
- if (vcpu->arch.mmio_vmx_copy_nums > 0)
+ if (vcpu->arch.mmio_vmx_copy_nums > 0) {
vcpu->arch.mmio_vmx_copy_nums--;
+ vcpu->arch.mmio_vmx_offset++;
+ }
if (vcpu->arch.mmio_vmx_copy_nums > 0) {
r = kvmppc_emulate_mmio_vmx_loadstore(vcpu, run);
void __user *argp = (void __user *)arg;
long r;
- vcpu_load(vcpu);
-
switch (ioctl) {
case KVM_ENABLE_CAP:
{
struct kvm_enable_cap cap;
r = -EFAULT;
+ vcpu_load(vcpu);
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+ vcpu_put(vcpu);
break;
}
case KVM_DIRTY_TLB: {
struct kvm_dirty_tlb dirty;
r = -EFAULT;
+ vcpu_load(vcpu);
if (copy_from_user(&dirty, argp, sizeof(dirty)))
goto out;
r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
+ vcpu_put(vcpu);
break;
}
#endif
}
out:
- vcpu_put(vcpu);
return r;
}
--- /dev/null
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Derived from book3s_hv_rmhandlers.S, which is:
+ *
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ */
+
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+#include <asm/tm.h>
+#include <asm/cputable.h>
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
+
+/*
+ * Save transactional state and TM-related registers.
+ * Called with:
+ * - r3 pointing to the vcpu struct
+ * - r4 points to the MSR with current TS bits:
+ * (For HV KVM, it is VCPU_MSR ; For PR KVM, it is host MSR).
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 before exit.
+ */
+_GLOBAL(__kvmppc_save_tm)
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM. */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ ori r8, r8, MSR_FP
+ oris r8, r8, (MSR_VEC | MSR_VSX)@h
+ mtmsrd r8
+
+ rldicl. r4, r4, 64 - MSR_TS_S_LG, 62
+ beq 1f /* TM not active in guest. */
+
+ std r1, HSTATE_SCRATCH2(r13)
+ std r3, HSTATE_SCRATCH1(r13)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+BEGIN_FTR_SECTION
+ /* Emulation of the treclaim instruction needs TEXASR before treclaim */
+ mfspr r6, SPRN_TEXASR
+ std r6, VCPU_ORIG_TEXASR(r3)
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+#endif
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ li r3, TM_CAUSE_KVM_RESCHED
+
+ /* All GPRs are volatile at this point. */
+ TRECLAIM(R3)
+
+ /* Temporarily store r13 and r9 so we have some regs to play with */
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+ std r9, PACATMSCRATCH(r13)
+ ld r9, HSTATE_SCRATCH1(r13)
+
+ /* Get a few more GPRs free. */
+ std r29, VCPU_GPRS_TM(29)(r9)
+ std r30, VCPU_GPRS_TM(30)(r9)
+ std r31, VCPU_GPRS_TM(31)(r9)
+
+ /* Save away PPR and DSCR soon so don't run with user values. */
+ mfspr r31, SPRN_PPR
+ HMT_MEDIUM
+ mfspr r30, SPRN_DSCR
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+#endif
+
+ /* Save all but r9, r13 & r29-r31 */
+ reg = 0
+ .rept 29
+ .if (reg != 9) && (reg != 13)
+ std reg, VCPU_GPRS_TM(reg)(r9)
+ .endif
+ reg = reg + 1
+ .endr
+ /* ... now save r13 */
+ GET_SCRATCH0(r4)
+ std r4, VCPU_GPRS_TM(13)(r9)
+ /* ... and save r9 */
+ ld r4, PACATMSCRATCH(r13)
+ std r4, VCPU_GPRS_TM(9)(r9)
+
+ /* Reload stack pointer and TOC. */
+ ld r1, HSTATE_SCRATCH2(r13)
+ ld r2, PACATOC(r13)
+
+ /* Set MSR RI now we have r1 and r13 back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+
+ /* Save away checkpinted SPRs. */
+ std r31, VCPU_PPR_TM(r9)
+ std r30, VCPU_DSCR_TM(r9)
+ mflr r5
+ mfcr r6
+ mfctr r7
+ mfspr r8, SPRN_AMR
+ mfspr r10, SPRN_TAR
+ mfxer r11
+ std r5, VCPU_LR_TM(r9)
+ stw r6, VCPU_CR_TM(r9)
+ std r7, VCPU_CTR_TM(r9)
+ std r8, VCPU_AMR_TM(r9)
+ std r10, VCPU_TAR_TM(r9)
+ std r11, VCPU_XER_TM(r9)
+
+ /* Restore r12 as trap number. */
+ lwz r12, VCPU_TRAP(r9)
+
+ /* Save FP/VSX. */
+ addi r3, r9, VCPU_FPRS_TM
+ bl store_fp_state
+ addi r3, r9, VCPU_VRS_TM
+ bl store_vr_state
+ mfspr r6, SPRN_VRSAVE
+ stw r6, VCPU_VRSAVE_TM(r9)
+1:
+ /*
+ * We need to save these SPRs after the treclaim so that the software
+ * error code is recorded correctly in the TEXASR. Also the user may
+ * change these outside of a transaction, so they must always be
+ * context switched.
+ */
+ mfspr r7, SPRN_TEXASR
+ std r7, VCPU_TEXASR(r9)
+11:
+ mfspr r5, SPRN_TFHAR
+ mfspr r6, SPRN_TFIAR
+ std r5, VCPU_TFHAR(r9)
+ std r6, VCPU_TFIAR(r9)
+
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+
+/*
+ * _kvmppc_save_tm_pr() is a wrapper around __kvmppc_save_tm(), so that it can
+ * be invoked from C function by PR KVM only.
+ */
+_GLOBAL(_kvmppc_save_tm_pr)
+ mflr r5
+ std r5, PPC_LR_STKOFF(r1)
+ stdu r1, -SWITCH_FRAME_SIZE(r1)
+ SAVE_NVGPRS(r1)
+
+ /* save MSR since TM/math bits might be impacted
+ * by __kvmppc_save_tm().
+ */
+ mfmsr r5
+ SAVE_GPR(5, r1)
+
+ /* also save DSCR/CR/TAR so that it can be recovered later */
+ mfspr r6, SPRN_DSCR
+ SAVE_GPR(6, r1)
+
+ mfcr r7
+ stw r7, _CCR(r1)
+
+ mfspr r8, SPRN_TAR
+ SAVE_GPR(8, r1)
+
+ bl __kvmppc_save_tm
+
+ REST_GPR(8, r1)
+ mtspr SPRN_TAR, r8
+
+ ld r7, _CCR(r1)
+ mtcr r7
+
+ REST_GPR(6, r1)
+ mtspr SPRN_DSCR, r6
+
+ /* need preserve current MSR's MSR_TS bits */
+ REST_GPR(5, r1)
+ mfmsr r6
+ rldicl r6, r6, 64 - MSR_TS_S_LG, 62
+ rldimi r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+ mtmsrd r5
+
+ REST_NVGPRS(r1)
+ addi r1, r1, SWITCH_FRAME_SIZE
+ ld r5, PPC_LR_STKOFF(r1)
+ mtlr r5
+ blr
+
+EXPORT_SYMBOL_GPL(_kvmppc_save_tm_pr);
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with:
+ * - r3 pointing to the vcpu struct.
+ * - r4 is the guest MSR with desired TS bits:
+ * For HV KVM, it is VCPU_MSR
+ * For PR KVM, it is provided by caller
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2 from the PACA.
+ */
+_GLOBAL(__kvmppc_restore_tm)
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM/FP/VSX/VMX so we can restore them. */
+ mfmsr r5
+ li r6, MSR_TM >> 32
+ sldi r6, r6, 32
+ or r5, r5, r6
+ ori r5, r5, MSR_FP
+ oris r5, r5, (MSR_VEC | MSR_VSX)@h
+ mtmsrd r5
+
+ /*
+ * The user may change these outside of a transaction, so they must
+ * always be context switched.
+ */
+ ld r5, VCPU_TFHAR(r3)
+ ld r6, VCPU_TFIAR(r3)
+ ld r7, VCPU_TEXASR(r3)
+ mtspr SPRN_TFHAR, r5
+ mtspr SPRN_TFIAR, r6
+ mtspr SPRN_TEXASR, r7
+
+ mr r5, r4
+ rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ beqlr /* TM not active in guest */
+ std r1, HSTATE_SCRATCH2(r13)
+
+ /* Make sure the failure summary is set, otherwise we'll program check
+ * when we trechkpt. It's possible that this might have been not set
+ * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+ * host.
+ */
+ oris r7, r7, (TEXASR_FS)@h
+ mtspr SPRN_TEXASR, r7
+
+ /*
+ * We need to load up the checkpointed state for the guest.
+ * We need to do this early as it will blow away any GPRs, VSRs and
+ * some SPRs.
+ */
+
+ mr r31, r3
+ addi r3, r31, VCPU_FPRS_TM
+ bl load_fp_state
+ addi r3, r31, VCPU_VRS_TM
+ bl load_vr_state
+ mr r3, r31
+ lwz r7, VCPU_VRSAVE_TM(r3)
+ mtspr SPRN_VRSAVE, r7
+
+ ld r5, VCPU_LR_TM(r3)
+ lwz r6, VCPU_CR_TM(r3)
+ ld r7, VCPU_CTR_TM(r3)
+ ld r8, VCPU_AMR_TM(r3)
+ ld r9, VCPU_TAR_TM(r3)
+ ld r10, VCPU_XER_TM(r3)
+ mtlr r5
+ mtcr r6
+ mtctr r7
+ mtspr SPRN_AMR, r8
+ mtspr SPRN_TAR, r9
+ mtxer r10
+
+ /*
+ * Load up PPR and DSCR values but don't put them in the actual SPRs
+ * till the last moment to avoid running with userspace PPR and DSCR for
+ * too long.
+ */
+ ld r29, VCPU_DSCR_TM(r3)
+ ld r30, VCPU_PPR_TM(r3)
+
+ std r2, PACATMSCRATCH(r13) /* Save TOC */
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /* Load GPRs r0-r28 */
+ reg = 0
+ .rept 29
+ ld reg, VCPU_GPRS_TM(reg)(r31)
+ reg = reg + 1
+ .endr
+
+ mtspr SPRN_DSCR, r29
+ mtspr SPRN_PPR, r30
+
+ /* Load final GPRs */
+ ld 29, VCPU_GPRS_TM(29)(r31)
+ ld 30, VCPU_GPRS_TM(30)(r31)
+ ld 31, VCPU_GPRS_TM(31)(r31)
+
+ /* TM checkpointed state is now setup. All GPRs are now volatile. */
+ TRECHKPT
+
+ /* Now let's get back the state we need. */
+ HMT_MEDIUM
+ GET_PACA(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+#endif
+ ld r1, HSTATE_SCRATCH2(r13)
+ ld r2, PACATMSCRATCH(r13)
+
+ /* Set the MSR RI since we have our registers back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+
+/*
+ * _kvmppc_restore_tm_pr() is a wrapper around __kvmppc_restore_tm(), so that it
+ * can be invoked from C function by PR KVM only.
+ */
+_GLOBAL(_kvmppc_restore_tm_pr)
+ mflr r5
+ std r5, PPC_LR_STKOFF(r1)
+ stdu r1, -SWITCH_FRAME_SIZE(r1)
+ SAVE_NVGPRS(r1)
+
+ /* save MSR to avoid TM/math bits change */
+ mfmsr r5
+ SAVE_GPR(5, r1)
+
+ /* also save DSCR/CR/TAR so that it can be recovered later */
+ mfspr r6, SPRN_DSCR
+ SAVE_GPR(6, r1)
+
+ mfcr r7
+ stw r7, _CCR(r1)
+
+ mfspr r8, SPRN_TAR
+ SAVE_GPR(8, r1)
+
+ bl __kvmppc_restore_tm
+
+ REST_GPR(8, r1)
+ mtspr SPRN_TAR, r8
+
+ ld r7, _CCR(r1)
+ mtcr r7
+
+ REST_GPR(6, r1)
+ mtspr SPRN_DSCR, r6
+
+ /* need preserve current MSR's MSR_TS bits */
+ REST_GPR(5, r1)
+ mfmsr r6
+ rldicl r6, r6, 64 - MSR_TS_S_LG, 62
+ rldimi r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+ mtmsrd r5
+
+ REST_NVGPRS(r1)
+ addi r1, r1, SWITCH_FRAME_SIZE
+ ld r5, PPC_LR_STKOFF(r1)
+ mtlr r5
+ blr
+
+EXPORT_SYMBOL_GPL(_kvmppc_restore_tm_pr);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
else
- pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+ pgtable_free_tlb(tlb, hugepte,
+ get_hugepd_cache_index(pdshift - shift));
}
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
/* Place all memblock_regions in the same node and merge contiguous
* memblock_regions
*/
- memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
}
void __init initmem_init(void)
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
static DEFINE_MUTEX(mem_list_mutex);
struct rcu_head rcu;
unsigned long used;
atomic64_t mapped;
+ unsigned int pageshift;
u64 ua; /* userspace address */
u64 entries; /* number of entries in hpas[] */
u64 *hpas; /* vmalloc'ed */
{
struct mm_iommu_table_group_mem_t *mem;
long i, j, ret = 0, locked_entries = 0;
+ unsigned int pageshift;
+ unsigned long flags;
struct page *page = NULL;
mutex_lock(&mem_list_mutex);
goto unlock_exit;
}
+ /*
+ * For a starting point for a maximum page size calculation
+ * we use @ua and @entries natural alignment to allow IOMMU pages
+ * smaller than huge pages but still bigger than PAGE_SIZE.
+ */
+ mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
if (!mem->hpas) {
kfree(mem);
}
}
populate:
+ pageshift = PAGE_SHIFT;
+ if (PageCompound(page)) {
+ pte_t *pte;
+ struct page *head = compound_head(page);
+ unsigned int compshift = compound_order(head);
+
+ local_irq_save(flags); /* disables as well */
+ pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+ local_irq_restore(flags);
+
+ /* Double check it is still the same pinned page */
+ if (pte && pte_page(*pte) == head &&
+ pageshift == compshift)
+ pageshift = max_t(unsigned int, pageshift,
+ PAGE_SHIFT);
+ }
+ mem->pageshift = min(mem->pageshift, pageshift);
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
EXPORT_SYMBOL_GPL(mm_iommu_find);
long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa)
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
const long entry = (ua - mem->ua) >> PAGE_SHIFT;
u64 *va = &mem->hpas[entry];
if (entry >= mem->entries)
return -EFAULT;
+ if (pageshift > mem->pageshift)
+ return -EFAULT;
+
*hpa = *va | (ua & ~PAGE_MASK);
return 0;
EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa)
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
const long entry = (ua - mem->ua) >> PAGE_SHIFT;
void *va = &mem->hpas[entry];
if (entry >= mem->entries)
return -EFAULT;
+ if (pageshift > mem->pageshift)
+ return -EFAULT;
+
pa = (void *) vmalloc_to_phys(va);
if (!pa)
return -EFAULT;
case PUD_INDEX:
kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
break;
+#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
+ /* 16M hugepd directory at pud level */
+ case HTLB_16M_INDEX:
+ BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
+ kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
+ break;
+ /* 16G hugepd directory at the pgd level */
+ case HTLB_16G_INDEX:
+ BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
+ kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
+ break;
+#endif
/* We don't free pgd table via RCU callback */
default:
BUG();
* in a 2-bit field won't allow writes to a page that is otherwise
* write-protected.
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(subpage_prot, unsigned long, addr,
unsigned long, len, u32 __user *, map)
{
up_write(&mm->mmap_sem);
return err;
}
-#pragma GCC diagnostic pop
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
-void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
+static inline void __radix__flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool flush_all_sizes)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned long pid;
unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
unsigned long page_size = 1UL << page_shift;
unsigned long nr_pages = (end - start) >> page_shift;
bool local, full;
-#ifdef CONFIG_HUGETLB_PAGE
- if (is_vm_hugetlb_page(vma))
- return radix__flush_hugetlb_tlb_range(vma, start, end);
-#endif
-
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
return;
_tlbie_pid(pid, RIC_FLUSH_TLB);
}
} else {
- bool hflush = false;
+ bool hflush = flush_all_sizes;
+ bool gflush = flush_all_sizes;
unsigned long hstart, hend;
+ unsigned long gstart, gend;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT;
- hend = end >> HPAGE_PMD_SHIFT;
- if (hstart < hend) {
- hstart <<= HPAGE_PMD_SHIFT;
- hend <<= HPAGE_PMD_SHIFT;
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
hflush = true;
+
+ if (hflush) {
+ hstart = (start + PMD_SIZE - 1) & PMD_MASK;
+ hend = end & PMD_MASK;
+ if (hstart == hend)
+ hflush = false;
+ }
+
+ if (gflush) {
+ gstart = (start + PUD_SIZE - 1) & PUD_MASK;
+ gend = end & PUD_MASK;
+ if (gstart == gend)
+ gflush = false;
}
-#endif
asm volatile("ptesync": : :"memory");
if (local) {
__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbiel_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbiel_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
asm volatile("ptesync": : :"memory");
} else {
__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbie_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbie_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
}
preempt_enable();
}
+
+void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ if (is_vm_hugetlb_page(vma))
+ return radix__flush_hugetlb_tlb_range(vma, start, end);
+#endif
+
+ __radix__flush_tlb_range(vma->vm_mm, start, end, false);
+}
EXPORT_SYMBOL(radix__flush_tlb_range);
static int radix_get_mmu_psize(int page_size)
int psize = 0;
struct mm_struct *mm = tlb->mm;
int page_size = tlb->page_size;
+ unsigned long start = tlb->start;
+ unsigned long end = tlb->end;
/*
* if page size is not something we understand, do a full mm flush
*/
if (tlb->fullmm) {
__flush_all_mm(mm, true);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+ } else if (mm_tlb_flush_nested(mm)) {
+ /*
+ * If there is a concurrent invalidation that is clearing ptes,
+ * then it's possible this invalidation will miss one of those
+ * cleared ptes and miss flushing the TLB. If this invalidate
+ * returns before the other one flushes TLBs, that can result
+ * in it returning while there are still valid TLBs inside the
+ * range to be invalidated.
+ *
+ * See mm/memory.c:tlb_finish_mmu() for more details.
+ *
+ * The solution to this is ensure the entire range is always
+ * flushed here. The problem for powerpc is that the flushes
+ * are page size specific, so this "forced flush" would not
+ * do the right thing if there are a mix of page sizes in
+ * the range to be invalidated. So use __flush_tlb_range
+ * which invalidates all possible page sizes in the range.
+ *
+ * PWC flush probably is not be required because the core code
+ * shouldn't free page tables in this path, but accounting
+ * for the possibility makes us a bit more robust.
+ *
+ * need_flush_all is an uncommon case because page table
+ * teardown should be done with exclusive locks held (but
+ * after locks are dropped another invalidate could come
+ * in), it could be optimized further if necessary.
+ */
+ if (!tlb->need_flush_all)
+ __radix__flush_tlb_range(mm, start, end, true);
+ else
+ radix__flush_all_mm(mm);
+#endif
} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
if (!tlb->need_flush_all)
radix__flush_tlb_mm(mm);
else
radix__flush_all_mm(mm);
} else {
- unsigned long start = tlb->start;
- unsigned long end = tlb->end;
-
if (!tlb->need_flush_all)
radix__flush_tlb_range_psize(mm, start, end, psize);
else
for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
if (sib == cpu)
continue;
+ if (!cpu_possible(sib))
+ continue;
if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
flush = true;
}
u64 imm64;
u8 *func;
u32 true_cond;
+ u32 tmp_idx;
/*
* addrs[] maps a BPF bytecode address into a real offset from
case BPF_STX | BPF_XADD | BPF_W:
/* Get EA into TMP_REG_1 */
PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
- /* error if EA is not word-aligned */
- PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
- PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
- PPC_LI(b2p[BPF_REG_0], 0);
- PPC_JMP(exit_addr);
+ tmp_idx = ctx->idx * 4;
/* load value from memory into TMP_REG_2 */
PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
/* add value from src_reg into this */
/* store result back */
PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
/* we're done if this succeeded */
- PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
- /* otherwise, let's try once more */
- PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
- PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
- PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
- /* exit if the store was not successful */
- PPC_LI(b2p[BPF_REG_0], 0);
- PPC_BCC(COND_NE, exit_addr);
+ PPC_BCC_SHORT(COND_NE, tmp_idx);
break;
/* *(u64 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_DW:
PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
- /* error if EA is not doubleword-aligned */
- PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
- PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
- PPC_LI(b2p[BPF_REG_0], 0);
- PPC_JMP(exit_addr);
- PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
- PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
- PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
- PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+ tmp_idx = ctx->idx * 4;
PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
- PPC_LI(b2p[BPF_REG_0], 0);
- PPC_BCC(COND_NE, exit_addr);
+ PPC_BCC_SHORT(COND_NE, tmp_idx);
break;
/*
}
/*
- * Add a event to the PMU.
+ * Add an event to the PMU.
* If all events are not already frozen, then we disable and
* re-enable the PMU in order to get hw_perf_enable to do the
* actual work of reconfiguring the PMU.
}
/*
- * Remove a event from the PMU.
+ * Remove an event from the PMU.
*/
static void power_pmu_del(struct perf_event *event, int ef_flags)
{
/*
* Return 1 if we might be able to put event on a limited PMC,
* or 0 if not.
- * A event can only go on a limited PMC if it counts something
+ * An event can only go on a limited PMC if it counts something
* that a limited PMC can count, doesn't require interrupts, and
* doesn't exclude any processor mode.
*/
#define DBG(x...)
#endif
-/* Apparently the RTC stores seconds since 1 Jan 1904 */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
#define RTC_OFFSET 2082844800
/*
if (req.reply_len != 7)
printk(KERN_ERR "cuda_get_time: got %d byte reply\n",
req.reply_len);
- now = (req.reply[3] << 24) + (req.reply[4] << 16)
- + (req.reply[5] << 8) + req.reply[6];
+ now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) +
+ (req.reply[5] << 8) + req.reply[6]);
+ /* it's either after year 2040, or the RTC has gone backwards */
+ WARN_ON(now < RTC_OFFSET);
+
return now - RTC_OFFSET;
}
static int cuda_set_rtc_time(struct rtc_time *tm)
{
- time64_t nowtime;
+ u32 nowtime;
struct adb_request req;
- nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+ nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
nowtime >> 24, nowtime >> 16, nowtime >> 8,
nowtime) < 0)
if (req.reply_len != 4)
printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n",
req.reply_len);
- now = (req.reply[0] << 24) + (req.reply[1] << 16)
- + (req.reply[2] << 8) + req.reply[3];
+ now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16) +
+ (req.reply[2] << 8) + req.reply[3]);
+
+ /* it's either after year 2040, or the RTC has gone backwards */
+ WARN_ON(now < RTC_OFFSET);
+
return now - RTC_OFFSET;
}
static int pmu_set_rtc_time(struct rtc_time *tm)
{
- time64_t nowtime;
+ u32 nowtime;
struct adb_request req;
- nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+ nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24,
nowtime >> 16, nowtime >> 8, nowtime) < 0)
return -ENXIO;
#include "powernv.h"
#include "pci.h"
+#include "../../../../drivers/pci/pci.h"
#define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */
#define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */
struct pci_dn *pdn;
int mul, total_vfs;
- if (!pdev->is_physfn || pdev->is_added)
+ if (!pdev->is_physfn || pci_dev_is_added(pdev))
return;
pdn = pci_get_pdn(pdev);
#include <asm/security_features.h>
#include "pseries.h"
+#include "../../../../drivers/pci/pci.h"
int CMO_PrPSP = -1;
int CMO_SecPSP = -1;
const int *indexes;
struct device_node *dn = pci_device_to_OF_node(pdev);
- if (!pdev->is_physfn || pdev->is_added)
+ if (!pdev->is_physfn || pci_dev_is_added(pdev))
return;
/*Firmware must support open sriov otherwise dont configure*/
indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
{
int nr, dotted;
unsigned long first_adr;
- unsigned long inst, last_inst = 0;
+ unsigned int inst, last_inst = 0;
unsigned char val[4];
dotted = 0;
dotted = 0;
last_inst = inst;
if (praddr)
- printf(REG" %.8lx", adr, inst);
+ printf(REG" %.8x", adr, inst);
printf("\t");
dump_func(inst, adr);
printf("\n");
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_DMA_CONTIGUOUS
select HAVE_GENERIC_DMA_COHERENT
+ select HAVE_PERF_EVENTS
select IRQ_DOMAIN
select NO_BOOTMEM
select RISCV_ISA_A if SMP
select GENERIC_LIB_ASHLDI3
select GENERIC_LIB_ASHRDI3
select GENERIC_LIB_LSHRDI3
+ select GENERIC_LIB_UCMPDI2
config ARCH_RV64I
bool "RV64I"
config RISCV_ISA_A
def_bool y
+menu "supported PMU type"
+ depends on PERF_EVENTS
+
+config RISCV_BASE_PMU
+ bool "Base Performance Monitoring Unit"
+ def_bool y
+ help
+ A base PMU that serves as a reference implementation and has limited
+ feature of perf. It can run on any RISC-V machines so serves as the
+ fallback, but this option can also be disable to reduce kernel size.
+
+endmenu
+
endmenu
menu "Kernel type"
# architectures. It's faster to have GCC emit only aligned accesses.
KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+# arch specific predefines for sparse
+CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS)
+
head-y := arch/riscv/kernel/head.o
core-y += arch/riscv/kernel/ arch/riscv/mm/
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_HVC_RISCV_SBI=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_DRM=y
CONFIG_DRM_RADEON=y
generic-y += kmap_types.h
generic-y += kvm_para.h
generic-y += local.h
+generic-y += local64.h
generic-y += mm-arch-hooks.h
generic-y += mman.h
generic-y += module.h
#define ATOMIC_INIT(i) { (i) }
-#define __atomic_op_acquire(op, args...) \
-({ \
- typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \
- __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \
- __ret; \
-})
-
-#define __atomic_op_release(op, args...) \
-({ \
- __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \
- op##_relaxed(args); \
-})
+#define __atomic_acquire_fence() \
+ __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence() \
+ __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
static __always_inline int atomic_read(const atomic_t *v)
{
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
-/*
- * The extra atomic operations that are constructed from one of the core
- * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a full barrier, but they're OK this way
- * because atomic_*_return is also required to perform a full barrier.
- *
- */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \
-static __always_inline \
-bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_##func_op##_return(i, v) comp_op I; \
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I) \
- ATOMIC_OP(op, func_op, comp_op, I, int, )
-#else
-#define ATOMIC_OPS(op, func_op, comp_op, I) \
- ATOMIC_OP(op, func_op, comp_op, I, int, ) \
- ATOMIC_OP(op, func_op, comp_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(add_and_test, add, ==, 0)
-ATOMIC_OPS(sub_and_test, sub, ==, 0)
-ATOMIC_OPS(add_negative, add, <, 0)
-
-#undef ATOMIC_OP
-#undef ATOMIC_OPS
-
-#define ATOMIC_OP(op, func_op, I, c_type, prefix) \
-static __always_inline \
-void atomic##prefix##_##op(atomic##prefix##_t *v) \
-{ \
- atomic##prefix##_##func_op(I, v); \
-}
-
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \
-static __always_inline \
-c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \
-} \
-static __always_inline \
-c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_fetch_##func_op(I, v); \
-}
-
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \
-static __always_inline \
-c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \
-} \
-static __always_inline \
-c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_fetch_##op(v) c_op I; \
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP( op, asm_op, I, int, ) \
- ATOMIC_FETCH_OP( op, asm_op, I, int, ) \
- ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, )
-#else
-#define ATOMIC_OPS(op, asm_op, c_op, I) \
- ATOMIC_OP( op, asm_op, I, int, ) \
- ATOMIC_FETCH_OP( op, asm_op, I, int, ) \
- ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \
- ATOMIC_OP( op, asm_op, I, long, 64) \
- ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \
- ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(inc, add, +, 1)
-ATOMIC_OPS(dec, add, +, -1)
-
-#define atomic_inc_return_relaxed atomic_inc_return_relaxed
-#define atomic_dec_return_relaxed atomic_dec_return_relaxed
-#define atomic_inc_return atomic_inc_return
-#define atomic_dec_return atomic_dec_return
-
-#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed
-#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed
-#define atomic_fetch_inc atomic_fetch_inc
-#define atomic_fetch_dec atomic_fetch_dec
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
-#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
-#define atomic64_inc_return atomic64_inc_return
-#define atomic64_dec_return atomic64_dec_return
-
-#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed
-#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed
-#define atomic64_fetch_inc atomic64_fetch_inc
-#define atomic64_fetch_dec atomic64_fetch_dec
-#endif
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \
-static __always_inline \
-bool atomic##prefix##_##op(atomic##prefix##_t *v) \
-{ \
- return atomic##prefix##_##func_op##_return(v) comp_op I; \
-}
-
-ATOMIC_OP(inc_and_test, inc, ==, 0, )
-ATOMIC_OP(dec_and_test, dec, ==, 0, )
-#ifndef CONFIG_GENERIC_ATOMIC64
-ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
-ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
-#endif
-
-#undef ATOMIC_OP
-
/* This is required to provide a full barrier on success. */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int prev, rc;
: "memory");
return prev;
}
+#define atomic_fetch_add_unless atomic_fetch_add_unless
#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
+static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
{
long prev, rc;
: "memory");
return prev;
}
-
-static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- return __atomic64_add_unless(v, a, u) != u;
-}
-#endif
-
-/*
- * The extra atomic operations that are constructed from one of the core
- * LR/SC-based operations above.
- */
-static __always_inline int atomic_inc_not_zero(atomic_t *v)
-{
- return __atomic_add_unless(v, 1, 0);
-}
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
-{
- return atomic64_add_unless(v, 1, 0);
-}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
#endif
/*
#else /* CONFIG_SMP */
-#define flush_icache_all() sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(NULL)
void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 SiFive
+ * Copyright (C) 2018 Andes Technology Corporation
+ *
+ */
+
+#ifndef _ASM_RISCV_PERF_EVENT_H
+#define _ASM_RISCV_PERF_EVENT_H
+
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+
+#define RISCV_BASE_COUNTERS 2
+
+/*
+ * The RISCV_MAX_COUNTERS parameter should be specified.
+ */
+
+#ifdef CONFIG_RISCV_BASE_PMU
+#define RISCV_MAX_COUNTERS 2
+#endif
+
+#ifndef RISCV_MAX_COUNTERS
+#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU."
+#endif
+
+/*
+ * These are the indexes of bits in counteren register *minus* 1,
+ * except for cycle. It would be coherent if it can directly mapped
+ * to counteren bit definition, but there is a *time* register at
+ * counteren[1]. Per-cpu structure is scarce resource here.
+ *
+ * According to the spec, an implementation can support counter up to
+ * mhpmcounter31, but many high-end processors has at most 6 general
+ * PMCs, we give the definition to MHPMCOUNTER8 here.
+ */
+#define RISCV_PMU_CYCLE 0
+#define RISCV_PMU_INSTRET 1
+#define RISCV_PMU_MHPMCOUNTER3 2
+#define RISCV_PMU_MHPMCOUNTER4 3
+#define RISCV_PMU_MHPMCOUNTER5 4
+#define RISCV_PMU_MHPMCOUNTER6 5
+#define RISCV_PMU_MHPMCOUNTER7 6
+#define RISCV_PMU_MHPMCOUNTER8 7
+
+#define RISCV_OP_UNSUPP (-EOPNOTSUPP)
+
+struct cpu_hw_events {
+ /* # currently enabled events*/
+ int n_events;
+ /* currently enabled events */
+ struct perf_event *events[RISCV_MAX_COUNTERS];
+ /* vendor-defined PMU data */
+ void *platform;
+};
+
+struct riscv_pmu {
+ struct pmu *pmu;
+
+ /* generic hw/cache events table */
+ const int *hw_events;
+ const int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX];
+ /* method used to map hw/cache events */
+ int (*map_hw_event)(u64 config);
+ int (*map_cache_event)(u64 config);
+
+ /* max generic hw events in map */
+ int max_events;
+ /* number total counters, 2(base) + x(general) */
+ int num_counters;
+ /* the width of the counter */
+ int counter_width;
+
+ /* vendor-defined PMU features */
+ void *platform;
+
+ irqreturn_t (*handle_irq)(int irq_num, void *dev);
+ int irq;
+};
+
+#endif /* _ASM_RISCV_PERF_EVENT_H */
#include <asm/sbi.h>
-#define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
+#define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
#define flush_tlb_range(vma, start, end) \
sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \
})
-extern unsigned long __must_check __copy_user(void __user *to,
+extern unsigned long __must_check __asm_copy_to_user(void __user *to,
+ const void *from, unsigned long n);
+extern unsigned long __must_check __asm_copy_from_user(void *to,
const void __user *from, unsigned long n);
static inline unsigned long
raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- return __copy_user(to, from, n);
+ return __asm_copy_to_user(to, from, n);
}
static inline unsigned long
raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- return __copy_user(to, from, n);
+ return __asm_copy_from_user(to, from, n);
}
extern long strncpy_from_user(char *dest, const char __user *src, long count);
typedef union __riscv_fp_state elf_fpregset_t;
-#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
-#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+#if __riscv_xlen == 64
+#define ELF_RISCV_R_SYM(r_info) ELF64_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info) ELF64_R_TYPE(r_info)
+#else
+#define ELF_RISCV_R_SYM(r_info) ELF32_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info) ELF32_R_TYPE(r_info)
+#endif
/*
* RISC-V relocation types
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o
obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+
clean:
#include <linux/irqchip.h>
#include <linux/irqdomain.h>
-#ifdef CONFIG_RISCV_INTC
-#include <linux/irqchip/irq-riscv-intc.h>
-#endif
-
void __init init_IRQ(void)
{
irqchip_init();
RESTORE_ABI_STATE
ret
ENDPROC(_mcount)
-EXPORT_SYMBOL(_mcount)
#endif
+EXPORT_SYMBOL(_mcount)
#include <linux/errno.h>
#include <linux/moduleloader.h>
+static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+ if (v != (u32)v) {
+ pr_err("%s: value %016llx out of range for 32-bit field\n",
+ me->name, v);
+ return -EINVAL;
+ }
+ *location = v;
+ return 0;
+}
+
static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
{
*(u64 *)location = v;
static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u32 imm12 = (offset & 0x1000) << (31 - 12);
u32 imm11 = (offset & 0x800) >> (11 - 7);
u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u32 imm20 = (offset & 0x100000) << (31 - 20);
u32 imm19_12 = (offset & 0xff000);
u32 imm11 = (offset & 0x800) << (20 - 11);
static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u16 imm8 = (offset & 0x100) << (12 - 8);
u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
u16 imm5 = (offset & 0x20) >> (5 - 2);
static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u16 imm11 = (offset & 0x800) << (12 - 11);
u16 imm10 = (offset & 0x400) >> (10 - 8);
u16 imm9_8 = (offset & 0x300) << (12 - 11);
static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 hi20;
if (offset != (s32)offset) {
static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 hi20;
/* Always emit the got entry */
static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 fill_v = offset;
u32 hi20, lo12;
static int apply_r_riscv_call_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 fill_v = offset;
u32 hi20, lo12;
static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- *(u32 *)location += (*(u32 *)v);
+ *(u32 *)location += (u32)v;
return 0;
}
static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- *(u32 *)location -= (*(u32 *)v);
+ *(u32 *)location -= (u32)v;
return 0;
}
static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
Elf_Addr v) = {
+ [R_RISCV_32] = apply_r_riscv_32_rela,
[R_RISCV_64] = apply_r_riscv_64_rela,
[R_RISCV_BRANCH] = apply_r_riscv_branch_rela,
[R_RISCV_JAL] = apply_r_riscv_jal_rela,
unsigned int j;
for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
- u64 hi20_loc =
+ unsigned long hi20_loc =
sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rel[j].r_offset;
u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
Elf_Sym *hi20_sym =
(Elf_Sym *)sechdrs[symindex].sh_addr
+ ELF_RISCV_R_SYM(rel[j].r_info);
- u64 hi20_sym_val =
+ unsigned long hi20_sym_val =
hi20_sym->st_value
+ rel[j].r_addend;
/* Calculate lo12 */
- u64 offset = hi20_sym_val - hi20_loc;
+ size_t offset = hi20_sym_val - hi20_loc;
if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
&& hi20_type == R_RISCV_GOT_HI20) {
offset = module_emit_got_entry(
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ * Copyright (C) 2009 Jaswinder Singh Rajput
+ * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
+ * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
+ * Copyright (C) 2009 Google, Inc., Stephane Eranian
+ * Copyright 2014 Tilera Corporation. All Rights Reserved.
+ * Copyright (C) 2018 Andes Technology Corporation
+ *
+ * Perf_events support for RISC-V platforms.
+ *
+ * Since the spec. (as of now, Priv-Spec 1.10) does not provide enough
+ * functionality for perf event to fully work, this file provides
+ * the very basic framework only.
+ *
+ * For platform portings, please check Documentations/riscv/pmu.txt.
+ *
+ * The Copyright line includes x86 and tile ones.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/kernel.h>
+#include <linux/kdebug.h>
+#include <linux/mutex.h>
+#include <linux/bitmap.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/atomic.h>
+#include <linux/of.h>
+#include <asm/perf_event.h>
+
+static const struct riscv_pmu *riscv_pmu __read_mostly;
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+/*
+ * Hardware & cache maps and their methods
+ */
+
+static const int riscv_hw_event_map[] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = RISCV_PMU_CYCLE,
+ [PERF_COUNT_HW_INSTRUCTIONS] = RISCV_PMU_INSTRET,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = RISCV_OP_UNSUPP,
+ [PERF_COUNT_HW_CACHE_MISSES] = RISCV_OP_UNSUPP,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = RISCV_OP_UNSUPP,
+ [PERF_COUNT_HW_BRANCH_MISSES] = RISCV_OP_UNSUPP,
+ [PERF_COUNT_HW_BUS_CYCLES] = RISCV_OP_UNSUPP,
+};
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+static const int riscv_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
+[PERF_COUNT_HW_CACHE_OP_MAX]
+[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+ [C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+ },
+ },
+};
+
+static int riscv_map_hw_event(u64 config)
+{
+ if (config >= riscv_pmu->max_events)
+ return -EINVAL;
+
+ return riscv_pmu->hw_events[config];
+}
+
+int riscv_map_cache_decode(u64 config, unsigned int *type,
+ unsigned int *op, unsigned int *result)
+{
+ return -ENOENT;
+}
+
+static int riscv_map_cache_event(u64 config)
+{
+ unsigned int type, op, result;
+ int err = -ENOENT;
+ int code;
+
+ err = riscv_map_cache_decode(config, &type, &op, &result);
+ if (!riscv_pmu->cache_events || err)
+ return err;
+
+ if (type >= PERF_COUNT_HW_CACHE_MAX ||
+ op >= PERF_COUNT_HW_CACHE_OP_MAX ||
+ result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+ return -EINVAL;
+
+ code = (*riscv_pmu->cache_events)[type][op][result];
+ if (code == RISCV_OP_UNSUPP)
+ return -EINVAL;
+
+ return code;
+}
+
+/*
+ * Low-level functions: reading/writing counters
+ */
+
+static inline u64 read_counter(int idx)
+{
+ u64 val = 0;
+
+ switch (idx) {
+ case RISCV_PMU_CYCLE:
+ val = csr_read(cycle);
+ break;
+ case RISCV_PMU_INSTRET:
+ val = csr_read(instret);
+ break;
+ default:
+ WARN_ON_ONCE(idx < 0 || idx > RISCV_MAX_COUNTERS);
+ return -EINVAL;
+ }
+
+ return val;
+}
+
+static inline void write_counter(int idx, u64 value)
+{
+ /* currently not supported */
+ WARN_ON_ONCE(1);
+}
+
+/*
+ * pmu->read: read and update the counter
+ *
+ * Other architectures' implementation often have a xxx_perf_event_update
+ * routine, which can return counter values when called in the IRQ, but
+ * return void when being called by the pmu->read method.
+ */
+static void riscv_pmu_read(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 prev_raw_count, new_raw_count;
+ u64 oldval;
+ int idx = hwc->idx;
+ u64 delta;
+
+ do {
+ prev_raw_count = local64_read(&hwc->prev_count);
+ new_raw_count = read_counter(idx);
+
+ oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ new_raw_count);
+ } while (oldval != prev_raw_count);
+
+ /*
+ * delta is the value to update the counter we maintain in the kernel.
+ */
+ delta = (new_raw_count - prev_raw_count) &
+ ((1ULL << riscv_pmu->counter_width) - 1);
+ local64_add(delta, &event->count);
+ /*
+ * Something like local64_sub(delta, &hwc->period_left) here is
+ * needed if there is an interrupt for perf.
+ */
+}
+
+/*
+ * State transition functions:
+ *
+ * stop()/start() & add()/del()
+ */
+
+/*
+ * pmu->stop: stop the counter
+ */
+static void riscv_pmu_stop(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+
+ if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ riscv_pmu->pmu->read(event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+/*
+ * pmu->start: start the event.
+ */
+static void riscv_pmu_start(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ if (flags & PERF_EF_RELOAD) {
+ WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+ /*
+ * Set the counter to the period to the next interrupt here,
+ * if you have any.
+ */
+ }
+
+ hwc->state = 0;
+ perf_event_update_userpage(event);
+
+ /*
+ * Since we cannot write to counters, this serves as an initialization
+ * to the delta-mechanism in pmu->read(); otherwise, the delta would be
+ * wrong when pmu->read is called for the first time.
+ */
+ local64_set(&hwc->prev_count, read_counter(hwc->idx));
+}
+
+/*
+ * pmu->add: add the event to PMU.
+ */
+static int riscv_pmu_add(struct perf_event *event, int flags)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (cpuc->n_events == riscv_pmu->num_counters)
+ return -ENOSPC;
+
+ /*
+ * We don't have general conunters, so no binding-event-to-counter
+ * process here.
+ *
+ * Indexing using hwc->config generally not works, since config may
+ * contain extra information, but here the only info we have in
+ * hwc->config is the event index.
+ */
+ hwc->idx = hwc->config;
+ cpuc->events[hwc->idx] = event;
+ cpuc->n_events++;
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+ if (flags & PERF_EF_START)
+ riscv_pmu->pmu->start(event, PERF_EF_RELOAD);
+
+ return 0;
+}
+
+/*
+ * pmu->del: delete the event from PMU.
+ */
+static void riscv_pmu_del(struct perf_event *event, int flags)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+
+ cpuc->events[hwc->idx] = NULL;
+ cpuc->n_events--;
+ riscv_pmu->pmu->stop(event, PERF_EF_UPDATE);
+ perf_event_update_userpage(event);
+}
+
+/*
+ * Interrupt: a skeletion for reference.
+ */
+
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
+{
+ return IRQ_NONE;
+}
+
+static int reserve_pmc_hardware(void)
+{
+ int err = 0;
+
+ mutex_lock(&pmc_reserve_mutex);
+ if (riscv_pmu->irq >= 0 && riscv_pmu->handle_irq) {
+ err = request_irq(riscv_pmu->irq, riscv_pmu->handle_irq,
+ IRQF_PERCPU, "riscv-base-perf", NULL);
+ }
+ mutex_unlock(&pmc_reserve_mutex);
+
+ return err;
+}
+
+void release_pmc_hardware(void)
+{
+ mutex_lock(&pmc_reserve_mutex);
+ if (riscv_pmu->irq >= 0)
+ free_irq(riscv_pmu->irq, NULL);
+ mutex_unlock(&pmc_reserve_mutex);
+}
+
+/*
+ * Event Initialization/Finalization
+ */
+
+static atomic_t riscv_active_events = ATOMIC_INIT(0);
+
+static void riscv_event_destroy(struct perf_event *event)
+{
+ if (atomic_dec_return(&riscv_active_events) == 0)
+ release_pmc_hardware();
+}
+
+static int riscv_event_init(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ struct hw_perf_event *hwc = &event->hw;
+ int err;
+ int code;
+
+ if (atomic_inc_return(&riscv_active_events) == 1) {
+ err = reserve_pmc_hardware();
+
+ if (err) {
+ pr_warn("PMC hardware not available\n");
+ atomic_dec(&riscv_active_events);
+ return -EBUSY;
+ }
+ }
+
+ switch (event->attr.type) {
+ case PERF_TYPE_HARDWARE:
+ code = riscv_pmu->map_hw_event(attr->config);
+ break;
+ case PERF_TYPE_HW_CACHE:
+ code = riscv_pmu->map_cache_event(attr->config);
+ break;
+ case PERF_TYPE_RAW:
+ return -EOPNOTSUPP;
+ default:
+ return -ENOENT;
+ }
+
+ event->destroy = riscv_event_destroy;
+ if (code < 0) {
+ event->destroy(event);
+ return code;
+ }
+
+ /*
+ * idx is set to -1 because the index of a general event should not be
+ * decided until binding to some counter in pmu->add().
+ *
+ * But since we don't have such support, later in pmu->add(), we just
+ * use hwc->config as the index instead.
+ */
+ hwc->config = code;
+ hwc->idx = -1;
+
+ return 0;
+}
+
+/*
+ * Initialization
+ */
+
+static struct pmu min_pmu = {
+ .name = "riscv-base",
+ .event_init = riscv_event_init,
+ .add = riscv_pmu_add,
+ .del = riscv_pmu_del,
+ .start = riscv_pmu_start,
+ .stop = riscv_pmu_stop,
+ .read = riscv_pmu_read,
+};
+
+static const struct riscv_pmu riscv_base_pmu = {
+ .pmu = &min_pmu,
+ .max_events = ARRAY_SIZE(riscv_hw_event_map),
+ .map_hw_event = riscv_map_hw_event,
+ .hw_events = riscv_hw_event_map,
+ .map_cache_event = riscv_map_cache_event,
+ .cache_events = &riscv_cache_event_map,
+ .counter_width = 63,
+ .num_counters = RISCV_BASE_COUNTERS + 0,
+ .handle_irq = &riscv_base_pmu_handle_irq,
+
+ /* This means this PMU has no IRQ. */
+ .irq = -1,
+};
+
+static const struct of_device_id riscv_pmu_of_ids[] = {
+ {.compatible = "riscv,base-pmu", .data = &riscv_base_pmu},
+ { /* sentinel value */ }
+};
+
+int __init init_hw_perf_events(void)
+{
+ struct device_node *node = of_find_node_by_type(NULL, "pmu");
+ const struct of_device_id *of_id;
+
+ riscv_pmu = &riscv_base_pmu;
+
+ if (node) {
+ of_id = of_match_node(riscv_pmu_of_ids, node);
+
+ if (of_id)
+ riscv_pmu = of_id->data;
+ }
+
+ perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW);
+ return 0;
+}
+arch_initcall(init_hw_perf_events);
struct pt_regs *regs;
regs = task_pt_regs(target);
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0, -1);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
return ret;
}
* Assembly functions that may be used (directly or indirectly) by modules
*/
EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(__asm_copy_to_user);
+EXPORT_SYMBOL(__asm_copy_from_user);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
riscv_fill_hwcap();
}
-static int __init riscv_device_init(void)
-{
- return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-subsys_initcall_sync(riscv_device_init);
if (pc < PAGE_OFFSET)
return 0;
- if (probe_kernel_address((bug_insn_t __user *)pc, insn))
+ if (probe_kernel_address((bug_insn_t *)pc, insn))
return 0;
return (insn == __BUG_INSN);
}
.previous
.endm
-ENTRY(__copy_user)
+ENTRY(__asm_copy_to_user)
+ENTRY(__asm_copy_from_user)
/* Enable access to user memory */
li t6, SR_SUM
addi a0, a0, 1
bltu a1, a3, 5b
j 3b
-ENDPROC(__copy_user)
+ENDPROC(__asm_copy_to_user)
+ENDPROC(__asm_copy_from_user)
ENTRY(__clear_user)
bgeu t0, t1, 2f
bltu a0, t0, 4f
1:
- fixup REG_S, zero, (a0), 10f
+ fixup REG_S, zero, (a0), 11f
addi a0, a0, SZREG
bltu a0, t1, 1b
2:
li a0, 0
ret
4: /* Edge case: unalignment */
- fixup sb, zero, (a0), 10f
+ fixup sb, zero, (a0), 11f
addi a0, a0, 1
bltu a0, t0, 4b
j 1b
5: /* Edge case: remainder */
- fixup sb, zero, (a0), 10f
+ fixup sb, zero, (a0), 11f
addi a0, a0, 1
bltu a0, a3, 5b
j 3b
.section .fixup,"ax"
.balign 4
+ /* Fixup code for __copy_user(10) and __clear_user(11) */
10:
/* Disable access to user memory */
csrs sstatus, t6
- sub a0, a3, a0
+ mv a0, a2
+ ret
+11:
+ csrs sstatus, t6
+ mv a0, a1
ret
.previous
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
+#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
- select ARCH_WANTS_UBSAN_NO_NULL
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS2
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUTEX_CMPXCHG if FUTEX
- select HAVE_GCC_PLUGINS
+ select HAVE_GCC_PLUGINS if BROKEN
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
select HAVE_KERNEL_LZMA
select HAVE_KERNEL_LZO
+ select HAVE_KERNEL_UNCOMPRESSED
select HAVE_KERNEL_XZ
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_OPROFILE
select HAVE_PERF_EVENTS
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_RSEQ
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
select MODULES_USE_ELF_RELA
LDFLAGS := -m elf64_s390
KBUILD_AFLAGS_MODULE += -fPIC
KBUILD_CFLAGS_MODULE += -fPIC
-KBUILD_CFLAGS += -m64
KBUILD_AFLAGS += -m64
+KBUILD_CFLAGS += -m64
+aflags_dwarf := -Wa,-gdwarf-2
+KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
+KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
UTS_MACHINE := s390x
STACK_SIZE := 16384
CHECKFLAGS += -D__s390__ -D__s390x__
#
cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
-# old style option for packed stacks
-ifeq ($(call cc-option-yn,-mkernel-backchain),y)
-cflags-$(CONFIG_PACK_STACK) += -mkernel-backchain -D__PACK_STACK
-aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK
-endif
-
-# new style option for packed stacks
ifeq ($(call cc-option-yn,-mpacked-stack),y)
cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK
aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK
endif
+KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
+KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
+
ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y)
cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
ifneq ($(call cc-option-yn,-mstack-size=8192),y)
endif
endif
-ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
-cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
+ifdef CONFIG_WARN_DYNAMIC_STACK
+ ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
+ KBUILD_CFLAGS += -mwarn-dynamicstack
+ KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
+ endif
endif
ifdef CONFIG_EXPOLINE
CC_FLAGS_EXPOLINE += -mindirect-branch-table
export CC_FLAGS_EXPOLINE
cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE
+ aflags-y += -DCC_USING_EXPOLINE
endif
endif
KBUILD_CFLAGS += -pipe -fno-strength-reduce -Wno-sign-compare
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables $(cfi)
KBUILD_AFLAGS += $(aflags-y) $(cfi)
+export KBUILD_AFLAGS_DECOMPRESSOR
+export KBUILD_CFLAGS_DECOMPRESSOR
OBJCOPYFLAGS := -O binary
-head-y := arch/s390/kernel/head.o
-head-y += arch/s390/kernel/head64.o
+head-y := arch/s390/kernel/head64.o
# See arch/s390/Kbuild for content of core part of the kernel
core-y += arch/s390/
syscalls := arch/s390/kernel/syscalls
tools := arch/s390/tools
-all: image bzImage
+all: bzImage
#KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
KBUILD_IMAGE := $(boot)/bzImage
install: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $@
-image bzImage: vmlinux
+bzImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
zfcpdump:
# Don't use tabs in echo arguments
define archhelp
- echo '* image - Kernel image for IPL ($(boot)/image)'
- echo '* bzImage - Compressed kernel image for IPL ($(boot)/bzImage)'
+ echo '* bzImage - Kernel image for IPL ($(boot)/bzImage)'
echo ' install - Install kernel using'
echo ' (your) ~/bin/$(INSTALLKERNEL) or'
echo ' (distribution) /sbin/$(INSTALLKERNEL) or'
appldata_timer_handler(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- unsigned int len;
- char buf[2];
+ int timer_active = appldata_timer_active;
+ int zero = 0;
+ int one = 1;
+ int rc;
+ struct ctl_table ctl_entry = {
+ .procname = ctl->procname,
+ .data = &timer_active,
+ .maxlen = sizeof(int),
+ .extra1 = &zero,
+ .extra2 = &one,
+ };
+
+ rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write)
+ return rc;
- if (!*lenp || *ppos) {
- *lenp = 0;
- return 0;
- }
- if (!write) {
- strncpy(buf, appldata_timer_active ? "1\n" : "0\n",
- ARRAY_SIZE(buf));
- len = strnlen(buf, ARRAY_SIZE(buf));
- if (len > *lenp)
- len = *lenp;
- if (copy_to_user(buffer, buf, len))
- return -EFAULT;
- goto out;
- }
- len = *lenp;
- if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
- return -EFAULT;
spin_lock(&appldata_timer_lock);
- if (buf[0] == '1')
+ if (timer_active)
__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
- else if (buf[0] == '0')
+ else
__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
spin_unlock(&appldata_timer_lock);
-out:
- *lenp = len;
- *ppos += len;
return 0;
}
appldata_interval_handler(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- unsigned int len;
- int interval;
- char buf[16];
+ int interval = appldata_interval;
+ int one = 1;
+ int rc;
+ struct ctl_table ctl_entry = {
+ .procname = ctl->procname,
+ .data = &interval,
+ .maxlen = sizeof(int),
+ .extra1 = &one,
+ };
- if (!*lenp || *ppos) {
- *lenp = 0;
- return 0;
- }
- if (!write) {
- len = sprintf(buf, "%i\n", appldata_interval);
- if (len > *lenp)
- len = *lenp;
- if (copy_to_user(buffer, buf, len))
- return -EFAULT;
- goto out;
- }
- len = *lenp;
- if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
- return -EFAULT;
- interval = 0;
- sscanf(buf, "%i", &interval);
- if (interval <= 0)
- return -EINVAL;
+ rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write)
+ return rc;
spin_lock(&appldata_timer_lock);
appldata_interval = interval;
__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
spin_unlock(&appldata_timer_lock);
-out:
- *lenp = len;
- *ppos += len;
return 0;
}
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct appldata_ops *ops = NULL, *tmp_ops;
- unsigned int len;
- int rc, found;
- char buf[2];
struct list_head *lh;
+ int rc, found;
+ int active;
+ int zero = 0;
+ int one = 1;
+ struct ctl_table ctl_entry = {
+ .data = &active,
+ .maxlen = sizeof(int),
+ .extra1 = &zero,
+ .extra2 = &one,
+ };
found = 0;
mutex_lock(&appldata_ops_mutex);
}
mutex_unlock(&appldata_ops_mutex);
- if (!*lenp || *ppos) {
- *lenp = 0;
+ active = ops->active;
+ rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write) {
module_put(ops->owner);
- return 0;
- }
- if (!write) {
- strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
- len = strnlen(buf, ARRAY_SIZE(buf));
- if (len > *lenp)
- len = *lenp;
- if (copy_to_user(buffer, buf, len)) {
- module_put(ops->owner);
- return -EFAULT;
- }
- goto out;
- }
- len = *lenp;
- if (copy_from_user(buf, buffer,
- len > sizeof(buf) ? sizeof(buf) : len)) {
- module_put(ops->owner);
- return -EFAULT;
+ return rc;
}
mutex_lock(&appldata_ops_mutex);
- if ((buf[0] == '1') && (ops->active == 0)) {
+ if (active && (ops->active == 0)) {
// protect work queue callback
if (!try_module_get(ops->owner)) {
mutex_unlock(&appldata_ops_mutex);
module_put(ops->owner);
} else
ops->active = 1;
- } else if ((buf[0] == '0') && (ops->active == 1)) {
+ } else if (!active && (ops->active == 1)) {
ops->active = 0;
rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
(unsigned long) ops->data, ops->size,
module_put(ops->owner);
}
mutex_unlock(&appldata_ops_mutex);
-out:
- *lenp = len;
- *ppos += len;
module_put(ops->owner);
return 0;
}
# Makefile for the linux s390-specific parts of the memory manager.
#
-targets := image
-targets += bzImage
-subdir- := compressed
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
-$(obj)/image: vmlinux FORCE
- $(call if_changed,objcopy)
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
+
+#
+# Use -march=z900 for als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
+#
+ifneq ($(CC_FLAGS_MARCH),-march=z900)
+AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH)
+AFLAGS_head.o += -march=z900
+AFLAGS_REMOVE_mem.o += $(CC_FLAGS_MARCH)
+AFLAGS_mem.o += -march=z900
+CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH)
+CFLAGS_als.o += -march=z900
+CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_MARCH)
+CFLAGS_sclp_early_core.o += -march=z900
+endif
+
+CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
+
+obj-y := head.o als.o ebcdic.o sclp_early_core.o mem.o
+targets := bzImage startup.a $(obj-y)
+subdir- := compressed
+
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
$(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
$(call if_changed,objcopy)
-$(obj)/compressed/vmlinux: FORCE
+$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
$(Q)$(MAKE) $(build)=$(obj)/compressed $@
+quiet_cmd_ar = AR $@
+ cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^)
+
+$(obj)/startup.a: $(OBJECTS) FORCE
+ $(call if_changed,ar)
+
install: $(CONFIGURE) $(obj)/bzImage
sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
System.map "$(INSTALL_PATH)"
+
+chkbss := $(OBJECTS)
+chkbss-target := $(obj)/startup.a
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2016
+ */
+#include <linux/kernel.h>
+#include <asm/processor.h>
+#include <asm/facility.h>
+#include <asm/lowcore.h>
+#include <asm/sclp.h>
+
+/*
+ * The code within this file will be called very early. It may _not_
+ * access anything within the bss section, since that is not cleared
+ * yet and may contain data (e.g. initrd) that must be saved by other
+ * code.
+ * For temporary objects the stack (16k) should be used.
+ */
+
+static unsigned long als[] = { FACILITIES_ALS };
+
+static void u16_to_hex(char *str, u16 val)
+{
+ int i, num;
+
+ for (i = 1; i <= 4; i++) {
+ num = (val >> (16 - 4 * i)) & 0xf;
+ if (num >= 10)
+ num += 7;
+ *str++ = '0' + num;
+ }
+ *str = '\0';
+}
+
+static void print_machine_type(void)
+{
+ static char mach_str[80] = "Detected machine-type number: ";
+ char type_str[5];
+ struct cpuid id;
+
+ get_cpu_id(&id);
+ u16_to_hex(type_str, id.machine);
+ strcat(mach_str, type_str);
+ strcat(mach_str, "\n");
+ sclp_early_printk(mach_str);
+}
+
+static void u16_to_decimal(char *str, u16 val)
+{
+ int div = 1;
+
+ while (div * 10 <= val)
+ div *= 10;
+ while (div) {
+ *str++ = '0' + val / div;
+ val %= div;
+ div /= 10;
+ }
+ *str = '\0';
+}
+
+static void print_missing_facilities(void)
+{
+ static char als_str[80] = "Missing facilities: ";
+ unsigned long val;
+ char val_str[6];
+ int i, j, first;
+
+ first = 1;
+ for (i = 0; i < ARRAY_SIZE(als); i++) {
+ val = ~S390_lowcore.stfle_fac_list[i] & als[i];
+ for (j = 0; j < BITS_PER_LONG; j++) {
+ if (!(val & (1UL << (BITS_PER_LONG - 1 - j))))
+ continue;
+ if (!first)
+ strcat(als_str, ",");
+ /*
+ * Make sure we stay within one line. Consider that
+ * each facility bit adds up to five characters and
+ * z/VM adds a four character prefix.
+ */
+ if (strlen(als_str) > 70) {
+ strcat(als_str, "\n");
+ sclp_early_printk(als_str);
+ *als_str = '\0';
+ }
+ u16_to_decimal(val_str, i * BITS_PER_LONG + j);
+ strcat(als_str, val_str);
+ first = 0;
+ }
+ }
+ strcat(als_str, "\n");
+ sclp_early_printk(als_str);
+ sclp_early_printk("See Principles of Operations for facility bits\n");
+}
+
+static void facility_mismatch(void)
+{
+ sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
+ print_machine_type();
+ print_missing_facilities();
+ disabled_wait(0x8badcccc);
+}
+
+void verify_facilities(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
+ S390_lowcore.stfle_fac_list[i] = 0;
+ asm volatile(
+ " stfl 0(0)\n"
+ : "=m" (S390_lowcore.stfl_fac_list));
+ S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
+ if (S390_lowcore.stfl_fac_list & 0x01000000) {
+ register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
+
+ asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
+ : "+d" (reg0)
+ : "a" (&S390_lowcore.stfle_fac_list)
+ : "memory", "cc");
+ }
+ for (i = 0; i < ARRAY_SIZE(als); i++) {
+ if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
+ facility_mismatch();
+ }
+}
sizes.h
vmlinux
vmlinux.lds
+vmlinux.scr.lds
vmlinux.bin.full
#
KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o
targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += misc.o piggy.o sizes.h head.o
-
-KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
-KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
-KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
+targets += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h)
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
-OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
-OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
$(call if_changed,ld)
-TRIM_HEAD_SIZE := 0x11000
-
-sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p'
+# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin
+sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p'
quiet_cmd_sizes = GEN $@
cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
-quiet_cmd_trim_head = TRIM $@
- cmd_trim_head = tail -c +$$(($(TRIM_HEAD_SIZE) + 1)) $< > $@
-
$(obj)/sizes.h: vmlinux
$(call if_changed,sizes)
CFLAGS_misc.o += -I$(objtree)/$(obj)
$(obj)/misc.o: $(obj)/sizes.h
-OBJCOPYFLAGS_vmlinux.bin.full := -R .comment -S
-$(obj)/vmlinux.bin.full: vmlinux
+OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
+$(obj)/vmlinux.bin: vmlinux
$(call if_changed,objcopy)
-$(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full
- $(call if_changed,trim_head)
-
vmlinux.bin.all-y := $(obj)/vmlinux.bin
-suffix-$(CONFIG_KERNEL_GZIP) := gz
-suffix-$(CONFIG_KERNEL_BZIP2) := bz2
-suffix-$(CONFIG_KERNEL_LZ4) := lz4
-suffix-$(CONFIG_KERNEL_LZMA) := lzma
-suffix-$(CONFIG_KERNEL_LZO) := lzo
-suffix-$(CONFIG_KERNEL_XZ) := xz
+suffix-$(CONFIG_KERNEL_GZIP) := .gz
+suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
+suffix-$(CONFIG_KERNEL_LZ4) := .lz4
+suffix-$(CONFIG_KERNEL_LZMA) := .lzma
+suffix-$(CONFIG_KERNEL_LZO) := .lzo
+suffix-$(CONFIG_KERNEL_XZ) := .xz
$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
$(call if_changed,gzip)
$(call if_changed,xzkern)
LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y)
$(call if_changed,ld)
+
+chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
+chkbss-target := $(obj)/vmlinux.bin
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
#include "sizes.h"
__HEAD
-ENTRY(startup_continue)
+ENTRY(startup_decompressor)
basr %r13,0 # get base
.LPG1:
# setup stack
aghi %r15,-160
brasl %r14,decompress_kernel
# Set up registers for memory mover. We move the decompressed image to
- # 0x11000, where startup_continue of the decompressed image is supposed
+ # 0x100000, where startup_continue of the decompressed image is supposed
# to be.
lgr %r4,%r2
lg %r2,.Loffset-.LPG1(%r13)
la %r1,0x200
mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13)
# When the memory mover is done we pass control to
- # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+ # arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in
# the decompressed image.
lgr %r6,%r2
br %r1
.Lstack:
.quad 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
.Loffset:
- .quad 0x11000
+ .quad 0x100000
.Lmvsize:
.quad SZ__bss_start
return 0;
}
-void *memset(void *s, int c, size_t n)
-{
- char *xs;
-
- xs = s;
- while (n--)
- *xs++ = c;
- return s;
-}
-
-void *memcpy(void *dest, const void *src, size_t n)
-{
- const char *s = src;
- char *d = dest;
-
- while (n--)
- *d++ = *s++;
- return dest;
-}
-
-void *memmove(void *dest, const void *src, size_t n)
-{
- const char *s = src;
- char *d = dest;
-
- if (d <= s) {
- while (n--)
- *d++ = *s++;
- } else {
- d += n;
- s += n;
- while (n--)
- *--d = *--s;
- }
- return dest;
-}
-
static void error(char *x)
{
unsigned long long psw = 0x000a0000deadbeefULL;
*(.text.*)
_etext = . ;
}
- .rodata.compressed : {
- *(.rodata.compressed)
- }
.rodata : {
_rodata = . ;
*(.rodata) /* read-only data */
- *(.rodata.*)
+ *(EXCLUDE_FILE (*piggy.o) .rodata.compressed)
_erodata = . ;
}
.data : {
*(.data.*)
_edata = . ;
}
+ startup_continue = 0x100000;
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+ . = 0x100000;
+#else
+ . = ALIGN(8);
+#endif
+ .rodata.compressed : {
+ *(.rodata.compressed)
+ }
. = ALIGN(256);
.bss : {
_bss = . ;
*(.eh_frame)
*(__ex_table)
*(*__ksymtab*)
+ *(___kcrctab*)
}
}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS
-{
- .rodata.compressed : {
- input_len = .;
- LONG(input_data_end - input_data) input_data = .;
- *(.data)
- output_len = . - 4;
- input_data_end = .;
- }
-}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+SECTIONS
+{
+ .rodata.compressed : {
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
+ input_len = .;
+ LONG(input_data_end - input_data) input_data = .;
+#endif
+ *(.data)
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
+ output_len = . - 4;
+ input_data_end = .;
+#endif
+ }
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/ebcdic.c"
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 1999, 2010
+ *
+ * Author(s): Hartmut Penner <hp@de.ibm.com>
+ * Martin Schwidefsky <schwidefsky@de.ibm.com>
+ * Rob van der Heij <rvdhei@iae.nl>
+ * Heiko Carstens <heiko.carstens@de.ibm.com>
+ *
+ * There are 5 different IPL methods
+ * 1) load the image directly into ram at address 0 and do an PSW restart
+ * 2) linload will load the image from address 0x10000 to memory 0x10000
+ * and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
+ * 3) generate the tape ipl header, store the generated image on a tape
+ * and ipl from it
+ * In case of SL tape you need to IPL 5 times to get past VOL1 etc
+ * 4) generate the vm reader ipl header, move the generated image to the
+ * VM reader (use option NOH!) and do a ipl from reader (VM only)
+ * 5) direct call of start by the SALIPL loader
+ * We use the cpuid to distinguish between VM and native ipl
+ * params for kernel are pushed to 0x10400 (see setup.h)
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+#define ARCH_OFFSET 4
+
+__HEAD
+
+#define IPL_BS 0x730
+ .org 0
+ .long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded
+ .long 0x02000018,0x60000050 # by ipl to addresses 0-23.
+ .long 0x02000068,0x60000050 # (a PSW and two CCWs).
+ .fill 80-24,1,0x40 # bytes 24-79 are discarded !!
+ .long 0x020000f0,0x60000050 # The next 160 byte are loaded
+ .long 0x02000140,0x60000050 # to addresses 0x18-0xb7
+ .long 0x02000190,0x60000050 # They form the continuation
+ .long 0x020001e0,0x60000050 # of the CCW program started
+ .long 0x02000230,0x60000050 # by ipl and load the range
+ .long 0x02000280,0x60000050 # 0x0f0-0x730 from the image
+ .long 0x020002d0,0x60000050 # to the range 0x0f0-0x730
+ .long 0x02000320,0x60000050 # in memory. At the end of
+ .long 0x02000370,0x60000050 # the channel program the PSW
+ .long 0x020003c0,0x60000050 # at location 0 is loaded.
+ .long 0x02000410,0x60000050 # Initial processing starts
+ .long 0x02000460,0x60000050 # at 0x200 = iplstart.
+ .long 0x020004b0,0x60000050
+ .long 0x02000500,0x60000050
+ .long 0x02000550,0x60000050
+ .long 0x020005a0,0x60000050
+ .long 0x020005f0,0x60000050
+ .long 0x02000640,0x60000050
+ .long 0x02000690,0x60000050
+ .long 0x020006e0,0x20000050
+
+ .org 0x200
+
+#
+# subroutine to wait for end I/O
+#
+.Lirqwait:
+ mvc __LC_IO_NEW_PSW(16),.Lnewpsw # set up IO interrupt psw
+ lpsw .Lwaitpsw
+.Lioint:
+ br %r14
+ .align 8
+.Lnewpsw:
+ .quad 0x0000000080000000,.Lioint
+.Lwaitpsw:
+ .long 0x020a0000,0x80000000+.Lioint
+
+#
+# subroutine for loading cards from the reader
+#
+.Lloader:
+ la %r4,0(%r14)
+ la %r3,.Lorb # r2 = address of orb into r2
+ la %r5,.Lirb # r4 = address of irb
+ la %r6,.Lccws
+ la %r7,20
+.Linit:
+ st %r2,4(%r6) # initialize CCW data addresses
+ la %r2,0x50(%r2)
+ la %r6,8(%r6)
+ bct 7,.Linit
+
+ lctl %c6,%c6,.Lcr6 # set IO subclass mask
+ slr %r2,%r2
+.Lldlp:
+ ssch 0(%r3) # load chunk of 1600 bytes
+ bnz .Llderr
+.Lwait4irq:
+ bas %r14,.Lirqwait
+ c %r1,__LC_SUBCHANNEL_ID # compare subchannel number
+ bne .Lwait4irq
+ tsch 0(%r5)
+
+ slr %r0,%r0
+ ic %r0,8(%r5) # get device status
+ chi %r0,8 # channel end ?
+ be .Lcont
+ chi %r0,12 # channel end + device end ?
+ be .Lcont
+
+ l %r0,4(%r5)
+ s %r0,8(%r3) # r0/8 = number of ccws executed
+ mhi %r0,10 # *10 = number of bytes in ccws
+ lh %r3,10(%r5) # get residual count
+ sr %r0,%r3 # #ccws*80-residual=#bytes read
+ ar %r2,%r0
+
+ br %r4 # r2 contains the total size
+
+.Lcont:
+ ahi %r2,0x640 # add 0x640 to total size
+ la %r6,.Lccws
+ la %r7,20
+.Lincr:
+ l %r0,4(%r6) # update CCW data addresses
+ ahi %r0,0x640
+ st %r0,4(%r6)
+ ahi %r6,8
+ bct 7,.Lincr
+
+ b .Lldlp
+.Llderr:
+ lpsw .Lcrash
+
+ .align 8
+.Lorb: .long 0x00000000,0x0080ff00,.Lccws
+.Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+.Lcr6: .long 0xff000000
+.Lloadp:.long 0,0
+ .align 8
+.Lcrash:.long 0x000a0000,0x00000000
+
+ .align 8
+.Lccws: .rept 19
+ .long 0x02600050,0x00000000
+ .endr
+ .long 0x02200050,0x00000000
+
+iplstart:
+ mvi __LC_AR_MODE_ID,1 # set esame flag
+ slr %r0,%r0 # set cpuid to zero
+ lhi %r1,2 # mode 2 = esame (dump)
+ sigp %r1,%r0,0x12 # switch to esame mode
+ bras %r13,0f
+ .fill 16,4,0x0
+0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
+ sam31 # switch to 31 bit addressing mode
+ lh %r1,__LC_SUBCHANNEL_ID # test if subchannel number
+ bct %r1,.Lnoload # is valid
+ l %r1,__LC_SUBCHANNEL_ID # load ipl subchannel number
+ la %r2,IPL_BS # load start address
+ bas %r14,.Lloader # load rest of ipl image
+ l %r12,.Lparm # pointer to parameter area
+ st %r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
+
+#
+# load parameter file from ipl device
+#
+.Lagain1:
+ l %r2,.Linitrd # ramdisk loc. is temp
+ bas %r14,.Lloader # load parameter file
+ ltr %r2,%r2 # got anything ?
+ bz .Lnopf
+ chi %r2,895
+ bnh .Lnotrunc
+ la %r2,895
+.Lnotrunc:
+ l %r4,.Linitrd
+ clc 0(3,%r4),.L_hdr # if it is HDRx
+ bz .Lagain1 # skip dataset header
+ clc 0(3,%r4),.L_eof # if it is EOFx
+ bz .Lagain1 # skip dateset trailer
+ la %r5,0(%r4,%r2)
+ lr %r3,%r2
+ la %r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
+ mvc 0(256,%r3),0(%r4)
+ mvc 256(256,%r3),256(%r4)
+ mvc 512(256,%r3),512(%r4)
+ mvc 768(122,%r3),768(%r4)
+ slr %r0,%r0
+ b .Lcntlp
+.Ldelspc:
+ ic %r0,0(%r2,%r3)
+ chi %r0,0x20 # is it a space ?
+ be .Lcntlp
+ ahi %r2,1
+ b .Leolp
+.Lcntlp:
+ brct %r2,.Ldelspc
+.Leolp:
+ slr %r0,%r0
+ stc %r0,0(%r2,%r3) # terminate buffer
+.Lnopf:
+
+#
+# load ramdisk from ipl device
+#
+.Lagain2:
+ l %r2,.Linitrd # addr of ramdisk
+ st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
+ bas %r14,.Lloader # load ramdisk
+ st %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
+ ltr %r2,%r2
+ bnz .Lrdcont
+ st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
+.Lrdcont:
+ l %r2,.Linitrd
+
+ clc 0(3,%r2),.L_hdr # skip HDRx and EOFx
+ bz .Lagain2
+ clc 0(3,%r2),.L_eof
+ bz .Lagain2
+
+#
+# reset files in VM reader
+#
+ stidp .Lcpuid # store cpuid
+ tm .Lcpuid,0xff # running VM ?
+ bno .Lnoreset
+ la %r2,.Lreset
+ lhi %r3,26
+ diag %r2,%r3,8
+ la %r5,.Lirb
+ stsch 0(%r5) # check if irq is pending
+ tm 30(%r5),0x0f # by verifying if any of the
+ bnz .Lwaitforirq # activity or status control
+ tm 31(%r5),0xff # bits is set in the schib
+ bz .Lnoreset
+.Lwaitforirq:
+ bas %r14,.Lirqwait # wait for IO interrupt
+ c %r1,__LC_SUBCHANNEL_ID # compare subchannel number
+ bne .Lwaitforirq
+ la %r5,.Lirb
+ tsch 0(%r5)
+.Lnoreset:
+ b .Lnoload
+
+#
+# everything loaded, go for it
+#
+.Lnoload:
+ l %r1,.Lstartup
+ br %r1
+
+.Linitrd:.long _end # default address of initrd
+.Lparm: .long PARMAREA
+.Lstartup: .long startup
+.Lreset:.byte 0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
+ .byte 0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
+ .byte 0xc8,0xd6,0xd3,0xc4 # "change rdr all keep nohold"
+.L_eof: .long 0xc5d6c600 /* C'EOF' */
+.L_hdr: .long 0xc8c4d900 /* C'HDR' */
+ .align 8
+.Lcpuid:.fill 8,1,0
+
+#
+# startup-code at 0x10000, running in absolute addressing mode
+# this is called either by the ipl loader or directly by PSW restart
+# or linload or SALIPL
+#
+ .org 0x10000
+ENTRY(startup)
+ j .Lep_startup_normal
+ .org EP_OFFSET
+#
+# This is a list of s390 kernel entry points. At address 0x1000f the number of
+# valid entry points is stored.
+#
+# IMPORTANT: Do not change this table, it is s390 kernel ABI!
+#
+ .ascii EP_STRING
+ .byte 0x00,0x01
+#
+# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
+#
+ .org 0x10010
+ENTRY(startup_kdump)
+ j .Lep_startup_kdump
+.Lep_startup_normal:
+ mvi __LC_AR_MODE_ID,1 # set esame flag
+ slr %r0,%r0 # set cpuid to zero
+ lhi %r1,2 # mode 2 = esame (dump)
+ sigp %r1,%r0,0x12 # switch to esame mode
+ bras %r13,0f
+ .fill 16,4,0x0
+0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
+ sam64 # switch to 64 bit addressing mode
+ basr %r13,0 # get base
+.LPG0:
+ xc 0x200(256),0x200 # partially clear lowcore
+ xc 0x300(256),0x300
+ xc 0xe00(256),0xe00
+ xc 0xf00(256),0xf00
+ lctlg %c0,%c15,0x200(%r0) # initialize control registers
+ stcke __LC_BOOT_CLOCK
+ mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
+ spt 6f-.LPG0(%r13)
+ mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
+ l %r15,.Lstack-.LPG0(%r13)
+ ahi %r15,-STACK_FRAME_OVERHEAD
+ brasl %r14,verify_facilities
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+ jg startup_continue
+#else
+ jg startup_decompressor
+#endif
+
+.Lstack:
+ .long 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
+ .align 8
+6: .long 0x7fffffff,0xffffffff
+
+#include "head_kdump.S"
+
+#
+# params at 10400 (setup.h)
+#
+ .org PARMAREA
+ .long 0,0 # IPL_DEVICE
+ .long 0,0 # INITRD_START
+ .long 0,0 # INITRD_SIZE
+ .long 0,0 # OLDMEM_BASE
+ .long 0,0 # OLDMEM_SIZE
+
+ .org COMMAND_LINE
+ .byte "root=/dev/ram0 ro"
+ .byte 0
+
+ .org 0x11000
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * S390 kdump lowlevel functions (new kernel)
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <asm/sigp.h>
+
+#define DATAMOVER_ADDR 0x4000
+#define COPY_PAGE_ADDR 0x6000
+
+#ifdef CONFIG_CRASH_DUMP
+
+#
+# kdump entry (new kernel - not yet relocated)
+#
+# Note: This code has to be position independent
+#
+
+.align 2
+.Lep_startup_kdump:
+ lhi %r1,2 # mode 2 = esame (dump)
+ sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to esame mode
+ sam64 # Switch to 64 bit addressing
+ basr %r13,0
+.Lbase:
+ larl %r2,.Lbase_addr # Check, if we have been
+ lg %r2,0(%r2) # already relocated:
+ clgr %r2,%r13 #
+ jne .Lrelocate # No : Start data mover
+ lghi %r2,0 # Yes: Start kdump kernel
+ brasl %r14,startup_kdump_relocated
+
+.Lrelocate:
+ larl %r4,startup
+ lg %r2,0x418(%r4) # Get kdump base
+ lg %r3,0x420(%r4) # Get kdump size
+
+ larl %r10,.Lcopy_start # Source of data mover
+ lghi %r8,DATAMOVER_ADDR # Target of data mover
+ mvc 0(256,%r8),0(%r10) # Copy data mover code
+
+ agr %r8,%r2 # Copy data mover to
+ mvc 0(256,%r8),0(%r10) # reserved mem
+
+ lghi %r14,DATAMOVER_ADDR # Jump to copied data mover
+ basr %r14,%r14
+.Lbase_addr:
+ .quad .Lbase
+
+#
+# kdump data mover code (runs at address DATAMOVER_ADDR)
+#
+# r2: kdump base address
+# r3: kdump size
+#
+.Lcopy_start:
+ basr %r13,0 # Base
+0:
+ lgr %r11,%r2 # Save kdump base address
+ lgr %r12,%r2
+ agr %r12,%r3 # Compute kdump end address
+
+ lghi %r5,0
+ lghi %r10,COPY_PAGE_ADDR # Load copy page address
+1:
+ mvc 0(256,%r10),0(%r5) # Copy old kernel to tmp
+ mvc 0(256,%r5),0(%r11) # Copy new kernel to old
+ mvc 0(256,%r11),0(%r10) # Copy tmp to new
+ aghi %r11,256
+ aghi %r5,256
+ clgr %r11,%r12
+ jl 1b
+
+ lg %r14,.Lstartup_kdump-0b(%r13)
+ basr %r14,%r14 # Start relocated kernel
+.Lstartup_kdump:
+ .long 0x00000000,0x00000000 + startup_kdump_relocated
+.Lcopy_end:
+
+#
+# Startup of kdump (relocated new kernel)
+#
+.align 2
+startup_kdump_relocated:
+ basr %r13,0
+0: lpswe .Lrestart_psw-0b(%r13) # Start new kernel...
+.align 8
+.Lrestart_psw:
+ .quad 0x0000000080000000,0x0000000000000000 + startup
+#else
+.align 2
+.Lep_startup_kdump:
+ larl %r13,startup_kdump_crash
+ lpswe 0(%r13)
+.align 8
+startup_kdump_crash:
+ .quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash
+#endif /* CONFIG_CRASH_DUMP */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../lib/mem.S"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../drivers/s390/char/sclp_early_core.c"
}
diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
rc = hypfs_create_str(cpu_dir, "type", buffer);
- return PTR_RET(rc);
+ return PTR_ERR_OR_ZERO(rc);
}
static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
return PTR_ERR(rc);
diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
rc = hypfs_create_str(cpu_dir, "type", buffer);
- return PTR_RET(rc);
+ return PTR_ERR_OR_ZERO(rc);
}
static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
kuid_t uid; /* uid used for files and dirs */
kgid_t gid; /* gid used for files and dirs */
struct dentry *update_file; /* file to trigger update */
- time_t last_update; /* last update time in secs since 1970 */
+ time64_t last_update; /* last update, CLOCK_MONOTONIC time */
struct mutex lock; /* lock to protect update process */
};
struct hypfs_sb_info *sb_info = sb->s_fs_info;
struct inode *inode = d_inode(sb_info->update_file);
- sb_info->last_update = get_seconds();
+ sb_info->last_update = ktime_get_seconds();
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
}
* to restart data collection in this case.
*/
mutex_lock(&fs_info->lock);
- if (fs_info->last_update == get_seconds()) {
+ if (fs_info->last_update == ktime_get_seconds()) {
rc = -EBUSY;
goto out;
}
unsigned int _pad2 : 16;
};
+/**
+ * ap_intructions_available() - Test if AP instructions are available.
+ *
+ * Returns 0 if the AP instructions are installed.
+ */
+static inline int ap_instructions_available(void)
+{
+ register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
+ register unsigned long reg1 asm ("1") = -ENODEV;
+ register unsigned long reg2 asm ("2");
+
+ asm volatile(
+ " .long 0xb2af0000\n" /* PQAP(TAPQ) */
+ "0: la %0,0\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : "+d" (reg1), "=d" (reg2)
+ : "d" (reg0)
+ : "cc");
+ return reg1;
+}
+
+/**
+ * ap_tapq(): Test adjunct processor queue.
+ * @qid: The AP queue number
+ * @info: Pointer to queue descriptor
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
+{
+ register unsigned long reg0 asm ("0") = qid;
+ register struct ap_queue_status reg1 asm ("1");
+ register unsigned long reg2 asm ("2");
+
+ asm volatile(".long 0xb2af0000" /* PQAP(TAPQ) */
+ : "=d" (reg1), "=d" (reg2)
+ : "d" (reg0)
+ : "cc");
+ if (info)
+ *info = reg2;
+ return reg1;
+}
+
/**
* ap_test_queue(): Test adjunct processor queue.
* @qid: The AP queue number
*
* Returns AP queue status structure.
*/
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
- int tbit,
- unsigned long *info);
+static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
+ int tbit,
+ unsigned long *info)
+{
+ if (tbit)
+ qid |= 1UL << 23; /* set T bit*/
+ return ap_tapq(qid, info);
+}
+/**
+ * ap_pqap_rapq(): Reset adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
+{
+ register unsigned long reg0 asm ("0") = qid | (1UL << 24);
+ register struct ap_queue_status reg1 asm ("1");
+
+ asm volatile(
+ ".long 0xb2af0000" /* PQAP(RAPQ) */
+ : "=d" (reg1)
+ : "d" (reg0)
+ : "cc");
+ return reg1;
+}
+
+/**
+ * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+{
+ register unsigned long reg0 asm ("0") = qid | (2UL << 24);
+ register struct ap_queue_status reg1 asm ("1");
+
+ asm volatile(
+ ".long 0xb2af0000" /* PQAP(ZAPQ) */
+ : "=d" (reg1)
+ : "d" (reg0)
+ : "cc");
+ return reg1;
+}
+
+/**
+ * struct ap_config_info - convenience struct for AP crypto
+ * config info as returned by the ap_qci() function.
+ */
struct ap_config_info {
unsigned int apsc : 1; /* S bit */
unsigned int apxa : 1; /* N bit */
unsigned char _reserved4[16];
} __aligned(8);
-/*
- * ap_query_configuration(): Fetch cryptographic config info
+/**
+ * ap_qci(): Get AP configuration data
*
- * Returns the ap configuration info fetched via PQAP(QCI).
- * On success 0 is returned, on failure a negative errno
- * is returned, e.g. if the PQAP(QCI) instruction is not
- * available, the return value will be -EOPNOTSUPP.
+ * Returns 0 on success, or -EOPNOTSUPP.
*/
-int ap_query_configuration(struct ap_config_info *info);
+static inline int ap_qci(struct ap_config_info *config)
+{
+ register unsigned long reg0 asm ("0") = 4UL << 24;
+ register unsigned long reg1 asm ("1") = -EOPNOTSUPP;
+ register struct ap_config_info *reg2 asm ("2") = config;
+
+ asm volatile(
+ ".long 0xb2af0000\n" /* PQAP(QCI) */
+ "0: la %0,0\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : "+d" (reg1)
+ : "d" (reg0), "d" (reg2)
+ : "cc", "memory");
+
+ return reg1;
+}
/*
* struct ap_qirq_ctrl - convenient struct for easy invocation
- * of the ap_queue_irq_ctrl() function. This struct is passed
- * as GR1 parameter to the PQAP(AQIC) instruction. For details
- * please see the AR documentation.
+ * of the ap_aqic() function. This struct is passed as GR1
+ * parameter to the PQAP(AQIC) instruction. For details please
+ * see the AR documentation.
*/
struct ap_qirq_ctrl {
unsigned int _res1 : 8;
- unsigned int zone : 8; /* zone info */
- unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */
+ unsigned int zone : 8; /* zone info */
+ unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */
unsigned int _res2 : 4;
- unsigned int gisc : 3; /* guest isc field */
+ unsigned int gisc : 3; /* guest isc field */
unsigned int _res3 : 6;
- unsigned int gf : 2; /* gisa format */
+ unsigned int gf : 2; /* gisa format */
unsigned int _res4 : 1;
- unsigned int gisa : 27; /* gisa origin */
+ unsigned int gisa : 27; /* gisa origin */
unsigned int _res5 : 1;
- unsigned int isc : 3; /* irq sub class */
+ unsigned int isc : 3; /* irq sub class */
};
/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
+ * ap_aqic(): Control interruption for a specific AP.
* @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl, see above
+ * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
* @ind: The notification indicator byte
*
* Returns AP queue status.
+ */
+static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
+ struct ap_qirq_ctrl qirqctrl,
+ void *ind)
+{
+ register unsigned long reg0 asm ("0") = qid | (3UL << 24);
+ register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
+ register struct ap_queue_status reg1_out asm ("1");
+ register void *reg2 asm ("2") = ind;
+
+ asm volatile(
+ ".long 0xb2af0000" /* PQAP(AQIC) */
+ : "=d" (reg1_out)
+ : "d" (reg0), "d" (reg1_in), "d" (reg2)
+ : "cc");
+ return reg1_out;
+}
+
+/*
+ * union ap_qact_ap_info - used together with the
+ * ap_aqic() function to provide a convenient way
+ * to handle the ap info needed by the qact function.
+ */
+union ap_qact_ap_info {
+ unsigned long val;
+ struct {
+ unsigned int : 3;
+ unsigned int mode : 3;
+ unsigned int : 26;
+ unsigned int cat : 8;
+ unsigned int : 8;
+ unsigned char ver[2];
+ };
+};
+
+/**
+ * ap_qact(): Query AP combatibility type.
+ * @qid: The AP queue number
+ * @apinfo: On input the info about the AP queue. On output the
+ * alternate AP queue info provided by the qact function
+ * in GR2 is stored in.
*
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
+ * Returns AP queue status. Check response_code field for failures.
*/
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
- struct ap_qirq_ctrl qirqctrl,
- void *ind);
+static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
+ union ap_qact_ap_info *apinfo)
+{
+ register unsigned long reg0 asm ("0") = qid | (5UL << 24)
+ | ((ifbit & 0x01) << 22);
+ register unsigned long reg1_in asm ("1") = apinfo->val;
+ register struct ap_queue_status reg1_out asm ("1");
+ register unsigned long reg2 asm ("2");
+
+ asm volatile(
+ ".long 0xb2af0000" /* PQAP(QACT) */
+ : "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+ : "d" (reg0)
+ : "cc");
+ apinfo->val = reg2;
+ return reg1_out;
+}
+
+/**
+ * ap_nqap(): Send message to adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: The program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on NQAP can't happen because the L bit is 1.
+ * Condition code 2 on NQAP also means the send is incomplete,
+ * because a segment boundary was reached. The NQAP is repeated.
+ */
+static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
+ unsigned long long psmid,
+ void *msg, size_t length)
+{
+ register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
+ register struct ap_queue_status reg1 asm ("1");
+ register unsigned long reg2 asm ("2") = (unsigned long) msg;
+ register unsigned long reg3 asm ("3") = (unsigned long) length;
+ register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
+ register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
+
+ asm volatile (
+ "0: .long 0xb2ad0042\n" /* NQAP */
+ " brc 2,0b"
+ : "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
+ : "d" (reg4), "d" (reg5)
+ : "cc", "memory");
+ return reg1;
+}
+
+/**
+ * ap_dqap(): Receive message from adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: Pointer to program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on DQAP means the receive has taken place
+ * but only partially. The response is incomplete, hence the
+ * DQAP is repeated.
+ * Condition code 2 on DQAP also means the receive is incomplete,
+ * this time because a segment boundary was reached. Again, the
+ * DQAP is repeated.
+ * Note that gpr2 is used by the DQAP instruction to keep track of
+ * any 'residual' length, in case the instruction gets interrupted.
+ * Hence it gets zeroed before the instruction.
+ */
+static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
+ unsigned long long *psmid,
+ void *msg, size_t length)
+{
+ register unsigned long reg0 asm("0") = qid | 0x80000000UL;
+ register struct ap_queue_status reg1 asm ("1");
+ register unsigned long reg2 asm("2") = 0UL;
+ register unsigned long reg4 asm("4") = (unsigned long) msg;
+ register unsigned long reg5 asm("5") = (unsigned long) length;
+ register unsigned long reg6 asm("6") = 0UL;
+ register unsigned long reg7 asm("7") = 0UL;
+
+
+ asm volatile(
+ "0: .long 0xb2ae0064\n" /* DQAP */
+ " brc 6,0b\n"
+ : "+d" (reg0), "=d" (reg1), "+d" (reg2),
+ "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
+ : : "cc", "memory");
+ *psmid = (((unsigned long long) reg6) << 32) + reg7;
+ return reg1;
+}
#endif /* _ASM_S390_AP_H_ */
__atomic_add(i, &v->counter);
}
-#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0)
-#define atomic_inc(_v) atomic_add(1, _v)
-#define atomic_inc_return(_v) atomic_add_return(1, _v)
-#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0)
#define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v)
#define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v)
#define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v)
-#define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0)
-#define atomic_dec(_v) atomic_sub(1, _v)
-#define atomic_dec_return(_v) atomic_sub_return(1, _v)
-#define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0)
#define ATOMIC_OPS(op) \
static inline void atomic_##op(int i, atomic_t *v) \
return __atomic_cmpxchg(&v->counter, old, new);
}
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == u))
- break;
- old = atomic_cmpxchg(v, c, c + a);
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
#define ATOMIC64_INIT(i) { (i) }
static inline long atomic64_read(const atomic64_t *v)
#undef ATOMIC64_OPS
-static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
-{
- long c, old;
-
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == u))
- break;
- old = atomic64_cmpxchg(v, c, c + i);
- if (likely(old == c))
- break;
- c = old;
- }
- return c != u;
-}
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
- long c, old, dec;
-
- c = atomic64_read(v);
- for (;;) {
- dec = c - 1;
- if (unlikely(dec < 0))
- break;
- old = atomic64_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
- return dec;
-}
-
-#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0)
-#define atomic64_inc(_v) atomic64_add(1, _v)
-#define atomic64_inc_return(_v) atomic64_add_return(1, _v)
-#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0)
#define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v)
#define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v)
#define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v)
-#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0)
-#define atomic64_dec(_v) atomic64_sub(1, _v)
-#define atomic64_dec_return(_v) atomic64_sub_return(1, _v)
-#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0)
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
#endif /* __ARCH_S390_ATOMIC__ */
/*
* CPU-measurement facilities
*
- * Copyright IBM Corp. 2012
+ * Copyright IBM Corp. 2012, 2018
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
* Jan Glauber <jang@linux.vnet.ibm.com>
*/
unsigned char timestamp[16]; /* 16 - 31 timestamp */
unsigned long long reserved1; /* 32 -Reserved */
unsigned long long reserved2; /* */
- unsigned long long progusage1; /* 48 - reserved for programming use */
- unsigned long long progusage2; /* */
+ union { /* 48 - reserved for programming use */
+ struct {
+ unsigned int clock_base:1; /* in progusage2 */
+ unsigned long long progusage1:63;
+ unsigned long long progusage2;
+ };
+ unsigned long long progusage[2];
+ };
} __packed;
/* Load program parameter */
struct css_general_char {
u64 : 12;
- u32 dynio : 1; /* bit 12 */
- u32 : 4;
- u32 eadm : 1; /* bit 17 */
- u32 : 23;
- u32 aif : 1; /* bit 41 */
- u32 : 3;
- u32 mcss : 1; /* bit 45 */
- u32 fcs : 1; /* bit 46 */
- u32 : 1;
- u32 ext_mb : 1; /* bit 48 */
- u32 : 7;
- u32 aif_tdd : 1; /* bit 56 */
- u32 : 1;
- u32 qebsm : 1; /* bit 58 */
- u32 : 2;
- u32 aiv : 1; /* bit 61 */
- u32 : 5;
- u32 aif_osa : 1; /* bit 67 */
- u32 : 12;
- u32 eadm_rf : 1; /* bit 80 */
- u32 : 1;
- u32 cib : 1; /* bit 82 */
- u32 : 5;
- u32 fcx : 1; /* bit 88 */
- u32 : 19;
- u32 alt_ssi : 1; /* bit 108 */
- u32 : 1;
- u32 narf : 1; /* bit 110 */
- u32 : 12;
- u32 util_str : 1;/* bit 123 */
+ u64 dynio : 1; /* bit 12 */
+ u64 : 4;
+ u64 eadm : 1; /* bit 17 */
+ u64 : 23;
+ u64 aif : 1; /* bit 41 */
+ u64 : 3;
+ u64 mcss : 1; /* bit 45 */
+ u64 fcs : 1; /* bit 46 */
+ u64 : 1;
+ u64 ext_mb : 1; /* bit 48 */
+ u64 : 7;
+ u64 aif_tdd : 1; /* bit 56 */
+ u64 : 1;
+ u64 qebsm : 1; /* bit 58 */
+ u64 : 2;
+ u64 aiv : 1; /* bit 61 */
+ u64 : 2;
+
+ u64 : 3;
+ u64 aif_osa : 1; /* bit 67 */
+ u64 : 12;
+ u64 eadm_rf : 1; /* bit 80 */
+ u64 : 1;
+ u64 cib : 1; /* bit 82 */
+ u64 : 5;
+ u64 fcx : 1; /* bit 88 */
+ u64 : 19;
+ u64 alt_ssi : 1; /* bit 108 */
+ u64 : 1;
+ u64 narf : 1; /* bit 110 */
+ u64 : 12;
+ u64 util_str : 1;/* bit 123 */
} __packed;
extern struct css_general_char css_general_characteristics;
#ifndef _ASM_S390_GMAP_H
#define _ASM_S390_GMAP_H
+/* Generic bits for GMAP notification on DAT table entry changes. */
+#define GMAP_NOTIFY_SHADOW 0x2
+#define GMAP_NOTIFY_MPROT 0x1
+
+/* Status bits only for huge segment entries */
+#define _SEGMENT_ENTRY_GMAP_IN 0x8000 /* invalidation notify bit */
+#define _SEGMENT_ENTRY_GMAP_UC 0x4000 /* dirty (migration) */
+
/**
* struct gmap_struct - guest address space
* @list: list head for the mm->context gmap list
int gmap_mprotect_notify(struct gmap *, unsigned long start,
unsigned long len, int prot);
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
+ unsigned long gaddr, unsigned long vmaddr);
#endif /* _ASM_S390_GMAP_H */
return 0;
}
-#define arch_clear_hugepage_flags(page) do { } while (0)
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+ clear_bit(PG_arch_1, &page->flags);
+}
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz)
unsigned long kprobe_saved_imask;
unsigned long kprobe_saved_ctl[3];
struct prev_kprobe prev_kprobe;
- struct pt_regs jprobe_saved_regs;
- kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
};
void arch_remove_kprobe(struct kprobe *p);
/* Transaction abort diagnostic block */
__u8 pgm_tdb[256]; /* 0x1800 */
__u8 pad_0x1900[0x2000-0x1900]; /* 0x1900 */
-} __packed;
+} __packed __aligned(8192);
#define S390_lowcore (*((struct lowcore *) 0))
unsigned int uses_skeys:1;
/* The mmu context uses CMM. */
unsigned int uses_cmm:1;
+ /* The gmaps associated with this context are allowed to use huge pages. */
+ unsigned int allow_gmap_hpage_1m:1;
} mm_context_t;
#define INIT_MM_CONTEXT(name) \
mm->context.has_pgste = 0;
mm->context.uses_skeys = 0;
mm->context.uses_cmm = 0;
+ mm->context.allow_gmap_hpage_1m = 0;
#endif
switch (mm->context.asce_limit) {
case _REGION2_SIZE:
#ifdef __ASSEMBLY__
-#ifdef CONFIG_EXPOLINE
+#ifdef CC_USING_EXPOLINE
_LC_BR_R1 = __LC_BR_R1
.macro BASR_EX rsave,rtarget,ruse=%r1
basr \rsave,\rtarget
.endm
-#endif
+#endif /* CC_USING_EXPOLINE */
#endif /* __ASSEMBLY__ */
u64 max_work_units;
};
+struct zpci_fmb_fmt3 {
+ u64 tx_bytes;
+};
+
struct zpci_fmb {
u32 format : 8;
u32 fmt_ind : 24;
struct zpci_fmb_fmt0 fmt0;
struct zpci_fmb_fmt1 fmt1;
struct zpci_fmb_fmt2 fmt2;
+ struct zpci_fmb_fmt3 fmt3;
};
} __packed __aligned(128);
#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
/* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL
#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */
#define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* page table origin */
#define _SEGMENT_ENTRY_PROTECT 0x200 /* segment protection bit */
pte_t *sptep, pte_t *tptep, pte_t pte);
void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address,
+ pte_t *ptep);
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned char key, bool nq);
int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
unsigned long *oldpte, unsigned long *oldpgste);
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
/*
* Certain architectures need to do special things when PTEs
int verify_sha256_digest(void);
-extern u64 kernel_entry;
-extern u64 kernel_type;
-
-extern u64 crash_start;
-extern u64 crash_size;
-
#endif /* __ASSEMBLY__ */
#endif /* _S390_PURGATORY_H_ */
void *user;
};
-#define QDIO_OUTBUF_STATE_FLAG_NONE 0x00
#define QDIO_OUTBUF_STATE_FLAG_PENDING 0x01
#define CHSC_AC1_INITIATE_INPUTQ 0x80
#include <asm-generic/sections.h>
-extern char _ehead[];
-
#endif
#include <linux/const.h>
#include <uapi/asm/setup.h>
-
+#define EP_OFFSET 0x10008
+#define EP_STRING "S390EP"
#define PARMAREA 0x10400
+#define PARMAREA_END 0x11000
/*
* Machine features detected in early.c
__u32 key : 4;
__u32 : 28;
struct subchannel_id sid;
-} __attribute__ ((packed));
+};
struct chsc_async_area {
struct chsc_async_header header;
__u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)];
-} __attribute__ ((packed));
+};
struct chsc_header {
__u16 length;
__u16 code;
-} __attribute__ ((packed));
+};
struct chsc_sync_area {
struct chsc_header header;
__u8 data[CHSC_SIZE - sizeof(struct chsc_header)];
-} __attribute__ ((packed));
+};
struct chsc_response_struct {
__u16 length;
__u16 code;
__u32 parms;
__u8 data[CHSC_SIZE - 2 * sizeof(__u16) - sizeof(__u32)];
-} __attribute__ ((packed));
+};
struct chsc_chp_cd {
struct chp_id chpid;
CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
# Do not trace early setup code
-CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_early_nobss.o = $(CC_FLAGS_FTRACE)
endif
-GCOV_PROFILE_als.o := n
GCOV_PROFILE_early.o := n
GCOV_PROFILE_early_nobss.o := n
-KCOV_INSTRUMENT_als.o := n
KCOV_INSTRUMENT_early.o := n
KCOV_INSTRUMENT_early_nobss.o := n
-UBSAN_SANITIZE_als.o := n
UBSAN_SANITIZE_early.o := n
UBSAN_SANITIZE_early_nobss.o := n
-#
-# Use -march=z900 for als.c to be able to print an error
-# message if the kernel is started on a machine which is too old
-#
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH)
-CFLAGS_REMOVE_als.o += $(CC_FLAGS_EXPOLINE)
-CFLAGS_als.o += -march=z900
-AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH)
-AFLAGS_head.o += -march=z900
-endif
-
-CFLAGS_als.o += -D__NO_FORTIFY
-
#
# Passing null pointers is ok for smp code, since we access the lowcore here.
#
obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
+obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
obj-y += nospec-branch.o
-extra-y += head.o head64.o vmlinux.lds
+extra-y += head64.o vmlinux.lds
obj-$(CONFIG_SYSFS) += nospec-sysfs.o
CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE)
obj-y += vdso64/
obj-$(CONFIG_COMPAT) += vdso32/
-chkbss := head.o head64.o als.o early_nobss.o
+chkbss := head64.o early_nobss.o
include $(srctree)/arch/s390/scripts/Makefile.chkbss
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright IBM Corp. 2016
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <asm/processor.h>
-#include <asm/facility.h>
-#include <asm/lowcore.h>
-#include <asm/sclp.h>
-#include "entry.h"
-
-/*
- * The code within this file will be called very early. It may _not_
- * access anything within the bss section, since that is not cleared
- * yet and may contain data (e.g. initrd) that must be saved by other
- * code.
- * For temporary objects the stack (16k) should be used.
- */
-
-static unsigned long als[] __initdata = { FACILITIES_ALS };
-
-static void __init u16_to_hex(char *str, u16 val)
-{
- int i, num;
-
- for (i = 1; i <= 4; i++) {
- num = (val >> (16 - 4 * i)) & 0xf;
- if (num >= 10)
- num += 7;
- *str++ = '0' + num;
- }
- *str = '\0';
-}
-
-static void __init print_machine_type(void)
-{
- static char mach_str[80] __initdata = "Detected machine-type number: ";
- char type_str[5];
- struct cpuid id;
-
- get_cpu_id(&id);
- u16_to_hex(type_str, id.machine);
- strcat(mach_str, type_str);
- strcat(mach_str, "\n");
- sclp_early_printk(mach_str);
-}
-
-static void __init u16_to_decimal(char *str, u16 val)
-{
- int div = 1;
-
- while (div * 10 <= val)
- div *= 10;
- while (div) {
- *str++ = '0' + val / div;
- val %= div;
- div /= 10;
- }
- *str = '\0';
-}
-
-static void __init print_missing_facilities(void)
-{
- static char als_str[80] __initdata = "Missing facilities: ";
- unsigned long val;
- char val_str[6];
- int i, j, first;
-
- first = 1;
- for (i = 0; i < ARRAY_SIZE(als); i++) {
- val = ~S390_lowcore.stfle_fac_list[i] & als[i];
- for (j = 0; j < BITS_PER_LONG; j++) {
- if (!(val & (1UL << (BITS_PER_LONG - 1 - j))))
- continue;
- if (!first)
- strcat(als_str, ",");
- /*
- * Make sure we stay within one line. Consider that
- * each facility bit adds up to five characters and
- * z/VM adds a four character prefix.
- */
- if (strlen(als_str) > 70) {
- strcat(als_str, "\n");
- sclp_early_printk(als_str);
- *als_str = '\0';
- }
- u16_to_decimal(val_str, i * BITS_PER_LONG + j);
- strcat(als_str, val_str);
- first = 0;
- }
- }
- strcat(als_str, "\n");
- sclp_early_printk(als_str);
- sclp_early_printk("See Principles of Operations for facility bits\n");
-}
-
-static void __init facility_mismatch(void)
-{
- sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
- print_machine_type();
- print_missing_facilities();
- disabled_wait(0x8badcccc);
-}
-
-void __init verify_facilities(void)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
- S390_lowcore.stfle_fac_list[i] = 0;
- asm volatile(
- " stfl 0(0)\n"
- : "=m" (S390_lowcore.stfl_fac_list));
- S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
- if (S390_lowcore.stfl_fac_list & 0x01000000) {
- register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
-
- asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
- : "+d" (reg0)
- : "a" (&S390_lowcore.stfle_fac_list)
- : "memory", "cc");
- }
- for (i = 0; i < ARRAY_SIZE(als); i++) {
- if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
- facility_mismatch();
- }
-}
COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
+COMPAT_SYSCALL_WRAP4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
return rc;
}
+static const char *nt_name(Elf64_Word type)
+{
+ const char *name = "LINUX";
+
+ if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
+ name = KEXEC_CORE_NOTE_NAME;
+ return name;
+}
+
/*
* Initialize ELF note
*/
static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
{
- const char *note_name = "LINUX";
+ return nt_init_name(buf, type, desc, d_len, nt_name(type));
+}
+
+/*
+ * Calculate the size of ELF note
+ */
+static size_t nt_size_name(int d_len, const char *name)
+{
+ size_t size;
- if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
- note_name = KEXEC_CORE_NOTE_NAME;
- return nt_init_name(buf, type, desc, d_len, note_name);
+ size = sizeof(Elf64_Nhdr);
+ size += roundup(strlen(name) + 1, 4);
+ size += roundup(d_len, 4);
+
+ return size;
+}
+
+static inline size_t nt_size(Elf64_Word type, int d_len)
+{
+ return nt_size_name(d_len, nt_name(type));
}
/*
return ptr;
}
+/*
+ * Calculate size of ELF notes per cpu
+ */
+static size_t get_cpu_elf_notes_size(void)
+{
+ struct save_area *sa = NULL;
+ size_t size;
+
+ size = nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
+ size += nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
+ size += nt_size(NT_S390_TIMER, sizeof(sa->timer));
+ size += nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
+ size += nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
+ size += nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
+ size += nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+ if (MACHINE_HAS_VX) {
+ size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
+ size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+ }
+
+ return size;
+}
+
/*
* Initialize prpsinfo note (new kernel)
*/
return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
}
+static size_t nt_vmcoreinfo_size(void)
+{
+ const char *name = "VMCOREINFO";
+ char nt_name[11];
+ Elf64_Nhdr note;
+ void *addr;
+
+ if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+ return 0;
+
+ if (copy_oldmem_kernel(¬e, addr, sizeof(note)))
+ return 0;
+
+ memset(nt_name, 0, sizeof(nt_name));
+ if (copy_oldmem_kernel(nt_name, addr + sizeof(note),
+ sizeof(nt_name) - 1))
+ return 0;
+
+ if (strcmp(nt_name, name) != 0)
+ return 0;
+
+ return nt_size_name(note.n_descsz, name);
+}
+
/*
* Initialize final note (needed for /proc/vmcore code)
*/
return ptr;
}
+static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+{
+ size_t size;
+
+ size = sizeof(Elf64_Ehdr);
+ /* PT_NOTES */
+ size += sizeof(Elf64_Phdr);
+ /* nt_prpsinfo */
+ size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+ /* regsets */
+ size += get_cpu_cnt() * get_cpu_elf_notes_size();
+ /* nt_vmcoreinfo */
+ size += nt_vmcoreinfo_size();
+ /* nt_final */
+ size += sizeof(Elf64_Nhdr);
+ /* PT_LOADS */
+ size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+
+ return size;
+}
+
/*
* Create ELF core header (new kernel)
*/
mem_chunk_cnt = get_mem_chunk_cnt();
- alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
- mem_chunk_cnt * sizeof(Elf64_Phdr);
+ alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+
hdr = kzalloc_panic(alloc_size);
/* Init elf header */
ptr = ehdr_init(hdr, mem_chunk_cnt);
append_to_cmdline(append_ipl_scpdata);
}
+static void __init check_image_bootable(void)
+{
+ if (!memcmp(EP_STRING, (void *)EP_OFFSET, strlen(EP_STRING)))
+ return;
+
+ sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
+ sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
+ sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
+ disabled_wait(0xbadb007);
+}
+
void __init startup_init(void)
{
+ check_image_bootable();
time_early_init();
init_kernel_storage_key();
lockdep_off();
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_return:
+#ifdef CONFIG_DEBUG_RSEQ
+ lgr %r2,%r11
+ brasl %r14,rseq_syscall
+#endif
LOCKDEP_SYS_EXIT
.Lsysc_tif:
TSTMSK __PT_FLAGS(%r11),_PIF_WORK
jl 0f
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
-0: BR_EX %r14
+0: BR_EX %r14,%r11
.align 8
.Lcleanup_table:
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
- BR_EX %r14
+ BR_EX %r14,%r11
#endif
.Lcleanup_system_call:
DECLARE_PER_CPU(u64, mt_cycles[8]);
-void verify_facilities(void);
void gs_load_bc_cb(struct pt_regs *regs);
void set_fs_fixup(void);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 1999, 2010
- *
- * Author(s): Hartmut Penner <hp@de.ibm.com>
- * Martin Schwidefsky <schwidefsky@de.ibm.com>
- * Rob van der Heij <rvdhei@iae.nl>
- * Heiko Carstens <heiko.carstens@de.ibm.com>
- *
- * There are 5 different IPL methods
- * 1) load the image directly into ram at address 0 and do an PSW restart
- * 2) linload will load the image from address 0x10000 to memory 0x10000
- * and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
- * 3) generate the tape ipl header, store the generated image on a tape
- * and ipl from it
- * In case of SL tape you need to IPL 5 times to get past VOL1 etc
- * 4) generate the vm reader ipl header, move the generated image to the
- * VM reader (use option NOH!) and do a ipl from reader (VM only)
- * 5) direct call of start by the SALIPL loader
- * We use the cpuid to distinguish between VM and native ipl
- * params for kernel are pushed to 0x10400 (see setup.h)
- *
- */
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/page.h>
-#include <asm/ptrace.h>
-
-#define ARCH_OFFSET 4
-
-__HEAD
-
-#define IPL_BS 0x730
- .org 0
- .long 0x00080000,0x80000000+iplstart # The first 24 bytes are loaded
- .long 0x02000018,0x60000050 # by ipl to addresses 0-23.
- .long 0x02000068,0x60000050 # (a PSW and two CCWs).
- .fill 80-24,1,0x40 # bytes 24-79 are discarded !!
- .long 0x020000f0,0x60000050 # The next 160 byte are loaded
- .long 0x02000140,0x60000050 # to addresses 0x18-0xb7
- .long 0x02000190,0x60000050 # They form the continuation
- .long 0x020001e0,0x60000050 # of the CCW program started
- .long 0x02000230,0x60000050 # by ipl and load the range
- .long 0x02000280,0x60000050 # 0x0f0-0x730 from the image
- .long 0x020002d0,0x60000050 # to the range 0x0f0-0x730
- .long 0x02000320,0x60000050 # in memory. At the end of
- .long 0x02000370,0x60000050 # the channel program the PSW
- .long 0x020003c0,0x60000050 # at location 0 is loaded.
- .long 0x02000410,0x60000050 # Initial processing starts
- .long 0x02000460,0x60000050 # at 0x200 = iplstart.
- .long 0x020004b0,0x60000050
- .long 0x02000500,0x60000050
- .long 0x02000550,0x60000050
- .long 0x020005a0,0x60000050
- .long 0x020005f0,0x60000050
- .long 0x02000640,0x60000050
- .long 0x02000690,0x60000050
- .long 0x020006e0,0x20000050
-
- .org 0x200
-
-#
-# subroutine to wait for end I/O
-#
-.Lirqwait:
- mvc __LC_IO_NEW_PSW(16),.Lnewpsw # set up IO interrupt psw
- lpsw .Lwaitpsw
-.Lioint:
- br %r14
- .align 8
-.Lnewpsw:
- .quad 0x0000000080000000,.Lioint
-.Lwaitpsw:
- .long 0x020a0000,0x80000000+.Lioint
-
-#
-# subroutine for loading cards from the reader
-#
-.Lloader:
- la %r4,0(%r14)
- la %r3,.Lorb # r2 = address of orb into r2
- la %r5,.Lirb # r4 = address of irb
- la %r6,.Lccws
- la %r7,20
-.Linit:
- st %r2,4(%r6) # initialize CCW data addresses
- la %r2,0x50(%r2)
- la %r6,8(%r6)
- bct 7,.Linit
-
- lctl %c6,%c6,.Lcr6 # set IO subclass mask
- slr %r2,%r2
-.Lldlp:
- ssch 0(%r3) # load chunk of 1600 bytes
- bnz .Llderr
-.Lwait4irq:
- bas %r14,.Lirqwait
- c %r1,__LC_SUBCHANNEL_ID # compare subchannel number
- bne .Lwait4irq
- tsch 0(%r5)
-
- slr %r0,%r0
- ic %r0,8(%r5) # get device status
- chi %r0,8 # channel end ?
- be .Lcont
- chi %r0,12 # channel end + device end ?
- be .Lcont
-
- l %r0,4(%r5)
- s %r0,8(%r3) # r0/8 = number of ccws executed
- mhi %r0,10 # *10 = number of bytes in ccws
- lh %r3,10(%r5) # get residual count
- sr %r0,%r3 # #ccws*80-residual=#bytes read
- ar %r2,%r0
-
- br %r4 # r2 contains the total size
-
-.Lcont:
- ahi %r2,0x640 # add 0x640 to total size
- la %r6,.Lccws
- la %r7,20
-.Lincr:
- l %r0,4(%r6) # update CCW data addresses
- ahi %r0,0x640
- st %r0,4(%r6)
- ahi %r6,8
- bct 7,.Lincr
-
- b .Lldlp
-.Llderr:
- lpsw .Lcrash
-
- .align 8
-.Lorb: .long 0x00000000,0x0080ff00,.Lccws
-.Lirb: .long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-.Lcr6: .long 0xff000000
-.Lloadp:.long 0,0
- .align 8
-.Lcrash:.long 0x000a0000,0x00000000
-
- .align 8
-.Lccws: .rept 19
- .long 0x02600050,0x00000000
- .endr
- .long 0x02200050,0x00000000
-
-iplstart:
- mvi __LC_AR_MODE_ID,1 # set esame flag
- slr %r0,%r0 # set cpuid to zero
- lhi %r1,2 # mode 2 = esame (dump)
- sigp %r1,%r0,0x12 # switch to esame mode
- bras %r13,0f
- .fill 16,4,0x0
-0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
- sam31 # switch to 31 bit addressing mode
- lh %r1,__LC_SUBCHANNEL_ID # test if subchannel number
- bct %r1,.Lnoload # is valid
- l %r1,__LC_SUBCHANNEL_ID # load ipl subchannel number
- la %r2,IPL_BS # load start address
- bas %r14,.Lloader # load rest of ipl image
- l %r12,.Lparm # pointer to parameter area
- st %r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
-
-#
-# load parameter file from ipl device
-#
-.Lagain1:
- l %r2,.Linitrd # ramdisk loc. is temp
- bas %r14,.Lloader # load parameter file
- ltr %r2,%r2 # got anything ?
- bz .Lnopf
- chi %r2,895
- bnh .Lnotrunc
- la %r2,895
-.Lnotrunc:
- l %r4,.Linitrd
- clc 0(3,%r4),.L_hdr # if it is HDRx
- bz .Lagain1 # skip dataset header
- clc 0(3,%r4),.L_eof # if it is EOFx
- bz .Lagain1 # skip dateset trailer
- la %r5,0(%r4,%r2)
- lr %r3,%r2
- la %r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
- mvc 0(256,%r3),0(%r4)
- mvc 256(256,%r3),256(%r4)
- mvc 512(256,%r3),512(%r4)
- mvc 768(122,%r3),768(%r4)
- slr %r0,%r0
- b .Lcntlp
-.Ldelspc:
- ic %r0,0(%r2,%r3)
- chi %r0,0x20 # is it a space ?
- be .Lcntlp
- ahi %r2,1
- b .Leolp
-.Lcntlp:
- brct %r2,.Ldelspc
-.Leolp:
- slr %r0,%r0
- stc %r0,0(%r2,%r3) # terminate buffer
-.Lnopf:
-
-#
-# load ramdisk from ipl device
-#
-.Lagain2:
- l %r2,.Linitrd # addr of ramdisk
- st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
- bas %r14,.Lloader # load ramdisk
- st %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
- ltr %r2,%r2
- bnz .Lrdcont
- st %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
-.Lrdcont:
- l %r2,.Linitrd
-
- clc 0(3,%r2),.L_hdr # skip HDRx and EOFx
- bz .Lagain2
- clc 0(3,%r2),.L_eof
- bz .Lagain2
-
-#
-# reset files in VM reader
-#
- stidp .Lcpuid # store cpuid
- tm .Lcpuid,0xff # running VM ?
- bno .Lnoreset
- la %r2,.Lreset
- lhi %r3,26
- diag %r2,%r3,8
- la %r5,.Lirb
- stsch 0(%r5) # check if irq is pending
- tm 30(%r5),0x0f # by verifying if any of the
- bnz .Lwaitforirq # activity or status control
- tm 31(%r5),0xff # bits is set in the schib
- bz .Lnoreset
-.Lwaitforirq:
- bas %r14,.Lirqwait # wait for IO interrupt
- c %r1,__LC_SUBCHANNEL_ID # compare subchannel number
- bne .Lwaitforirq
- la %r5,.Lirb
- tsch 0(%r5)
-.Lnoreset:
- b .Lnoload
-
-#
-# everything loaded, go for it
-#
-.Lnoload:
- l %r1,.Lstartup
- br %r1
-
-.Linitrd:.long _end # default address of initrd
-.Lparm: .long PARMAREA
-.Lstartup: .long startup
-.Lreset:.byte 0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
- .byte 0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
- .byte 0xc8,0xd6,0xd3,0xc4 # "change rdr all keep nohold"
-.L_eof: .long 0xc5d6c600 /* C'EOF' */
-.L_hdr: .long 0xc8c4d900 /* C'HDR' */
- .align 8
-.Lcpuid:.fill 8,1,0
-
-#
-# startup-code at 0x10000, running in absolute addressing mode
-# this is called either by the ipl loader or directly by PSW restart
-# or linload or SALIPL
-#
- .org 0x10000
-ENTRY(startup)
- j .Lep_startup_normal
- .org 0x10008
-#
-# This is a list of s390 kernel entry points. At address 0x1000f the number of
-# valid entry points is stored.
-#
-# IMPORTANT: Do not change this table, it is s390 kernel ABI!
-#
- .ascii "S390EP"
- .byte 0x00,0x01
-#
-# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
-#
- .org 0x10010
-ENTRY(startup_kdump)
- j .Lep_startup_kdump
-.Lep_startup_normal:
- mvi __LC_AR_MODE_ID,1 # set esame flag
- slr %r0,%r0 # set cpuid to zero
- lhi %r1,2 # mode 2 = esame (dump)
- sigp %r1,%r0,0x12 # switch to esame mode
- bras %r13,0f
- .fill 16,4,0x0
-0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs
- sam64 # switch to 64 bit addressing mode
- basr %r13,0 # get base
-.LPG0:
- xc 0x200(256),0x200 # partially clear lowcore
- xc 0x300(256),0x300
- xc 0xe00(256),0xe00
- xc 0xf00(256),0xf00
- lctlg %c0,%c15,0x200(%r0) # initialize control registers
- stcke __LC_BOOT_CLOCK
- mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
- spt 6f-.LPG0(%r13)
- mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
- l %r15,.Lstack-.LPG0(%r13)
- ahi %r15,-STACK_FRAME_OVERHEAD
- brasl %r14,verify_facilities
-# For uncompressed images, continue in
-# arch/s390/kernel/head64.S. For compressed images, continue in
-# arch/s390/boot/compressed/head.S.
- jg startup_continue
-
-.Lstack:
- .long 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
- .align 8
-6: .long 0x7fffffff,0xffffffff
-
-#include "head_kdump.S"
-
-#
-# params at 10400 (setup.h)
-#
- .org PARMAREA
- .long 0,0 # IPL_DEVICE
- .long 0,0 # INITRD_START
- .long 0,0 # INITRD_SIZE
- .long 0,0 # OLDMEM_BASE
- .long 0,0 # OLDMEM_SIZE
-
- .org COMMAND_LINE
- .byte "root=/dev/ram0 ro"
- .byte 0
-
- .org 0x11000
# Early machine initialization and detection functions.
#
brasl %r14,startup_init
- lpswe .Lentry-.LPG1(13) # jump to _stext in primary-space,
- # virtual and never return ...
+
+# check control registers
+ stctg %c0,%c15,0(%r15)
+ oi 6(%r15),0x60 # enable sigp emergency & external call
+ oi 4(%r15),0x10 # switch on low address proctection
+ lctlg %c0,%c15,0(%r15)
+
+ lam 0,15,.Laregs-.LPG1(%r13) # load acrs needed by uaccess
+ brasl %r14,start_kernel # go to C code
+#
+# We returned from start_kernel ?!? PANIK
+#
+ basr %r13,0
+ lpswe .Ldw-.(%r13) # load disabled wait psw
+
.align 16
.LPG1:
-.Lentry:.quad 0x0000000180000000,_stext
.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
.quad 0 # cr1: primary space segment table
.quad .Lduct # cr2: dispatchable unit control table
.endr
.Llinkage_stack:
.long 0,0,0x89000000,0,0,0,0x8a000000,0
-
-ENTRY(_ehead)
-
- .org 0x100000 - 0x11000 # head.o ends at 0x11000
-#
-# startup-code, running in absolute addressing mode
-#
-ENTRY(_stext)
- basr %r13,0 # get base
-.LPG3:
-# check control registers
- stctg %c0,%c15,0(%r15)
- oi 6(%r15),0x60 # enable sigp emergency & external call
- oi 4(%r15),0x10 # switch on low address proctection
- lctlg %c0,%c15,0(%r15)
-
- lam 0,15,.Laregs-.LPG3(%r13) # load acrs needed by uaccess
- brasl %r14,start_kernel # go to C code
-#
-# We returned from start_kernel ?!? PANIK
-#
- basr %r13,0
- lpswe .Ldw-.(%r13) # load disabled wait psw
-
- .align 8
.Ldw: .quad 0x0002000180000000,0x0000000000000000
.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * S390 kdump lowlevel functions (new kernel)
- *
- * Copyright IBM Corp. 2011
- * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <asm/sigp.h>
-
-#define DATAMOVER_ADDR 0x4000
-#define COPY_PAGE_ADDR 0x6000
-
-#ifdef CONFIG_CRASH_DUMP
-
-#
-# kdump entry (new kernel - not yet relocated)
-#
-# Note: This code has to be position independent
-#
-
-.align 2
-.Lep_startup_kdump:
- lhi %r1,2 # mode 2 = esame (dump)
- sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to esame mode
- sam64 # Switch to 64 bit addressing
- basr %r13,0
-.Lbase:
- larl %r2,.Lbase_addr # Check, if we have been
- lg %r2,0(%r2) # already relocated:
- clgr %r2,%r13 #
- jne .Lrelocate # No : Start data mover
- lghi %r2,0 # Yes: Start kdump kernel
- brasl %r14,startup_kdump_relocated
-
-.Lrelocate:
- larl %r4,startup
- lg %r2,0x418(%r4) # Get kdump base
- lg %r3,0x420(%r4) # Get kdump size
-
- larl %r10,.Lcopy_start # Source of data mover
- lghi %r8,DATAMOVER_ADDR # Target of data mover
- mvc 0(256,%r8),0(%r10) # Copy data mover code
-
- agr %r8,%r2 # Copy data mover to
- mvc 0(256,%r8),0(%r10) # reserved mem
-
- lghi %r14,DATAMOVER_ADDR # Jump to copied data mover
- basr %r14,%r14
-.Lbase_addr:
- .quad .Lbase
-
-#
-# kdump data mover code (runs at address DATAMOVER_ADDR)
-#
-# r2: kdump base address
-# r3: kdump size
-#
-.Lcopy_start:
- basr %r13,0 # Base
-0:
- lgr %r11,%r2 # Save kdump base address
- lgr %r12,%r2
- agr %r12,%r3 # Compute kdump end address
-
- lghi %r5,0
- lghi %r10,COPY_PAGE_ADDR # Load copy page address
-1:
- mvc 0(256,%r10),0(%r5) # Copy old kernel to tmp
- mvc 0(256,%r5),0(%r11) # Copy new kernel to old
- mvc 0(256,%r11),0(%r10) # Copy tmp to new
- aghi %r11,256
- aghi %r5,256
- clgr %r11,%r12
- jl 1b
-
- lg %r14,.Lstartup_kdump-0b(%r13)
- basr %r14,%r14 # Start relocated kernel
-.Lstartup_kdump:
- .long 0x00000000,0x00000000 + startup_kdump_relocated
-.Lcopy_end:
-
-#
-# Startup of kdump (relocated new kernel)
-#
-.align 2
-startup_kdump_relocated:
- basr %r13,0
-0: lpswe .Lrestart_psw-0b(%r13) # Start new kernel...
-.align 8
-.Lrestart_psw:
- .quad 0x0000000080000000,0x0000000000000000 + startup
-#else
-.align 2
-.Lep_startup_kdump:
- larl %r13,startup_kdump_crash
- lpswe 0(%r13)
-.align 8
-startup_kdump_crash:
- .quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash
-#endif /* CONFIG_CRASH_DUMP */
* If we have no pre-handler or it returned 0, we
* continue with single stepping. If we have a
* pre-handler and it returned non-zero, it prepped
- * for calling the break_handler below on re-entry
- * for jprobe processing, so get out doing nothing
- * more here.
+ * for changing execution path, so get out doing
+ * nothing more here.
*/
push_kprobe(kcb, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (p->pre_handler && p->pre_handler(p, regs))
+ if (p->pre_handler && p->pre_handler(p, regs)) {
+ pop_kprobe(kcb);
+ preempt_enable_no_resched();
return 1;
+ }
kcb->kprobe_status = KPROBE_HIT_SS;
}
enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
return 1;
- } else if (kprobe_running()) {
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- /*
- * Continuation after the jprobe completed and
- * caused the jprobe_return trap. The jprobe
- * break_handler "returns" to the original
- * function that still has the kprobe breakpoint
- * installed. We continue with single stepping.
- */
- kcb->kprobe_status = KPROBE_HIT_SS;
- enable_singlestep(kcb, regs,
- (unsigned long) p->ainsn.insn);
- return 1;
- } /* else:
- * No kprobe at this address and the current kprobe
- * has no break handler (no jprobe!). The kernel just
- * exploded, let the standard trap handler pick up the
- * pieces.
- */
} /* else:
* No kprobe at this address and no active kprobe. The trap has
* not been caused by a kprobe breakpoint. The race of breakpoint
regs->psw.addr = orig_ret_address;
- pop_kprobe(get_kprobe_ctlblk());
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
}
NOKPROBE_SYMBOL(kprobe_exceptions_notify);
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- unsigned long stack;
-
- memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
- /* setup return addr to the jprobe handler routine */
- regs->psw.addr = (unsigned long) jp->entry;
- regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-
- /* r15 is the stack pointer */
- stack = (unsigned long) regs->gprs[15];
-
- memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
-
- /*
- * jprobes use jprobe_return() which skips the normal return
- * path of the function, and this messes up the accounting of the
- * function graph tracer to get messed up.
- *
- * Pause function graph tracing while performing the jprobe function.
- */
- pause_graph_tracing();
- return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
- asm volatile(".word 0x0002");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- unsigned long stack;
-
- /* It's OK to start function graph tracing again */
- unpause_graph_tracing();
-
- stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
-
- /* Put the regs back */
- memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
- /* put the stack back */
- memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
- preempt_enable_no_resched();
- return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
static struct kprobe trampoline = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
static int __init nospec_report(void)
{
+ if (test_facility(156))
+ pr_info("Spectre V2 mitigation: etokens\n");
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
pr_info("Spectre V2 mitigation: execute trampolines\n");
if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
void __init nospec_auto_detect(void)
{
- if (IS_ENABLED(CC_USING_EXPOLINE)) {
+ if (test_facility(156)) {
+ /*
+ * The machine supports etokens.
+ * Disable expolines and disable nobp.
+ */
+ if (IS_ENABLED(CC_USING_EXPOLINE))
+ nospec_disable = 1;
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+ } else if (IS_ENABLED(CC_USING_EXPOLINE)) {
/*
* The kernel has been compiled with expolines.
* Keep expolines enabled and disable nobp.
ssize_t cpu_show_spectre_v2(struct device *dev,
struct device_attribute *attr, char *buf)
{
+ if (test_facility(156))
+ return sprintf(buf, "Mitigation: etokens\n");
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
return sprintf(buf, "Mitigation: execute trampolines\n");
if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
/*
* Performance event support for the System z CPU-measurement Sampling Facility
*
- * Copyright IBM Corp. 2013
+ * Copyright IBM Corp. 2013, 2018
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
*/
#define KMSG_COMPONENT "cpum_sf"
"%lu SDBTs\n", num_sdbt);
}
+static void aux_sdb_init(unsigned long sdb)
+{
+ struct hws_trailer_entry *te;
+
+ te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+
+ /* Save clock base */
+ te->clock_base = 1;
+ memcpy(&te->progusage2, &tod_clock_base[1], 8);
+}
+
/*
* aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
* @cpu: On which to allocate, -1 means current
/* Tail is the entry in a SDBT */
*tail = (unsigned long)pages[i];
aux->sdb_index[i] = (unsigned long)pages[i];
+ aux_sdb_init((unsigned long)pages[i]);
}
sfb->num_sdb = nr_pages;
{
freg_t fp;
- if (WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX))
- return 0;
-
if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15)
return regs->gprs[idx];
if (idx == PERF_REG_S390_PC)
return regs->psw.addr;
- return regs->gprs[idx];
+ WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX);
+ return 0;
}
#define REG_RESERVED (~((1UL << PERF_REG_S390_MAX) - 1))
#ifdef CONFIG_DMA_API_DEBUG
/*
* DMA_API_DEBUG code stumbles over addresses from the
- * range [_ehead, _stext]. Mark the memory as reserved
+ * range [PARMAREA_END, _stext]. Mark the memory as reserved
* so it is not used for CONFIG_DMA_API_DEBUG=y.
*/
memblock_reserve(0, PFN_PHYS(start_pfn));
#else
- memblock_reserve(0, (unsigned long)_ehead);
+ memblock_reserve(0, PARMAREA_END);
memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
- (unsigned long)_stext);
#endif
}
/* No longer in a system call */
clear_pt_regs_flag(regs, PIF_SYSCALL);
-
+ rseq_signal_deliver(&ksig, regs);
if (is_compat_task())
handle_signal32(&ksig, oldset, regs);
else
{
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
379 common statx sys_statx compat_sys_statx
380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi
381 common kexec_file_load sys_kexec_file_load compat_sys_kexec_file_load
+382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents
+383 common rseq sys_rseq compat_sys_rseq
}
EXPORT_SYMBOL(stsi);
+#ifdef CONFIG_PROC_FS
+
static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
{
switch (encoding) {
}
device_initcall(sysinfo_create_proc);
+#endif /* CONFIG_PROC_FS */
+
/*
* Service levels interface.
*/
ext_to_timespec64(clk, ts);
}
-void read_boot_clock64(struct timespec64 *ts)
+void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+ struct timespec64 *boot_offset)
{
unsigned char clk[STORE_CLOCK_EXT_SIZE];
+ struct timespec64 boot_time;
__u64 delta;
delta = initial_leap_seconds + TOD_UNIX_EPOCH;
- memcpy(clk, tod_clock_base, 16);
- *(__u64 *) &clk[1] -= delta;
- if (*(__u64 *) &clk[1] > delta)
+ memcpy(clk, tod_clock_base, STORE_CLOCK_EXT_SIZE);
+ *(__u64 *)&clk[1] -= delta;
+ if (*(__u64 *)&clk[1] > delta)
clk[0]--;
- ext_to_timespec64(clk, ts);
+ ext_to_timespec64(clk, &boot_time);
+
+ read_persistent_clock64(wall_time);
+ *boot_offset = timespec64_sub(*wall_time, boot_time);
}
static u64 read_tod_clock(struct clocksource *cs)
static int topology_ctl_handler(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- unsigned int len;
+ int enabled = topology_is_enabled();
int new_mode;
- char buf[2];
+ int zero = 0;
+ int one = 1;
+ int rc;
+ struct ctl_table ctl_entry = {
+ .procname = ctl->procname,
+ .data = &enabled,
+ .maxlen = sizeof(int),
+ .extra1 = &zero,
+ .extra2 = &one,
+ };
+
+ rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write)
+ return rc;
- if (!*lenp || *ppos) {
- *lenp = 0;
- return 0;
- }
- if (!write) {
- strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
- ARRAY_SIZE(buf));
- len = strnlen(buf, ARRAY_SIZE(buf));
- if (len > *lenp)
- len = *lenp;
- if (copy_to_user(buffer, buf, len))
- return -EFAULT;
- goto out;
- }
- len = *lenp;
- if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
- return -EFAULT;
- if (buf[0] != '0' && buf[0] != '1')
- return -EINVAL;
mutex_lock(&smp_cpu_state_mutex);
- new_mode = topology_get_mode(buf[0] == '1');
+ new_mode = topology_get_mode(enabled);
if (topology_mode != new_mode) {
topology_mode = new_mode;
topology_schedule_update();
}
mutex_unlock(&smp_cpu_state_mutex);
topology_flush_work();
-out:
- *lenp = len;
- *ppos += len;
- return 0;
+
+ return rc;
}
static struct ctl_table topology_ctl_table[] = {
*/
unsigned int __read_mostly vdso_enabled = 1;
-static int vdso_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page **vdso_pagelist;
OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
OUTPUT_ARCH(s390:64-bit)
-ENTRY(startup)
+ENTRY(startup_continue)
jiffies = jiffies_64;
PHDRS {
SECTIONS
{
- . = 0x00000000;
+ . = 0x100000;
+ _stext = .; /* Start of text section */
.text : {
/* Text and read-only data */
+ _text = .;
HEAD_TEXT
- /*
- * E.g. perf doesn't like symbols starting at address zero,
- * therefore skip the initial PSW and channel program located
- * at address zero and let _text start at 0x200.
- */
- _text = 0x200;
TEXT_TEXT
SCHED_TEXT
CPUIDLE_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
+ *(.text.*_indirect_*)
*(.fixup)
*(.gnu.warning)
} :text = 0x0700
* yield-candidate.
*/
vcpu->preempted = true;
- swake_up(&vcpu->wq);
+ swake_up_one(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
/*
module_param(nested, int, S_IRUGO);
MODULE_PARM_DESC(nested, "Nested virtualization support");
+/* allow 1m huge page guest backing, if !nested */
+static int hpage;
+module_param(hpage, int, 0444);
+MODULE_PARM_DESC(hpage, "1m huge page backing support");
/*
* For now we handle at most 16 double words as this is what the s390 base
case KVM_CAP_S390_AIS_MIGRATION:
r = 1;
break;
+ case KVM_CAP_S390_HPAGE_1M:
+ r = 0;
+ if (hpage)
+ r = 1;
+ break;
case KVM_CAP_S390_MEM_OP:
r = MEM_OP_MAX_SIZE;
break;
}
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
- struct kvm_memory_slot *memslot)
+ struct kvm_memory_slot *memslot)
{
+ int i;
gfn_t cur_gfn, last_gfn;
- unsigned long address;
+ unsigned long gaddr, vmaddr;
struct gmap *gmap = kvm->arch.gmap;
+ DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
- /* Loop over all guest pages */
+ /* Loop over all guest segments */
+ cur_gfn = memslot->base_gfn;
last_gfn = memslot->base_gfn + memslot->npages;
- for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
- address = gfn_to_hva_memslot(memslot, cur_gfn);
+ for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
+ gaddr = gfn_to_gpa(cur_gfn);
+ vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
+ if (kvm_is_error_hva(vmaddr))
+ continue;
+
+ bitmap_zero(bitmap, _PAGE_ENTRIES);
+ gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
+ for (i = 0; i < _PAGE_ENTRIES; i++) {
+ if (test_bit(i, bitmap))
+ mark_page_dirty(kvm, cur_gfn + i);
+ }
- if (test_and_clear_guest_dirty(gmap->mm, address))
- mark_page_dirty(kvm, cur_gfn);
if (fatal_signal_pending(current))
return;
cond_resched();
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
r ? "(not available)" : "(success)");
break;
+ case KVM_CAP_S390_HPAGE_1M:
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus)
+ r = -EBUSY;
+ else if (!hpage || kvm->arch.use_cmma)
+ r = -EINVAL;
+ else {
+ r = 0;
+ kvm->mm->context.allow_gmap_hpage_1m = 1;
+ /*
+ * We might have to create fake 4k page
+ * tables. To avoid that the hardware works on
+ * stale PGSTEs, we emulate these instructions.
+ */
+ kvm->arch.use_skf = 0;
+ kvm->arch.use_pfmfi = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
+ r ? "(not available)" : "(success)");
+ break;
case KVM_CAP_S390_USER_STSI:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
kvm->arch.user_stsi = 1;
if (!sclp.has_cmma)
break;
- ret = -EBUSY;
VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
mutex_lock(&kvm->lock);
- if (!kvm->created_vcpus) {
+ if (kvm->created_vcpus)
+ ret = -EBUSY;
+ else if (kvm->mm->context.allow_gmap_hpage_1m)
+ ret = -EINVAL;
+ else {
kvm->arch.use_cmma = 1;
/* Not compatible with cmma. */
kvm->arch.use_pfmfi = 0;
uint8_t *keys;
uint64_t hva;
int srcu_idx, i, r = 0;
+ bool unlocked;
if (args->flags != 0)
return -EINVAL;
if (r)
goto out;
+ i = 0;
down_read(¤t->mm->mmap_sem);
srcu_idx = srcu_read_lock(&kvm->srcu);
- for (i = 0; i < args->count; i++) {
+ while (i < args->count) {
+ unlocked = false;
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
}
r = set_guest_storage_key(current->mm, hva, keys[i], 0);
- if (r)
- break;
+ if (r) {
+ r = fixup_user_fault(current, current->mm, hva,
+ FAULT_FLAG_WRITE, &unlocked);
+ if (r)
+ break;
+ }
+ if (!r)
+ i++;
}
srcu_read_unlock(&kvm->srcu, srcu_idx);
up_read(¤t->mm->mmap_sem);
return -ENODEV;
}
+ if (nested && hpage) {
+ pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+ return -EINVAL;
+ }
+
for (i = 0; i < 16; i++)
kvm_s390_fac_base[i] |=
S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);
static int handle_iske(struct kvm_vcpu *vcpu)
{
- unsigned long addr;
+ unsigned long gaddr, vmaddr;
unsigned char key;
int reg1, reg2;
+ bool unlocked;
int rc;
vcpu->stat.instruction_iske++;
kvm_s390_get_regs_rre(vcpu, ®1, ®2);
- addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
- addr = kvm_s390_logical_to_effective(vcpu, addr);
- addr = kvm_s390_real_to_abs(vcpu, addr);
- addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
- if (kvm_is_error_hva(addr))
+ gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+ gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+ gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+ vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+ if (kvm_is_error_hva(vmaddr))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+ unlocked = false;
down_read(¤t->mm->mmap_sem);
- rc = get_guest_storage_key(current->mm, addr, &key);
- up_read(¤t->mm->mmap_sem);
+ rc = get_guest_storage_key(current->mm, vmaddr, &key);
+
+ if (rc) {
+ rc = fixup_user_fault(current, current->mm, vmaddr,
+ FAULT_FLAG_WRITE, &unlocked);
+ if (!rc) {
+ up_read(¤t->mm->mmap_sem);
+ goto retry;
+ }
+ }
if (rc)
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ up_read(¤t->mm->mmap_sem);
vcpu->run->s.regs.gprs[reg1] &= ~0xff;
vcpu->run->s.regs.gprs[reg1] |= key;
return 0;
static int handle_rrbe(struct kvm_vcpu *vcpu)
{
- unsigned long addr;
+ unsigned long vmaddr, gaddr;
int reg1, reg2;
+ bool unlocked;
int rc;
vcpu->stat.instruction_rrbe++;
kvm_s390_get_regs_rre(vcpu, ®1, ®2);
- addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
- addr = kvm_s390_logical_to_effective(vcpu, addr);
- addr = kvm_s390_real_to_abs(vcpu, addr);
- addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
- if (kvm_is_error_hva(addr))
+ gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+ gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+ gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+ vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+ if (kvm_is_error_hva(vmaddr))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+ unlocked = false;
down_read(¤t->mm->mmap_sem);
- rc = reset_guest_reference_bit(current->mm, addr);
- up_read(¤t->mm->mmap_sem);
+ rc = reset_guest_reference_bit(current->mm, vmaddr);
+ if (rc < 0) {
+ rc = fixup_user_fault(current, current->mm, vmaddr,
+ FAULT_FLAG_WRITE, &unlocked);
+ if (!rc) {
+ up_read(¤t->mm->mmap_sem);
+ goto retry;
+ }
+ }
if (rc < 0)
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+ up_read(¤t->mm->mmap_sem);
kvm_s390_set_psw_cc(vcpu, rc);
return 0;
}
unsigned long start, end;
unsigned char key, oldkey;
int reg1, reg2;
+ bool unlocked;
int rc;
vcpu->stat.instruction_sske++;
}
while (start != end) {
- unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+ unsigned long vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+ unlocked = false;
- if (kvm_is_error_hva(addr))
+ if (kvm_is_error_hva(vmaddr))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
down_read(¤t->mm->mmap_sem);
- rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey,
+ rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey,
m3 & SSKE_NQ, m3 & SSKE_MR,
m3 & SSKE_MC);
- up_read(¤t->mm->mmap_sem);
- if (rc < 0)
+
+ if (rc < 0) {
+ rc = fixup_user_fault(current, current->mm, vmaddr,
+ FAULT_FLAG_WRITE, &unlocked);
+ rc = !rc ? -EAGAIN : rc;
+ }
+ if (rc == -EFAULT)
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
- start += PAGE_SIZE;
+
+ up_read(¤t->mm->mmap_sem);
+ if (rc >= 0)
+ start += PAGE_SIZE;
}
if (m3 & (SSKE_MC | SSKE_MR)) {
}
while (start != end) {
- unsigned long useraddr;
+ unsigned long vmaddr;
+ bool unlocked = false;
/* Translate guest address to host address */
- useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
- if (kvm_is_error_hva(useraddr))
+ vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+ if (kvm_is_error_hva(vmaddr))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
- if (clear_user((void __user *)useraddr, PAGE_SIZE))
+ if (clear_user((void __user *)vmaddr, PAGE_SIZE))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
}
if (rc)
return rc;
down_read(¤t->mm->mmap_sem);
- rc = cond_set_guest_storage_key(current->mm, useraddr,
+ rc = cond_set_guest_storage_key(current->mm, vmaddr,
key, NULL, nq, mr, mc);
- up_read(¤t->mm->mmap_sem);
- if (rc < 0)
+ if (rc < 0) {
+ rc = fixup_user_fault(current, current->mm, vmaddr,
+ FAULT_FLAG_WRITE, &unlocked);
+ rc = !rc ? -EAGAIN : rc;
+ }
+ if (rc == -EFAULT)
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
- }
- start += PAGE_SIZE;
+ up_read(¤t->mm->mmap_sem);
+ if (rc >= 0)
+ start += PAGE_SIZE;
+ }
}
if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
ENTRY(memmove)
ltgr %r4,%r4
lgr %r1,%r2
- bzr %r14
+ jz .Lmemmove_exit
aghi %r4,-1
clgr %r2,%r3
jnh .Lmemmove_forward
.Lmemmove_forward_remainder:
larl %r5,.Lmemmove_mvc
ex %r4,0(%r5)
+.Lmemmove_exit:
BR_EX %r14
.Lmemmove_reverse:
ic %r0,0(%r4,%r3)
*/
ENTRY(memset)
ltgr %r4,%r4
- bzr %r14
+ jz .Lmemset_exit
ltgr %r3,%r3
jnz .Lmemset_fill
aghi %r4,-1
.Lmemset_clear_remainder:
larl %r3,.Lmemset_xc
ex %r4,0(%r3)
+.Lmemset_exit:
BR_EX %r14
.Lmemset_fill:
cghi %r4,1
*/
ENTRY(memcpy)
ltgr %r4,%r4
- bzr %r14
+ jz .Lmemcpy_exit
aghi %r4,-1
srlg %r5,%r4,8
ltgr %r5,%r5
.Lmemcpy_remainder:
larl %r5,.Lmemcpy_mvc
ex %r4,0(%r5)
+.Lmemcpy_exit:
BR_EX %r14
.Lmemcpy_loop:
mvc 0(256,%r1),0(%r3)
.macro __MEMSET bits,bytes,insn
ENTRY(__memset\bits)
ltgr %r4,%r4
- bzr %r14
+ jz .L__memset_exit\bits
cghi %r4,\bytes
- je .L__memset_exit\bits
+ je .L__memset_store\bits
aghi %r4,-(\bytes+1)
srlg %r5,%r4,8
ltgr %r5,%r5
larl %r5,.L__memset_mvc\bits
ex %r4,0(%r5)
BR_EX %r14
-.L__memset_exit\bits:
+.L__memset_store\bits:
\insn %r3,0(%r2)
+.L__memset_exit\bits:
BR_EX %r14
.L__memset_mvc\bits:
mvc \bytes(1,%r1),0(%r1)
del_timer(&cmm_timer);
return;
}
- if (timer_pending(&cmm_timer)) {
- if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ))
- return;
- }
- cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ;
- add_timer(&cmm_timer);
+ mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ);
}
static void cmm_timer_fn(struct timer_list *unused)
return str != cp;
}
-static struct ctl_table cmm_table[];
-
static int cmm_pages_handler(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- char buf[16], *p;
- unsigned int len;
- long nr;
+ long nr = cmm_get_pages();
+ struct ctl_table ctl_entry = {
+ .procname = ctl->procname,
+ .data = &nr,
+ .maxlen = sizeof(long),
+ };
+ int rc;
- if (!*lenp || (*ppos && !write)) {
- *lenp = 0;
- return 0;
- }
+ rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write)
+ return rc;
- if (write) {
- len = *lenp;
- if (copy_from_user(buf, buffer,
- len > sizeof(buf) ? sizeof(buf) : len))
- return -EFAULT;
- buf[sizeof(buf) - 1] = '\0';
- cmm_skip_blanks(buf, &p);
- nr = simple_strtoul(p, &p, 0);
- if (ctl == &cmm_table[0])
- cmm_set_pages(nr);
- else
- cmm_add_timed_pages(nr);
- } else {
- if (ctl == &cmm_table[0])
- nr = cmm_get_pages();
- else
- nr = cmm_get_timed_pages();
- len = sprintf(buf, "%ld\n", nr);
- if (len > *lenp)
- len = *lenp;
- if (copy_to_user(buffer, buf, len))
- return -EFAULT;
- }
- *lenp = len;
- *ppos += len;
+ cmm_set_pages(nr);
+ return 0;
+}
+
+static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ long nr = cmm_get_timed_pages();
+ struct ctl_table ctl_entry = {
+ .procname = ctl->procname,
+ .data = &nr,
+ .maxlen = sizeof(long),
+ };
+ int rc;
+
+ rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+ if (rc < 0 || !write)
+ return rc;
+
+ cmm_add_timed_pages(nr);
return 0;
}
{
.procname = "cmm_timed_pages",
.mode = 0644,
- .proc_handler = cmm_pages_handler,
+ .proc_handler = cmm_timed_pages_handler,
},
{
.procname = "cmm_timeout",
struct dcss_segment {
struct list_head list;
char dcss_name[8];
- char res_name[15];
+ char res_name[16];
unsigned long start_addr;
unsigned long end;
atomic_t ref_count;
memcpy(&seg->res_name, seg->dcss_name, 8);
EBCASC(seg->res_name, 8);
seg->res_name[8] = '\0';
- strncat(seg->res_name, " (DCSS)", 7);
+ strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name));
seg->res->name = seg->res_name;
rc = seg->vm_segtype;
if (rc == SEG_TYPE_SC ||
/* No reason to continue if interrupted by SIGKILL. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
fault = VM_FAULT_SIGNAL;
+ if (flags & FAULT_FLAG_RETRY_NOWAIT)
+ goto out_up;
goto out;
}
if (unlikely(fault & VM_FAULT_ERROR))
/*
* KVM guest address space mapping code
*
- * Copyright IBM Corp. 2007, 2016
+ * Copyright IBM Corp. 2007, 2016, 2018
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ * David Hildenbrand <david@redhat.com>
+ * Janosch Frank <frankja@linux.vnet.ibm.com>
*/
#include <linux/kernel.h>
rcu_read_unlock();
}
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new,
+ unsigned long gaddr);
+
/**
* gmap_link - set up shadow page tables to connect a host to a guest address
* @gmap: pointer to guest mapping meta data structure
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
+ u64 unprot;
int rc;
BUG_ON(gmap_is_shadow(gmap));
return -EFAULT;
pmd = pmd_offset(pud, vmaddr);
VM_BUG_ON(pmd_none(*pmd));
- /* large pmds cannot yet be handled */
- if (pmd_large(*pmd))
+ /* Are we allowed to use huge pages? */
+ if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
return -EFAULT;
/* Link gmap segment table entry location to page table. */
rc = radix_tree_preload(GFP_KERNEL);
if (*table == _SEGMENT_ENTRY_EMPTY) {
rc = radix_tree_insert(&gmap->host_to_guest,
vmaddr >> PMD_SHIFT, table);
- if (!rc)
- *table = pmd_val(*pmd);
- } else
- rc = 0;
+ if (!rc) {
+ if (pmd_large(*pmd)) {
+ *table = (pmd_val(*pmd) &
+ _SEGMENT_ENTRY_HARDWARE_BITS_LARGE)
+ | _SEGMENT_ENTRY_GMAP_UC;
+ } else
+ *table = pmd_val(*pmd) &
+ _SEGMENT_ENTRY_HARDWARE_BITS;
+ }
+ } else if (*table & _SEGMENT_ENTRY_PROTECT &&
+ !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) {
+ unprot = (u64)*table;
+ unprot &= ~_SEGMENT_ENTRY_PROTECT;
+ unprot |= _SEGMENT_ENTRY_GMAP_UC;
+ gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr);
+ }
spin_unlock(&gmap->guest_table_lock);
spin_unlock(ptl);
radix_tree_preload_end();
vmaddr |= gaddr & ~PMD_MASK;
/* Find vma in the parent mm */
vma = find_vma(gmap->mm, vmaddr);
+ /*
+ * We do not discard pages that are backed by
+ * hugetlbfs, so we don't have to refault them.
+ */
+ if (vma && is_vm_hugetlb_page(vma))
+ continue;
size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
zap_page_range(vma, vmaddr, size);
}
*/
static void gmap_pte_op_end(spinlock_t *ptl)
{
- spin_unlock(ptl);
+ if (ptl)
+ spin_unlock(ptl);
+}
+
+/**
+ * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock
+ * and return the pmd pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ *
+ * Returns a pointer to the pmd for a guest address, or NULL
+ */
+static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
+{
+ pmd_t *pmdp;
+
+ BUG_ON(gmap_is_shadow(gmap));
+ spin_lock(&gmap->guest_table_lock);
+ pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+
+ if (!pmdp || pmd_none(*pmdp)) {
+ spin_unlock(&gmap->guest_table_lock);
+ return NULL;
+ }
+
+ /* 4k page table entries are locked via the pte (pte_alloc_map_lock). */
+ if (!pmd_large(*pmdp))
+ spin_unlock(&gmap->guest_table_lock);
+ return pmdp;
+}
+
+/**
+ * gmap_pmd_op_end - release the guest_table_lock if needed
+ * @gmap: pointer to the guest mapping meta data structure
+ * @pmdp: pointer to the pmd
+ */
+static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
+{
+ if (pmd_large(*pmdp))
+ spin_unlock(&gmap->guest_table_lock);
+}
+
+/*
+ * gmap_protect_pmd - remove access rights to memory and set pmd notification bits
+ * @pmdp: pointer to the pmd to be protected
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns:
+ * 0 if successfully protected
+ * -EAGAIN if a fixup is needed
+ * -EINVAL if unsupported notifier bits have been specified
+ *
+ * Expected to be called with sg->mm->mmap_sem in read and
+ * guest_table_lock held.
+ */
+static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
+ pmd_t *pmdp, int prot, unsigned long bits)
+{
+ int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
+ int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
+ pmd_t new = *pmdp;
+
+ /* Fixup needed */
+ if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
+ return -EAGAIN;
+
+ if (prot == PROT_NONE && !pmd_i) {
+ pmd_val(new) |= _SEGMENT_ENTRY_INVALID;
+ gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+ }
+
+ if (prot == PROT_READ && !pmd_p) {
+ pmd_val(new) &= ~_SEGMENT_ENTRY_INVALID;
+ pmd_val(new) |= _SEGMENT_ENTRY_PROTECT;
+ gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+ }
+
+ if (bits & GMAP_NOTIFY_MPROT)
+ pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN;
+
+ /* Shadow GMAP protection needs split PMDs */
+ if (bits & GMAP_NOTIFY_SHADOW)
+ return -EINVAL;
+
+ return 0;
+}
+
+/*
+ * gmap_protect_pte - remove access rights to memory and set pgste bits
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @pmdp: pointer to the pmd associated with the pte
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EAGAIN if a fixup is needed.
+ *
+ * Expected to be called with sg->mm->mmap_sem in read
+ */
+static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
+ pmd_t *pmdp, int prot, unsigned long bits)
+{
+ int rc;
+ pte_t *ptep;
+ spinlock_t *ptl = NULL;
+ unsigned long pbits = 0;
+
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return -EAGAIN;
+
+ ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl);
+ if (!ptep)
+ return -ENOMEM;
+
+ pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0;
+ pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
+ /* Protect and unlock. */
+ rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
+ gmap_pte_op_end(ptl);
+ return rc;
}
/*
static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
unsigned long len, int prot, unsigned long bits)
{
- unsigned long vmaddr;
- spinlock_t *ptl;
- pte_t *ptep;
+ unsigned long vmaddr, dist;
+ pmd_t *pmdp;
int rc;
BUG_ON(gmap_is_shadow(gmap));
while (len) {
rc = -EAGAIN;
- ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
- if (ptep) {
- rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
- gmap_pte_op_end(ptl);
+ pmdp = gmap_pmd_op_walk(gmap, gaddr);
+ if (pmdp) {
+ if (!pmd_large(*pmdp)) {
+ rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
+ bits);
+ if (!rc) {
+ len -= PAGE_SIZE;
+ gaddr += PAGE_SIZE;
+ }
+ } else {
+ rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
+ bits);
+ if (!rc) {
+ dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
+ len = len < dist ? 0 : len - dist;
+ gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
+ }
+ }
+ gmap_pmd_op_end(gmap, pmdp);
}
if (rc) {
+ if (rc == -EINVAL)
+ return rc;
+
+ /* -EAGAIN, fixup of userspace mm and gmap */
vmaddr = __gmap_translate(gmap, gaddr);
if (IS_ERR_VALUE(vmaddr))
return vmaddr;
rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
if (rc)
return rc;
- continue;
}
- gaddr += PAGE_SIZE;
- len -= PAGE_SIZE;
}
return 0;
}
if (!MACHINE_HAS_ESOP && prot == PROT_READ)
return -EINVAL;
down_read(&gmap->mm->mmap_sem);
- rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+ rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
up_read(&gmap->mm->mmap_sem);
return rc;
}
unsigned long limit;
int rc;
+ BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
BUG_ON(gmap_is_shadow(parent));
spin_lock(&parent->shadow_lock);
sg = gmap_find_shadow(parent, asce, edat_level);
down_read(&parent->mm->mmap_sem);
rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
- PROT_READ, PGSTE_VSIE_BIT);
+ PROT_READ, GMAP_NOTIFY_SHADOW);
up_read(&parent->mm->mmap_sem);
spin_lock(&parent->shadow_lock);
new->initialized = true;
}
EXPORT_SYMBOL_GPL(ptep_notify);
+static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
+ unsigned long gaddr)
+{
+ pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_IN;
+ gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
+}
+
+/**
+ * gmap_pmdp_xchg - exchange a gmap pmd with another
+ * @gmap: pointer to the guest address space structure
+ * @pmdp: pointer to the pmd entry
+ * @new: replacement entry
+ * @gaddr: the affected guest address
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
+ unsigned long gaddr)
+{
+ gaddr &= HPAGE_MASK;
+ pmdp_notify_gmap(gmap, pmdp, gaddr);
+ pmd_val(new) &= ~_SEGMENT_ENTRY_GMAP_IN;
+ if (MACHINE_HAS_TLB_GUEST)
+ __pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
+ IDTE_GLOBAL);
+ else if (MACHINE_HAS_IDTE)
+ __pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
+ else
+ __pmdp_csp(pmdp);
+ *pmdp = new;
+}
+
+static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
+ int purge)
+{
+ pmd_t *pmdp;
+ struct gmap *gmap;
+ unsigned long gaddr;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+ spin_lock(&gmap->guest_table_lock);
+ pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
+ vmaddr >> PMD_SHIFT);
+ if (pmdp) {
+ gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
+ pmdp_notify_gmap(gmap, pmdp, gaddr);
+ WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+ _SEGMENT_ENTRY_GMAP_UC));
+ if (purge)
+ __pmdp_csp(pmdp);
+ pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+ }
+ spin_unlock(&gmap->guest_table_lock);
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without
+ * flushing
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr)
+{
+ gmap_pmdp_clear(mm, vmaddr, 0);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate);
+
+/**
+ * gmap_pmdp_csp - csp all affected guest pmd entries
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr)
+{
+ gmap_pmdp_clear(mm, vmaddr, 1);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
+
+/**
+ * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
+{
+ unsigned long *entry, gaddr;
+ struct gmap *gmap;
+ pmd_t *pmdp;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+ spin_lock(&gmap->guest_table_lock);
+ entry = radix_tree_delete(&gmap->host_to_guest,
+ vmaddr >> PMD_SHIFT);
+ if (entry) {
+ pmdp = (pmd_t *)entry;
+ gaddr = __gmap_segment_gaddr(entry);
+ pmdp_notify_gmap(gmap, pmdp, gaddr);
+ WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+ _SEGMENT_ENTRY_GMAP_UC));
+ if (MACHINE_HAS_TLB_GUEST)
+ __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+ gmap->asce, IDTE_LOCAL);
+ else if (MACHINE_HAS_IDTE)
+ __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
+ *entry = _SEGMENT_ENTRY_EMPTY;
+ }
+ spin_unlock(&gmap->guest_table_lock);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
+
+/**
+ * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
+{
+ unsigned long *entry, gaddr;
+ struct gmap *gmap;
+ pmd_t *pmdp;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+ spin_lock(&gmap->guest_table_lock);
+ entry = radix_tree_delete(&gmap->host_to_guest,
+ vmaddr >> PMD_SHIFT);
+ if (entry) {
+ pmdp = (pmd_t *)entry;
+ gaddr = __gmap_segment_gaddr(entry);
+ pmdp_notify_gmap(gmap, pmdp, gaddr);
+ WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+ _SEGMENT_ENTRY_GMAP_UC));
+ if (MACHINE_HAS_TLB_GUEST)
+ __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+ gmap->asce, IDTE_GLOBAL);
+ else if (MACHINE_HAS_IDTE)
+ __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
+ else
+ __pmdp_csp(pmdp);
+ *entry = _SEGMENT_ENTRY_EMPTY;
+ }
+ spin_unlock(&gmap->guest_table_lock);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);
+
+/**
+ * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status
+ * @gmap: pointer to guest address space
+ * @pmdp: pointer to the pmd to be tested
+ * @gaddr: virtual address in the guest address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+ unsigned long gaddr)
+{
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return false;
+
+ /* Already protected memory, which did not change is clean */
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT &&
+ !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC))
+ return false;
+
+ /* Clear UC indication and reset protection */
+ pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_UC;
+ gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0);
+ return true;
+}
+
+/**
+ * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment
+ * @gmap: pointer to guest address space
+ * @bitmap: dirty bitmap for this pmd
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: virtual address in the host address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
+ unsigned long gaddr, unsigned long vmaddr)
+{
+ int i;
+ pmd_t *pmdp;
+ pte_t *ptep;
+ spinlock_t *ptl;
+
+ pmdp = gmap_pmd_op_walk(gmap, gaddr);
+ if (!pmdp)
+ return;
+
+ if (pmd_large(*pmdp)) {
+ if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr))
+ bitmap_fill(bitmap, _PAGE_ENTRIES);
+ } else {
+ for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) {
+ ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl);
+ if (!ptep)
+ continue;
+ if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
+ set_bit(i, bitmap);
+ spin_unlock(ptl);
+ }
+ }
+ gmap_pmd_op_end(gmap, pmdp);
+}
+EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
+
static inline void thp_split_mm(struct mm_struct *mm)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
* Enable storage key handling from now on and initialize the storage
* keys with the default key.
*/
-static int __s390_enable_skey(pte_t *pte, unsigned long addr,
- unsigned long next, struct mm_walk *walk)
+static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
{
/* Clear storage key */
ptep_zap_key(walk->mm, addr, pte);
return 0;
}
+static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
+ unsigned long hmask, unsigned long next,
+ struct mm_walk *walk)
+{
+ pmd_t *pmd = (pmd_t *)pte;
+ unsigned long start, end;
+ struct page *page = pmd_page(*pmd);
+
+ /*
+ * The write check makes sure we do not set a key on shared
+ * memory. This is needed as the walker does not differentiate
+ * between actual guest memory and the process executable or
+ * shared libraries.
+ */
+ if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID ||
+ !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE))
+ return 0;
+
+ start = pmd_val(*pmd) & HPAGE_MASK;
+ end = start + HPAGE_SIZE - 1;
+ __storage_key_init_range(start, end);
+ set_bit(PG_arch_1, &page->flags);
+ return 0;
+}
+
int s390_enable_skey(void)
{
- struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+ struct mm_walk walk = {
+ .hugetlb_entry = __s390_enable_skey_hugetlb,
+ .pte_entry = __s390_enable_skey_pte,
+ };
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int rc = 0;
return pte;
}
+static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
+{
+ struct page *page;
+ unsigned long size, paddr;
+
+ if (!mm_uses_skeys(mm) ||
+ rste & _SEGMENT_ENTRY_INVALID)
+ return;
+
+ if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+ page = pud_page(__pud(rste));
+ size = PUD_SIZE;
+ paddr = rste & PUD_MASK;
+ } else {
+ page = pmd_page(__pmd(rste));
+ size = PMD_SIZE;
+ paddr = rste & PMD_MASK;
+ }
+
+ if (!test_and_set_bit(PG_arch_1, &page->flags))
+ __storage_key_init_range(paddr, paddr + size - 1);
+}
+
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
else
rste |= _SEGMENT_ENTRY_LARGE;
+ clear_huge_pte_skeys(mm, rste);
pte_val(*ptep) = rste;
}
list_for_each(l, &zone->free_area[order].free_list[t]) {
page = list_entry(l, struct page, lru);
if (make_stable)
- set_page_stable_dat(page, 0);
+ set_page_stable_dat(page, order);
else
set_page_unused(page, order);
}
static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
{
- asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
+ asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0"
: [addr] "+a" (addr) : [skey] "d" (skey));
return addr;
}
{
unsigned long boundary, size;
- if (!PAGE_DEFAULT_KEY)
- return;
while (start < end) {
if (MACHINE_HAS_EDAT1) {
/* set storage keys for a 1MB frame */
continue;
}
}
- page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+ page_set_storage_key(start, PAGE_DEFAULT_KEY, 1);
start += PAGE_SIZE;
}
}
.data = &page_table_allocate_pgste,
.maxlen = sizeof(int),
.mode = S_IRUGO | S_IWUSR,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &page_table_allocate_pgste_min,
.extra2 = &page_table_allocate_pgste_max,
},
spin_unlock_bh(&mm->context.lock);
if (mask != 0)
return;
+ } else {
+ atomic_xor_bits(&page->_refcount, 3U << 24);
}
pgtable_page_dtor(page);
break;
/* fallthrough */
case 3: /* 4K page table with pgstes */
+ if (mask & 3)
+ atomic_xor_bits(&page->_refcount, 3 << 24);
pgtable_page_dtor(page);
__free_page(page);
break;
mm->context.asce, IDTE_LOCAL);
else
__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
+ if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+ gmap_pmdp_idte_local(mm, addr);
}
static inline void pmdp_idte_global(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
{
- if (MACHINE_HAS_TLB_GUEST)
+ if (MACHINE_HAS_TLB_GUEST) {
__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
mm->context.asce, IDTE_GLOBAL);
- else if (MACHINE_HAS_IDTE)
+ if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+ gmap_pmdp_idte_global(mm, addr);
+ } else if (MACHINE_HAS_IDTE) {
__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
- else
+ if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+ gmap_pmdp_idte_global(mm, addr);
+ } else {
__pmdp_csp(pmdp);
+ if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+ gmap_pmdp_csp(mm, addr);
+ }
}
static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
cpumask_of(smp_processor_id()))) {
pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
mm->context.flush_mm = 1;
+ if (mm_has_pgste(mm))
+ gmap_pmdp_invalidate(mm, addr);
} else {
pmdp_idte_global(mm, addr, pmdp);
}
return old;
}
+static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset(mm, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, addr);
+ if (!pud)
+ return NULL;
+ pmd = pmd_alloc(mm, pud, addr);
+ return pmd;
+}
+
pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t new)
{
/*
* Test and reset if a guest page is dirty
*/
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
{
- spinlock_t *ptl;
- pgd_t *pgd;
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
pgste_t pgste;
- pte_t *ptep;
pte_t pte;
bool dirty;
int nodat;
- pgd = pgd_offset(mm, addr);
- p4d = p4d_alloc(mm, pgd, addr);
- if (!p4d)
- return false;
- pud = pud_alloc(mm, p4d, addr);
- if (!pud)
- return false;
- pmd = pmd_alloc(mm, pud, addr);
- if (!pmd)
- return false;
- /* We can't run guests backed by huge pages, but userspace can
- * still set them up and then try to migrate them without any
- * migration support.
- */
- if (pmd_large(*pmd))
- return true;
-
- ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
- if (unlikely(!ptep))
- return false;
-
pgste = pgste_get_lock(ptep);
dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
pgste_val(pgste) &= ~PGSTE_UC_BIT;
*ptep = pte;
}
pgste_set_unlock(ptep, pgste);
-
- spin_unlock(ptl);
return dirty;
}
-EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc);
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned char key, bool nq)
{
- unsigned long keyul;
+ unsigned long keyul, paddr;
spinlock_t *ptl;
pgste_t old, new;
+ pmd_t *pmdp;
pte_t *ptep;
- ptep = get_locked_pte(mm, addr, &ptl);
+ pmdp = pmd_alloc_map(mm, addr);
+ if (unlikely(!pmdp))
+ return -EFAULT;
+
+ ptl = pmd_lock(mm, pmdp);
+ if (!pmd_present(*pmdp)) {
+ spin_unlock(ptl);
+ return -EFAULT;
+ }
+
+ if (pmd_large(*pmdp)) {
+ paddr = pmd_val(*pmdp) & HPAGE_MASK;
+ paddr |= addr & ~HPAGE_MASK;
+ /*
+ * Huge pmds need quiescing operations, they are
+ * always mapped.
+ */
+ page_set_storage_key(paddr, key, 1);
+ spin_unlock(ptl);
+ return 0;
+ }
+ spin_unlock(ptl);
+
+ ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
if (unlikely(!ptep))
return -EFAULT;
pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
if (!(pte_val(*ptep) & _PAGE_INVALID)) {
- unsigned long address, bits, skey;
+ unsigned long bits, skey;
- address = pte_val(*ptep) & PAGE_MASK;
- skey = (unsigned long) page_get_storage_key(address);
+ paddr = pte_val(*ptep) & PAGE_MASK;
+ skey = (unsigned long) page_get_storage_key(paddr);
bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
/* Set storage key ACC and FP */
- page_set_storage_key(address, skey, !nq);
+ page_set_storage_key(paddr, skey, !nq);
/* Merge host changed & referenced into pgste */
pgste_val(new) |= bits << 52;
}
int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
{
spinlock_t *ptl;
+ unsigned long paddr;
pgste_t old, new;
+ pmd_t *pmdp;
pte_t *ptep;
int cc = 0;
- ptep = get_locked_pte(mm, addr, &ptl);
+ pmdp = pmd_alloc_map(mm, addr);
+ if (unlikely(!pmdp))
+ return -EFAULT;
+
+ ptl = pmd_lock(mm, pmdp);
+ if (!pmd_present(*pmdp)) {
+ spin_unlock(ptl);
+ return -EFAULT;
+ }
+
+ if (pmd_large(*pmdp)) {
+ paddr = pmd_val(*pmdp) & HPAGE_MASK;
+ paddr |= addr & ~HPAGE_MASK;
+ cc = page_reset_referenced(paddr);
+ spin_unlock(ptl);
+ return cc;
+ }
+ spin_unlock(ptl);
+
+ ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
if (unlikely(!ptep))
return -EFAULT;
pgste_val(new) &= ~PGSTE_GR_BIT;
if (!(pte_val(*ptep) & _PAGE_INVALID)) {
- cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+ paddr = pte_val(*ptep) & PAGE_MASK;
+ cc = page_reset_referenced(paddr);
/* Merge real referenced bit into host-set */
pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
}
int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned char *key)
{
+ unsigned long paddr;
spinlock_t *ptl;
pgste_t pgste;
+ pmd_t *pmdp;
pte_t *ptep;
- ptep = get_locked_pte(mm, addr, &ptl);
+ pmdp = pmd_alloc_map(mm, addr);
+ if (unlikely(!pmdp))
+ return -EFAULT;
+
+ ptl = pmd_lock(mm, pmdp);
+ if (!pmd_present(*pmdp)) {
+ /* Not yet mapped memory has a zero key */
+ spin_unlock(ptl);
+ *key = 0;
+ return 0;
+ }
+
+ if (pmd_large(*pmdp)) {
+ paddr = pmd_val(*pmdp) & HPAGE_MASK;
+ paddr |= addr & ~HPAGE_MASK;
+ *key = page_get_storage_key(paddr);
+ spin_unlock(ptl);
+ return 0;
+ }
+ spin_unlock(ptl);
+
+ ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
if (unlikely(!ptep))
return -EFAULT;
pgste = pgste_get_lock(ptep);
*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+ paddr = pte_val(*ptep) & PAGE_MASK;
if (!(pte_val(*ptep) & _PAGE_INVALID))
- *key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+ *key = page_get_storage_key(paddr);
/* Reflect guest's logical view, not physical */
*key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
pgste_set_unlock(ptep, pgste);
/* br %r1 */
_EMIT2(0x07f1);
} else {
- /* larl %r1,.+14 */
- EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
/* ex 0,S390_lowcore.br_r1_tampoline */
EMIT4_DISP(0x44000000, REG_0, REG_0,
offsetof(struct lowcore, br_r1_trampoline));
goto free_addrs;
}
if (bpf_jit_prog(&jit, fp)) {
+ bpf_jit_binary_free(header);
fp = orig_fp;
goto free_addrs;
}
{
pr_info("NUMA mode: %s\n", mode->name);
nodes_clear(node_possible_map);
+ /* Initially attach all possible CPUs to node 0. */
+ cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
if (mode->setup)
mode->setup();
numa_setup_memory();
memblock_dump_all();
}
-/*
- * numa_init_early() - Initialization initcall
- *
- * This runs when only one CPU is online and before the first
- * topology update is called for by the scheduler.
- */
-static int __init numa_init_early(void)
-{
- /* Attach all possible CPUs to node 0 for now. */
- cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
- return 0;
-}
-early_initcall(numa_init_early);
-
/*
* numa_init_late() - Initialization initcall
*
"Maximum work units",
};
+static char *pci_fmt3_names[] = {
+ "Transmitted bytes",
+};
+
static char *pci_sw_names[] = {
"Allocated pages",
"Mapped pages",
pci_fmb_show(m, pci_fmt2_names, ARRAY_SIZE(pci_fmt2_names),
&zdev->fmb->fmt2.consumed_work_units);
break;
+ case 3:
+ pci_fmb_show(m, pci_fmt3_names, ARRAY_SIZE(pci_fmt3_names),
+ &zdev->fmb->fmt3.tx_bytes);
+ break;
default:
seq_puts(m, "Unknown format\n");
}
targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
$(call if_changed_rule,cc_o_c)
-$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
$(call if_changed_rule,as_o_S)
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
$(call if_changed_rule,cc_o_c)
LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
-KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
.quad 0
.endr
-purgatory_sha256_digest:
- .global purgatory_sha256_digest
- .rept 32 /* SHA256_DIGEST_SIZE */
- .byte 0
- .endr
-
-purgatory_sha_regions:
- .global purgatory_sha_regions
- .rept 16 * __KEXEC_SHA_REGION_SIZE /* KEXEC_SEGMENTS_MAX */
- .byte 0
- .endr
-
-kernel_entry:
- .global kernel_entry
- .quad 0
-
-kernel_type:
- .global kernel_type
- .quad 0
-
-crash_start:
- .global crash_start
- .quad 0
+/* Macro to define a global variable with name and size (in bytes) to be
+ * shared with C code.
+ *
+ * Add the .size and .type attribute to satisfy checks on the Elf_Sym during
+ * purgatory load.
+ */
+.macro GLOBAL_VARIABLE name,size
+\name:
+ .global \name
+ .size \name,\size
+ .type \name,object
+ .skip \size,0
+.endm
-crash_size:
- .global crash_size
- .quad 0
+GLOBAL_VARIABLE purgatory_sha256_digest,32
+GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE
+GLOBAL_VARIABLE kernel_entry,8
+GLOBAL_VARIABLE kernel_type,8
+GLOBAL_VARIABLE crash_start,8
+GLOBAL_VARIABLE crash_size,8
.align PAGE_SIZE
stack:
#include <linux/string.h>
#include <asm/purgatory.h>
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
-
-u64 kernel_entry;
-u64 kernel_type;
-
-u64 crash_start;
-u64 crash_size;
-
int verify_sha256_digest(void)
{
struct kexec_sha_region *ptr, *end;
quiet_cmd_chkbss = CHKBSS $<
define cmd_chkbss
+ rm -f $@; \
if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
echo "error: $< .bss section is not empty" >&2; exit 1; \
fi; \
touch $@;
endef
-$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+chkbss-target ?= $(obj)/built-in.a
+ifneq (,$(findstring /,$(chkbss)))
+chkbss-files := $(patsubst %, %.chkbss, $(chkbss))
+else
+chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+endif
+
+$(chkbss-target): $(chkbss-files)
+targets += $(notdir $(chkbss-files))
%.o.chkbss: %.o
$(call cmd,chkbss)
if (!desc->group)
exit(EXIT_FAILURE);
group = &desc->group[desc->nr_groups - 1];
- strncpy(group->opcode, insn->opcode, 2);
+ memcpy(group->opcode, insn->opcode, 2);
group->type = insn->type;
group->offset = offset;
group->count = 1;
continue;
add_to_group(desc, insn, offset);
if (strncmp(opcode, insn->opcode, 2)) {
- strncpy(opcode, insn->opcode, 2);
+ memcpy(opcode, insn->opcode, 2);
printf("\t/* %.2s */ \\\n", opcode);
}
print_opcode(insn, offset);
select PERF_EVENTS
select ARCH_HIBERNATION_POSSIBLE if MMU
select SPARSE_IRQ
- select HAVE_CC_STACKPROTECTOR
+ select HAVE_STACKPROTECTOR
config SUPERH64
def_bool "$(ARCH)" = "sh64"
People using multiprocessor machines who say Y here should also say
Y to "Enhanced Real Time Clock Support", below.
- See also <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO
+ See also <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO
available at <http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
#include <asm/atomic-irq.h>
#endif
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
-
- return c;
-}
-
#endif /* CONFIG_CPU_J2 */
#endif /* __ASM_SH_ATOMIC_H */
* This work is licensed under the terms of the GNU GPL, version 2. See the
* file "COPYING" in the main directory of this archive for more details.
*/
-#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler.h>
#include <asm/byteorder.h>
/*
#include <linux/types.h>
struct arch_hw_breakpoint {
- char *name; /* Contains name of the symbol to set bkpt */
unsigned long address;
u16 len;
u16 type;
struct clk *clk; /* optional interface clock / MSTP bit */
};
+struct perf_event_attr;
struct perf_event;
struct task_struct;
struct pmu;
}
/* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
void arch_remove_kprobe(struct kprobe *);
void kretprobe_trampoline(void);
-void jprobe_return_end(void);
/* Architecture specific copy of original instruction*/
struct arch_specific_insn {
/* per-cpu kprobe control block */
struct kprobe_ctlblk {
unsigned long kprobe_status;
- unsigned long jprobe_saved_r15;
- struct pt_regs jprobe_saved_regs;
- kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
struct prev_kprobe prev_kprobe;
};
/*
* Check for virtual address in kernel space.
*/
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
unsigned int len;
unsigned long va;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- va = info->address;
- len = get_hbp_len(info->len);
+ va = hw->address;
+ len = get_hbp_len(hw->len);
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
return 0;
}
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
- info->address = bp->attr.bp_addr;
+ hw->address = attr->bp_addr;
/* Len */
- switch (bp->attr.bp_len) {
+ switch (attr->bp_len) {
case HW_BREAKPOINT_LEN_1:
- info->len = SH_BREAKPOINT_LEN_1;
+ hw->len = SH_BREAKPOINT_LEN_1;
break;
case HW_BREAKPOINT_LEN_2:
- info->len = SH_BREAKPOINT_LEN_2;
+ hw->len = SH_BREAKPOINT_LEN_2;
break;
case HW_BREAKPOINT_LEN_4:
- info->len = SH_BREAKPOINT_LEN_4;
+ hw->len = SH_BREAKPOINT_LEN_4;
break;
case HW_BREAKPOINT_LEN_8:
- info->len = SH_BREAKPOINT_LEN_8;
+ hw->len = SH_BREAKPOINT_LEN_8;
break;
default:
return -EINVAL;
}
/* Type */
- switch (bp->attr.bp_type) {
+ switch (attr->bp_type) {
case HW_BREAKPOINT_R:
- info->type = SH_BREAKPOINT_READ;
+ hw->type = SH_BREAKPOINT_READ;
break;
case HW_BREAKPOINT_W:
- info->type = SH_BREAKPOINT_WRITE;
+ hw->type = SH_BREAKPOINT_WRITE;
break;
case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
- info->type = SH_BREAKPOINT_RW;
+ hw->type = SH_BREAKPOINT_RW;
break;
default:
return -EINVAL;
/*
* Validate the arch-specific HW Breakpoint register settings
*/
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
unsigned int align;
int ret;
- ret = arch_build_bp_info(bp);
+ ret = arch_build_bp_info(bp, attr, hw);
if (ret)
return ret;
ret = -EINVAL;
- switch (info->len) {
+ switch (hw->len) {
case SH_BREAKPOINT_LEN_1:
align = 0;
break;
return ret;
}
- /*
- * For kernel-addresses, either the address or symbol name can be
- * specified.
- */
- if (info->name)
- info->address = (unsigned long)kallsyms_lookup_name(info->name);
-
/*
* Check that the low-order bits of the address are appropriate
* for the alignment implied by len.
*/
- if (info->address & align)
+ if (hw->address & align)
return -EINVAL;
return 0;
perf_bp_event(bp, args->regs);
/* Deliver the signal to userspace */
- if (!arch_check_bp_in_kernelspace(bp)) {
+ if (!arch_check_bp_in_kernelspace(&bp->hw.info)) {
force_sig_fault(SIGTRAP, TRAP_HWBKPT,
(void __user *)NULL, current);
}
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
return 1;
- } else {
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- goto ss_probe;
- }
}
goto no_kprobe;
}
set_current_kprobe(p, regs, kcb);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (p->pre_handler && p->pre_handler(p, regs))
+ if (p->pre_handler && p->pre_handler(p, regs)) {
/* handler has already set things up, so skip ss setup */
+ reset_current_kprobe();
+ preempt_enable_no_resched();
return 1;
+ }
-ss_probe:
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
regs->pc = orig_ret_address;
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
-
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
if (post_kprobe_handler(args->regs))
ret = NOTIFY_STOP;
} else {
- if (kprobe_handler(args->regs)) {
+ if (kprobe_handler(args->regs))
ret = NOTIFY_STOP;
- } else {
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler &&
- p->break_handler(p, args->regs))
- ret = NOTIFY_STOP;
- }
}
}
}
return ret;
}
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- unsigned long addr;
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- kcb->jprobe_saved_regs = *regs;
- kcb->jprobe_saved_r15 = regs->regs[15];
- addr = kcb->jprobe_saved_r15;
-
- /*
- * TBD: As Linus pointed out, gcc assumes that the callee
- * owns the argument space and could overwrite it, e.g.
- * tailcall optimization. So, to be absolutely safe
- * we also save and restore enough stack bytes to cover
- * the argument area.
- */
- memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
- MIN_STACK_SIZE(addr));
-
- regs->pc = (unsigned long)(jp->entry);
-
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- unsigned long stack_addr = kcb->jprobe_saved_r15;
- u8 *addr = (u8 *)regs->pc;
-
- if ((addr >= (u8 *)jprobe_return) &&
- (addr <= (u8 *)jprobe_return_end)) {
- *regs = kcb->jprobe_saved_regs;
-
- memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
- MIN_STACK_SIZE(stack_addr));
-
- kcb->kprobe_status = KPROBE_HIT_SS;
- preempt_enable_no_resched();
- return 1;
- }
-
- return 0;
-}
-
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
Y to "Enhanced Real Time Clock Support", below. The "Advanced Power
Management" code will be disabled if you say Y here.
- See also <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO
+ See also <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO
available at <http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
generic-y += module.h
+generic-y += msi.h
generic-y += preempt.h
generic-y += rwsem.h
generic-y += serial.h
int atomic_fetch_xor(int, atomic_t *);
int atomic_cmpxchg(atomic_t *, int, int);
int atomic_xchg(atomic_t *, int);
-int __atomic_add_unless(atomic_t *, int, int);
+int atomic_fetch_add_unless(atomic_t *, int, int);
void atomic_set(atomic_t *, int);
+#define atomic_fetch_add_unless atomic_fetch_add_unless
+
#define atomic_set_release(v, i) atomic_set((v), (i))
#define atomic_read(v) READ_ONCE((v)->counter)
#define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v)))
#define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v) ((void)atomic_add_return( 1, (v)))
-#define atomic_dec(v) ((void)atomic_add_return( -1, (v)))
#define atomic_and(i, v) ((void)atomic_fetch_and((i), (v)))
#define atomic_or(i, v) ((void)atomic_fetch_or((i), (v)))
#define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v)))
#define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v)))
-#define atomic_inc_return(v) (atomic_add_return( 1, (v)))
-#define atomic_dec_return(v) (atomic_add_return( -1, (v)))
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
#endif /* !(__ARCH_SPARC_ATOMIC__) */
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-#define atomic_dec_return(v) atomic_sub_return(1, v)
-#define atomic64_dec_return(v) atomic64_sub_return(1, v)
-
-#define atomic_inc_return(v) atomic_add_return(1, v)
-#define atomic64_inc_return(v) atomic64_add_return(1, v)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic64_inc(v) atomic64_add(1, v)
-
-#define atomic_dec(v) atomic_sub(1, v)
-#define atomic64_dec(v) atomic64_sub(1, v)
-
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
-
#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
static inline int atomic_xchg(atomic_t *v, int new)
return xchg(&v->counter, new);
}
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
#define atomic64_cmpxchg(v, o, n) \
((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
#endif /* !(__ARCH_SPARC64_ATOMIC__) */
unsigned long kprobe_status;
unsigned long kprobe_orig_tnpc;
unsigned long kprobe_orig_tstate_pil;
- struct pt_regs jprobe_saved_regs;
struct prev_kprobe prev_kprobe;
};
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * msi.h: Defines specific to the MBus - Sbus - Interface.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
- */
-
-#ifndef _SPARC_MSI_H
-#define _SPARC_MSI_H
-
-/*
- * Locations of MSI Registers.
- */
-#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */
-
-/*
- * Useful bits in the MSI Registers.
- */
-#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */
-
-
-static inline void msi_set_sync(void)
-{
- __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
- "andn %%g3, %2, %%g3\n\t"
- "sta %%g3, [%0] %1\n\t" : :
- "r" (MSI_MBUS_ARBEN),
- "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
-}
-
-#endif /* !(_SPARC_MSI_H) */
kcb->kprobe_status = KPROBE_REENTER;
prepare_singlestep(p, regs, kcb);
return 1;
- } else {
- if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
+ } else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
/* The breakpoint instruction was removed by
* another cpu right after we hit, no further
* handling of this interrupt is appropriate
*/
- ret = 1;
- goto no_kprobe;
- }
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs))
- goto ss_probe;
+ ret = 1;
}
goto no_kprobe;
}
set_current_kprobe(p, regs, kcb);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (p->pre_handler && p->pre_handler(p, regs))
+ if (p->pre_handler && p->pre_handler(p, regs)) {
+ reset_current_kprobe();
+ preempt_enable_no_resched();
return 1;
+ }
-ss_probe:
prepare_singlestep(p, regs, kcb);
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
exception_exit(prev_state);
}
-/* Jprobes support. */
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
-
- regs->tpc = (unsigned long) jp->entry;
- regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
- regs->tstate |= TSTATE_PIL;
-
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- register unsigned long orig_fp asm("g1");
-
- orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
- __asm__ __volatile__("\n"
-"1: cmp %%sp, %0\n\t"
- "blu,a,pt %%xcc, 1b\n\t"
- " restore\n\t"
- ".globl jprobe_return_trap_instruction\n"
-"jprobe_return_trap_instruction:\n\t"
- "ta 0x70"
- : /* no outputs */
- : "r" (orig_fp));
-}
-
-extern void jprobe_return_trap_instruction(void);
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- u32 *addr = (u32 *) regs->tpc;
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- if (addr == (u32 *) jprobe_return_trap_instruction) {
- memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
- preempt_enable_no_resched();
- return 1;
- }
- return 0;
-}
-
/* The value stored in the return address register is actually 2
* instructions before where the callee will return to.
* Sequences usually look something like this
regs->tpc = orig_ret_address;
regs->tnpc = orig_ret_address + 4;
- reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
- preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
}
}
-static void init_tick_ops(struct sparc64_tick_ops *ops)
+static void __init init_tick_ops(struct sparc64_tick_ops *ops)
{
unsigned long freq, quotient, tick;
}
EXPORT_SYMBOL(atomic_cmpxchg);
-int __atomic_add_unless(atomic_t *v, int a, int u)
+int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int ret;
unsigned long flags;
spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
return ret;
}
-EXPORT_SYMBOL(__atomic_add_unless);
+EXPORT_SYMBOL(atomic_fetch_add_unless);
/* Atomic operations are already serializing */
void atomic_set(atomic_t *v, int i)
(top_of_ram - total_ram) >> 20);
init_node_masks_nonnuma();
- memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
allocate_node_data(0);
node_set_online(0);
}
#include <asm/mbus.h>
#include <asm/page.h>
#include <asm/asi.h>
-#include <asm/msi.h>
#include <asm/smp.h>
#include <asm/io.h>
set_pte((pte_t *)ctxp, pte);
}
+/*
+ * Locations of MSI Registers.
+ */
+#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */
+
+/*
+ * Useful bits in the MSI Registers.
+ */
+#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */
+
+static void msi_set_sync(void)
+{
+ __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
+ "andn %%g3, %2, %%g3\n\t"
+ "sta %%g3, [%0] %1\n\t" : :
+ "r" (MSI_MBUS_ARBEN),
+ "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
+}
+
void pmd_set(pmd_t *pmdp, pte_t *ptep)
{
unsigned long ptp; /* Physical address, shifted right by 4 */
On UML, this is accomplished by sending a "sysrq" command with
mconsole, followed by the letter for the requested command.
- The keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
+ The keys are documented in <file:Documentation/admin-guide/sysrq.rst>. Don't say Y
unless you really know what this hack does.
config KERNEL_STACK_ORDER
if (strncmp(transport, TRANS_TAP, TRANS_TAP_LEN) == 0)
return (vec_rx | VECTOR_BPF);
if (strncmp(transport, TRANS_RAW, TRANS_RAW_LEN) == 0)
- return (vec_rx | vec_tx);
+ return (vec_rx | vec_tx | VECTOR_QDISC_BYPASS);
return (vec_rx | vec_tx);
}
result = kmalloc(sizeof(struct vector_queue), GFP_KERNEL);
if (result == NULL)
- goto out_fail;
+ return NULL;
result->max_depth = max_size;
result->dev = vp->dev;
result->mmsg_vector = kmalloc(
(sizeof(struct mmsghdr) * max_size), GFP_KERNEL);
+ if (result->mmsg_vector == NULL)
+ goto out_mmsg_fail;
result->skbuff_vector = kmalloc(
(sizeof(void *) * max_size), GFP_KERNEL);
- if (result->mmsg_vector == NULL || result->skbuff_vector == NULL)
- goto out_fail;
+ if (result->skbuff_vector == NULL)
+ goto out_skb_fail;
+
+ /* further failures can be handled safely by destroy_queue*/
mmsg_vector = result->mmsg_vector;
for (i = 0; i < max_size; i++) {
result->head = 0;
result->tail = 0;
return result;
+out_skb_fail:
+ kfree(result->mmsg_vector);
+out_mmsg_fail:
+ kfree(result);
+ return NULL;
out_fail:
destroy_queue(result);
return NULL;
if ((vp->options & VECTOR_QDISC_BYPASS) != 0) {
if (!uml_raw_enable_qdisc_bypass(vp->fds->rx_fd))
- vp->options = vp->options | VECTOR_BPF;
+ vp->options |= VECTOR_BPF;
}
-
if ((vp->options & VECTOR_BPF) != 0)
vp->bpf = uml_vector_default_bpf(vp->fds->rx_fd, dev->dev_addr);
CON_INITCALL
}
- .uml.initcall.init : {
- __uml_initcall_start = .;
- *(.uml.initcall.init)
- __uml_initcall_end = .;
- }
-
SECURITY_INIT
.exitcall : {
int (*setup_func)(char *, int *);
};
-extern initcall_t __uml_initcall_start, __uml_initcall_end;
extern initcall_t __uml_postsetup_start, __uml_postsetup_end;
extern const char *__uml_help_start, *__uml_help_end;
#endif
-#define __uml_initcall(fn) \
- static initcall_t __uml_initcall_##fn __uml_init_call = fn
-
#define __uml_exitcall(fn) \
static exitcall_t __uml_exitcall_##fn __uml_exit_call = fn
*/
#define __uml_init_setup __used __section(.uml.setup.init)
#define __uml_setup_help __used __section(.uml.help.init)
-#define __uml_init_call __used __section(.uml.initcall.init)
#define __uml_postsetup_call __used __section(.uml.postsetup.init)
#define __uml_exit_call __used __section(.uml.exitcall.exit)
}
}
-static __init void do_uml_initcalls(void)
-{
- initcall_t *call;
-
- call = &__uml_initcall_start;
- while (call < &__uml_initcall_end) {
- (*call)();
- call++;
- }
-}
-
static void last_ditch_exit(int sig)
{
uml_cleanup();
scan_elf_aux(envp);
#endif
- do_uml_initcalls();
change_sig(SIGPIPE, 0);
ret = linux_main(argc, argv);
* Start addresses are inclusive and end addresses are exclusive;
* start addresses should be rounded down, end addresses up.
*
- * See Documentation/cachetlb.txt for more information.
+ * See Documentation/core-api/cachetlb.rst for more information.
* Please note that the implementation of these, and the required
* effects are cache-type (VIVT/VIPT/PIPT) specific.
*
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_REFCOUNT
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
- select ARCH_HAS_UACCESS_MCSAFE if X86_64
+ select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
select HAVE_ARCH_VMAP_STACK if X86_64
select HAVE_ARCH_WITHIN_STACK_FRAMES
- select HAVE_CC_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_CONTEXT_TRACKING if X86_64
select HAVE_PERF_USER_STACK_DUMP
select HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
+ select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
+ select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR
select HAVE_STACK_VALIDATION if X86_64
select HAVE_RSEQ
select HAVE_SYSCALL_TRACEPOINTS
config X86_32_LAZY_GS
def_bool y
- depends on X86_32 && CC_STACKPROTECTOR_NONE
+ depends on X86_32 && !STACKPROTECTOR
config ARCH_SUPPORTS_UPROBES
def_bool y
# alignment instructions.
KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
- # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
- # a lot more stack due to the lack of sharing of stacklots:
- KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
- $(call cc-option,-fno-unit-at-a-time))
-
# CPU-specific tuning. Anything which can be shared with UML should go here.
include arch/x86/Makefile_32.cpu
KBUILD_CFLAGS += $(cflags-y)
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
-archprepare:
-ifeq ($(CONFIG_KEXEC_FILE),y)
- $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
-endif
-
###
# Kernel objects
$(Q)rm -rf $(objtree)/arch/x86_64
$(Q)$(MAKE) $(clean)=$(boot)
$(Q)$(MAKE) $(clean)=arch/x86/tools
- $(Q)$(MAKE) $(clean)=arch/x86/purgatory
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
#define _LINUX_BITOPS_H /* Inhibit inclusion of <linux/bitops.h> */
#include <linux/types.h>
+#include <asm/asm.h>
static inline bool constant_test_bit(int nr, const void *addr)
{
bool v;
const u32 *p = (const u32 *)addr;
- asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+ asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
return v;
}
done
endef
+# We need to run two commands under "if_changed", so merge them into a
+# single invocation.
+quiet_cmd_check-and-link-vmlinux = LD $@
+ cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
+
$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
- $(call if_changed,check_data_rel)
- $(call if_changed,ld)
+ $(call if_changed,check-and-link-vmlinux)
OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
\
table = (typeof(table))sys_table; \
\
- c->runtime_services = table->runtime; \
- c->boot_services = table->boottime; \
- c->text_output = table->con_out; \
+ c->runtime_services = table->runtime; \
+ c->boot_services = table->boottime; \
+ c->text_output = table->con_out; \
}
BOOT_SERVICES(32);
BOOT_SERVICES(64);
-static inline efi_status_t __open_volume32(void *__image, void **__fh)
-{
- efi_file_io_interface_t *io;
- efi_loaded_image_32_t *image = __image;
- efi_file_handle_32_t *fh;
- efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
- efi_status_t status;
- void *handle = (void *)(unsigned long)image->device_handle;
- unsigned long func;
-
- status = efi_call_early(handle_protocol, handle,
- &fs_proto, (void **)&io);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to handle fs_proto\n");
- return status;
- }
-
- func = (unsigned long)io->open_volume;
- status = efi_early->call(func, io, &fh);
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to open volume\n");
-
- *__fh = fh;
- return status;
-}
-
-static inline efi_status_t __open_volume64(void *__image, void **__fh)
-{
- efi_file_io_interface_t *io;
- efi_loaded_image_64_t *image = __image;
- efi_file_handle_64_t *fh;
- efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
- efi_status_t status;
- void *handle = (void *)(unsigned long)image->device_handle;
- unsigned long func;
-
- status = efi_call_early(handle_protocol, handle,
- &fs_proto, (void **)&io);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to handle fs_proto\n");
- return status;
- }
-
- func = (unsigned long)io->open_volume;
- status = efi_early->call(func, io, &fh);
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to open volume\n");
-
- *__fh = fh;
- return status;
-}
-
-efi_status_t
-efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
-{
- if (efi_early->is64)
- return __open_volume64(__image, __fh);
-
- return __open_volume32(__image, __fh);
-}
-
void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
{
efi_call_proto(efi_simple_text_output_protocol, output_string,
}
static efi_status_t
-__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
+preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
{
struct pci_setup_rom *rom = NULL;
efi_status_t status;
unsigned long size;
- uint64_t attributes, romsize;
+ uint64_t romsize;
void *romimage;
- status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
- EfiPciIoAttributeOperationGet, 0, 0,
- &attributes);
- if (status != EFI_SUCCESS)
- return status;
-
/*
- * Some firmware images contain EFI function pointers at the place where the
- * romimage and romsize fields are supposed to be. Typically the EFI
+ * Some firmware images contain EFI function pointers at the place where
+ * the romimage and romsize fields are supposed to be. Typically the EFI
* code is mapped at high addresses, translating to an unrealistically
* large romsize. The UEFI spec limits the size of option ROMs to 16
* MiB so we reject any ROMs over 16 MiB in size to catch this.
status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for rom\n");
+ efi_printk(sys_table, "Failed to allocate memory for 'rom'\n");
return status;
}
memset(rom, 0, sizeof(*rom));
- rom->data.type = SETUP_PCI;
- rom->data.len = size - sizeof(struct setup_data);
- rom->data.next = 0;
- rom->pcilen = pci->romsize;
+ rom->data.type = SETUP_PCI;
+ rom->data.len = size - sizeof(struct setup_data);
+ rom->data.next = 0;
+ rom->pcilen = pci->romsize;
*__rom = rom;
status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
return status;
}
-static void
-setup_efi_pci32(struct boot_params *params, void **pci_handle,
- unsigned long size)
-{
- efi_pci_io_protocol_t *pci = NULL;
- efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
- u32 *handles = (u32 *)(unsigned long)pci_handle;
- efi_status_t status;
- unsigned long nr_pci;
- struct setup_data *data;
- int i;
-
- data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
- while (data && data->next)
- data = (struct setup_data *)(unsigned long)data->next;
-
- nr_pci = size / sizeof(u32);
- for (i = 0; i < nr_pci; i++) {
- struct pci_setup_rom *rom = NULL;
- u32 h = handles[i];
-
- status = efi_call_early(handle_protocol, h,
- &pci_proto, (void **)&pci);
-
- if (status != EFI_SUCCESS)
- continue;
-
- if (!pci)
- continue;
-
- status = __setup_efi_pci(pci, &rom);
- if (status != EFI_SUCCESS)
- continue;
-
- if (data)
- data->next = (unsigned long)rom;
- else
- params->hdr.setup_data = (unsigned long)rom;
-
- data = (struct setup_data *)rom;
-
- }
-}
-
-static void
-setup_efi_pci64(struct boot_params *params, void **pci_handle,
- unsigned long size)
-{
- efi_pci_io_protocol_t *pci = NULL;
- efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
- u64 *handles = (u64 *)(unsigned long)pci_handle;
- efi_status_t status;
- unsigned long nr_pci;
- struct setup_data *data;
- int i;
-
- data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
- while (data && data->next)
- data = (struct setup_data *)(unsigned long)data->next;
-
- nr_pci = size / sizeof(u64);
- for (i = 0; i < nr_pci; i++) {
- struct pci_setup_rom *rom = NULL;
- u64 h = handles[i];
-
- status = efi_call_early(handle_protocol, h,
- &pci_proto, (void **)&pci);
-
- if (status != EFI_SUCCESS)
- continue;
-
- if (!pci)
- continue;
-
- status = __setup_efi_pci(pci, &rom);
- if (status != EFI_SUCCESS)
- continue;
-
- if (data)
- data->next = (unsigned long)rom;
- else
- params->hdr.setup_data = (unsigned long)rom;
-
- data = (struct setup_data *)rom;
-
- }
-}
-
/*
* There's no way to return an informative status from this function,
* because any analysis (and printing of error messages) needs to be
void **pci_handle = NULL;
efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
unsigned long size = 0;
+ unsigned long nr_pci;
+ struct setup_data *data;
+ int i;
status = efi_call_early(locate_handle,
EFI_LOCATE_BY_PROTOCOL,
size, (void **)&pci_handle);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for pci_handle\n");
+ efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n");
return;
}
if (status != EFI_SUCCESS)
goto free_handle;
- if (efi_early->is64)
- setup_efi_pci64(params, pci_handle, size);
- else
- setup_efi_pci32(params, pci_handle, size);
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
+
+ nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
+ for (i = 0; i < nr_pci; i++) {
+ efi_pci_io_protocol_t *pci = NULL;
+ struct pci_setup_rom *rom;
+
+ status = efi_call_early(handle_protocol,
+ efi_is_64bit() ? ((u64 *)pci_handle)[i]
+ : ((u32 *)pci_handle)[i],
+ &pci_proto, (void **)&pci);
+ if (status != EFI_SUCCESS || !pci)
+ continue;
+
+ status = preserve_pci_rom_image(pci, &rom);
+ if (status != EFI_SUCCESS)
+ continue;
+
+ if (data)
+ data->next = (unsigned long)rom;
+ else
+ params->hdr.setup_data = (unsigned long)rom;
+
+ data = (struct setup_data *)rom;
+ }
free_handle:
efi_call_early(free_pool, pci_handle);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
size + sizeof(struct setup_data), &new);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table,
- "Failed to alloc mem for properties\n");
+ efi_printk(sys_table, "Failed to allocate memory for 'properties'\n");
return;
}
new->next = 0;
data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
- if (!data)
+ if (!data) {
boot_params->hdr.setup_data = (unsigned long)new;
- else {
+ } else {
while (data->next)
data = (struct setup_data *)(unsigned long)data->next;
data->next = (unsigned long)new;
}
}
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
static efi_status_t
-setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
{
- struct efi_uga_draw_protocol *uga = NULL, *first_uga;
- efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ efi_status_t status;
+ u32 width, height;
+ void **uga_handle = NULL;
+ efi_uga_draw_protocol_t *uga = NULL, *first_uga;
unsigned long nr_ugas;
- u32 *handles = (u32 *)uga_handle;
- efi_status_t status = EFI_INVALID_PARAMETER;
int i;
- first_uga = NULL;
- nr_ugas = size / sizeof(u32);
- for (i = 0; i < nr_ugas; i++) {
- efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
- u32 w, h, depth, refresh;
- void *pciio;
- u32 handle = handles[i];
-
- status = efi_call_early(handle_protocol, handle,
- &uga_proto, (void **)&uga);
- if (status != EFI_SUCCESS)
- continue;
-
- efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
-
- status = efi_early->call((unsigned long)uga->get_mode, uga,
- &w, &h, &depth, &refresh);
- if (status == EFI_SUCCESS && (!first_uga || pciio)) {
- *width = w;
- *height = h;
-
- /*
- * Once we've found a UGA supporting PCIIO,
- * don't bother looking any further.
- */
- if (pciio)
- break;
-
- first_uga = uga;
- }
- }
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ size, (void **)&uga_handle);
+ if (status != EFI_SUCCESS)
+ return status;
- return status;
-}
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ uga_proto, NULL, &size, uga_handle);
+ if (status != EFI_SUCCESS)
+ goto free_handle;
-static efi_status_t
-setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
-{
- struct efi_uga_draw_protocol *uga = NULL, *first_uga;
- efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
- unsigned long nr_ugas;
- u64 *handles = (u64 *)uga_handle;
- efi_status_t status = EFI_INVALID_PARAMETER;
- int i;
+ height = 0;
+ width = 0;
first_uga = NULL;
- nr_ugas = size / sizeof(u64);
+ nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
for (i = 0; i < nr_ugas; i++) {
efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
u32 w, h, depth, refresh;
void *pciio;
- u64 handle = handles[i];
+ unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i]
+ : ((u32 *)uga_handle)[i];
status = efi_call_early(handle_protocol, handle,
- &uga_proto, (void **)&uga);
+ uga_proto, (void **)&uga);
if (status != EFI_SUCCESS)
continue;
+ pciio = NULL;
efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
- status = efi_early->call((unsigned long)uga->get_mode, uga,
- &w, &h, &depth, &refresh);
+ status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga,
+ &w, &h, &depth, &refresh);
if (status == EFI_SUCCESS && (!first_uga || pciio)) {
- *width = w;
- *height = h;
+ width = w;
+ height = h;
/*
* Once we've found a UGA supporting PCIIO,
}
}
- return status;
-}
-
-/*
- * See if we have Universal Graphics Adapter (UGA) protocol
- */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
- unsigned long size)
-{
- efi_status_t status;
- u32 width, height;
- void **uga_handle = NULL;
-
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- size, (void **)&uga_handle);
- if (status != EFI_SUCCESS)
- return status;
-
- status = efi_call_early(locate_handle,
- EFI_LOCATE_BY_PROTOCOL,
- uga_proto, NULL, &size, uga_handle);
- if (status != EFI_SUCCESS)
- goto free_handle;
-
- height = 0;
- width = 0;
-
- if (efi_early->is64)
- status = setup_uga64(uga_handle, size, &width, &height);
- else
- status = setup_uga32(uga_handle, size, &width, &height);
-
if (!width && !height)
goto free_handle;
/* EFI framebuffer */
- si->orig_video_isVGA = VIDEO_TYPE_EFI;
+ si->orig_video_isVGA = VIDEO_TYPE_EFI;
- si->lfb_depth = 32;
- si->lfb_width = width;
- si->lfb_height = height;
+ si->lfb_depth = 32;
+ si->lfb_width = width;
+ si->lfb_height = height;
- si->red_size = 8;
- si->red_pos = 16;
- si->green_size = 8;
- si->green_pos = 8;
- si->blue_size = 8;
- si->blue_pos = 0;
- si->rsvd_size = 8;
- si->rsvd_pos = 24;
+ si->red_size = 8;
+ si->red_pos = 16;
+ si->green_size = 8;
+ si->green_pos = 8;
+ si->blue_size = 8;
+ si->blue_pos = 0;
+ si->rsvd_size = 8;
+ si->rsvd_pos = 24;
free_handle:
efi_call_early(free_pool, uga_handle);
+
return status;
}
if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
return NULL;
- if (efi_early->is64)
+ if (efi_is_64bit())
setup_boot_services64(efi_early);
else
setup_boot_services32(efi_early);
status = efi_low_alloc(sys_table, 0x4000, 1,
(unsigned long *)&boot_params);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
+ efi_printk(sys_table, "Failed to allocate lowmem for boot params\n");
return NULL;
}
* Fill out some of the header fields ourselves because the
* EFI firmware loader doesn't load the first sector.
*/
- hdr->root_flags = 1;
- hdr->vid_mode = 0xffff;
- hdr->boot_flag = 0xAA55;
+ hdr->root_flags = 1;
+ hdr->vid_mode = 0xffff;
+ hdr->boot_flag = 0xAA55;
hdr->type_of_loader = 0x21;
cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
if (!cmdline_ptr)
goto fail;
+
hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
/* Fill in upper bits of command line address, NOP on 32 bit */
boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32;
return boot_params;
+
fail2:
efi_free(sys_table, options_size, hdr->cmd_line_ptr);
fail:
efi_free(sys_table, 0x4000, (unsigned long)boot_params);
+
return NULL;
}
unsigned long size;
e820ext->type = SETUP_E820_EXT;
- e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
+ e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
e820ext->next = 0;
data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
params->hdr.setup_data = (unsigned long)e820ext;
}
-static efi_status_t setup_e820(struct boot_params *params,
- struct setup_data *e820ext, u32 e820ext_size)
+static efi_status_t
+setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size)
{
struct boot_e820_entry *entry = params->e820_table;
struct efi_info *efi = ¶ms->efi_info;
}
struct exit_boot_struct {
- struct boot_params *boot_params;
- struct efi_info *efi;
- struct setup_data *e820ext;
- __u32 e820ext_size;
- bool is64;
+ struct boot_params *boot_params;
+ struct efi_info *efi;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
};
static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
first = false;
}
- signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE
+ : EFI32_LOADER_SIGNATURE;
memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
- p->efi->efi_systab = (unsigned long)sys_table_arg;
- p->efi->efi_memdesc_size = *map->desc_size;
- p->efi->efi_memdesc_version = *map->desc_ver;
- p->efi->efi_memmap = (unsigned long)*map->map;
- p->efi->efi_memmap_size = *map->map_size;
+ p->efi->efi_systab = (unsigned long)sys_table_arg;
+ p->efi->efi_memdesc_size = *map->desc_size;
+ p->efi->efi_memdesc_version = *map->desc_ver;
+ p->efi->efi_memmap = (unsigned long)*map->map;
+ p->efi->efi_memmap_size = *map->map_size;
#ifdef CONFIG_X86_64
- p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
- p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
+ p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+ p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
#endif
return EFI_SUCCESS;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle, bool is64)
+static efi_status_t exit_boot(struct boot_params *boot_params, void *handle)
{
unsigned long map_sz, key, desc_size, buff_size;
efi_memory_desc_t *mem_map;
struct efi_boot_memmap map;
struct exit_boot_struct priv;
- map.map = &mem_map;
- map.map_size = &map_sz;
- map.desc_size = &desc_size;
- map.desc_ver = &desc_version;
- map.key_ptr = &key;
- map.buff_size = &buff_size;
- priv.boot_params = boot_params;
- priv.efi = &boot_params->efi_info;
- priv.e820ext = NULL;
- priv.e820ext_size = 0;
- priv.is64 = is64;
+ map.map = &mem_map;
+ map.map_size = &map_sz;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_version;
+ map.key_ptr = &key;
+ map.buff_size = &buff_size;
+ priv.boot_params = boot_params;
+ priv.efi = &boot_params->efi_info;
+ priv.e820ext = NULL;
+ priv.e820ext_size = 0;
/* Might as well exit boot services now */
status = efi_exit_boot_services(sys_table, handle, &map, &priv,
if (status != EFI_SUCCESS)
return status;
- e820ext = priv.e820ext;
- e820ext_size = priv.e820ext_size;
+ e820ext = priv.e820ext;
+ e820ext_size = priv.e820ext_size;
+
/* Historic? */
- boot_params->alt_mem_k = 32 * 1024;
+ boot_params->alt_mem_k = 32 * 1024;
status = setup_e820(boot_params, e820ext, e820ext_size);
if (status != EFI_SUCCESS)
* On success we return a pointer to a boot_params structure, and NULL
* on failure.
*/
-struct boot_params *efi_main(struct efi_config *c,
- struct boot_params *boot_params)
+struct boot_params *
+efi_main(struct efi_config *c, struct boot_params *boot_params)
{
struct desc_ptr *gdt = NULL;
efi_loaded_image_t *image;
struct desc_struct *desc;
void *handle;
efi_system_table_t *_table;
- bool is64;
efi_early = c;
_table = (efi_system_table_t *)(unsigned long)efi_early->table;
handle = (void *)(unsigned long)efi_early->image_handle;
- is64 = efi_early->is64;
sys_table = _table;
if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
goto fail;
- if (is64)
+ if (efi_is_64bit())
setup_boot_services64(efi_early);
else
setup_boot_services32(efi_early);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
sizeof(*gdt), (void **)&gdt);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
+ efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n");
goto fail;
}
status = efi_low_alloc(sys_table, gdt->size, 8,
(unsigned long *)&gdt->address);
if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for gdt\n");
+ efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n");
goto fail;
}
hdr->code32_start = bzimage_addr;
}
- status = exit_boot(boot_params, handle, is64);
+ status = exit_boot(boot_params, handle);
if (status != EFI_SUCCESS) {
efi_printk(sys_table, "exit_boot() failed!\n");
goto fail;
if (IS_ENABLED(CONFIG_X86_64)) {
/* __KERNEL32_CS */
- desc->limit0 = 0xffff;
- desc->base0 = 0x0000;
- desc->base1 = 0x0000;
- desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
- desc->s = DESC_TYPE_CODE_DATA;
- desc->dpl = 0;
- desc->p = 1;
- desc->limit1 = 0xf;
- desc->avl = 0;
- desc->l = 0;
- desc->d = SEG_OP_SIZE_32BIT;
- desc->g = SEG_GRANULARITY_4KB;
- desc->base2 = 0x00;
+ desc->limit0 = 0xffff;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+ desc->s = DESC_TYPE_CODE_DATA;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit1 = 0xf;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = SEG_OP_SIZE_32BIT;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
+
desc++;
} else {
/* Second entry is unused on 32-bit */
}
/* __KERNEL_CS */
- desc->limit0 = 0xffff;
- desc->base0 = 0x0000;
- desc->base1 = 0x0000;
- desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
- desc->s = DESC_TYPE_CODE_DATA;
- desc->dpl = 0;
- desc->p = 1;
- desc->limit1 = 0xf;
- desc->avl = 0;
+ desc->limit0 = 0xffff;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+ desc->s = DESC_TYPE_CODE_DATA;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit1 = 0xf;
+ desc->avl = 0;
+
if (IS_ENABLED(CONFIG_X86_64)) {
desc->l = 1;
desc->d = 0;
desc->l = 0;
desc->d = SEG_OP_SIZE_32BIT;
}
- desc->g = SEG_GRANULARITY_4KB;
- desc->base2 = 0x00;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
desc++;
/* __KERNEL_DS */
- desc->limit0 = 0xffff;
- desc->base0 = 0x0000;
- desc->base1 = 0x0000;
- desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
- desc->s = DESC_TYPE_CODE_DATA;
- desc->dpl = 0;
- desc->p = 1;
- desc->limit1 = 0xf;
- desc->avl = 0;
- desc->l = 0;
- desc->d = SEG_OP_SIZE_32BIT;
- desc->g = SEG_GRANULARITY_4KB;
- desc->base2 = 0x00;
+ desc->limit0 = 0xffff;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+ desc->s = DESC_TYPE_CODE_DATA;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit1 = 0xf;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = SEG_OP_SIZE_32BIT;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
desc++;
if (IS_ENABLED(CONFIG_X86_64)) {
/* Task segment value */
- desc->limit0 = 0x0000;
- desc->base0 = 0x0000;
- desc->base1 = 0x0000;
- desc->type = SEG_TYPE_TSS;
- desc->s = 0;
- desc->dpl = 0;
- desc->p = 1;
- desc->limit1 = 0x0;
- desc->avl = 0;
- desc->l = 0;
- desc->d = 0;
- desc->g = SEG_GRANULARITY_4KB;
- desc->base2 = 0x00;
+ desc->limit0 = 0x0000;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_TSS;
+ desc->s = 0;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit1 = 0x0;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = 0;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
desc++;
}
return boot_params;
fail:
efi_printk(sys_table, "efi_main() failed!\n");
+
return NULL;
}
#define DESC_TYPE_CODE_DATA (1 << 0)
-struct efi_uga_draw_protocol_32 {
+typedef struct {
u32 get_mode;
u32 set_mode;
u32 blt;
-};
+} efi_uga_draw_protocol_32_t;
-struct efi_uga_draw_protocol_64 {
+typedef struct {
u64 get_mode;
u64 set_mode;
u64 blt;
-};
+} efi_uga_draw_protocol_64_t;
-struct efi_uga_draw_protocol {
+typedef struct {
void *get_mode;
void *set_mode;
void *blt;
-};
+} efi_uga_draw_protocol_t;
#endif /* BOOT_COMPRESSED_EBOOT_H */
/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+static unsigned long long mem_limit = ULLONG_MAX;
enum mem_avoid_index {
memmap_too_large = true;
}
-static int handle_mem_memmap(void)
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+ static bool gbpage_sz;
+ char *p;
+
+ if (!strcmp(param, "hugepagesz")) {
+ p = val;
+ if (memparse(p, &p) != PUD_SIZE) {
+ gbpage_sz = false;
+ return;
+ }
+
+ if (gbpage_sz)
+ warn("Repeatedly set hugeTLB page size of 1G!\n");
+ gbpage_sz = true;
+ return;
+ }
+
+ if (!strcmp(param, "hugepages") && gbpage_sz) {
+ p = val;
+ max_gb_huge_pages = simple_strtoull(p, &p, 0);
+ return;
+ }
+}
+
+
+static int handle_mem_options(void)
{
char *args = (char *)get_cmd_line_ptr();
size_t len = strlen((char *)args);
char *param, *val;
u64 mem_size;
- if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+ if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
+ !strstr(args, "hugepages"))
return 0;
tmp_cmdline = malloc(len + 1);
if (!strcmp(param, "memmap")) {
mem_avoid_memmap(val);
+ } else if (strstr(param, "hugepages")) {
+ parse_gb_huge_pages(param, val);
} else if (!strcmp(param, "mem")) {
char *p = val;
/* We don't need to set a mapping for setup_data. */
/* Mark the memmap regions we need to avoid */
- handle_mem_memmap();
+ handle_mem_options();
#ifdef CONFIG_X86_VERBOSE_BOOTUP
/* Make sure video RAM can be used. */
}
}
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+ unsigned long addr, size = 0;
+ struct mem_vector tmp;
+ int i = 0;
+
+ if (!max_gb_huge_pages) {
+ store_slot_info(region, image_size);
+ return;
+ }
+
+ addr = ALIGN(region->start, PUD_SIZE);
+ /* Did we raise the address above the passed in memory entry? */
+ if (addr < region->start + region->size)
+ size = region->size - (addr - region->start);
+
+ /* Check how many 1GB huge pages can be filtered out: */
+ while (size > PUD_SIZE && max_gb_huge_pages) {
+ size -= PUD_SIZE;
+ max_gb_huge_pages--;
+ i++;
+ }
+
+ /* No good 1GB huge pages found: */
+ if (!i) {
+ store_slot_info(region, image_size);
+ return;
+ }
+
+ /*
+ * Skip those 'i'*1GB good huge pages, and continue checking and
+ * processing the remaining head or tail part of the passed region
+ * if available.
+ */
+
+ if (addr >= region->start + image_size) {
+ tmp.start = region->start;
+ tmp.size = addr - region->start;
+ store_slot_info(&tmp, image_size);
+ }
+
+ size = region->size - (addr - region->start) - i * PUD_SIZE;
+ if (size >= image_size) {
+ tmp.start = addr + i * PUD_SIZE;
+ tmp.size = size;
+ store_slot_info(&tmp, image_size);
+ }
+}
+
static unsigned long slots_fetch_random(void)
{
unsigned long slot;
/* If nothing overlaps, store the region and return. */
if (!mem_avoid_overlap(®ion, &overlap)) {
- store_slot_info(®ion, image_size);
+ process_gb_huge_pages(®ion, image_size);
return;
}
beginning.start = region.start;
beginning.size = overlap.start - region.start;
- store_slot_info(&beginning, image_size);
+ process_gb_huge_pages(&beginning, image_size);
}
/* Return if overlap extends to or past end of region. */
+#include <asm/e820/types.h>
#include <asm/processor.h>
#include "pgtable.h"
#include "../string.h"
extern struct boot_params *boot_params;
int cmdline_find_option_bool(const char *option);
+static unsigned long find_trampoline_placement(void)
+{
+ unsigned long bios_start, ebda_start;
+ unsigned long trampoline_start;
+ struct boot_e820_entry *entry;
+ int i;
+
+ /*
+ * Find a suitable spot for the trampoline.
+ * This code is based on reserve_bios_regions().
+ */
+
+ ebda_start = *(unsigned short *)0x40e << 4;
+ bios_start = *(unsigned short *)0x413 << 10;
+
+ if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+ bios_start = BIOS_START_MAX;
+
+ if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+ bios_start = ebda_start;
+
+ bios_start = round_down(bios_start, PAGE_SIZE);
+
+ /* Find the first usable memory region under bios_start. */
+ for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+ entry = &boot_params->e820_table[i];
+
+ /* Skip all entries above bios_start. */
+ if (bios_start <= entry->addr)
+ continue;
+
+ /* Skip non-RAM entries. */
+ if (entry->type != E820_TYPE_RAM)
+ continue;
+
+ /* Adjust bios_start to the end of the entry if needed. */
+ if (bios_start > entry->addr + entry->size)
+ bios_start = entry->addr + entry->size;
+
+ /* Keep bios_start page-aligned. */
+ bios_start = round_down(bios_start, PAGE_SIZE);
+
+ /* Skip the entry if it's too small. */
+ if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+ continue;
+
+ break;
+ }
+
+ /* Place the trampoline just below the end of low memory */
+ return bios_start - TRAMPOLINE_32BIT_SIZE;
+}
+
struct paging_config paging_prepare(void *rmode)
{
struct paging_config paging_config = {};
- unsigned long bios_start, ebda_start;
/* Initialize boot_params. Required for cmdline_find_option_bool(). */
boot_params = rmode;
paging_config.l5_required = 1;
}
- /*
- * Find a suitable spot for the trampoline.
- * This code is based on reserve_bios_regions().
- */
-
- ebda_start = *(unsigned short *)0x40e << 4;
- bios_start = *(unsigned short *)0x413 << 10;
-
- if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
- bios_start = BIOS_START_MAX;
-
- if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
- bios_start = ebda_start;
-
- /* Place the trampoline just below the end of low memory, aligned to 4k */
- paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
- paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+ paging_config.trampoline_start = find_trampoline_placement();
trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
*/
#include <linux/types.h>
+#include <asm/asm.h>
#include "ctype.h"
#include "string.h"
int memcmp(const void *s1, const void *s2, size_t len)
{
bool diff;
- asm("repe; cmpsb; setnz %0"
- : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+ asm("repe; cmpsb" CC_SET(nz)
+ : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG
mov LEN, %r8
movdqu STATE3, 0x40(STATEP)
FRAME_END
+ ret
ENDPROC(crypto_aegis128_aesni_enc_tail)
.macro decrypt_block a s0 s1 s2 s3 s4 i
}
};
-static const struct x86_cpu_id aesni_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_AES),
- X86_FEATURE_MATCH(X86_FEATURE_XMM2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
static int __init crypto_aegis128_aesni_module_init(void)
{
- if (!x86_match_cpu(aesni_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+ !boot_cpu_has(X86_FEATURE_AES) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_aegis128_aesni_alg,
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG0, MSG0
pxor MSG1, MSG1
state_store0
FRAME_END
+ ret
ENDPROC(crypto_aegis128l_aesni_enc_tail)
/*
}
};
-static const struct x86_cpu_id aesni_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_AES),
- X86_FEATURE_MATCH(X86_FEATURE_XMM2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
static int __init crypto_aegis128l_aesni_module_init(void)
{
- if (!x86_match_cpu(aesni_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+ !boot_cpu_has(X86_FEATURE_AES) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_aegis128l_aesni_alg,
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG
mov LEN, %r8
state_store0
FRAME_END
+ ret
ENDPROC(crypto_aegis256_aesni_enc_tail)
/*
}
};
-static const struct x86_cpu_id aesni_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_AES),
- X86_FEATURE_MATCH(X86_FEATURE_XMM2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
static int __init crypto_aegis256_aesni_module_init(void)
{
- if (!x86_match_cpu(aesni_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+ !boot_cpu_has(X86_FEATURE_AES) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_aegis256_aesni_alg,
.macro GCM_INIT Iv SUBKEY AAD AADLEN
mov \AADLEN, %r11
mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
- xor %r11, %r11
+ xor %r11d, %r11d
mov %r11, InLen(%arg2) # ctx_data.in_length = 0
mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
movdqu HashKey(%arg2), %xmm13
add %arg5, InLen(%arg2)
- xor %r11, %r11 # initialise the data pointer offset as zero
+ xor %r11d, %r11d # initialise the data pointer offset as zero
PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
sub %r11, %arg5 # sub partial block data used
# GHASH computation for the last <16 Byte block
GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %rax,%rax
+ xor %eax, %eax
mov %rax, PBlockLen(%arg2)
jmp _dec_done_\@
# GHASH computation for the last <16 Byte block
GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %rax,%rax
+ xor %eax, %eax
mov %rax, PBlockLen(%arg2)
jmp _encode_done_\@
_get_AAD_done\@:
# initialize the data pointer offset as zero
- xor %r11, %r11
+ xor %r11d, %r11d
# start AES for num_initial_blocks blocks
mov arg5, %rax # rax = *Y0
_get_AAD_done\@:
# initialize the data pointer offset as zero
- xor %r11, %r11
+ xor %r11d, %r11d
# start AES for num_initial_blocks blocks
mov arg5, %rax # rax = *Y0
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
vpxor MSG, MSG, MSG
mov %rcx, %r8
vmovdqu STATE4, (4 * 32)(%rdi)
FRAME_END
+ ret
ENDPROC(crypto_morus1280_avx2_enc_tail)
/*
MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
-static const struct x86_cpu_id avx2_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_AVX2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id);
-
static int __init crypto_morus1280_avx2_module_init(void)
{
- if (!x86_match_cpu(avx2_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_morus1280_avx2_algs,
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG_LO, MSG_LO
pxor MSG_HI, MSG_HI
movdqu STATE4_HI, (9 * 16)(%rdi)
FRAME_END
+ ret
ENDPROC(crypto_morus1280_sse2_enc_tail)
/*
MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
-static const struct x86_cpu_id sse2_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_XMM2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
static int __init crypto_morus1280_sse2_module_init(void)
{
- if (!x86_match_cpu(sse2_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_morus1280_sse2_algs,
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG
mov %rcx, %r8
movdqu STATE4, (4 * 16)(%rdi)
FRAME_END
+ ret
ENDPROC(crypto_morus640_sse2_enc_tail)
/*
MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
-static const struct x86_cpu_id sse2_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_XMM2),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
static int __init crypto_morus640_sse2_module_init(void)
{
- if (!x86_match_cpu(sse2_cpu_id))
+ if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
return crypto_register_aeads(crypto_morus640_sse2_algs,
# cleanup workspace
mov $8, %ecx
mov %rsp, %rdi
- xor %rax, %rax
+ xor %eax, %eax
rep stosq
mov %rbp, %rsp # deallocate workspace
if (cached_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
if (cached_flags & _TIF_USER_RETURN_NOTIFY)
# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
#else
# define preempt_stop(clobbers)
-# define resume_kernel restore_all
+# define resume_kernel restore_all_kernel
#endif
.macro TRACE_IRQS_IRET
#endif
.endm
+#define PTI_SWITCH_MASK (1 << PAGE_SHIFT)
+
/*
* User gs save/restore
*
#endif /* CONFIG_X86_32_LAZY_GS */
-.macro SAVE_ALL pt_regs_ax=%eax
+/* Unconditionally switch to user cr3 */
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ movl %cr3, \scratch_reg
+ orl $PTI_SWITCH_MASK, \scratch_reg
+ movl \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro BUG_IF_WRONG_CR3 no_user_check=0
+#ifdef CONFIG_DEBUG_ENTRY
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ .if \no_user_check == 0
+ /* coming from usermode? */
+ testl $SEGMENT_RPL_MASK, PT_CS(%esp)
+ jz .Lend_\@
+ .endif
+ /* On user-cr3? */
+ movl %cr3, %eax
+ testl $PTI_SWITCH_MASK, %eax
+ jnz .Lend_\@
+ /* From userspace with kernel cr3 - BUG */
+ ud2
+.Lend_\@:
+#endif
+.endm
+
+/*
+ * Switch to kernel cr3 if not already loaded and return current cr3 in
+ * \scratch_reg
+ */
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ movl %cr3, \scratch_reg
+ /* Test if we are already on kernel CR3 */
+ testl $PTI_SWITCH_MASK, \scratch_reg
+ jz .Lend_\@
+ andl $(~PTI_SWITCH_MASK), \scratch_reg
+ movl \scratch_reg, %cr3
+ /* Return original CR3 in \scratch_reg */
+ orl $PTI_SWITCH_MASK, \scratch_reg
+.Lend_\@:
+.endm
+
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
cld
PUSH_GS
pushl %fs
movl $(__KERNEL_PERCPU), %edx
movl %edx, %fs
SET_KERNEL_GS %edx
+
+ /* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+ SWITCH_TO_KERNEL_STACK
+.endif
+
+.endm
+
+.macro SAVE_ALL_NMI cr3_reg:req
+ SAVE_ALL
+
+ BUG_IF_WRONG_CR3
+
+ /*
+ * Now switch the CR3 when PTI is enabled.
+ *
+ * We can enter with either user or kernel cr3, the code will
+ * store the old cr3 in \cr3_reg and switches to the kernel cr3
+ * if necessary.
+ */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
.endm
/*
POP_GS_EX
.endm
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+ /*
+ * Now switch the CR3 when PTI is enabled.
+ *
+ * We enter with kernel cr3 and switch the cr3 to the value
+ * stored on \cr3_reg, which is either a user or a kernel cr3.
+ */
+ ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+ testl $PTI_SWITCH_MASK, \cr3_reg
+ jz .Lswitched_\@
+
+ /* User cr3 in \cr3_reg - write it to hardware cr3 */
+ movl \cr3_reg, %cr3
+
+.Lswitched_\@:
+
+ BUG_IF_WRONG_CR3
+
+ RESTORE_REGS pop=\pop
+.endm
+
+.macro CHECK_AND_APPLY_ESPFIX
+#ifdef CONFIG_X86_ESPFIX32
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+
+ ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
+
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
+ /*
+ * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+ * are returning to the kernel.
+ * See comments in process.c:copy_thread() for details.
+ */
+ movb PT_OLDSS(%esp), %ah
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+ cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
+ jne .Lend_\@ # returning to user-space with LDT SS
+
+ /*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+ mov %esp, %edx /* load kernel esp */
+ mov PT_OLDESP(%esp), %eax /* load userspace esp */
+ mov %dx, %ax /* eax: new kernel esp */
+ sub %eax, %edx /* offset (low word is 0) */
+ shr $16, %edx
+ mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
+ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
+ pushl $__ESPFIX_SS
+ pushl %eax /* new kernel esp */
+ /*
+ * Disable interrupts, but do not irqtrace this section: we
+ * will soon execute iret and the tracer was already set to
+ * the irqstate after the IRET:
+ */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ lss (%esp), %esp /* switch to espfix segment */
+.Lend_\@:
+#endif /* CONFIG_X86_ESPFIX32 */
+.endm
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+
+#define CS_FROM_ENTRY_STACK (1 << 31)
+#define CS_FROM_USER_CR3 (1 << 30)
+
+.macro SWITCH_TO_KERNEL_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ BUG_IF_WRONG_CR3
+
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+
+ /*
+ * %eax now contains the entry cr3 and we carry it forward in
+ * that register for the time this macro runs
+ */
+
+ /* Are we on the entry stack? Bail out if not! */
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %esp, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
+ jae .Lend_\@
+
+ /* Load stack pointer into %esi and %edi */
+ movl %esp, %esi
+ movl %esi, %edi
+
+ /* Move %edi to the top of the entry stack */
+ andl $(MASK_entry_stack), %edi
+ addl $(SIZEOF_entry_stack), %edi
+
+ /* Load top of task-stack into %edi */
+ movl TSS_entry2task_stack(%edi), %edi
+
+ /*
+ * Clear unused upper bits of the dword containing the word-sized CS
+ * slot in pt_regs in case hardware didn't clear it for us.
+ */
+ andl $(0x0000ffff), PT_CS(%esp)
+
+ /* Special case - entry from kernel mode via entry stack */
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS
+ movb PT_CS(%esp), %cl
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
+#else
+ movl PT_CS(%esp), %ecx
+ andl $SEGMENT_RPL_MASK, %ecx
+#endif
+ cmpl $USER_RPL, %ecx
+ jb .Lentry_from_kernel_\@
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esi)
+ jz .Lcopy_pt_regs_\@
+
+ /*
+ * Stack-frame contains 4 additional segment registers when
+ * coming from VM86 mode
+ */
+ addl $(4 * 4), %ecx
+
+#endif
+.Lcopy_pt_regs_\@:
+
+ /* Allocate frame on task-stack */
+ subl %ecx, %edi
+
+ /* Switch to task-stack */
+ movl %edi, %esp
+
+ /*
+ * We are now on the task-stack and can safely copy over the
+ * stack-frame
+ */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ jmp .Lend_\@
+
+.Lentry_from_kernel_\@:
+
+ /*
+ * This handles the case when we enter the kernel from
+ * kernel-mode and %esp points to the entry-stack. When this
+ * happens we need to switch to the task-stack to run C code,
+ * but switch back to the entry-stack again when we approach
+ * iret and return to the interrupted code-path. This usually
+ * happens when we hit an exception while restoring user-space
+ * segment registers on the way back to user-space or when the
+ * sysenter handler runs with eflags.tf set.
+ *
+ * When we switch to the task-stack here, we can't trust the
+ * contents of the entry-stack anymore, as the exception handler
+ * might be scheduled out or moved to another CPU. Therefore we
+ * copy the complete entry-stack to the task-stack and set a
+ * marker in the iret-frame (bit 31 of the CS dword) to detect
+ * what we've done on the iret path.
+ *
+ * On the iret path we copy everything back and switch to the
+ * entry-stack, so that the interrupted kernel code-path
+ * continues on the same stack it was interrupted with.
+ *
+ * Be aware that an NMI can happen anytime in this code.
+ *
+ * %esi: Entry-Stack pointer (same as %esp)
+ * %edi: Top of the task stack
+ * %eax: CR3 on kernel entry
+ */
+
+ /* Calculate number of bytes on the entry stack in %ecx */
+ movl %esi, %ecx
+
+ /* %ecx to the top of entry-stack */
+ andl $(MASK_entry_stack), %ecx
+ addl $(SIZEOF_entry_stack), %ecx
+
+ /* Number of bytes on the entry stack to %ecx */
+ sub %esi, %ecx
+
+ /* Mark stackframe as coming from entry stack */
+ orl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
+
+ /*
+ * Test the cr3 used to enter the kernel and add a marker
+ * so that we can switch back to it before iret.
+ */
+ testl $PTI_SWITCH_MASK, %eax
+ jz .Lcopy_pt_regs_\@
+ orl $CS_FROM_USER_CR3, PT_CS(%esp)
+
+ /*
+ * %esi and %edi are unchanged, %ecx contains the number of
+ * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
+ * the stack-frame on task-stack and copy everything over
+ */
+ jmp .Lcopy_pt_regs_\@
+
+.Lend_\@:
+.endm
+
+/*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsl'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+ jz .Lcopy_pt_regs_\@
+
+ /* Additional 4 registers to copy when returning to VM86 mode */
+ addl $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+ /* Initialize source and destination for movsl */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+ subl %ecx, %edi
+ movl %esp, %esi
+
+ /* Save future stack pointer in %ebx */
+ movl %edi, %ebx
+
+ /* Copy over the stack-frame */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ /*
+ * Switch to entry-stack - needs to happen after everything is
+ * copied because the NMI handler will overwrite the task-stack
+ * when on entry-stack
+ */
+ movl %ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
+ * This macro handles the case when we return to kernel-mode on the iret
+ * path and have to switch back to the entry stack and/or user-cr3
+ *
+ * See the comments below the .Lentry_from_kernel_\@ label in the
+ * SWITCH_TO_KERNEL_STACK macro for more details.
+ */
+.macro PARANOID_EXIT_TO_KERNEL_MODE
+
+ /*
+ * Test if we entered the kernel with the entry-stack. Most
+ * likely we did not, because this code only runs on the
+ * return-to-kernel path.
+ */
+ testl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
+ jz .Lend_\@
+
+ /* Unlikely slow-path */
+
+ /* Clear marker from stack-frame */
+ andl $(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
+
+ /* Copy the remaining task-stack contents to entry-stack */
+ movl %esp, %esi
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+
+ /* Bytes on the task-stack to ecx */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+ subl %esi, %ecx
+
+ /* Allocate stack-frame on entry-stack */
+ subl %ecx, %edi
+
+ /*
+ * Save future stack-pointer, we must not switch until the
+ * copy is done, otherwise the NMI handler could destroy the
+ * contents of the task-stack we are about to copy.
+ */
+ movl %edi, %ebx
+
+ /* Do the copy */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ /* Safe to switch to entry-stack now */
+ movl %ebx, %esp
+
+ /*
+ * We came from entry-stack and need to check if we also need to
+ * switch back to user cr3.
+ */
+ testl $CS_FROM_USER_CR3, PT_CS(%esp)
+ jz .Lend_\@
+
+ /* Clear marker from stack-frame */
+ andl $(~CS_FROM_USER_CR3), PT_CS(%esp)
+
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+.Lend_\@:
+.endm
/*
* %eax: prev task
* %edx: next task
DISABLE_INTERRUPTS(CLBR_ANY)
.Lneed_resched:
cmpl $0, PER_CPU_VAR(__preempt_count)
- jnz restore_all
+ jnz restore_all_kernel
testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
- jz restore_all
+ jz restore_all_kernel
call preempt_schedule_irq
jmp .Lneed_resched
END(resume_kernel)
* 0(%ebp) arg6
*/
ENTRY(entry_SYSENTER_32)
- movl TSS_sysenter_sp0(%esp), %esp
+ /*
+ * On entry-stack with all userspace-regs live - save and
+ * restore eflags and %eax to use it as scratch-reg for the cr3
+ * switch.
+ */
+ pushfl
+ pushl %eax
+ BUG_IF_WRONG_CR3 no_user_check=1
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+ popl %eax
+ popfl
+
+ /* Stack empty again, switch to task stack */
+ movl TSS_entry2task_stack(%esp), %esp
+
.Lsysenter_past_esp:
pushl $__USER_DS /* pt_regs->ss */
pushl %ebp /* pt_regs->sp (stashed in bp) */
pushl $__USER_CS /* pt_regs->cs */
pushl $0 /* pt_regs->ip = 0 (placeholder) */
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest, stack already switched */
/*
* SYSENTER doesn't filter flags, so we need to clear NT, AC
/* Opportunistic SYSEXIT */
TRACE_IRQS_ON /* User mode traces as IRQs on. */
+
+ /*
+ * Setup entry stack - we keep the pointer in %eax and do the
+ * switch after almost all user-state is restored.
+ */
+
+ /* Load entry stack pointer and allocate frame for eflags/eax */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
+ subl $(2*4), %eax
+
+ /* Copy eflags and eax to entry stack */
+ movl PT_EFLAGS(%esp), %edi
+ movl PT_EAX(%esp), %esi
+ movl %edi, (%eax)
+ movl %esi, 4(%eax)
+
+ /* Restore user registers and segments */
movl PT_EIP(%esp), %edx /* pt_regs->ip */
movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */
1: mov PT_FS(%esp), %fs
PTGS_TO_GS
+
popl %ebx /* pt_regs->bx */
addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */
popl %esi /* pt_regs->si */
popl %edi /* pt_regs->di */
popl %ebp /* pt_regs->bp */
- popl %eax /* pt_regs->ax */
+
+ /* Switch to entry stack */
+ movl %eax, %esp
+
+ /* Now ready to switch the cr3 */
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
/*
* Restore all flags except IF. (We restore IF separately because
* STI gives a one-instruction window in which we won't be interrupted,
* whereas POPF does not.)
*/
- addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */
- btr $X86_EFLAGS_IF_BIT, (%esp)
+ btrl $X86_EFLAGS_IF_BIT, (%esp)
+ BUG_IF_WRONG_CR3 no_user_check=1
popfl
+ popl %eax
/*
* Return back to the vDSO, which will pop ecx and edx.
ENTRY(entry_INT80_32)
ASM_CLAC
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+
+ SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */
/*
* User mode is traced as though IRQs are on, and the interrupt gate
restore_all:
TRACE_IRQS_IRET
+ SWITCH_TO_ENTRY_STACK
.Lrestore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
- ALTERNATIVE "jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX
-
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
- /*
- * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
- * are returning to the kernel.
- * See comments in process.c:copy_thread() for details.
- */
- movb PT_OLDSS(%esp), %ah
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
- cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
- je .Lldt_ss # returning to user-space with LDT SS
-#endif
+ CHECK_AND_APPLY_ESPFIX
.Lrestore_nocheck:
- RESTORE_REGS 4 # skip orig_eax/error_code
+ /* Switch back to user CR3 */
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+ BUG_IF_WRONG_CR3
+
+ /* Restore user state */
+ RESTORE_REGS pop=4 # skip orig_eax/error_code
.Lirq_return:
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
*/
INTERRUPT_RETURN
+restore_all_kernel:
+ TRACE_IRQS_IRET
+ PARANOID_EXIT_TO_KERNEL_MODE
+ BUG_IF_WRONG_CR3
+ RESTORE_REGS 4
+ jmp .Lirq_return
+
.section .fixup, "ax"
ENTRY(iret_exc )
pushl $0 # no error code
pushl $do_iret_error
- jmp common_exception
-.previous
- _ASM_EXTABLE(.Lirq_return, iret_exc)
-#ifdef CONFIG_X86_ESPFIX32
-.Lldt_ss:
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
- mov %esp, %edx /* load kernel esp */
- mov PT_OLDESP(%esp), %eax /* load userspace esp */
- mov %dx, %ax /* eax: new kernel esp */
- sub %eax, %edx /* offset (low word is 0) */
- shr $16, %edx
- mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
- mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
- pushl $__ESPFIX_SS
- pushl %eax /* new kernel esp */
+#ifdef CONFIG_DEBUG_ENTRY
/*
- * Disable interrupts, but do not irqtrace this section: we
- * will soon execute iret and the tracer was already set to
- * the irqstate after the IRET:
+ * The stack-frame here is the one that iret faulted on, so its a
+ * return-to-user frame. We are on kernel-cr3 because we come here from
+ * the fixup code. This confuses the CR3 checker, so switch to user-cr3
+ * as the checker expects it.
*/
- DISABLE_INTERRUPTS(CLBR_ANY)
- lss (%esp), %esp /* switch to espfix segment */
- jmp .Lrestore_nocheck
+ pushl %eax
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+ popl %eax
#endif
+
+ jmp common_exception
+.previous
+ _ASM_EXTABLE(.Lirq_return, iret_exc)
ENDPROC(entry_INT80_32)
.macro FIXUP_ESPFIX_STACK
common_interrupt:
ASM_CLAC
addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
movl %esp, %eax
jmp ret_from_intr
ENDPROC(common_interrupt)
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- ASM_CLAC; \
- pushl $~(nr); \
- SAVE_ALL; \
- ENCODE_FRAME_POINTER; \
- TRACE_IRQS_OFF \
- movl %esp, %eax; \
- call fn; \
- jmp ret_from_intr; \
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL switch_stacks=1; \
+ ENCODE_FRAME_POINTER; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
ENDPROC(name)
#define BUILD_INTERRUPT(name, nr) \
pushl %es
pushl %ds
pushl %eax
+ movl $(__USER_DS), %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax, %fs
pushl %ebp
pushl %edi
pushl %esi
pushl %edx
pushl %ecx
pushl %ebx
+ SWITCH_TO_KERNEL_STACK
ENCODE_FRAME_POINTER
cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
UNWIND_ESPFIX_STACK
GS_TO_REG %ecx
movl PT_GS(%esp), %edi # get the function address
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
CALL_NOSPEC %edi
ENTRY(debug)
/*
- * #DB can happen at the first instruction of
- * entry_SYSENTER_32 or in Xen's SYSENTER prologue. If this
- * happens, then we will be running on a very small stack. We
- * need to detect this condition and switch to the thread
- * stack before calling any C code at all.
- *
- * If you edit this code, keep in mind that NMIs can happen in here.
+ * Entry from sysenter is now handled in common_exception
*/
ASM_CLAC
pushl $-1 # mark this as an int
- SAVE_ALL
- ENCODE_FRAME_POINTER
- xorl %edx, %edx # error code 0
- movl %esp, %eax # pt_regs pointer
-
- /* Are we currently on the SYSENTER stack? */
- movl PER_CPU_VAR(cpu_entry_area), %ecx
- addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
- subl %eax, %ecx /* ecx = (end of entry_stack) - esp */
- cmpl $SIZEOF_entry_stack, %ecx
- jb .Ldebug_from_sysenter_stack
-
- TRACE_IRQS_OFF
- call do_debug
- jmp ret_from_exception
-
-.Ldebug_from_sysenter_stack:
- /* We're on the SYSENTER stack. Switch off. */
- movl %esp, %ebx
- movl PER_CPU_VAR(cpu_current_top_of_stack), %esp
- TRACE_IRQS_OFF
- call do_debug
- movl %ebx, %esp
- jmp ret_from_exception
+ pushl $do_debug
+ jmp common_exception
END(debug)
/*
*/
ENTRY(nmi)
ASM_CLAC
+
#ifdef CONFIG_X86_ESPFIX32
pushl %eax
movl %ss, %eax
#endif
pushl %eax # pt_regs->orig_ax
- SAVE_ALL
+ SAVE_ALL_NMI cr3_reg=%edi
ENCODE_FRAME_POINTER
xorl %edx, %edx # zero error code
movl %esp, %eax # pt_regs pointer
/* Not on SYSENTER stack. */
call do_nmi
- jmp .Lrestore_all_notrace
+ jmp .Lnmi_return
.Lnmi_from_sysenter_stack:
/*
movl PER_CPU_VAR(cpu_current_top_of_stack), %esp
call do_nmi
movl %ebx, %esp
- jmp .Lrestore_all_notrace
+
+.Lnmi_return:
+ CHECK_AND_APPLY_ESPFIX
+ RESTORE_ALL_NMI cr3_reg=%edi pop=4
+ jmp .Lirq_return
#ifdef CONFIG_X86_ESPFIX32
.Lnmi_espfix_stack:
pushl 16(%esp)
.endr
pushl %eax
- SAVE_ALL
+ SAVE_ALL_NMI cr3_reg=%edi
ENCODE_FRAME_POINTER
FIXUP_ESPFIX_STACK # %eax == %esp
xorl %edx, %edx # zero error code
call do_nmi
- RESTORE_REGS
+ RESTORE_ALL_NMI cr3_reg=%edi
lss 12+4(%esp), %esp # back to espfix stack
jmp .Lirq_return
#endif
ENTRY(int3)
ASM_CLAC
pushl $-1 # mark this as an int
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
xorl %edx, %edx # zero error code
.endm
.macro TRACE_IRQS_IRETQ_DEBUG
- bt $9, EFLAGS(%rsp) /* interrupts off? */
+ btl $9, EFLAGS(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON_DEBUG
1:
1:
/* kernel thread */
+ UNWIND_HINT_EMPTY
movq %r12, %rdi
CALL_NOSPEC %rbx
/*
#ifdef CONFIG_PREEMPT
/* Interrupts are off */
/* Check if we need preemption */
- bt $9, EFLAGS(%rsp) /* were interrupts off? */
+ btl $9, EFLAGS(%rsp) /* were interrupts off? */
jnc 1f
0: cmpl $0, PER_CPU_VAR(__preempt_count)
jnz 1f
call \do_sym
- jmp error_exit /* %ebx: no swapgs flag */
+ jmp error_exit
.endif
END(\sym)
.endm
/*
* Save all registers in pt_regs, and switch GS if needed.
- * Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
UNWIND_HINT_FUNC
* for these here too.
*/
.Lerror_kernelspace:
- incl %ebx
leaq native_irq_return_iret(%rip), %rcx
cmpq %rcx, RIP+8(%rsp)
je .Lerror_bad_iret
/*
* Pretend that the exception came from user mode: set up pt_regs
- * as if we faulted immediately after IRET and clear EBX so that
- * error_exit knows that we will be returning to user mode.
+ * as if we faulted immediately after IRET.
*/
mov %rsp, %rdi
call fixup_bad_iret
mov %rax, %rsp
- decl %ebx
jmp .Lerror_entry_from_usermode_after_swapgs
END(error_entry)
-
-/*
- * On entry, EBX is a "return to kernel mode" flag:
- * 1: already in kernel mode, don't need SWAPGS
- * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
- */
ENTRY(error_exit)
UNWIND_HINT_REGS
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
- testl %ebx, %ebx
- jnz retint_kernel
+ testb $3, CS(%rsp)
+ jz retint_kernel
jmp retint_user
END(error_exit)
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq %r8 /* pt_regs->r8 */
+ pushq $0 /* pt_regs->r8 = 0 */
xorl %r8d, %r8d /* nospec r8 */
- pushq %r9 /* pt_regs->r9 */
+ pushq $0 /* pt_regs->r9 = 0 */
xorl %r9d, %r9d /* nospec r9 */
- pushq %r10 /* pt_regs->r10 */
+ pushq $0 /* pt_regs->r10 = 0 */
xorl %r10d, %r10d /* nospec r10 */
- pushq %r11 /* pt_regs->r11 */
+ pushq $0 /* pt_regs->r11 = 0 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
pushq %rcx /* pt_regs->cx */
xorl %ecx, %ecx /* nospec cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq $0 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r8 */
xorl %r8d, %r8d /* nospec r8 */
- pushq $0 /* pt_regs->r9 = 0 */
+ pushq %r9 /* pt_regs->r9 */
xorl %r9d, %r9d /* nospec r9 */
- pushq $0 /* pt_regs->r10 = 0 */
+ pushq %r10 /* pt_regs->r10*/
xorl %r10d, %r10d /* nospec r10 */
- pushq $0 /* pt_regs->r11 = 0 */
+ pushq %r11 /* pt_regs->r11 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
CPPFLAGS_vdso.lds += -P -C
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
- -Wl,--no-undefined \
- -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
- $(DISABLE_LTO)
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+ -z max-page-size=4096 -z common-page-size=4096
$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
$(call if_changed,vdso)
hostprogs-y += vdso2c
quiet_cmd_vdso2c = VDSO2C $@
-define cmd_vdso2c
- $(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
+ cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
$(call if_changed,vdso2c)
#
CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
- -Wl,-soname=linux-vdso.so.1 \
- -Wl,-z,max-page-size=4096 \
- -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+ -z max-page-size=4096 -z common-page-size=4096
# x32-rebranded versions
vobjx32s-y := $(vobjs-y:.o=-x32.o)
$(call if_changed,vdso)
CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
targets += vdso32/vdso32.lds
targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
# The DSO images are built using a special linker script.
#
quiet_cmd_vdso = VDSO $@
- cmd_vdso = $(CC) -nostdlib -o $@ \
+ cmd_vdso = $(LD) -nostdlib -o $@ \
$(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
- -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+ -T $(filter %.lds,$^) $(filter %.o,$^) && \
sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \
- $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
+VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
+ $(call ld-option, --build-id) -Bsymbolic
GCOV_PROFILE := n
#
/*
* Handle seccomp. regs->ip must be the original value.
- * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
+ * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst.
*
* We could optimize the seccomp disabled case, but performance
* here doesn't matter.
{
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
struct perf_event *event = pcpu->event;
- struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event *hwc;
struct perf_sample_data data;
struct perf_raw_record raw;
struct pt_regs regs;
return 0;
}
+ if (WARN_ON_ONCE(!event))
+ goto fail;
+
+ hwc = &event->hw;
msr = hwc->config_base;
buf = ibs_data.regs;
rdmsrl(msr, *buf);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_disable(event);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
-
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
x86_perf_event_update(event);
}
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
{
+ struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
- u64 ctrl_val, bits, mask;
+ u64 ctrl_val, mask, bits = 0;
/*
- * Enable IRQ generation (0x8),
+ * Enable IRQ generation (0x8), if not PEBS,
* and enable ring-3 counting (0x2) and ring-0 counting (0x1)
* if requested:
*/
- bits = 0x8ULL;
+ if (!event->attr.precise_ip)
+ bits |= 0x8;
if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
bits |= 0x2;
if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
if (unlikely(event_is_checkpointed(event)))
cpuc->intel_cp_status |= (1ull << hwc->idx);
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_enable(event);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_enable_fixed(hwc);
+ intel_pmu_enable_fixed(event);
return;
}
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_enable(event);
-
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
* counters from the GLOBAL_STATUS mask and we always process PEBS
* events via drain_pebs().
*/
- status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ status &= ~cpuc->pebs_enabled;
+ else
+ status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
/*
* PEBS overflow sets bit 62 in the global status register
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
+
+ if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+ event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
}
if (needs_branch_stack(event)) {
intel_pmu_lbr_init_skl();
x86_pmu.event_constraints = intel_slm_event_constraints;
- x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
x86_pmu.extra_regs = intel_glm_extra_regs;
/*
* It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
x86_pmu.cpu_events = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
ds->bts_buffer_base = (unsigned long) cea;
ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
ds->bts_index = ds->bts_buffer_base;
- max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
- ds->bts_absolute_maximum = ds->bts_buffer_base + max;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+ max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+ ds->bts_absolute_maximum = ds->bts_buffer_base +
+ max * BTS_RECORD_SIZE;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+ (max / 16) * BTS_RECORD_SIZE;
return 0;
}
EVENT_CONSTRAINT_END
};
-struct event_constraint intel_glp_pebs_event_constraints[] = {
- /* Allow all events as PEBS with no flags */
- INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
- EVENT_CONSTRAINT_END
-};
-
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
}
}
+ /*
+ * Extended PEBS support
+ * Makes the PEBS code search the normal constraints.
+ */
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ return NULL;
+
return &emptyconstraint;
}
{
struct debug_store *ds = cpuc->ds;
u64 threshold;
+ int reserved;
+
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+ else
+ reserved = x86_pmu.max_pebs_events;
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+ reserved * x86_pmu.pebs_record_size;
} else {
threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
}
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
*/
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
- ds->pebs_event_reset[hwc->idx] =
+ unsigned int idx = hwc->idx;
+
+ if (idx >= INTEL_PMC_IDX_FIXED)
+ idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+ ds->pebs_event_reset[idx] =
(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
} else {
ds->pebs_event_reset[hwc->idx] = 0;
data->data_src.val = val;
}
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happend between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
/*
* We use the interrupt regs as a base because the PEBS record does not
* contain a full regs set, specifically it seems to lack segment
* descriptors, which get used by things like user_mode().
*
* In the simple case fix up only the IP for PERF_SAMPLE_IP.
- *
- * We must however always use BP,SP from iregs for the unwinder to stay
- * sane; the record BP,SP can point into thin air when the record is
- * from a previous PMI context or an (I)RET happend between the record
- * and PMI.
*/
*regs = *iregs;
regs->si = pebs->si;
regs->di = pebs->di;
- /*
- * Per the above; only set BP,SP if we don't need callchains.
- *
- * XXX: does this make sense?
- */
- if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
- regs->bp = pebs->bp;
- regs->sp = pebs->sp;
- }
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
#ifndef CONFIG_X86_32
regs->r8 = pebs->r8;
struct debug_store *ds = cpuc->ds;
struct perf_event *event;
void *base, *at, *top;
- short counts[MAX_PEBS_EVENTS] = {};
- short error[MAX_PEBS_EVENTS] = {};
- int bit, i;
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ int bit, i, size;
+ u64 mask;
if (!x86_pmu.pebs_active)
return;
ds->pebs_index = ds->pebs_buffer_base;
+ mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+ size = x86_pmu.max_pebs_events;
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+ mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+ }
+
if (unlikely(base >= top)) {
/*
* The drain_pebs() could be called twice in a short period
* update the event->count for this case.
*/
for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- x86_pmu.max_pebs_events) {
+ size) {
event = cpuc->events[bit];
if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
intel_pmu_save_and_restart_reload(event, 0);
u64 pebs_status;
pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+ pebs_status &= mask;
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
for_each_set_bit(bit, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ size)
counts[bit]++;
continue;
counts[bit]++;
}
- for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+ for (bit = 0; bit < size; bit++) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
void intel_pmu_lbr_reset(void)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
if (!x86_pmu.lbr_nr)
return;
intel_pmu_lbr_reset_32();
else
intel_pmu_lbr_reset_64();
+
+ cpuc->last_task_ctx = NULL;
+ cpuc->last_log_id = 0;
}
/*
static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
unsigned lbr_idx, mask;
u64 tos;
return;
}
- mask = x86_pmu.lbr_nr - 1;
tos = task_ctx->tos;
- for (i = 0; i < tos; i++) {
+ /*
+ * Does not restore the LBR registers, if
+ * - No one else touched them, and
+ * - Did not enter C6
+ */
+ if ((task_ctx == cpuc->last_task_ctx) &&
+ (task_ctx->log_id == cpuc->last_log_id) &&
+ rdlbr_from(tos)) {
+ task_ctx->lbr_stack_state = LBR_NONE;
+ return;
+ }
+
+ mask = x86_pmu.lbr_nr - 1;
+ for (i = 0; i < task_ctx->valid_lbrs; i++) {
lbr_idx = (tos - i) & mask;
wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
wrlbr_to (lbr_idx, task_ctx->lbr_to[i]);
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+
+ for (; i < x86_pmu.lbr_nr; i++) {
+ lbr_idx = (tos - i) & mask;
+ wrlbr_from(lbr_idx, 0);
+ wrlbr_to(lbr_idx, 0);
+ if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+ wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+ }
+
wrmsrl(x86_pmu.lbr_tos, tos);
task_ctx->lbr_stack_state = LBR_NONE;
}
static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
unsigned lbr_idx, mask;
- u64 tos;
+ u64 tos, from;
int i;
if (task_ctx->lbr_callstack_users == 0) {
mask = x86_pmu.lbr_nr - 1;
tos = intel_pmu_lbr_tos();
- for (i = 0; i < tos; i++) {
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
lbr_idx = (tos - i) & mask;
- task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+ from = rdlbr_from(lbr_idx);
+ if (!from)
+ break;
+ task_ctx->lbr_from[i] = from;
task_ctx->lbr_to[i] = rdlbr_to(lbr_idx);
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+ task_ctx->valid_lbrs = i;
task_ctx->tos = tos;
task_ctx->lbr_stack_state = LBR_VALID;
+
+ cpuc->last_task_ctx = task_ctx;
+ cpuc->last_log_id = ++task_ctx->log_id;
}
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
*/
static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
{
- bool need_info = false;
+ bool need_info = false, call_stack = false;
unsigned long mask = x86_pmu.lbr_nr - 1;
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
if (cpuc->lbr_sel) {
need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
if (cpuc->lbr_sel->config & LBR_CALL_STACK)
- num = tos;
+ call_stack = true;
}
for (i = 0; i < num; i++) {
from = rdlbr_from(lbr_idx);
to = rdlbr_to(lbr_idx);
+ /*
+ * Read LBR call stack entries
+ * until invalid entry (0s) is detected.
+ */
+ if (call_stack && !from)
+ break;
+
if (lbr_format == LBR_FORMAT_INFO && need_info) {
u64 info;
#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff)
#define UNCORE_PCI_DEV_IDX(data) (data & 0xff)
#define UNCORE_EXTRA_PCI_DEV 0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX 3
+#define UNCORE_EXTRA_PCI_DEV_MAX 4
#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
enum {
SNBEP_PCI_QPI_PORT0_FILTER,
SNBEP_PCI_QPI_PORT1_FILTER,
+ BDX_PCI_QPI_PORT2_FILTER,
HSWEP_PCI_PCU_3,
};
},
{ /* QPI Port 0 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
},
{ /* QPI Port 1 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* QPI Port 2 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ BDX_PCI_QPI_PORT2_FILTER),
},
{ /* PCU.3 (for Capability registers) */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
unsigned core_id; /* per-core: core id */
};
+struct x86_perf_task_context;
#define MAX_LBR_ENTRIES 32
enum {
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
u64 br_sel;
+ struct x86_perf_task_context *last_task_ctx;
+ int last_log_id;
/*
* Intel host/guest exclude bits
u64 lbr_to[MAX_LBR_ENTRIES];
u64 lbr_info[MAX_LBR_ENTRIES];
int tos;
+ int valid_lbrs;
int lbr_callstack_users;
int lbr_stack_state;
+ int log_id;
};
#define x86_add_quirk(func_) \
#define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */
#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */
#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
#include <asm/mshyperv.h>
#include <asm/apic.h>
+#include <asm/trace/hyperv.h>
+
static struct apic orig_apic;
static u64 hv_apic_icr_read(void)
int nr_bank = 0;
int ret = 1;
+ if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ return false;
+
local_irq_save(flags);
arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
}
+ if (nr_bank < 0)
+ goto ipi_mask_ex_done;
if (!nr_bank)
ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
static bool __send_ipi_mask(const struct cpumask *mask, int vector)
{
int cur_cpu, vcpu;
- struct ipi_arg_non_ex **arg;
- struct ipi_arg_non_ex *ipi_arg;
+ struct ipi_arg_non_ex ipi_arg;
int ret = 1;
- unsigned long flags;
+
+ trace_hyperv_send_ipi_mask(mask, vector);
if (cpumask_empty(mask))
return true;
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return false;
- if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
- return __send_ipi_mask_ex(mask, vector);
-
- local_irq_save(flags);
- arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
-
- ipi_arg = *arg;
- if (unlikely(!ipi_arg))
- goto ipi_mask_done;
-
- ipi_arg->vector = vector;
- ipi_arg->reserved = 0;
- ipi_arg->cpu_mask = 0;
+ /*
+ * From the supplied CPU set we need to figure out if we can get away
+ * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the
+ * highest VP number in the set is < 64. As VP numbers are usually in
+ * ascending order and match Linux CPU ids, here is an optimization:
+ * we check the VP number for the highest bit in the supplied set first
+ * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is
+ * a must. We will also check all VP numbers when walking the supplied
+ * CPU set to remain correct in all cases.
+ */
+ if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64)
+ goto do_ex_hypercall;
+
+ ipi_arg.vector = vector;
+ ipi_arg.cpu_mask = 0;
for_each_cpu(cur_cpu, mask) {
vcpu = hv_cpu_number_to_vp_number(cur_cpu);
+ if (vcpu == VP_INVAL)
+ return false;
+
/*
* This particular version of the IPI hypercall can
* only target upto 64 CPUs.
*/
if (vcpu >= 64)
- goto ipi_mask_done;
+ goto do_ex_hypercall;
- __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+ __set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
}
- ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
-
-ipi_mask_done:
- local_irq_restore(flags);
+ ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
+ ipi_arg.cpu_mask);
return ((ret == 0) ? true : false);
+
+do_ex_hypercall:
+ return __send_ipi_mask_ex(mask, vector);
}
static bool __send_ipi_one(int cpu, int vector)
void __init hv_apic_init(void)
{
if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
- if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
- pr_info("Hyper-V: Using ext hypercalls for IPI\n");
- else
- pr_info("Hyper-V: Using IPI hypercalls\n");
+ pr_info("Hyper-V: Using IPI hypercalls\n");
/*
* Set the IPI entry points.
*/
{
u64 guest_id, required_msrs;
union hv_x64_msr_hypercall_contents hypercall_msr;
- int cpuhp;
+ int cpuhp, i;
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
return;
if (!hv_vp_index)
return;
+ for (i = 0; i < num_possible_cpus(); i++)
+ hv_vp_index[i] = VP_INVAL;
+
hv_vp_assist_page = kcalloc(num_possible_cpus(),
sizeof(*hv_vp_assist_page), GFP_KERNEL);
if (!hv_vp_assist_page) {
/* Each gva in gva_list encodes up to 4096 pages to flush */
#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+ const struct flush_tlb_info *info);
/*
* Fills in gva_list starting from offset. Returns the number of items added.
if (cpumask_equal(cpus, cpu_present_mask)) {
flush->flags |= HV_FLUSH_ALL_PROCESSORS;
} else {
+ /*
+ * From the supplied CPU set we need to figure out if we can get
+ * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
+ * hypercalls. This is possible when the highest VP number in
+ * the set is < 64. As VP numbers are usually in ascending order
+ * and match Linux CPU ids, here is an optimization: we check
+ * the VP number for the highest bit in the supplied set first
+ * so we can quickly find out if using *_EX hypercalls is a
+ * must. We will also check all VP numbers when walking the
+ * supplied CPU set to remain correct in all cases.
+ */
+ if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
+ goto do_ex_hypercall;
+
for_each_cpu(cpu, cpus) {
vcpu = hv_cpu_number_to_vp_number(cpu);
- if (vcpu >= 64)
+ if (vcpu == VP_INVAL) {
+ local_irq_restore(flags);
goto do_native;
+ }
+
+ if (vcpu >= 64)
+ goto do_ex_hypercall;
__set_bit(vcpu, (unsigned long *)
&flush->processor_mask);
status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
gva_n, 0, flush, NULL);
}
+ goto check_status;
+
+do_ex_hypercall:
+ status = hyperv_flush_tlb_others_ex(cpus, info);
+check_status:
local_irq_restore(flags);
if (!(status & HV_HYPERCALL_RESULT_MASK))
native_flush_tlb_others(cpus, info);
}
-static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
- const struct flush_tlb_info *info)
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+ const struct flush_tlb_info *info)
{
int nr_bank = 0, max_gvas, gva_n;
struct hv_tlb_flush_ex **flush_pcpu;
struct hv_tlb_flush_ex *flush;
- u64 status = U64_MAX;
- unsigned long flags;
+ u64 status;
- trace_hyperv_mmu_flush_tlb_others(cpus, info);
-
- if (!hv_hypercall_pg)
- goto do_native;
-
- if (cpumask_empty(cpus))
- return;
-
- local_irq_save(flags);
+ if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ return U64_MAX;
flush_pcpu = (struct hv_tlb_flush_ex **)
this_cpu_ptr(hyperv_pcpu_input_arg);
flush = *flush_pcpu;
- if (unlikely(!flush)) {
- local_irq_restore(flags);
- goto do_native;
- }
-
if (info->mm) {
/*
* AddressSpace argument must match the CR3 with PCID bits
flush->hv_vp_set.valid_bank_mask = 0;
- if (!cpumask_equal(cpus, cpu_present_mask)) {
- flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
- nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
- }
-
- if (!nr_bank) {
- flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
- flush->flags |= HV_FLUSH_ALL_PROCESSORS;
- }
+ flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
+ if (nr_bank < 0)
+ return U64_MAX;
/*
* We can flush not more than max_gvas with one hypercall. Flush the
gva_n, nr_bank, flush, NULL);
}
- local_irq_restore(flags);
-
- if (!(status & HV_HYPERCALL_RESULT_MASK))
- return;
-do_native:
- native_flush_tlb_others(cpus, info);
+ return status;
}
void hyperv_setup_mmu_ops(void)
if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
return;
- if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
- pr_info("Using hypercall for remote TLB flush\n");
- pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
- } else {
- pr_info("Using ext hypercall for remote TLB flush\n");
- pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
- }
+ pr_info("Using hypercall for remote TLB flush\n");
+ pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
}
#ifndef _ASM_X86_MACH_DEFAULT_APM_H
#define _ASM_X86_MACH_DEFAULT_APM_H
-#include <asm/nospec-branch.h>
-
#ifdef APM_ZERO_SEGS
# define APM_DO_ZERO_SEGS \
"pushl %%ds\n\t" \
* N.B. We do NOT need a cld after the BIOS call
* because we always save and restore the flags.
*/
- firmware_restrict_branch_speculation_start();
__asm__ __volatile__(APM_DO_ZERO_SEGS
"pushl %%edi\n\t"
"pushl %%ebp\n\t"
"=S" (*esi)
: "a" (func), "b" (ebx_in), "c" (ecx_in)
: "memory", "cc");
- firmware_restrict_branch_speculation_end();
}
static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
* N.B. We do NOT need a cld after the BIOS call
* because we always save and restore the flags.
*/
- firmware_restrict_branch_speculation_start();
__asm__ __volatile__(APM_DO_ZERO_SEGS
"pushl %%edi\n\t"
"pushl %%ebp\n\t"
"=S" (si)
: "a" (func), "b" (ebx_in), "c" (ecx_in)
: "memory", "cc");
- firmware_restrict_branch_speculation_end();
return error;
}
#define _ASM_SI __ASM_REG(si)
#define _ASM_DI __ASM_REG(di)
+#ifndef __x86_64__
+/* 32 bit */
+
+#define _ASM_ARG1 _ASM_AX
+#define _ASM_ARG2 _ASM_DX
+#define _ASM_ARG3 _ASM_CX
+
+#define _ASM_ARG1L eax
+#define _ASM_ARG2L edx
+#define _ASM_ARG3L ecx
+
+#define _ASM_ARG1W ax
+#define _ASM_ARG2W dx
+#define _ASM_ARG3W cx
+
+#define _ASM_ARG1B al
+#define _ASM_ARG2B dl
+#define _ASM_ARG3B cl
+
+#else
+/* 64 bit */
+
+#define _ASM_ARG1 _ASM_DI
+#define _ASM_ARG2 _ASM_SI
+#define _ASM_ARG3 _ASM_DX
+#define _ASM_ARG4 _ASM_CX
+#define _ASM_ARG5 r8
+#define _ASM_ARG6 r9
+
+#define _ASM_ARG1Q rdi
+#define _ASM_ARG2Q rsi
+#define _ASM_ARG3Q rdx
+#define _ASM_ARG4Q rcx
+#define _ASM_ARG5Q r8
+#define _ASM_ARG6Q r9
+
+#define _ASM_ARG1L edi
+#define _ASM_ARG2L esi
+#define _ASM_ARG3L edx
+#define _ASM_ARG4L ecx
+#define _ASM_ARG5L r8d
+#define _ASM_ARG6L r9d
+
+#define _ASM_ARG1W di
+#define _ASM_ARG2W si
+#define _ASM_ARG3W dx
+#define _ASM_ARG4W cx
+#define _ASM_ARG5W r8w
+#define _ASM_ARG6W r9w
+
+#define _ASM_ARG1B dil
+#define _ASM_ARG2B sil
+#define _ASM_ARG3B dl
+#define _ASM_ARG4B cl
+#define _ASM_ARG5B r8b
+#define _ASM_ARG6B r9b
+
+#endif
+
/*
* Macros to generate condition code outputs from inline assembly,
* The output operand must be type "bool".
* true if the result is zero, or false for all
* other cases.
*/
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
*
* Atomically increments @v by 1.
*/
+#define arch_atomic_inc arch_atomic_inc
static __always_inline void arch_atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
*
* Atomically decrements @v by 1.
*/
+#define arch_atomic_dec arch_atomic_dec
static __always_inline void arch_atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
* returns true if the result is 0, or false for all other
* cases.
*/
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
* and returns true if the result is zero, or false for all
* other cases.
*/
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
+#define arch_atomic_add_negative arch_atomic_add_negative
static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
return arch_atomic_add_return(-i, v);
}
-#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v))
-#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v))
-
static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
return xadd(&v->counter, i);
static inline int arch_atomic_xchg(atomic_t *v, int new)
{
- return xchg(&v->counter, new);
+ return arch_xchg(&v->counter, new);
}
static inline void arch_atomic_and(int i, atomic_t *v)
return val;
}
-/**
- * __arch_atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
- */
-static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c = arch_atomic_read(v);
-
- do {
- if (unlikely(c == u))
- break;
- } while (!arch_atomic_try_cmpxchg(v, &c, c + a));
-
- return c;
-}
-
#ifdef CONFIG_X86_32
# include <asm/atomic64_32.h>
#else
"S" (v) : "memory", "ecx");
return a;
}
+#define arch_atomic64_inc_return arch_atomic64_inc_return
static inline long long arch_atomic64_dec_return(atomic64_t *v)
{
"S" (v) : "memory", "ecx");
return a;
}
+#define arch_atomic64_dec_return arch_atomic64_dec_return
/**
* arch_atomic64_add - add integer to atomic64 variable
return i;
}
-/**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
-{
- return arch_atomic64_sub_return(i, v) == 0;
-}
-
/**
* arch_atomic64_inc - increment atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically increments @v by 1.
*/
+#define arch_atomic64_inc arch_atomic64_inc
static inline void arch_atomic64_inc(atomic64_t *v)
{
__alternative_atomic64(inc, inc_return, /* no output */,
*
* Atomically decrements @v by 1.
*/
+#define arch_atomic64_dec arch_atomic64_dec
static inline void arch_atomic64_dec(atomic64_t *v)
{
__alternative_atomic64(dec, dec_return, /* no output */,
"S" (v) : "memory", "eax", "ecx", "edx");
}
-/**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int arch_atomic64_dec_and_test(atomic64_t *v)
-{
- return arch_atomic64_dec_return(v) == 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_inc_and_test(atomic64_t *v)
-{
- return arch_atomic64_inc_return(v) == 0;
-}
-
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
-{
- return arch_atomic64_add_return(i, v) < 0;
-}
-
/**
* arch_atomic64_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
return (int)a;
}
-
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
{
int r;
return r;
}
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
{
long long r;
* true if the result is zero, or false for all
* other cases.
*/
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
*
* Atomically increments @v by 1.
*/
+#define arch_atomic64_inc arch_atomic64_inc
static __always_inline void arch_atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
*
* Atomically decrements @v by 1.
*/
+#define arch_atomic64_dec arch_atomic64_dec
static __always_inline void arch_atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
* returns true if the result is 0, or false for all other
* cases.
*/
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
* and returns true if the result is zero, or false for all
* other cases.
*/
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
+#define arch_atomic64_add_negative arch_atomic64_add_negative
static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
return xadd(&v->counter, -i);
}
-#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v)))
-#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v)))
-
static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
{
return arch_cmpxchg(&v->counter, old, new);
static inline long arch_atomic64_xchg(atomic64_t *v, long new)
{
- return xchg(&v->counter, new);
-}
-
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- s64 c = arch_atomic64_read(v);
- do {
- if (unlikely(c == u))
- return false;
- } while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
- return true;
-}
-
-#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
-
-/*
- * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
-{
- s64 dec, c = arch_atomic64_read(v);
- do {
- dec = c - 1;
- if (unlikely(dec < 0))
- break;
- } while (!arch_atomic64_try_cmpxchg(v, &c, dec));
- return dec;
+ return arch_xchg(&v->counter, new);
}
static inline void arch_atomic64_and(long i, atomic64_t *v)
{
unsigned long mask;
- asm ("cmp %1,%2; sbb %0,%0;"
+ asm volatile ("cmp %1,%2; sbb %0,%0;"
:"=r" (mask)
:"g"(size),"r" (index)
:"cc");
* use "asm volatile" and "memory" clobbers to prevent gcc from moving
* information around.
*/
-#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "")
+#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "")
/*
* Atomic compare and exchange. Compare OLD with MEM, if identical,
#define arch_cmpxchg64(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
- cmpxchg((ptr), (o), (n)); \
+ arch_cmpxchg((ptr), (o), (n)); \
})
#define arch_cmpxchg64_local(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
- cmpxchg_local((ptr), (o), (n)); \
+ arch_cmpxchg_local((ptr), (o), (n)); \
})
#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_IBRS_ENHANCED ( 7*32+29) /* Enhanced IBRS */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */
#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */
-
+#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
return HBP_NUM;
}
+struct perf_event_attr;
struct perf_event;
struct pmu;
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */
+/* Useful macros */
+#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data) \
+{ \
+ .vendor = X86_VENDOR_INTEL, \
+ .family = _family, \
+ .model = _model, \
+ .feature = X86_FEATURE_ANY, \
+ .driver_data = (kernel_ulong_t)&_driver_data \
+}
+
+#define INTEL_CPU_FAM6(_model, _driver_data) \
+ INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data)
+
#endif /* _ASM_X86_INTEL_FAMILY_H */
extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
-/**
- * struct intel_mid_ops - Interface between intel-mid & sub archs
- * @arch_setup: arch_setup function to re-initialize platform
- * structures (x86_init, x86_platform_init)
- *
- * This structure can be extended if any new interface is required
- * between intel-mid & its sub arch files.
- */
-struct intel_mid_ops {
- void (*arch_setup)(void);
-};
-
-/* Helper API's for INTEL_MID_OPS_INIT */
-#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid) \
- [cpuid] = get_##cpuname##_ops
-
-/* Maximum number of CPU ops */
-#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *))
-
-/*
- * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
- * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
- */
-#define INTEL_MID_OPS_INIT { \
- DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \
- DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \
- DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \
-};
-
#ifdef CONFIG_X86_INTEL_MID
static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
extern enum intel_mid_timer_options intel_mid_timer_options;
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define FSB_FREQ_83SKU 83200
-#define FSB_FREQ_100SKU 99840
-#define FSB_FREQ_133SKU 133000
-
-#define FSB_FREQ_167SKU 167000
-#define FSB_FREQ_200SKU 200000
-#define FSB_FREQ_267SKU 267000
-#define FSB_FREQ_333SKU 333000
-#define FSB_FREQ_400SKU 400000
-
/* Bus Select SoC Fuse value */
#define BSEL_SOC_FUSE_MASK 0x7
/* FSB 133MHz */
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
+#define MAX_FIXED_PEBS_EVENTS 3
/*
* A debug store configuration.
u64 pebs_index;
u64 pebs_absolute_maximum;
u64 pebs_interrupt_threshold;
- u64 pebs_event_reset[MAX_PEBS_EVENTS];
+ u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS];
} __aligned(PAGE_SIZE);
DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
* Interrupt control:
*/
-static inline unsigned long native_save_fl(void)
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
+extern inline unsigned long native_save_fl(void)
{
unsigned long flags;
* boostable = true: This instruction has been boosted: we have
* added a relative jump after the instruction copy in insn,
* so no single-step and fixup are needed (unless there's
- * a post_handler or break_handler).
+ * a post_handler).
*/
bool boostable;
bool if_modifier;
unsigned long kprobe_status;
unsigned long kprobe_old_flags;
unsigned long kprobe_saved_flags;
- unsigned long *jprobe_saved_sp;
- struct pt_regs jprobe_saved_regs;
- kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
struct prev_kprobe prev_kprobe;
};
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_KVM_GUEST_H
-#define _ASM_X86_KVM_GUEST_H
-
-int kvm_setup_vsyscall_timeinfo(void);
-
-#endif /* _ASM_X86_KVM_GUEST_H */
#include <uapi/asm/kvm_para.h>
extern void kvmclock_init(void);
-extern int kvm_register_clock(char *txt);
#ifdef CONFIG_KVM_GUEST
bool kvm_check_and_clear_guest_paused(void);
static inline void *ldt_slot_va(int slot)
{
-#ifdef CONFIG_X86_64
return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
-#else
- BUG();
- return (void *)fix_to_virt(FIX_HOLE);
-#endif
}
/*
#include <asm/hyperv-tlfs.h>
#include <asm/nospec-branch.h>
+#define VP_INVAL U32_MAX
+
struct ms_hyperv_info {
u32 features;
u32 misc_features;
extern struct ms_hyperv_info ms_hyperv;
-
/*
* Generate the guest ID.
*/
return hv_status;
}
+/* Fast hypercall with 16 bytes of input */
+static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+ u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+#ifdef CONFIG_X86_64
+ {
+ __asm__ __volatile__("mov %4, %%r8\n"
+ CALL_NOSPEC
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+ "+c" (control), "+d" (input1)
+ : "r" (input2),
+ THUNK_TARGET(hv_hypercall_pg)
+ : "cc", "r8", "r9", "r10", "r11");
+ }
+#else
+ {
+ u32 input1_hi = upper_32_bits(input1);
+ u32 input1_lo = lower_32_bits(input1);
+ u32 input2_hi = upper_32_bits(input2);
+ u32 input2_lo = lower_32_bits(input2);
+
+ __asm__ __volatile__ (CALL_NOSPEC
+ : "=A"(hv_status),
+ "+c"(input1_lo), ASM_CALL_CONSTRAINT
+ : "A" (control), "b" (input1_hi),
+ "D"(input2_hi), "S"(input2_lo),
+ THUNK_TARGET(hv_hypercall_pg)
+ : "cc");
+ }
+#endif
+ return hv_status;
+}
+
/*
* Rep hypercalls. Callers of this functions are supposed to ensure that
* rep_count and varhead_size comply with Hyper-V hypercall definition.
*/
for_each_cpu(cpu, cpus) {
vcpu = hv_cpu_number_to_vp_number(cpu);
+ if (vcpu == VP_INVAL)
+ return -1;
vcpu_bank = vcpu / 64;
vcpu_offset = vcpu % 64;
__set_bit(vcpu_offset, (unsigned long *)
SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
SPECTRE_V2_RETPOLINE_GENERIC,
SPECTRE_V2_RETPOLINE_AMD,
- SPECTRE_V2_IBRS,
+ SPECTRE_V2_IBRS_ENHANCED,
};
/* The Speculative Store Bypass disable variants */
unsigned sp_reg:4;
unsigned bp_reg:4;
unsigned type:2;
+ unsigned end:1;
} __packed;
/*
s16 sp_offset;
u8 sp_reg;
u8 type;
+ u8 end;
};
#endif /* __ASSEMBLY__ */
bool __ret; \
typeof(pcp1) __o1 = (o1), __n1 = (n1); \
typeof(pcp2) __o2 = (o2), __n2 = (n2); \
- asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \
- : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
- : "b" (__n1), "c" (__n2), "a" (__o1)); \
+ asm volatile("cmpxchg8b "__percpu_arg(1) \
+ CC_SET(z) \
+ : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \
+ : "b" (__n1), "c" (__n2)); \
__ret; \
})
static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
{
+ if (!pgtable_l5_enabled())
+ return;
+
BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
free_page((unsigned long)p4d);
}
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
+#endif
*pmdp = pmd;
}
#ifdef CONFIG_SMP
static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
+#endif
return __pmd(xchg((pmdval_t *)xp, 0));
}
#else
#ifdef CONFIG_SMP
static inline pud_t native_pudp_get_and_clear(pud_t *xp)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
+#endif
return __pud(xchg((pudval_t *)xp, 0));
}
#else
#define PTRS_PER_PTE 1024
+/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */
+#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
+
#endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
+#endif
set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
}
{
union split_pud res, *orig = (union split_pud *)pudp;
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
+#endif
+
/* xchg acts as a barrier before setting of the high bits */
res.pud_low = xchg(&orig->pud_low, 0);
res.pud_high = orig->pud_high;
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD (pv_info.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \
+ (pv_info.shared_kernel_pmd)))
#else
-#define SHARED_KERNEL_PMD 1
+#define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI))
#endif
/*
#define PTRS_PER_PTE 512
#define MAX_POSSIBLE_PHYSMEM_BITS 36
+#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
#endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
void ptdump_walk_pgd_level_checkwx(void);
+void ptdump_walk_user_pgd_level_checkwx(void);
#ifdef CONFIG_DEBUG_WX
-#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx()
#else
-#define debug_checkwx() do { } while (0)
+#define debug_checkwx() do { } while (0)
+#define debug_checkwx_user() do { } while (0)
#endif
/*
pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return pgd;
+ return __pti_set_user_pgtbl(pgdp, pgd);
+}
+#else /* CONFIG_PAGE_TABLE_ISOLATION */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
#endif /* __ASSEMBLY__ */
+
#ifdef CONFIG_X86_32
# include <asm/pgtable_32.h>
#else
#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
/* to find an entry in a page-table-directory. */
-static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
if (!pgtable_l5_enabled())
return (p4d_t *)pgd;
}
}
#endif
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
+}
+
+static inline int pgd_large(pgd_t pgd) { return 0; }
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
+ * the user one is in the last 4k. To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr |= BIT(bit);
+ return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr &= ~BIT(bit);
+ return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+ return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+ return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+ return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+ return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
void paging_init(void);
void sync_initial_page_table(void);
-static inline int pgd_large(pgd_t pgd) { return 0; }
-
/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \
& PMD_MASK)
-#define PKMAP_BASE \
+#define LDT_BASE_ADDR \
((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
+#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE)
+
+#define PKMAP_BASE \
+ ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
+
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE)
#else
-# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
+# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE)
#endif
#define MODULES_VADDR VMALLOC_START
#endif
}
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
- * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
- * the user one is in the last 4k. To switch between them, you
- * just need to flip the 12th bit in their addresses.
- */
-#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
-
-/*
- * This generates better code than the inline assembly in
- * __set_bit().
- */
-static inline void *ptr_set_bit(void *ptr, int bit)
-{
- unsigned long __ptr = (unsigned long)ptr;
-
- __ptr |= BIT(bit);
- return (void *)__ptr;
-}
-static inline void *ptr_clear_bit(void *ptr, int bit)
-{
- unsigned long __ptr = (unsigned long)ptr;
-
- __ptr &= ~BIT(bit);
- return (void *)__ptr;
-}
-
-static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
-{
- return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
-{
- return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
-{
- return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
-{
- return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
-
-/*
- * Page table pages are page-aligned. The lower half of the top
- * level is used for userspace and the top half for the kernel.
- *
- * Returns true for parts of the PGD that map userspace and
- * false for the parts that map the kernel.
- */
-static inline bool pgdp_maps_userspace(void *__ptr)
-{
- unsigned long ptr = (unsigned long)__ptr;
-
- return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
-}
-
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
-
-/*
- * Take a PGD location (pgdp) and a pgd value that needs to be set there.
- * Populates the user and returns the resulting PGD that must be set in
- * the kernel copy of the page tables.
- */
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
- if (!static_cpu_has(X86_FEATURE_PTI))
- return pgd;
- return __pti_set_user_pgd(pgdp, pgd);
-}
-#else
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
- return pgd;
-}
-#endif
-
-static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
+static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
pgd_t pgd;
}
pgd = native_make_pgd(native_p4d_val(p4d));
- pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+ pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
*p4dp = native_make_p4d(native_pgd_val(pgd));
}
-static __always_inline void native_p4d_clear(p4d_t *p4d)
+static inline void native_p4d_clear(p4d_t *p4d)
{
native_set_p4d(p4d, native_make_p4d(0));
}
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- *pgdp = pti_set_user_pgd(pgdp, pgd);
+ *pgdp = pti_set_user_pgtbl(pgdp, pgd);
}
static inline void native_pgd_clear(pgd_t *pgd)
/*
* Level 4 access.
*/
-static inline int pgd_large(pgd_t pgd) { return 0; }
#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
/* PUD - Level3 access */
#define LDT_PGD_ENTRY_L5 -112UL
#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
+#define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE)
#define __VMALLOC_BASE_L4 0xffffc90000000000UL
#define __VMALLOC_BASE_L5 0xffa0000000000000UL
#define EARLY_DYNAMIC_PAGE_TABLES 64
+#define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t))
+
#endif /* _ASM_X86_PGTABLE_64_DEFS_H */
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
+#define _PAGE_SOFTW3 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
typedef struct { pgdval_t pgd; } pgd_t;
+#ifdef CONFIG_X86_PAE
+
+/*
+ * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't
+ * use it here.
+ */
+
+#define PGD_PAE_PAGE_MASK ((signed long)PAGE_MASK)
+#define PGD_PAE_PHYS_MASK (((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK)
+
+/*
+ * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries.
+ * All other bits are Reserved MBZ
+ */
+#define PGD_ALLOWED_BITS (PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \
+ _PAGE_PWT | _PAGE_PCD | \
+ _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3)
+
+#else
+/* No need to mask any bits for !PAE */
+#define PGD_ALLOWED_BITS (~0ULL)
+#endif
+
static inline pgd_t native_make_pgd(pgdval_t val)
{
- return (pgd_t) { val };
+ return (pgd_t) { val & PGD_ALLOWED_BITS };
}
static inline pgdval_t native_pgd_val(pgd_t pgd)
{
- return pgd.pgd;
+ return pgd.pgd & PGD_ALLOWED_BITS;
}
static inline pgdval_t pgd_flags(pgd_t pgd)
#define CR3_PCID_MASK 0xFFFull
#define CR3_NOFLUSH BIT_ULL(63)
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-# define X86_CR3_PTI_PCID_USER_BIT 11
-#endif
-
#else
/*
* CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
#define CR3_NOFLUSH 0
#endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT 11
+#endif
+
#endif /* _ASM_X86_PROCESSOR_FLAGS_H */
extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+extern void free_kernel_image_pages(void *begin, void *end);
void default_idle(void);
#ifdef CONFIG_XEN
#ifdef CONFIG_PAGE_TABLE_ISOLATION
extern void pti_init(void);
extern void pti_check_boottime_disable(void);
-extern void pti_clone_kernel_text(void);
+extern void pti_finalize(void);
#else
static inline void pti_check_boottime_disable(void) { }
-static inline void pti_clone_kernel_text(void) { }
#endif
#endif /* __ASSEMBLY__ */
"push %rdx;"
"mov $0x1,%eax;"
"xor %edx,%edx;"
- "lock cmpxchg %dl,(%rdi);"
+ LOCK_PREFIX "cmpxchg %dl,(%rdi);"
"cmp $0x1,%al;"
"jne .slowpath;"
"pop %rdx;"
* PaX/grsecurity.
*/
#include <linux/refcount.h>
+#include <asm/bug.h>
/*
* This is the first portion of the refcount error handling, which lives in
extern char __brk_base[], __brk_limit[];
extern struct exception_table_entry __stop___ex_table[];
+extern char __end_rodata_aligned[];
#if defined(CONFIG_X86_64)
extern char __end_rodata_hpage_align[];
int set_memory_4k(unsigned long addr, int numpages);
int set_memory_encrypted(unsigned long addr, int numpages);
int set_memory_decrypted(unsigned long addr, int numpages);
+int set_memory_np_noalias(unsigned long addr, int numpages);
int set_memory_array_uc(unsigned long *addr, int addrinarray);
int set_memory_array_wc(unsigned long *addr, int addrinarray);
#endif
/* This is used when switching tasks or entering/exiting vm86 mode. */
-static inline void update_sp0(struct task_struct *task)
+static inline void update_task_stack(struct task_struct *task)
{
- /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+ /* sp0 always points to the entry trampoline stack, which is constant: */
#ifdef CONFIG_X86_32
- load_sp0(task->thread.sp0);
+ if (static_cpu_has(X86_FEATURE_XENPV))
+ load_sp0(task->thread.sp0);
+ else
+ this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
#else
+ /*
+ * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
+ * doesn't work on x86-32 because sp1 and
+ * cpu_current_top_of_stack have different values (because of
+ * the non-zero stack-padding on 32bit).
+ */
if (static_cpu_has(X86_FEATURE_XENPV))
load_sp0(task_top_of_stack(task));
#endif
+
}
#endif /* _ASM_X86_SWITCH_TO_H */
extern void *text_poke(void *addr, const void *opcode, size_t len);
extern int poke_int3_handler(struct pt_regs *regs);
extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern int after_bootmem;
#endif /* _ASM_X86_TEXT_PATCHING_H */
#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
#endif
-static inline bool tlb_defer_switch_to_init_mm(void)
-{
- /*
- * If we have PCID, then switching to init_mm is reasonably
- * fast. If we don't have PCID, then switching to init_mm is
- * quite slow, so we try to defer it in the hopes that we can
- * avoid it entirely. The latter approach runs the risk of
- * receiving otherwise unnecessary IPIs.
- *
- * This choice is just a heuristic. The tlb code can handle this
- * function returning true or false regardless of whether we have
- * PCID.
- */
- return !static_cpu_has(X86_FEATURE_PCID);
-}
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
native_flush_tlb_others(mask, info)
#endif
+extern void tlb_flush_remove_tables(struct mm_struct *mm);
+extern void tlb_flush_remove_tables_local(void *arg);
+
+#define HAVE_TLB_FLUSH_REMOVE_TABLES
+
#endif /* _ASM_X86_TLBFLUSH_H */
__entry->addr, __entry->end)
);
+TRACE_EVENT(hyperv_send_ipi_mask,
+ TP_PROTO(const struct cpumask *cpus,
+ int vector),
+ TP_ARGS(cpus, vector),
+ TP_STRUCT__entry(
+ __field(unsigned int, ncpus)
+ __field(int, vector)
+ ),
+ TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+ __entry->vector = vector;
+ ),
+ TP_printk("ncpus %d vector %x",
+ __entry->ncpus, __entry->vector)
+ );
+
#endif /* CONFIG_HYPERV */
#undef TRACE_INCLUDE_PATH
extern struct system_counterval_t convert_art_to_tsc(u64 art);
extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
-extern void tsc_early_delay_calibrate(void);
+extern void tsc_early_init(void);
extern void tsc_init(void);
extern void mark_tsc_unstable(char *reason);
extern int unsynchronized_tsc(void);
extern int check_tsc_unstable(void);
extern void mark_tsc_async_resets(char *reason);
-extern unsigned long native_calibrate_cpu(void);
+extern unsigned long native_calibrate_cpu_early(void);
extern unsigned long native_calibrate_tsc(void);
extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
unsigned long ret;
__uaccess_begin();
- ret = memcpy_mcsafe(to, from, len);
+ /*
+ * Note, __memcpy_mcsafe() is explicitly used since it can
+ * handle exceptions / faults. memcpy_mcsafe() may fall back to
+ * memcpy() which lacks this handling.
+ */
+ ret = __memcpy_mcsafe(to, from, len);
__uaccess_end();
return ret;
}
* the debuginfo as necessary. It will also warn if it sees any
* inconsistencies.
*/
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL
+.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
#ifdef CONFIG_STACK_VALIDATION
.Lunwind_hint_ip_\@:
.pushsection .discard.unwind_hints
.short \sp_offset
.byte \sp_reg
.byte \type
+ .byte \end
+ .balign 4
.popsection
#endif
.endm
.macro UNWIND_HINT_EMPTY
- UNWIND_HINT sp_reg=ORC_REG_UNDEFINED
+ UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
.endm
.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
#else /* !__ASSEMBLY__ */
-#define UNWIND_HINT(sp_reg, sp_offset, type) \
+#define UNWIND_HINT(sp_reg, sp_offset, type, end) \
"987: \n\t" \
".pushsection .discard.unwind_hints\n\t" \
/* struct unwind_hint */ \
".long 987b - .\n\t" \
- ".short " __stringify(sp_offset) "\n\t" \
+ ".short " __stringify(sp_offset) "\n\t" \
".byte " __stringify(sp_reg) "\n\t" \
".byte " __stringify(type) "\n\t" \
+ ".byte " __stringify(end) "\n\t" \
+ ".balign 4 \n\t" \
".popsection\n\t"
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE)
+#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE)
+#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
#endif /* __ASSEMBLY__ */
#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
#define VMX_MISC_SAVE_EFER_LMA 0x00000020
#define VMX_MISC_ACTIVITY_HLT 0x00000040
+#define VMX_MISC_ZERO_LEN_INS 0x40000000
/* VMFUNC functions */
#define VMX_VMFUNC_EPTP_SWITCHING 0x00000001
#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK
#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
+#define INTR_TYPE_RESERVED (1 << 8) /* reserved */
#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */
#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */
#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */
+#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */
/* GUEST_INTERRUPTIBILITY_INFO flags. */
#define GUEST_INTR_STATE_STI 0x00000001
obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
+obj-y += irqflags.o
obj-y += process.o
obj-y += fpu/
local_irq_save(flags);
memcpy(addr, opcode, len);
local_irq_restore(flags);
+ sync_core();
/* Could also do a CLFLUSH here to speed up CPU recovery; but
that causes hangs on some VIA CPUs. */
return addr;
struct page *pages[2];
int i;
+ /*
+ * While boot memory allocator is runnig we cannot use struct
+ * pages as they are not yet initialized.
+ */
+ BUG_ON(!after_bootmem);
+
if (!core_kernel_text((unsigned long)addr)) {
pages[0] = vmalloc_to_page(addr);
pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
case 0x04: return 0x02000014;
}
+ if (boot_cpu_data.x86_stepping > 4)
+ return 0;
+
return ~0U;
}
if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
pr_warning("APIC timer disabled due to verification failure\n");
- return -1;
+ return -1;
}
return 0;
return 0;
}
-static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
+static int
+assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
{
struct apic_chip_data *apicd = apic_chip_data(irqd);
bool resvd = apicd->has_reserved;
return -EBUSY;
vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
- if (vector > 0)
- apic_update_vector(irqd, vector, cpu);
trace_vector_alloc(irqd->irq, vector, resvd, vector);
- return vector;
-}
-
-static int assign_vector_locked(struct irq_data *irqd,
- const struct cpumask *dest)
-{
- struct apic_chip_data *apicd = apic_chip_data(irqd);
- int vector = allocate_vector(irqd, dest);
-
if (vector < 0)
return vector;
+ apic_update_vector(irqd, vector, cpu);
+ apic_update_irq_cfg(irqd, vector, cpu);
- apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu);
return 0;
}
pr_err("Managed startup irq %u, no vector available\n",
irqd->irq);
}
- return ret;
+ return ret;
}
static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/reboot.h>
+#include <linux/memory.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
}
EXPORT_SYMBOL(uv_hub_info_version);
+/* Default UV memory block size is 2GB */
+static unsigned long mem_block_size __initdata = (2UL << 30);
+
+/* Kernel parameter to specify UV mem block size */
+static int __init parse_mem_block_size(char *ptr)
+{
+ unsigned long size = memparse(ptr, NULL);
+
+ /* Size will be rounded down by set_block_size() below */
+ mem_block_size = size;
+ return 0;
+}
+early_param("uv_memblksize", parse_mem_block_size);
+
+static __init int adj_blksize(u32 lgre)
+{
+ unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT;
+ unsigned long size;
+
+ for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1)
+ if (IS_ALIGNED(base, size))
+ break;
+
+ if (size >= mem_block_size)
+ return 0;
+
+ mem_block_size = size;
+ return 1;
+}
+
+static __init void set_block_size(void)
+{
+ unsigned int order = ffs(mem_block_size);
+
+ if (order) {
+ /* adjust for ffs return of 1..64 */
+ set_memory_block_size_order(order - 1);
+ pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size);
+ } else {
+ /* bad or zero value, default to 1UL << 31 (2GB) */
+ pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size);
+ set_memory_block_size_order(31);
+ }
+}
+
/* Build GAM range lookup table: */
static __init void build_uv_gr_table(void)
{
<< UV_GAM_RANGE_SHFT);
int order = 0;
char suffix[] = " KMGTPE";
+ int flag = ' ';
while (size > 9999 && order < sizeof(suffix)) {
size /= 1024;
order++;
}
+ /* adjust max block size to current range start */
+ if (gre->type == 1 || gre->type == 2)
+ if (adj_blksize(lgre))
+ flag = '*';
+
if (!index) {
pr_info("UV: GAM Range Table...\n");
- pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
+ pr_info("UV: # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
}
- pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n",
+ pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d %04x %02x %02x\n",
index++,
(unsigned long)lgre << UV_GAM_RANGE_SHFT,
(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
- size, suffix[order],
+ flag, size, suffix[order],
gre->type, gre->nasid, gre->sockid, gre->pnode);
+ /* update to next range start */
lgre = gre->limit;
if (sock_min > gre->sockid)
sock_min = gre->sockid;
build_socket_tables();
build_uv_gr_table();
+ set_block_size();
uv_init_hub_info(&hub_info);
uv_possible_blades = num_possible_nodes();
if (!_node_to_pnode)
#include <asm/olpc.h>
#include <asm/paravirt.h>
#include <asm/reboot.h>
+#include <asm/nospec-branch.h>
#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
extern int (*console_blank_hook)(int);
gdt[0x40 / 8] = bad_bios_desc;
apm_irq_save(flags);
+ firmware_restrict_branch_speculation_start();
APM_DO_SAVE_SEGS;
apm_bios_call_asm(call->func, call->ebx, call->ecx,
&call->eax, &call->ebx, &call->ecx, &call->edx,
&call->esi);
APM_DO_RESTORE_SEGS;
+ firmware_restrict_branch_speculation_end();
apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
gdt[0x40 / 8] = bad_bios_desc;
apm_irq_save(flags);
+ firmware_restrict_branch_speculation_start();
APM_DO_SAVE_SEGS;
error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
&call->eax);
APM_DO_RESTORE_SEGS;
+ firmware_restrict_branch_speculation_end();
apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+ DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
+
+ /* Offset for sp0 and sp1 into the tss_struct */
+ OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+ OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
}
OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
BLANK();
- /* Offset from the sysenter stack to tss.sp0 */
- DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+ /*
+ * Offset from the entry stack to task stack stored in TSS. Kernel entry
+ * happens on the per-cpu entry-stack, and the asm code switches to the
+ * task-stack pointer stored in x86_tss.sp1, which is a copy of
+ * task->thread.sp0 where entry code can find it.
+ */
+ DEFINE(TSS_entry2task_stack,
+ offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
offsetofend(struct cpu_entry_area, entry_stack_page.stack));
#ifdef CONFIG_STACKPROTECTOR
#undef ENTRY
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
- OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
- OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
BLANK();
#ifdef CONFIG_STACKPROTECTOR
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o
-obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o
+obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
+obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
+CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
obj-$(CONFIG_X86_MCE) += mcheck/
obj-$(CONFIG_MTRR) += mtrr/
}
}
- set_cpu_cap(c, X86_FEATURE_K7);
-
/* calling is from identify_secondary_cpu() ? */
if (!c->cpu_index)
return;
nodes_per_socket = ((value >> 3) & 7) + 1;
}
- if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+ if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+ !boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
+ c->x86 >= 0x15 && c->x86 <= 0x17) {
unsigned int bit;
switch (c->x86) {
early_init_amd_mc(c);
+#ifdef CONFIG_X86_32
+ if (c->x86 == 6)
+ set_cpu_cap(c, X86_FEATURE_K7);
+#endif
+
+ if (c->x86 >= 0xf)
+ set_cpu_cap(c, X86_FEATURE_K8);
+
rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
/*
init_amd_cacheinfo(c);
- if (c->x86 >= 0xf)
- set_cpu_cap(c, X86_FEATURE_K8);
-
if (cpu_has(c, X86_FEATURE_XMM2)) {
unsigned long long val;
int ret;
#include <asm/pgtable.h>
#include <asm/set_memory.h>
#include <asm/intel-family.h>
+#include <asm/hypervisor.h>
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
[SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline",
[SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline",
[SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline",
+ [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS",
};
#undef pr_fmt
guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
/* SSBD controlled in MSR_SPEC_CTRL */
- if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+ if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+ static_cpu_has(X86_FEATURE_AMD_SSBD))
hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
if (hostval != guestval) {
return cmd;
}
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
- boot_cpu_data.x86 == 6) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
- return true;
- }
- }
- return false;
-}
-
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
case SPECTRE_V2_CMD_FORCE:
case SPECTRE_V2_CMD_AUTO:
+ if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+ mode = SPECTRE_V2_IBRS_ENHANCED;
+ /* Force it so VMEXIT will restore correctly */
+ x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ goto specv2_set_mode;
+ }
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
}
+specv2_set_mode:
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
/*
- * If neither SMEP nor PTI are available, there is a risk of
- * hitting userspace addresses in the RSB after a context switch
- * from a shallow call stack to a deeper one. To prevent this fill
- * the entire RSB, even when using IBRS.
+ * If spectre v2 protection has been enabled, unconditionally fill
+ * RSB during a context switch; this protects against two independent
+ * issues:
*
- * Skylake era CPUs have a separate issue with *underflow* of the
- * RSB, when they will predict 'ret' targets from the generic BTB.
- * The proper mitigation for this is IBRS. If IBRS is not supported
- * or deactivated in favour of retpolines the RSB fill on context
- * switch is required.
+ * - RSB underflow (and switch to BTB) on Skylake+
+ * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
*/
- if ((!boot_cpu_has(X86_FEATURE_PTI) &&
- !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
- setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
- pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
- }
+ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+ pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
/* Initialize Indirect Branch Prediction Barrier if supported */
if (boot_cpu_has(X86_FEATURE_IBPB)) {
/*
* Retpoline means the kernel is safe because it has no indirect
- * branches. But firmware isn't, so use IBRS to protect that.
+ * branches. Enhanced IBRS protects firmware too, so, enable restricted
+ * speculation around firmware calls only when Enhanced IBRS isn't
+ * supported.
+ *
+ * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
+ * the user might select retpoline on the kernel command line and if
+ * the CPU supports Enhanced IBRS, kernel might un-intentionally not
+ * enable IBRS around firmware calls.
*/
- if (boot_cpu_has(X86_FEATURE_IBRS)) {
+ if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
* Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
* use a completely different MSR and bit dependent on family.
*/
- if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
+ !static_cpu_has(X86_FEATURE_AMD_SSBD)) {
x86_amd_ssb_disable();
- else {
+ } else {
x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
if (boot_cpu_has(X86_FEATURE_PTI))
return sprintf(buf, "Mitigation: PTI\n");
+ if (hypervisor_is_type(X86_HYPER_XEN_PV))
+ return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n");
+
break;
case X86_BUG_SPECTRE_V1:
num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
if (num_sharing_cache) {
- int bits = get_count_order(num_sharing_cache) - 1;
+ int bits = get_count_order(num_sharing_cache);
per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
}
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
#include <linux/bootmem.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+ if (ia32_cap & ARCH_CAP_IBRS_ALL)
+ setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+
if (x86_match_cpu(cpu_no_meltdown))
return;
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
}
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(void)
+{
+#ifdef CONFIG_X86_32
+ setup_clear_cpu_cap(X86_FEATURE_NOPL);
+#else
+ setup_force_cpu_cap(X86_FEATURE_NOPL);
+#endif
+}
+
/*
* Do minimum CPU detection early.
* Fields really needed: vendor, cpuid_level, family, model, mask,
*/
if (!pgtable_l5_enabled())
setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+ detect_nopl();
}
void __init early_cpu_init(void)
early_identify_cpu(&boot_cpu_data);
}
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
- clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
- set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
get_model_name(c); /* Default name */
- detect_nopl(c);
-
detect_null_seg_behavior(c);
/*
enter_lazy_tlb(&init_mm, curr);
/*
- * Initialize the TSS. Don't bother initializing sp0, as the initial
- * task never enters user mode.
+ * Initialize the TSS. sp0 points to the entry trampoline stack
+ * regardless of what task is running.
*/
set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
+ load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
load_mm_ldt(&init_mm);
#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000
u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+ u32 msr_vpid_cap, msr_ept_cap;
clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
clear_cpu_cap(c, X86_FEATURE_VNMI);
clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
clear_cpu_cap(c, X86_FEATURE_EPT);
clear_cpu_cap(c, X86_FEATURE_VPID);
+ clear_cpu_cap(c, X86_FEATURE_EPT_AD);
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
msr_ctl = vmx_msr_high | vmx_msr_low;
if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
(msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
- if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) {
set_cpu_cap(c, X86_FEATURE_EPT);
+ rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
+ msr_ept_cap, msr_vpid_cap);
+ if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD)
+ set_cpu_cap(c, X86_FEATURE_EPT_AD);
+ }
if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
set_cpu_cap(c, X86_FEATURE_VPID);
}
return (rdt_mon_capable || rdt_alloc_capable);
}
+static enum cpuhp_state rdt_online;
+
static int __init intel_rdt_late_init(void)
{
struct rdt_resource *r;
cpuhp_remove_state(state);
return ret;
}
+ rdt_online = state;
for_each_alloc_capable_rdt_resource(r)
pr_info("Intel RDT %s allocation detected\n", r->name);
}
late_initcall(intel_rdt_late_init);
+
+static void __exit intel_rdt_exit(void)
+{
+ cpuhp_remove_state(rdt_online);
+ rdtgroup_exit();
+}
+
+__exitcall(intel_rdt_exit);
RDT_NUM_GROUP,
};
+/**
+ * enum rdtgrp_mode - Mode of a RDT resource group
+ * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
+ * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
+ * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
+ * allowed AND the allocations are Cache Pseudo-Locked
+ *
+ * The mode of a resource group enables control over the allowed overlap
+ * between allocations associated with different resource groups (classes
+ * of service). User is able to modify the mode of a resource group by
+ * writing to the "mode" resctrl file associated with the resource group.
+ *
+ * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
+ * writing the appropriate text to the "mode" file. A resource group enters
+ * "pseudo-locked" mode after the schemata is written while the resource
+ * group is in "pseudo-locksetup" mode.
+ */
+enum rdtgrp_mode {
+ RDT_MODE_SHAREABLE = 0,
+ RDT_MODE_EXCLUSIVE,
+ RDT_MODE_PSEUDO_LOCKSETUP,
+ RDT_MODE_PSEUDO_LOCKED,
+
+ /* Must be last */
+ RDT_NUM_MODES,
+};
+
/**
* struct mongroup - store mon group's data in resctrl fs.
* @mon_data_kn kernlfs node for the mon_data directory
u32 rmid;
};
+/**
+ * struct pseudo_lock_region - pseudo-lock region information
+ * @r: RDT resource to which this pseudo-locked region
+ * belongs
+ * @d: RDT domain to which this pseudo-locked region
+ * belongs
+ * @cbm: bitmask of the pseudo-locked region
+ * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread
+ * completion
+ * @thread_done: variable used by waitqueue to test if pseudo-locking
+ * thread completed
+ * @cpu: core associated with the cache on which the setup code
+ * will be run
+ * @line_size: size of the cache lines
+ * @size: size of pseudo-locked region in bytes
+ * @kmem: the kernel memory associated with pseudo-locked region
+ * @minor: minor number of character device associated with this
+ * region
+ * @debugfs_dir: pointer to this region's directory in the debugfs
+ * filesystem
+ * @pm_reqs: Power management QoS requests related to this region
+ */
+struct pseudo_lock_region {
+ struct rdt_resource *r;
+ struct rdt_domain *d;
+ u32 cbm;
+ wait_queue_head_t lock_thread_wq;
+ int thread_done;
+ int cpu;
+ unsigned int line_size;
+ unsigned int size;
+ void *kmem;
+ unsigned int minor;
+ struct dentry *debugfs_dir;
+ struct list_head pm_reqs;
+};
+
/**
* struct rdtgroup - store rdtgroup's data in resctrl file system.
* @kn: kernfs node
* @type: indicates type of this rdtgroup - either
* monitor only or ctrl_mon group
* @mon: mongroup related data
+ * @mode: mode of resource group
+ * @plr: pseudo-locked region
*/
struct rdtgroup {
- struct kernfs_node *kn;
- struct list_head rdtgroup_list;
- u32 closid;
- struct cpumask cpu_mask;
- int flags;
- atomic_t waitcount;
- enum rdt_group_type type;
- struct mongroup mon;
+ struct kernfs_node *kn;
+ struct list_head rdtgroup_list;
+ u32 closid;
+ struct cpumask cpu_mask;
+ int flags;
+ atomic_t waitcount;
+ enum rdt_group_type type;
+ struct mongroup mon;
+ enum rdtgrp_mode mode;
+ struct pseudo_lock_region *plr;
};
/* rdtgroup.flags */
extern int max_name_width, max_data_width;
int __init rdtgroup_init(void);
+void __exit rdtgroup_exit(void);
/**
* struct rftype - describe each file in the resctrl file system
* @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps
* @new_ctrl: new ctrl value to be loaded
* @have_new_ctrl: did user provide new_ctrl for this domain
+ * @plr: pseudo-locked region (if any) associated with domain
*/
struct rdt_domain {
- struct list_head list;
- int id;
- struct cpumask cpu_mask;
- unsigned long *rmid_busy_llc;
- struct mbm_state *mbm_total;
- struct mbm_state *mbm_local;
- struct delayed_work mbm_over;
- struct delayed_work cqm_limbo;
- int mbm_work_cpu;
- int cqm_work_cpu;
- u32 *ctrl_val;
- u32 *mbps_val;
- u32 new_ctrl;
- bool have_new_ctrl;
+ struct list_head list;
+ int id;
+ struct cpumask cpu_mask;
+ unsigned long *rmid_busy_llc;
+ struct mbm_state *mbm_total;
+ struct mbm_state *mbm_local;
+ struct delayed_work mbm_over;
+ struct delayed_work cqm_limbo;
+ int mbm_work_cpu;
+ int cqm_work_cpu;
+ u32 *ctrl_val;
+ u32 *mbps_val;
+ u32 new_ctrl;
+ bool have_new_ctrl;
+ struct pseudo_lock_region *plr;
};
/**
struct rdt_cache cache;
struct rdt_membw membw;
const char *format_str;
- int (*parse_ctrlval) (char *buf, struct rdt_resource *r,
+ int (*parse_ctrlval) (void *data, struct rdt_resource *r,
struct rdt_domain *d);
struct list_head evt_list;
int num_rmid;
unsigned long fflags;
};
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
extern struct rdtgroup rdtgroup_default;
DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-int __init rdtgroup_init(void);
+extern struct dentry *debugfs_resctrl;
enum {
RDT_RESOURCE_L3,
void rdt_ctrl_update(void *arg);
struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
void rdtgroup_kn_unlock(struct kernfs_node *kn);
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+ umode_t mask);
struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
struct list_head **pos);
ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+ u32 _cbm, int closid, bool exclusive);
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+ u32 cbm);
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
+int rdtgroup_tasks_assigned(struct rdtgroup *r);
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+int update_domains(struct rdt_resource *r, int closid);
+void closid_free(int closid);
int alloc_rmid(void);
void free_rmid(u32 rmid);
int rdt_get_mon_l3_config(struct rdt_resource *r);
return true;
}
-int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
{
unsigned long data;
+ char *buf = _buf;
if (d->have_new_ctrl) {
rdt_last_cmd_printf("duplicate domain %d\n", d->id);
* are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
* Additionally Haswell requires at least two bits set.
*/
-static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
{
unsigned long first_bit, zero_bit, val;
unsigned int cbm_len = r->cache.cbm_len;
return true;
}
+struct rdt_cbm_parse_data {
+ struct rdtgroup *rdtgrp;
+ char *buf;
+};
+
/*
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
{
- unsigned long data;
+ struct rdt_cbm_parse_data *data = _data;
+ struct rdtgroup *rdtgrp = data->rdtgrp;
+ u32 cbm_val;
if (d->have_new_ctrl) {
rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
}
- if(!cbm_validate(buf, &data, r))
+ /*
+ * Cannot set up more than one pseudo-locked region in a cache
+ * hierarchy.
+ */
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+ rdtgroup_pseudo_locked_in_hierarchy(d)) {
+ rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
return -EINVAL;
- d->new_ctrl = data;
+ }
+
+ if (!cbm_validate(data->buf, &cbm_val, r))
+ return -EINVAL;
+
+ if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+ rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+ rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
+ rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+ return -EINVAL;
+ }
+
+ /*
+ * The CBM may not overlap with the CBM of another closid if
+ * either is exclusive.
+ */
+ if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
+ rdt_last_cmd_printf("overlaps with exclusive group\n");
+ return -EINVAL;
+ }
+
+ if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
+ if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ rdt_last_cmd_printf("overlaps with other group\n");
+ return -EINVAL;
+ }
+ }
+
+ d->new_ctrl = cbm_val;
d->have_new_ctrl = true;
return 0;
* separated by ";". The "id" is in decimal, and must match one of
* the "id"s for this resource.
*/
-static int parse_line(char *line, struct rdt_resource *r)
+static int parse_line(char *line, struct rdt_resource *r,
+ struct rdtgroup *rdtgrp)
{
+ struct rdt_cbm_parse_data data;
char *dom = NULL, *id;
struct rdt_domain *d;
unsigned long dom_id;
dom = strim(dom);
list_for_each_entry(d, &r->domains, list) {
if (d->id == dom_id) {
- if (r->parse_ctrlval(dom, r, d))
+ data.buf = dom;
+ data.rdtgrp = rdtgrp;
+ if (r->parse_ctrlval(&data, r, d))
return -EINVAL;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ /*
+ * In pseudo-locking setup mode and just
+ * parsed a valid CBM that should be
+ * pseudo-locked. Only one locked region per
+ * resource group and domain so just do
+ * the required initialization for single
+ * region and return.
+ */
+ rdtgrp->plr->r = r;
+ rdtgrp->plr->d = d;
+ rdtgrp->plr->cbm = d->new_ctrl;
+ d->plr = rdtgrp->plr;
+ return 0;
+ }
goto next;
}
}
return -EINVAL;
}
-static int update_domains(struct rdt_resource *r, int closid)
+int update_domains(struct rdt_resource *r, int closid)
{
struct msr_param msr_param;
cpumask_var_t cpu_mask;
return 0;
}
-static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+static int rdtgroup_parse_resource(char *resname, char *tok,
+ struct rdtgroup *rdtgrp)
{
struct rdt_resource *r;
for_each_alloc_enabled_rdt_resource(r) {
- if (!strcmp(resname, r->name) && closid < r->num_closid)
- return parse_line(tok, r);
+ if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
+ return parse_line(tok, r, rdtgrp);
}
rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
return -EINVAL;
struct rdt_domain *dom;
struct rdt_resource *r;
char *tok, *resname;
- int closid, ret = 0;
+ int ret = 0;
/* Valid input requires a trailing newline */
if (nbytes == 0 || buf[nbytes - 1] != '\n')
}
rdt_last_cmd_clear();
- closid = rdtgrp->closid;
+ /*
+ * No changes to pseudo-locked region allowed. It has to be removed
+ * and re-created instead.
+ */
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ ret = -EINVAL;
+ rdt_last_cmd_puts("resource group is pseudo-locked\n");
+ goto out;
+ }
for_each_alloc_enabled_rdt_resource(r) {
list_for_each_entry(dom, &r->domains, list)
ret = -EINVAL;
goto out;
}
- ret = rdtgroup_parse_resource(resname, tok, closid);
+ ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
if (ret)
goto out;
}
for_each_alloc_enabled_rdt_resource(r) {
- ret = update_domains(r, closid);
+ ret = update_domains(r, rdtgrp->closid);
if (ret)
goto out;
}
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ /*
+ * If pseudo-locking fails we keep the resource group in
+ * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
+ * active and updated for just the domain the pseudo-locked
+ * region was requested for.
+ */
+ ret = rdtgroup_pseudo_lock_create(rdtgrp);
+ }
+
out:
rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
- closid = rdtgrp->closid;
- for_each_alloc_enabled_rdt_resource(r) {
- if (closid < r->num_closid)
- show_doms(s, r, closid);
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ for_each_alloc_enabled_rdt_resource(r)
+ seq_printf(s, "%s:uninitialized\n", r->name);
+ } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
+ rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+ } else {
+ closid = rdtgrp->closid;
+ for_each_alloc_enabled_rdt_resource(r) {
+ if (closid < r->num_closid)
+ show_doms(s, r, closid);
+ }
}
} else {
ret = -ENOENT;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource Director Technology (RDT)
+ *
+ * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Reinette Chatre <reinette.chatre@intel.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/mman.h>
+#include <linux/pm_qos.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/intel-family.h>
+#include <asm/intel_rdt_sched.h>
+#include <asm/perf_event.h>
+
+#include "intel_rdt.h"
+
+#define CREATE_TRACE_POINTS
+#include "intel_rdt_pseudo_lock_event.h"
+
+/*
+ * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
+ * prefetcher state. Details about this register can be found in the MSR
+ * tables for specific platforms found in Intel's SDM.
+ */
+#define MSR_MISC_FEATURE_CONTROL 0x000001a4
+
+/*
+ * The bits needed to disable hardware prefetching varies based on the
+ * platform. During initialization we will discover which bits to use.
+ */
+static u64 prefetch_disable_bits;
+
+/*
+ * Major number assigned to and shared by all devices exposing
+ * pseudo-locked regions.
+ */
+static unsigned int pseudo_lock_major;
+static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
+static struct class *pseudo_lock_class;
+
+/**
+ * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ *
+ * Capture the list of platforms that have been validated to support
+ * pseudo-locking. This includes testing to ensure pseudo-locked regions
+ * with low cache miss rates can be created under variety of load conditions
+ * as well as that these pseudo-locked regions can maintain their low cache
+ * miss rates under variety of load conditions for significant lengths of time.
+ *
+ * After a platform has been validated to support pseudo-locking its
+ * hardware prefetch disable bits are included here as they are documented
+ * in the SDM.
+ *
+ * When adding a platform here also add support for its cache events to
+ * measure_cycles_perf_fn()
+ *
+ * Return:
+ * If platform is supported, the bits to disable hardware prefetchers, 0
+ * if platform is not supported.
+ */
+static u64 get_prefetch_disable_bits(void)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+ boot_cpu_data.x86 != 6)
+ return 0;
+
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_BROADWELL_X:
+ /*
+ * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+ * as:
+ * 0 L2 Hardware Prefetcher Disable (R/W)
+ * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W)
+ * 2 DCU Hardware Prefetcher Disable (R/W)
+ * 3 DCU IP Prefetcher Disable (R/W)
+ * 63:4 Reserved
+ */
+ return 0xF;
+ case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ /*
+ * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+ * as:
+ * 0 L2 Hardware Prefetcher Disable (R/W)
+ * 1 Reserved
+ * 2 DCU Hardware Prefetcher Disable (R/W)
+ * 63:3 Reserved
+ */
+ return 0x5;
+ }
+
+ return 0;
+}
+
+/*
+ * Helper to write 64bit value to MSR without tracing. Used when
+ * use of the cache should be restricted and use of registers used
+ * for local variables avoided.
+ */
+static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
+{
+ __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+}
+
+/**
+ * pseudo_lock_minor_get - Obtain available minor number
+ * @minor: Pointer to where new minor number will be stored
+ *
+ * A bitmask is used to track available minor numbers. Here the next free
+ * minor number is marked as unavailable and returned.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int pseudo_lock_minor_get(unsigned int *minor)
+{
+ unsigned long first_bit;
+
+ first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
+
+ if (first_bit == MINORBITS)
+ return -ENOSPC;
+
+ __clear_bit(first_bit, &pseudo_lock_minor_avail);
+ *minor = first_bit;
+
+ return 0;
+}
+
+/**
+ * pseudo_lock_minor_release - Return minor number to available
+ * @minor: The minor number made available
+ */
+static void pseudo_lock_minor_release(unsigned int minor)
+{
+ __set_bit(minor, &pseudo_lock_minor_avail);
+}
+
+/**
+ * region_find_by_minor - Locate a pseudo-lock region by inode minor number
+ * @minor: The minor number of the device representing pseudo-locked region
+ *
+ * When the character device is accessed we need to determine which
+ * pseudo-locked region it belongs to. This is done by matching the minor
+ * number of the device to the pseudo-locked region it belongs.
+ *
+ * Minor numbers are assigned at the time a pseudo-locked region is associated
+ * with a cache instance.
+ *
+ * Return: On success return pointer to resource group owning the pseudo-locked
+ * region, NULL on failure.
+ */
+static struct rdtgroup *region_find_by_minor(unsigned int minor)
+{
+ struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
+
+ list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+ if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
+ rdtgrp_match = rdtgrp;
+ break;
+ }
+ }
+ return rdtgrp_match;
+}
+
+/**
+ * pseudo_lock_pm_req - A power management QoS request list entry
+ * @list: Entry within the @pm_reqs list for a pseudo-locked region
+ * @req: PM QoS request
+ */
+struct pseudo_lock_pm_req {
+ struct list_head list;
+ struct dev_pm_qos_request req;
+};
+
+static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
+{
+ struct pseudo_lock_pm_req *pm_req, *next;
+
+ list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
+ dev_pm_qos_remove_request(&pm_req->req);
+ list_del(&pm_req->list);
+ kfree(pm_req);
+ }
+}
+
+/**
+ * pseudo_lock_cstates_constrain - Restrict cores from entering C6
+ *
+ * To prevent the cache from being affected by power management entering
+ * C6 has to be avoided. This is accomplished by requesting a latency
+ * requirement lower than lowest C6 exit latency of all supported
+ * platforms as found in the cpuidle state tables in the intel_idle driver.
+ * At this time it is possible to do so with a single latency requirement
+ * for all supported platforms.
+ *
+ * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
+ * the ACPI latencies need to be considered while keeping in mind that C2
+ * may be set to map to deeper sleep states. In this case the latency
+ * requirement needs to prevent entering C2 also.
+ */
+static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
+{
+ struct pseudo_lock_pm_req *pm_req;
+ int cpu;
+ int ret;
+
+ for_each_cpu(cpu, &plr->d->cpu_mask) {
+ pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
+ if (!pm_req) {
+ rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+ ret = -ENOMEM;
+ goto out_err;
+ }
+ ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+ &pm_req->req,
+ DEV_PM_QOS_RESUME_LATENCY,
+ 30);
+ if (ret < 0) {
+ rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+ cpu);
+ kfree(pm_req);
+ ret = -1;
+ goto out_err;
+ }
+ list_add(&pm_req->list, &plr->pm_reqs);
+ }
+
+ return 0;
+
+out_err:
+ pseudo_lock_cstates_relax(plr);
+ return ret;
+}
+
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+ plr->size = 0;
+ plr->line_size = 0;
+ kfree(plr->kmem);
+ plr->kmem = NULL;
+ plr->r = NULL;
+ if (plr->d)
+ plr->d->plr = NULL;
+ plr->d = NULL;
+ plr->cbm = 0;
+ plr->debugfs_dir = NULL;
+}
+
+/**
+ * pseudo_lock_region_init - Initialize pseudo-lock region information
+ * @plr: pseudo-lock region
+ *
+ * Called after user provided a schemata to be pseudo-locked. From the
+ * schemata the &struct pseudo_lock_region is on entry already initialized
+ * with the resource, domain, and capacity bitmask. Here the information
+ * required for pseudo-locking is deduced from this data and &struct
+ * pseudo_lock_region initialized further. This information includes:
+ * - size in bytes of the region to be pseudo-locked
+ * - cache line size to know the stride with which data needs to be accessed
+ * to be pseudo-locked
+ * - a cpu associated with the cache instance on which the pseudo-locking
+ * flow can be executed
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
+{
+ struct cpu_cacheinfo *ci;
+ int ret;
+ int i;
+
+ /* Pick the first cpu we find that is associated with the cache. */
+ plr->cpu = cpumask_first(&plr->d->cpu_mask);
+
+ if (!cpu_online(plr->cpu)) {
+ rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+ plr->cpu);
+ ret = -ENODEV;
+ goto out_region;
+ }
+
+ ci = get_cpu_cacheinfo(plr->cpu);
+
+ plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+
+ for (i = 0; i < ci->num_leaves; i++) {
+ if (ci->info_list[i].level == plr->r->cache_level) {
+ plr->line_size = ci->info_list[i].coherency_line_size;
+ return 0;
+ }
+ }
+
+ ret = -1;
+ rdt_last_cmd_puts("unable to determine cache line size\n");
+out_region:
+ pseudo_lock_region_clear(plr);
+ return ret;
+}
+
+/**
+ * pseudo_lock_init - Initialize a pseudo-lock region
+ * @rdtgrp: resource group to which new pseudo-locked region will belong
+ *
+ * A pseudo-locked region is associated with a resource group. When this
+ * association is created the pseudo-locked region is initialized. The
+ * details of the pseudo-locked region are not known at this time so only
+ * allocation is done and association established.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_init(struct rdtgroup *rdtgrp)
+{
+ struct pseudo_lock_region *plr;
+
+ plr = kzalloc(sizeof(*plr), GFP_KERNEL);
+ if (!plr)
+ return -ENOMEM;
+
+ init_waitqueue_head(&plr->lock_thread_wq);
+ INIT_LIST_HEAD(&plr->pm_reqs);
+ rdtgrp->plr = plr;
+ return 0;
+}
+
+/**
+ * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
+ * @plr: pseudo-lock region
+ *
+ * Initialize the details required to set up the pseudo-locked region and
+ * allocate the contiguous memory that will be pseudo-locked to the cache.
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
+{
+ int ret;
+
+ ret = pseudo_lock_region_init(plr);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * We do not yet support contiguous regions larger than
+ * KMALLOC_MAX_SIZE.
+ */
+ if (plr->size > KMALLOC_MAX_SIZE) {
+ rdt_last_cmd_puts("requested region exceeds maximum size\n");
+ ret = -E2BIG;
+ goto out_region;
+ }
+
+ plr->kmem = kzalloc(plr->size, GFP_KERNEL);
+ if (!plr->kmem) {
+ rdt_last_cmd_puts("unable to allocate memory\n");
+ ret = -ENOMEM;
+ goto out_region;
+ }
+
+ ret = 0;
+ goto out;
+out_region:
+ pseudo_lock_region_clear(plr);
+out:
+ return ret;
+}
+
+/**
+ * pseudo_lock_free - Free a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-locked region belonged
+ *
+ * The pseudo-locked region's resources have already been released, or not
+ * yet created at this point. Now it can be freed and disassociated from the
+ * resource group.
+ *
+ * Return: void
+ */
+static void pseudo_lock_free(struct rdtgroup *rdtgrp)
+{
+ pseudo_lock_region_clear(rdtgrp->plr);
+ kfree(rdtgrp->plr);
+ rdtgrp->plr = NULL;
+}
+
+/**
+ * pseudo_lock_fn - Load kernel memory into cache
+ * @_rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * This is the core pseudo-locking flow.
+ *
+ * First we ensure that the kernel memory cannot be found in the cache.
+ * Then, while taking care that there will be as little interference as
+ * possible, the memory to be loaded is accessed while core is running
+ * with class of service set to the bitmask of the pseudo-locked region.
+ * After this is complete no future CAT allocations will be allowed to
+ * overlap with this bitmask.
+ *
+ * Local register variables are utilized to ensure that the memory region
+ * to be locked is the only memory access made during the critical locking
+ * loop.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int pseudo_lock_fn(void *_rdtgrp)
+{
+ struct rdtgroup *rdtgrp = _rdtgrp;
+ struct pseudo_lock_region *plr = rdtgrp->plr;
+ u32 rmid_p, closid_p;
+ unsigned long i;
+#ifdef CONFIG_KASAN
+ /*
+ * The registers used for local register variables are also used
+ * when KASAN is active. When KASAN is active we use a regular
+ * variable to ensure we always use a valid pointer, but the cost
+ * is that this variable will enter the cache through evicting the
+ * memory we are trying to lock into the cache. Thus expect lower
+ * pseudo-locking success rate when KASAN is active.
+ */
+ unsigned int line_size;
+ unsigned int size;
+ void *mem_r;
+#else
+ register unsigned int line_size asm("esi");
+ register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+ register void *mem_r asm("rbx");
+#else
+ register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+ /*
+ * Make sure none of the allocated memory is cached. If it is we
+ * will get a cache hit in below loop from outside of pseudo-locked
+ * region.
+ * wbinvd (as opposed to clflush/clflushopt) is required to
+ * increase likelihood that allocated cache portion will be filled
+ * with associated memory.
+ */
+ native_wbinvd();
+
+ /*
+ * Always called with interrupts enabled. By disabling interrupts
+ * ensure that we will not be preempted during this critical section.
+ */
+ local_irq_disable();
+
+ /*
+ * Call wrmsr and rdmsr as directly as possible to avoid tracing
+ * clobbering local register variables or affecting cache accesses.
+ *
+ * Disable the hardware prefetcher so that when the end of the memory
+ * being pseudo-locked is reached the hardware will not read beyond
+ * the buffer and evict pseudo-locked memory read earlier from the
+ * cache.
+ */
+ __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ closid_p = this_cpu_read(pqr_state.cur_closid);
+ rmid_p = this_cpu_read(pqr_state.cur_rmid);
+ mem_r = plr->kmem;
+ size = plr->size;
+ line_size = plr->line_size;
+ /*
+ * Critical section begin: start by writing the closid associated
+ * with the capacity bitmask of the cache region being
+ * pseudo-locked followed by reading of kernel memory to load it
+ * into the cache.
+ */
+ __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+ /*
+ * Cache was flushed earlier. Now access kernel memory to read it
+ * into cache region associated with just activated plr->closid.
+ * Loop over data twice:
+ * - In first loop the cache region is shared with the page walker
+ * as it populates the paging structure caches (including TLB).
+ * - In the second loop the paging structure caches are used and
+ * cache region is populated with the memory being referenced.
+ */
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ /*
+ * Add a barrier to prevent speculative execution of this
+ * loop reading beyond the end of the buffer.
+ */
+ rmb();
+ asm volatile("mov (%0,%1,1), %%eax\n\t"
+ :
+ : "r" (mem_r), "r" (i)
+ : "%eax", "memory");
+ }
+ for (i = 0; i < size; i += line_size) {
+ /*
+ * Add a barrier to prevent speculative execution of this
+ * loop reading beyond the end of the buffer.
+ */
+ rmb();
+ asm volatile("mov (%0,%1,1), %%eax\n\t"
+ :
+ : "r" (mem_r), "r" (i)
+ : "%eax", "memory");
+ }
+ /*
+ * Critical section end: restore closid with capacity bitmask that
+ * does not overlap with pseudo-locked region.
+ */
+ __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
+
+ /* Re-enable the hardware prefetcher(s) */
+ wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ local_irq_enable();
+
+ plr->thread_done = 1;
+ wake_up_interruptible(&plr->lock_thread_wq);
+ return 0;
+}
+
+/**
+ * rdtgroup_monitor_in_progress - Test if monitoring in progress
+ * @r: resource group being queried
+ *
+ * Return: 1 if monitor groups have been created for this resource
+ * group, 0 otherwise.
+ */
+static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+{
+ return !list_empty(&rdtgrp->mon.crdtgrp_list);
+}
+
+/**
+ * rdtgroup_locksetup_user_restrict - Restrict user access to group
+ * @rdtgrp: resource group needing access restricted
+ *
+ * A resource group used for cache pseudo-locking cannot have cpus or tasks
+ * assigned to it. This is communicated to the user by restricting access
+ * to all the files that can be used to make such changes.
+ *
+ * Permissions restored with rdtgroup_locksetup_user_restore()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restriction of access an attempt will be made to restore permissions but
+ * the state of the mode of these files will be uncertain when a failure
+ * occurs.
+ */
+static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+{
+ int ret;
+
+ ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+ if (ret)
+ return ret;
+
+ ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+ if (ret)
+ goto err_tasks;
+
+ ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+ if (ret)
+ goto err_cpus;
+
+ if (rdt_mon_capable) {
+ ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
+ if (ret)
+ goto err_cpus_list;
+ }
+
+ ret = 0;
+ goto out;
+
+err_cpus_list:
+ rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+err_cpus:
+ rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+err_tasks:
+ rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+out:
+ return ret;
+}
+
+/**
+ * rdtgroup_locksetup_user_restore - Restore user access to group
+ * @rdtgrp: resource group needing access restored
+ *
+ * Restore all file access previously removed using
+ * rdtgroup_locksetup_user_restrict()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restoration of access an attempt will be made to restrict permissions
+ * again but the state of the mode of these files will be uncertain when
+ * a failure occurs.
+ */
+static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+{
+ int ret;
+
+ ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+ if (ret)
+ return ret;
+
+ ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+ if (ret)
+ goto err_tasks;
+
+ ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+ if (ret)
+ goto err_cpus;
+
+ if (rdt_mon_capable) {
+ ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
+ if (ret)
+ goto err_cpus_list;
+ }
+
+ ret = 0;
+ goto out;
+
+err_cpus_list:
+ rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+err_cpus:
+ rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+err_tasks:
+ rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+out:
+ return ret;
+}
+
+/**
+ * rdtgroup_locksetup_enter - Resource group enters locksetup mode
+ * @rdtgrp: resource group requested to enter locksetup mode
+ *
+ * A resource group enters locksetup mode to reflect that it would be used
+ * to represent a pseudo-locked region and is in the process of being set
+ * up to do so. A resource group used for a pseudo-locked region would
+ * lose the closid associated with it so we cannot allow it to have any
+ * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
+ * future. Monitoring of a pseudo-locked region is not allowed either.
+ *
+ * The above and more restrictions on a pseudo-locked region are checked
+ * for and enforced before the resource group enters the locksetup mode.
+ *
+ * Returns: 0 if the resource group successfully entered locksetup mode, <0
+ * on failure. On failure the last_cmd_status buffer is updated with text to
+ * communicate details of failure to the user.
+ */
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+ int ret;
+
+ /*
+ * The default resource group can neither be removed nor lose the
+ * default closid associated with it.
+ */
+ if (rdtgrp == &rdtgroup_default) {
+ rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Cache Pseudo-locking not supported when CDP is enabled.
+ *
+ * Some things to consider if you would like to enable this
+ * support (using L3 CDP as example):
+ * - When CDP is enabled two separate resources are exposed,
+ * L3DATA and L3CODE, but they are actually on the same cache.
+ * The implication for pseudo-locking is that if a
+ * pseudo-locked region is created on a domain of one
+ * resource (eg. L3CODE), then a pseudo-locked region cannot
+ * be created on that same domain of the other resource
+ * (eg. L3DATA). This is because the creation of a
+ * pseudo-locked region involves a call to wbinvd that will
+ * affect all cache allocations on particular domain.
+ * - Considering the previous, it may be possible to only
+ * expose one of the CDP resources to pseudo-locking and
+ * hide the other. For example, we could consider to only
+ * expose L3DATA and since the L3 cache is unified it is
+ * still possible to place instructions there are execute it.
+ * - If only one region is exposed to pseudo-locking we should
+ * still keep in mind that availability of a portion of cache
+ * for pseudo-locking should take into account both resources.
+ * Similarly, if a pseudo-locked region is created in one
+ * resource, the portion of cache used by it should be made
+ * unavailable to all future allocations from both resources.
+ */
+ if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
+ rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+ rdt_last_cmd_puts("CDP enabled\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Not knowing the bits to disable prefetching implies that this
+ * platform does not support Cache Pseudo-Locking.
+ */
+ prefetch_disable_bits = get_prefetch_disable_bits();
+ if (prefetch_disable_bits == 0) {
+ rdt_last_cmd_puts("pseudo-locking not supported\n");
+ return -EINVAL;
+ }
+
+ if (rdtgroup_monitor_in_progress(rdtgrp)) {
+ rdt_last_cmd_puts("monitoring in progress\n");
+ return -EINVAL;
+ }
+
+ if (rdtgroup_tasks_assigned(rdtgrp)) {
+ rdt_last_cmd_puts("tasks assigned to resource group\n");
+ return -EINVAL;
+ }
+
+ if (!cpumask_empty(&rdtgrp->cpu_mask)) {
+ rdt_last_cmd_puts("CPUs assigned to resource group\n");
+ return -EINVAL;
+ }
+
+ if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
+ rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+ return -EIO;
+ }
+
+ ret = pseudo_lock_init(rdtgrp);
+ if (ret) {
+ rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+ goto out_release;
+ }
+
+ /*
+ * If this system is capable of monitoring a rmid would have been
+ * allocated when the control group was created. This is not needed
+ * anymore when this group would be used for pseudo-locking. This
+ * is safe to call on platforms not capable of monitoring.
+ */
+ free_rmid(rdtgrp->mon.rmid);
+
+ ret = 0;
+ goto out;
+
+out_release:
+ rdtgroup_locksetup_user_restore(rdtgrp);
+out:
+ return ret;
+}
+
+/**
+ * rdtgroup_locksetup_exit - resource group exist locksetup mode
+ * @rdtgrp: resource group
+ *
+ * When a resource group exits locksetup mode the earlier restrictions are
+ * lifted.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+ int ret;
+
+ if (rdt_mon_capable) {
+ ret = alloc_rmid();
+ if (ret < 0) {
+ rdt_last_cmd_puts("out of RMIDs\n");
+ return ret;
+ }
+ rdtgrp->mon.rmid = ret;
+ }
+
+ ret = rdtgroup_locksetup_user_restore(rdtgrp);
+ if (ret) {
+ free_rmid(rdtgrp->mon.rmid);
+ return ret;
+ }
+
+ pseudo_lock_free(rdtgrp);
+ return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
+ * @d: RDT domain
+ * @_cbm: CBM to test
+ *
+ * @d represents a cache instance and @_cbm a capacity bitmask that is
+ * considered for it. Determine if @_cbm overlaps with any existing
+ * pseudo-locked region on @d.
+ *
+ * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * otherwise.
+ */
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+{
+ unsigned long *cbm = (unsigned long *)&_cbm;
+ unsigned long *cbm_b;
+ unsigned int cbm_len;
+
+ if (d->plr) {
+ cbm_len = d->plr->r->cache.cbm_len;
+ cbm_b = (unsigned long *)&d->plr->cbm;
+ if (bitmap_intersects(cbm, cbm_b, cbm_len))
+ return true;
+ }
+ return false;
+}
+
+/**
+ * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
+ * @d: RDT domain under test
+ *
+ * The setup of a pseudo-locked region affects all cache instances within
+ * the hierarchy of the region. It is thus essential to know if any
+ * pseudo-locked regions exist within a cache hierarchy to prevent any
+ * attempts to create new pseudo-locked regions in the same hierarchy.
+ *
+ * Return: true if a pseudo-locked region exists in the hierarchy of @d or
+ * if it is not possible to test due to memory allocation issue,
+ * false otherwise.
+ */
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+{
+ cpumask_var_t cpu_with_psl;
+ struct rdt_resource *r;
+ struct rdt_domain *d_i;
+ bool ret = false;
+
+ if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
+ return true;
+
+ /*
+ * First determine which cpus have pseudo-locked regions
+ * associated with them.
+ */
+ for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(d_i, &r->domains, list) {
+ if (d_i->plr)
+ cpumask_or(cpu_with_psl, cpu_with_psl,
+ &d_i->cpu_mask);
+ }
+ }
+
+ /*
+ * Next test if new pseudo-locked region would intersect with
+ * existing region.
+ */
+ if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+ ret = true;
+
+ free_cpumask_var(cpu_with_psl);
+ return ret;
+}
+
+/**
+ * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * @_plr: pseudo-lock region to measure
+ *
+ * There is no deterministic way to test if a memory region is cached. One
+ * way is to measure how long it takes to read the memory, the speed of
+ * access is a good way to learn how close to the cpu the data was. Even
+ * more, if the prefetcher is disabled and the memory is read at a stride
+ * of half the cache line, then a cache miss will be easy to spot since the
+ * read of the first half would be significantly slower than the read of
+ * the second half.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int measure_cycles_lat_fn(void *_plr)
+{
+ struct pseudo_lock_region *plr = _plr;
+ unsigned long i;
+ u64 start, end;
+#ifdef CONFIG_KASAN
+ /*
+ * The registers used for local register variables are also used
+ * when KASAN is active. When KASAN is active we use a regular
+ * variable to ensure we always use a valid pointer to access memory.
+ * The cost is that accessing this pointer, which could be in
+ * cache, will be included in the measurement of memory read latency.
+ */
+ void *mem_r;
+#else
+#ifdef CONFIG_X86_64
+ register void *mem_r asm("rbx");
+#else
+ register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+ local_irq_disable();
+ /*
+ * The wrmsr call may be reordered with the assignment below it.
+ * Call wrmsr as directly as possible to avoid tracing clobbering
+ * local register variable used for memory pointer.
+ */
+ __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ mem_r = plr->kmem;
+ /*
+ * Dummy execute of the time measurement to load the needed
+ * instructions into the L1 instruction cache.
+ */
+ start = rdtsc_ordered();
+ for (i = 0; i < plr->size; i += 32) {
+ start = rdtsc_ordered();
+ asm volatile("mov (%0,%1,1), %%eax\n\t"
+ :
+ : "r" (mem_r), "r" (i)
+ : "%eax", "memory");
+ end = rdtsc_ordered();
+ trace_pseudo_lock_mem_latency((u32)(end - start));
+ }
+ wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ local_irq_enable();
+ plr->thread_done = 1;
+ wake_up_interruptible(&plr->lock_thread_wq);
+ return 0;
+}
+
+static int measure_cycles_perf_fn(void *_plr)
+{
+ unsigned long long l3_hits = 0, l3_miss = 0;
+ u64 l3_hit_bits = 0, l3_miss_bits = 0;
+ struct pseudo_lock_region *plr = _plr;
+ unsigned long long l2_hits, l2_miss;
+ u64 l2_hit_bits, l2_miss_bits;
+ unsigned long i;
+#ifdef CONFIG_KASAN
+ /*
+ * The registers used for local register variables are also used
+ * when KASAN is active. When KASAN is active we use regular variables
+ * at the cost of including cache access latency to these variables
+ * in the measurements.
+ */
+ unsigned int line_size;
+ unsigned int size;
+ void *mem_r;
+#else
+ register unsigned int line_size asm("esi");
+ register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+ register void *mem_r asm("rbx");
+#else
+ register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+ /*
+ * Non-architectural event for the Goldmont Microarchitecture
+ * from Intel x86 Architecture Software Developer Manual (SDM):
+ * MEM_LOAD_UOPS_RETIRED D1H (event number)
+ * Umask values:
+ * L1_HIT 01H
+ * L2_HIT 02H
+ * L1_MISS 08H
+ * L2_MISS 10H
+ *
+ * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+ * has two "no fix" errata associated with it: BDM35 and BDM100. On
+ * this platform we use the following events instead:
+ * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
+ * REFERENCES FFH
+ * MISS 3FH
+ * LONGEST_LAT_CACHE 2EH (Documented in SDM)
+ * REFERENCE 4FH
+ * MISS 41H
+ */
+
+ /*
+ * Start by setting flags for IA32_PERFEVTSELx:
+ * OS (Operating system mode) 0x2
+ * INT (APIC interrupt enable) 0x10
+ * EN (Enable counter) 0x40
+ *
+ * Then add the Umask value and event number to select performance
+ * event.
+ */
+
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
+ l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
+ break;
+ case INTEL_FAM6_BROADWELL_X:
+ /* On BDW the l2_hit_bits count references, not hits */
+ l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
+ l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
+ /* On BDW the l3_hit_bits count references, not hits */
+ l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
+ l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+ break;
+ default:
+ goto out;
+ }
+
+ local_irq_disable();
+ /*
+ * Call wrmsr direcly to avoid the local register variables from
+ * being overwritten due to reordering of their assignment with
+ * the wrmsr calls.
+ */
+ __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ /* Disable events and reset counters */
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+ if (l3_hit_bits > 0) {
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+ }
+ /* Set and enable the L2 counters */
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+ if (l3_hit_bits > 0) {
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+ l3_hit_bits);
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+ l3_miss_bits);
+ }
+ mem_r = plr->kmem;
+ size = plr->size;
+ line_size = plr->line_size;
+ for (i = 0; i < size; i += line_size) {
+ asm volatile("mov (%0,%1,1), %%eax\n\t"
+ :
+ : "r" (mem_r), "r" (i)
+ : "%eax", "memory");
+ }
+ /*
+ * Call wrmsr directly (no tracing) to not influence
+ * the cache access counters as they are disabled.
+ */
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
+ l2_hit_bits & ~(0x40ULL << 16));
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
+ l2_miss_bits & ~(0x40ULL << 16));
+ if (l3_hit_bits > 0) {
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+ l3_hit_bits & ~(0x40ULL << 16));
+ pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+ l3_miss_bits & ~(0x40ULL << 16));
+ }
+ l2_hits = native_read_pmc(0);
+ l2_miss = native_read_pmc(1);
+ if (l3_hit_bits > 0) {
+ l3_hits = native_read_pmc(2);
+ l3_miss = native_read_pmc(3);
+ }
+ wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ local_irq_enable();
+ /*
+ * On BDW we count references and misses, need to adjust. Sometimes
+ * the "hits" counter is a bit more than the references, for
+ * example, x references but x + 1 hits. To not report invalid
+ * hit values in this case we treat that as misses eaqual to
+ * references.
+ */
+ if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+ l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
+ trace_pseudo_lock_l2(l2_hits, l2_miss);
+ if (l3_hit_bits > 0) {
+ if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+ l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
+ trace_pseudo_lock_l3(l3_hits, l3_miss);
+ }
+
+out:
+ plr->thread_done = 1;
+ wake_up_interruptible(&plr->lock_thread_wq);
+ return 0;
+}
+
+/**
+ * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
+ *
+ * The measurement of latency to access a pseudo-locked region should be
+ * done from a cpu that is associated with that pseudo-locked region.
+ * Determine which cpu is associated with this region and start a thread on
+ * that cpu to perform the measurement, wait for that thread to complete.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
+{
+ struct pseudo_lock_region *plr = rdtgrp->plr;
+ struct task_struct *thread;
+ unsigned int cpu;
+ int ret = -1;
+
+ cpus_read_lock();
+ mutex_lock(&rdtgroup_mutex);
+
+ if (rdtgrp->flags & RDT_DELETED) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ plr->thread_done = 0;
+ cpu = cpumask_first(&plr->d->cpu_mask);
+ if (!cpu_online(cpu)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (sel == 1)
+ thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
+ cpu_to_node(cpu),
+ "pseudo_lock_measure/%u",
+ cpu);
+ else if (sel == 2)
+ thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+ cpu_to_node(cpu),
+ "pseudo_lock_measure/%u",
+ cpu);
+ else
+ goto out;
+
+ if (IS_ERR(thread)) {
+ ret = PTR_ERR(thread);
+ goto out;
+ }
+ kthread_bind(thread, cpu);
+ wake_up_process(thread);
+
+ ret = wait_event_interruptible(plr->lock_thread_wq,
+ plr->thread_done == 1);
+ if (ret < 0)
+ goto out;
+
+ ret = 0;
+
+out:
+ mutex_unlock(&rdtgroup_mutex);
+ cpus_read_unlock();
+ return ret;
+}
+
+static ssize_t pseudo_lock_measure_trigger(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct rdtgroup *rdtgrp = file->private_data;
+ size_t buf_size;
+ char buf[32];
+ int ret;
+ int sel;
+
+ buf_size = min(count, (sizeof(buf) - 1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size] = '\0';
+ ret = kstrtoint(buf, 10, &sel);
+ if (ret == 0) {
+ if (sel != 1)
+ return -EINVAL;
+ ret = debugfs_file_get(file->f_path.dentry);
+ if (ret)
+ return ret;
+ ret = pseudo_lock_measure_cycles(rdtgrp, sel);
+ if (ret == 0)
+ ret = count;
+ debugfs_file_put(file->f_path.dentry);
+ }
+
+ return ret;
+}
+
+static const struct file_operations pseudo_measure_fops = {
+ .write = pseudo_lock_measure_trigger,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
+/**
+ * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * Called when a resource group in the pseudo-locksetup mode receives a
+ * valid schemata that should be pseudo-locked. Since the resource group is
+ * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
+ * allocated and initialized with the essential information. If a failure
+ * occurs the resource group remains in the pseudo-locksetup mode with the
+ * &struct pseudo_lock_region associated with it, but cleared from all
+ * information and ready for the user to re-attempt pseudo-locking by
+ * writing the schemata again.
+ *
+ * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
+ * on failure. Descriptive error will be written to last_cmd_status buffer.
+ */
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+ struct pseudo_lock_region *plr = rdtgrp->plr;
+ struct task_struct *thread;
+ unsigned int new_minor;
+ struct device *dev;
+ int ret;
+
+ ret = pseudo_lock_region_alloc(plr);
+ if (ret < 0)
+ return ret;
+
+ ret = pseudo_lock_cstates_constrain(plr);
+ if (ret < 0) {
+ ret = -EINVAL;
+ goto out_region;
+ }
+
+ plr->thread_done = 0;
+
+ thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
+ cpu_to_node(plr->cpu),
+ "pseudo_lock/%u", plr->cpu);
+ if (IS_ERR(thread)) {
+ ret = PTR_ERR(thread);
+ rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+ goto out_cstates;
+ }
+
+ kthread_bind(thread, plr->cpu);
+ wake_up_process(thread);
+
+ ret = wait_event_interruptible(plr->lock_thread_wq,
+ plr->thread_done == 1);
+ if (ret < 0) {
+ /*
+ * If the thread does not get on the CPU for whatever
+ * reason and the process which sets up the region is
+ * interrupted then this will leave the thread in runnable
+ * state and once it gets on the CPU it will derefence
+ * the cleared, but not freed, plr struct resulting in an
+ * empty pseudo-locking loop.
+ */
+ rdt_last_cmd_puts("locking thread interrupted\n");
+ goto out_cstates;
+ }
+
+ ret = pseudo_lock_minor_get(&new_minor);
+ if (ret < 0) {
+ rdt_last_cmd_puts("unable to obtain a new minor number\n");
+ goto out_cstates;
+ }
+
+ /*
+ * Unlock access but do not release the reference. The
+ * pseudo-locked region will still be here on return.
+ *
+ * The mutex has to be released temporarily to avoid a potential
+ * deadlock with the mm->mmap_sem semaphore which is obtained in
+ * the device_create() and debugfs_create_dir() callpath below
+ * as well as before the mmap() callback is called.
+ */
+ mutex_unlock(&rdtgroup_mutex);
+
+ if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+ plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+ debugfs_resctrl);
+ if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+ debugfs_create_file("pseudo_lock_measure", 0200,
+ plr->debugfs_dir, rdtgrp,
+ &pseudo_measure_fops);
+ }
+
+ dev = device_create(pseudo_lock_class, NULL,
+ MKDEV(pseudo_lock_major, new_minor),
+ rdtgrp, "%s", rdtgrp->kn->name);
+
+ mutex_lock(&rdtgroup_mutex);
+
+ if (IS_ERR(dev)) {
+ ret = PTR_ERR(dev);
+ rdt_last_cmd_printf("failed to create character device: %d\n",
+ ret);
+ goto out_debugfs;
+ }
+
+ /* We released the mutex - check if group was removed while we did so */
+ if (rdtgrp->flags & RDT_DELETED) {
+ ret = -ENODEV;
+ goto out_device;
+ }
+
+ plr->minor = new_minor;
+
+ rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
+ closid_free(rdtgrp->closid);
+ rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
+ rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
+
+ ret = 0;
+ goto out;
+
+out_device:
+ device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+out_debugfs:
+ debugfs_remove_recursive(plr->debugfs_dir);
+ pseudo_lock_minor_release(new_minor);
+out_cstates:
+ pseudo_lock_cstates_relax(plr);
+out_region:
+ pseudo_lock_region_clear(plr);
+out:
+ return ret;
+}
+
+/**
+ * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
+ * @rdtgrp: resource group to which the pseudo-locked region belongs
+ *
+ * The removal of a pseudo-locked region can be initiated when the resource
+ * group is removed from user space via a "rmdir" from userspace or the
+ * unmount of the resctrl filesystem. On removal the resource group does
+ * not go back to pseudo-locksetup mode before it is removed, instead it is
+ * removed directly. There is thus assymmetry with the creation where the
+ * &struct pseudo_lock_region is removed here while it was not created in
+ * rdtgroup_pseudo_lock_create().
+ *
+ * Return: void
+ */
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
+{
+ struct pseudo_lock_region *plr = rdtgrp->plr;
+
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ /*
+ * Default group cannot be a pseudo-locked region so we can
+ * free closid here.
+ */
+ closid_free(rdtgrp->closid);
+ goto free;
+ }
+
+ pseudo_lock_cstates_relax(plr);
+ debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
+ device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+ pseudo_lock_minor_release(plr->minor);
+
+free:
+ pseudo_lock_free(rdtgrp);
+}
+
+static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
+{
+ struct rdtgroup *rdtgrp;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ rdtgrp = region_find_by_minor(iminor(inode));
+ if (!rdtgrp) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENODEV;
+ }
+
+ filp->private_data = rdtgrp;
+ atomic_inc(&rdtgrp->waitcount);
+ /* Perform a non-seekable open - llseek is not supported */
+ filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+ mutex_unlock(&rdtgroup_mutex);
+
+ return 0;
+}
+
+static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
+{
+ struct rdtgroup *rdtgrp;
+
+ mutex_lock(&rdtgroup_mutex);
+ rdtgrp = filp->private_data;
+ WARN_ON(!rdtgrp);
+ if (!rdtgrp) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENODEV;
+ }
+ filp->private_data = NULL;
+ atomic_dec(&rdtgrp->waitcount);
+ mutex_unlock(&rdtgroup_mutex);
+ return 0;
+}
+
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+{
+ /* Not supported */
+ return -EINVAL;
+}
+
+static const struct vm_operations_struct pseudo_mmap_ops = {
+ .mremap = pseudo_lock_dev_mremap,
+};
+
+static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ unsigned long vsize = vma->vm_end - vma->vm_start;
+ unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+ struct pseudo_lock_region *plr;
+ struct rdtgroup *rdtgrp;
+ unsigned long physical;
+ unsigned long psize;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ rdtgrp = filp->private_data;
+ WARN_ON(!rdtgrp);
+ if (!rdtgrp) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENODEV;
+ }
+
+ plr = rdtgrp->plr;
+
+ /*
+ * Task is required to run with affinity to the cpus associated
+ * with the pseudo-locked region. If this is not the case the task
+ * may be scheduled elsewhere and invalidate entries in the
+ * pseudo-locked region.
+ */
+ if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -EINVAL;
+ }
+
+ physical = __pa(plr->kmem) >> PAGE_SHIFT;
+ psize = plr->size - off;
+
+ if (off > plr->size) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENOSPC;
+ }
+
+ /*
+ * Ensure changes are carried directly to the memory being mapped,
+ * do not allow copy-on-write mapping.
+ */
+ if (!(vma->vm_flags & VM_SHARED)) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -EINVAL;
+ }
+
+ if (vsize > psize) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENOSPC;
+ }
+
+ memset(plr->kmem + off, 0, vsize);
+
+ if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
+ vsize, vma->vm_page_prot)) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -EAGAIN;
+ }
+ vma->vm_ops = &pseudo_mmap_ops;
+ mutex_unlock(&rdtgroup_mutex);
+ return 0;
+}
+
+static const struct file_operations pseudo_lock_dev_fops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .read = NULL,
+ .write = NULL,
+ .open = pseudo_lock_dev_open,
+ .release = pseudo_lock_dev_release,
+ .mmap = pseudo_lock_dev_mmap,
+};
+
+static char *pseudo_lock_devnode(struct device *dev, umode_t *mode)
+{
+ struct rdtgroup *rdtgrp;
+
+ rdtgrp = dev_get_drvdata(dev);
+ if (mode)
+ *mode = 0600;
+ return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+}
+
+int rdt_pseudo_lock_init(void)
+{
+ int ret;
+
+ ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
+ if (ret < 0)
+ return ret;
+
+ pseudo_lock_major = ret;
+
+ pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock");
+ if (IS_ERR(pseudo_lock_class)) {
+ ret = PTR_ERR(pseudo_lock_class);
+ unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+ return ret;
+ }
+
+ pseudo_lock_class->devnode = pseudo_lock_devnode;
+ return 0;
+}
+
+void rdt_pseudo_lock_release(void)
+{
+ class_destroy(pseudo_lock_class);
+ pseudo_lock_class = NULL;
+ unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+ pseudo_lock_major = 0;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PSEUDO_LOCK_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pseudo_lock_mem_latency,
+ TP_PROTO(u32 latency),
+ TP_ARGS(latency),
+ TP_STRUCT__entry(__field(u32, latency)),
+ TP_fast_assign(__entry->latency = latency),
+ TP_printk("latency=%u", __entry->latency)
+ );
+
+TRACE_EVENT(pseudo_lock_l2,
+ TP_PROTO(u64 l2_hits, u64 l2_miss),
+ TP_ARGS(l2_hits, l2_miss),
+ TP_STRUCT__entry(__field(u64, l2_hits)
+ __field(u64, l2_miss)),
+ TP_fast_assign(__entry->l2_hits = l2_hits;
+ __entry->l2_miss = l2_miss;),
+ TP_printk("hits=%llu miss=%llu",
+ __entry->l2_hits, __entry->l2_miss));
+
+TRACE_EVENT(pseudo_lock_l3,
+ TP_PROTO(u64 l3_hits, u64 l3_miss),
+ TP_ARGS(l3_hits, l3_miss),
+ TP_STRUCT__entry(__field(u64, l3_hits)
+ __field(u64, l3_miss)),
+ TP_fast_assign(__entry->l3_hits = l3_hits;
+ __entry->l3_miss = l3_miss;),
+ TP_printk("hits=%llu miss=%llu",
+ __entry->l3_hits, __entry->l3_miss));
+
+#endif /* _TRACE_PSEUDO_LOCK_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#include <trace/define_trace.h>
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/cacheinfo.h>
#include <linux/cpu.h>
+#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];
+struct dentry *debugfs_resctrl;
+
void rdt_last_cmd_clear(void)
{
lockdep_assert_held(&rdtgroup_mutex);
return closid;
}
-static void closid_free(int closid)
+void closid_free(int closid)
{
closid_free_map |= 1 << closid;
}
+/**
+ * closid_allocated - test if provided closid is in use
+ * @closid: closid to be tested
+ *
+ * Return: true if @closid is currently associated with a resource group,
+ * false if @closid is free
+ */
+static bool closid_allocated(unsigned int closid)
+{
+ return (closid_free_map & (1 << closid)) == 0;
+}
+
+/**
+ * rdtgroup_mode_by_closid - Return mode of resource group with closid
+ * @closid: closid if the resource group
+ *
+ * Each resource group is associated with a @closid. Here the mode
+ * of a resource group can be queried by searching for it using its closid.
+ *
+ * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
+ */
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+{
+ struct rdtgroup *rdtgrp;
+
+ list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+ if (rdtgrp->closid == closid)
+ return rdtgrp->mode;
+ }
+
+ return RDT_NUM_MODES;
+}
+
+static const char * const rdt_mode_str[] = {
+ [RDT_MODE_SHAREABLE] = "shareable",
+ [RDT_MODE_EXCLUSIVE] = "exclusive",
+ [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup",
+ [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked",
+};
+
+/**
+ * rdtgroup_mode_str - Return the string representation of mode
+ * @mode: the resource group mode as &enum rdtgroup_mode
+ *
+ * Return: string representation of valid mode, "unknown" otherwise
+ */
+static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+{
+ if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
+ return "unknown";
+
+ return rdt_mode_str[mode];
+}
+
/* set uid and gid of rdtgroup dirs and files to that of the creator */
static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
{
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
- seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
- cpumask_pr_args(&rdtgrp->cpu_mask));
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+ seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+ cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
+ else
+ seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+ cpumask_pr_args(&rdtgrp->cpu_mask));
} else {
ret = -ENOENT;
}
goto unlock;
}
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ ret = -EINVAL;
+ rdt_last_cmd_puts("pseudo-locking in progress\n");
+ goto unlock;
+ }
+
if (is_cpu_list(of))
ret = cpulist_parse(buf, newmask);
else
return ret;
}
+/**
+ * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
+ * @r: Resource group
+ *
+ * Return: 1 if tasks have been assigned to @r, 0 otherwise
+ */
+int rdtgroup_tasks_assigned(struct rdtgroup *r)
+{
+ struct task_struct *p, *t;
+ int ret = 0;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ rcu_read_lock();
+ for_each_process_thread(p, t) {
+ if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
+ (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+ ret = 1;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
static int rdtgroup_task_write_permission(struct task_struct *task,
struct kernfs_open_file *of)
{
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (!rdtgrp) {
+ rdtgroup_kn_unlock(of->kn);
+ return -ENOENT;
+ }
rdt_last_cmd_clear();
- if (rdtgrp)
- ret = rdtgroup_move_task(pid, rdtgrp, of);
- else
- ret = -ENOENT;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ ret = -EINVAL;
+ rdt_last_cmd_puts("pseudo-locking in progress\n");
+ goto unlock;
+ }
+ ret = rdtgroup_move_task(pid, rdtgrp, of);
+
+unlock:
rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
return 0;
}
+/**
+ * rdt_bit_usage_show - Display current usage of resources
+ *
+ * A domain is a shared resource that can now be allocated differently. Here
+ * we display the current regions of the domain as an annotated bitmask.
+ * For each domain of this resource its allocation bitmask
+ * is annotated as below to indicate the current usage of the corresponding bit:
+ * 0 - currently unused
+ * X - currently available for sharing and used by software and hardware
+ * H - currently used by hardware only but available for software use
+ * S - currently used and shareable by software only
+ * E - currently used exclusively by one resource group
+ * P - currently pseudo-locked by one resource group
+ */
+static int rdt_bit_usage_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+ u32 sw_shareable = 0, hw_shareable = 0;
+ u32 exclusive = 0, pseudo_locked = 0;
+ struct rdt_domain *dom;
+ int i, hwb, swb, excl, psl;
+ enum rdtgrp_mode mode;
+ bool sep = false;
+ u32 *ctrl;
+
+ mutex_lock(&rdtgroup_mutex);
+ hw_shareable = r->cache.shareable_bits;
+ list_for_each_entry(dom, &r->domains, list) {
+ if (sep)
+ seq_putc(seq, ';');
+ ctrl = dom->ctrl_val;
+ sw_shareable = 0;
+ exclusive = 0;
+ seq_printf(seq, "%d=", dom->id);
+ for (i = 0; i < r->num_closid; i++, ctrl++) {
+ if (!closid_allocated(i))
+ continue;
+ mode = rdtgroup_mode_by_closid(i);
+ switch (mode) {
+ case RDT_MODE_SHAREABLE:
+ sw_shareable |= *ctrl;
+ break;
+ case RDT_MODE_EXCLUSIVE:
+ exclusive |= *ctrl;
+ break;
+ case RDT_MODE_PSEUDO_LOCKSETUP:
+ /*
+ * RDT_MODE_PSEUDO_LOCKSETUP is possible
+ * here but not included since the CBM
+ * associated with this CLOSID in this mode
+ * is not initialized and no task or cpu can be
+ * assigned this CLOSID.
+ */
+ break;
+ case RDT_MODE_PSEUDO_LOCKED:
+ case RDT_NUM_MODES:
+ WARN(1,
+ "invalid mode for closid %d\n", i);
+ break;
+ }
+ }
+ for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+ pseudo_locked = dom->plr ? dom->plr->cbm : 0;
+ hwb = test_bit(i, (unsigned long *)&hw_shareable);
+ swb = test_bit(i, (unsigned long *)&sw_shareable);
+ excl = test_bit(i, (unsigned long *)&exclusive);
+ psl = test_bit(i, (unsigned long *)&pseudo_locked);
+ if (hwb && swb)
+ seq_putc(seq, 'X');
+ else if (hwb && !swb)
+ seq_putc(seq, 'H');
+ else if (!hwb && swb)
+ seq_putc(seq, 'S');
+ else if (excl)
+ seq_putc(seq, 'E');
+ else if (psl)
+ seq_putc(seq, 'P');
+ else /* Unused bits remain */
+ seq_putc(seq, '0');
+ }
+ sep = true;
+ }
+ seq_putc(seq, '\n');
+ mutex_unlock(&rdtgroup_mutex);
+ return 0;
+}
+
static int rdt_min_bw_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
return nbytes;
}
+/*
+ * rdtgroup_mode_show - Display mode of this resource group
+ */
+static int rdtgroup_mode_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (!rdtgrp) {
+ rdtgroup_kn_unlock(of->kn);
+ return -ENOENT;
+ }
+
+ seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
+
+ rdtgroup_kn_unlock(of->kn);
+ return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Checks if provided @cbm intended to be used for @closid on domain
+ * @d overlaps with any other closids or other hardware usage associated
+ * with this domain. If @exclusive is true then only overlaps with
+ * resource groups in exclusive mode will be considered. If @exclusive
+ * is false then overlaps with any resource group or hardware entities
+ * will be considered.
+ *
+ * Return: false if CBM does not overlap, true if it does.
+ */
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+ u32 _cbm, int closid, bool exclusive)
+{
+ unsigned long *cbm = (unsigned long *)&_cbm;
+ unsigned long *ctrl_b;
+ enum rdtgrp_mode mode;
+ u32 *ctrl;
+ int i;
+
+ /* Check for any overlap with regions used by hardware directly */
+ if (!exclusive) {
+ if (bitmap_intersects(cbm,
+ (unsigned long *)&r->cache.shareable_bits,
+ r->cache.cbm_len))
+ return true;
+ }
+
+ /* Check for overlap with other resource groups */
+ ctrl = d->ctrl_val;
+ for (i = 0; i < r->num_closid; i++, ctrl++) {
+ ctrl_b = (unsigned long *)ctrl;
+ mode = rdtgroup_mode_by_closid(i);
+ if (closid_allocated(i) && i != closid &&
+ mode != RDT_MODE_PSEUDO_LOCKSETUP) {
+ if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+ if (exclusive) {
+ if (mode == RDT_MODE_EXCLUSIVE)
+ return true;
+ continue;
+ }
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+
+/**
+ * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ *
+ * An exclusive resource group implies that there should be no sharing of
+ * its allocated resources. At the time this group is considered to be
+ * exclusive this test can determine if its current schemata supports this
+ * setting by testing for overlap with all other resource groups.
+ *
+ * Return: true if resource group can be exclusive, false if there is overlap
+ * with allocations of other resource groups and thus this resource group
+ * cannot be exclusive.
+ */
+static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
+{
+ int closid = rdtgrp->closid;
+ struct rdt_resource *r;
+ struct rdt_domain *d;
+
+ for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(d, &r->domains, list) {
+ if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
+ rdtgrp->closid, false))
+ return false;
+ }
+ }
+
+ return true;
+}
+
+/**
+ * rdtgroup_mode_write - Modify the resource group's mode
+ *
+ */
+static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct rdtgroup *rdtgrp;
+ enum rdtgrp_mode mode;
+ int ret = 0;
+
+ /* Valid input requires a trailing newline */
+ if (nbytes == 0 || buf[nbytes - 1] != '\n')
+ return -EINVAL;
+ buf[nbytes - 1] = '\0';
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (!rdtgrp) {
+ rdtgroup_kn_unlock(of->kn);
+ return -ENOENT;
+ }
+
+ rdt_last_cmd_clear();
+
+ mode = rdtgrp->mode;
+
+ if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
+ (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
+ (!strcmp(buf, "pseudo-locksetup") &&
+ mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
+ (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
+ goto out;
+
+ if (mode == RDT_MODE_PSEUDO_LOCKED) {
+ rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!strcmp(buf, "shareable")) {
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ ret = rdtgroup_locksetup_exit(rdtgrp);
+ if (ret)
+ goto out;
+ }
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+ } else if (!strcmp(buf, "exclusive")) {
+ if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
+ rdt_last_cmd_printf("schemata overlaps\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ ret = rdtgroup_locksetup_exit(rdtgrp);
+ if (ret)
+ goto out;
+ }
+ rdtgrp->mode = RDT_MODE_EXCLUSIVE;
+ } else if (!strcmp(buf, "pseudo-locksetup")) {
+ ret = rdtgroup_locksetup_enter(rdtgrp);
+ if (ret)
+ goto out;
+ rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
+ } else {
+ rdt_last_cmd_printf("unknown/unsupported mode\n");
+ ret = -EINVAL;
+ }
+
+out:
+ rdtgroup_kn_unlock(of->kn);
+ return ret ?: nbytes;
+}
+
+/**
+ * rdtgroup_cbm_to_size - Translate CBM to size in bytes
+ * @r: RDT resource to which @d belongs.
+ * @d: RDT domain instance.
+ * @cbm: bitmask for which the size should be computed.
+ *
+ * The bitmask provided associated with the RDT domain instance @d will be
+ * translated into how many bytes it represents. The size in bytes is
+ * computed by first dividing the total cache size by the CBM length to
+ * determine how many bytes each bit in the bitmask represents. The result
+ * is multiplied with the number of bits set in the bitmask.
+ */
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
+ struct rdt_domain *d, u32 cbm)
+{
+ struct cpu_cacheinfo *ci;
+ unsigned int size = 0;
+ int num_b, i;
+
+ num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+ ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+ for (i = 0; i < ci->num_leaves; i++) {
+ if (ci->info_list[i].level == r->cache_level) {
+ size = ci->info_list[i].size / r->cache.cbm_len * num_b;
+ break;
+ }
+ }
+
+ return size;
+}
+
+/**
+ * rdtgroup_size_show - Display size in bytes of allocated regions
+ *
+ * The "size" file mirrors the layout of the "schemata" file, printing the
+ * size in bytes of each region instead of the capacity bitmask.
+ *
+ */
+static int rdtgroup_size_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ struct rdt_resource *r;
+ struct rdt_domain *d;
+ unsigned int size;
+ bool sep = false;
+ u32 cbm;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (!rdtgrp) {
+ rdtgroup_kn_unlock(of->kn);
+ return -ENOENT;
+ }
+
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
+ size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+ rdtgrp->plr->d,
+ rdtgrp->plr->cbm);
+ seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ goto out;
+ }
+
+ for_each_alloc_enabled_rdt_resource(r) {
+ seq_printf(s, "%*s:", max_name_width, r->name);
+ list_for_each_entry(d, &r->domains, list) {
+ if (sep)
+ seq_putc(s, ';');
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ size = 0;
+ } else {
+ cbm = d->ctrl_val[rdtgrp->closid];
+ size = rdtgroup_cbm_to_size(r, d, cbm);
+ }
+ seq_printf(s, "%d=%u", d->id, size);
+ sep = true;
+ }
+ seq_putc(s, '\n');
+ }
+
+out:
+ rdtgroup_kn_unlock(of->kn);
+
+ return 0;
+}
+
/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
{
.seq_show = rdt_shareable_bits_show,
.fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
},
+ {
+ .name = "bit_usage",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdt_bit_usage_show,
+ .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ },
{
.name = "min_bandwidth",
.mode = 0444,
.seq_show = rdtgroup_schemata_show,
.fflags = RF_CTRL_BASE,
},
+ {
+ .name = "mode",
+ .mode = 0644,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .write = rdtgroup_mode_write,
+ .seq_show = rdtgroup_mode_show,
+ .fflags = RF_CTRL_BASE,
+ },
+ {
+ .name = "size",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdtgroup_size_show,
+ .fflags = RF_CTRL_BASE,
+ },
+
};
static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
return ret;
}
+/**
+ * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * The permissions of named resctrl file, directory, or link are modified
+ * to not allow read, write, or execute by any user.
+ *
+ * WARNING: This function is intended to communicate to the user that the
+ * resctrl file has been locked down - that it is not relevant to the
+ * particular state the system finds itself in. It should not be relied
+ * on to protect from user access because after the file's permissions
+ * are restricted the user can still change the permissions using chmod
+ * from the command line.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
+{
+ struct iattr iattr = {.ia_valid = ATTR_MODE,};
+ struct kernfs_node *kn;
+ int ret = 0;
+
+ kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+ if (!kn)
+ return -ENOENT;
+
+ switch (kernfs_type(kn)) {
+ case KERNFS_DIR:
+ iattr.ia_mode = S_IFDIR;
+ break;
+ case KERNFS_FILE:
+ iattr.ia_mode = S_IFREG;
+ break;
+ case KERNFS_LINK:
+ iattr.ia_mode = S_IFLNK;
+ break;
+ }
+
+ ret = kernfs_setattr(kn, &iattr);
+ kernfs_put(kn);
+ return ret;
+}
+
+/**
+ * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ * @mask: Mask of permissions that should be restored
+ *
+ * Restore the permissions of the named file. If @name is a directory the
+ * permissions of its parent will be used.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+ umode_t mask)
+{
+ struct iattr iattr = {.ia_valid = ATTR_MODE,};
+ struct kernfs_node *kn, *parent;
+ struct rftype *rfts, *rft;
+ int ret, len;
+
+ rfts = res_common_files;
+ len = ARRAY_SIZE(res_common_files);
+
+ for (rft = rfts; rft < rfts + len; rft++) {
+ if (!strcmp(rft->name, name))
+ iattr.ia_mode = rft->mode & mask;
+ }
+
+ kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+ if (!kn)
+ return -ENOENT;
+
+ switch (kernfs_type(kn)) {
+ case KERNFS_DIR:
+ parent = kernfs_get_parent(kn);
+ if (parent) {
+ iattr.ia_mode |= parent->mode;
+ kernfs_put(parent);
+ }
+ iattr.ia_mode |= S_IFDIR;
+ break;
+ case KERNFS_FILE:
+ iattr.ia_mode |= S_IFREG;
+ break;
+ case KERNFS_LINK:
+ iattr.ia_mode |= S_IFLNK;
+ break;
+ }
+
+ ret = kernfs_setattr(kn, &iattr);
+ kernfs_put(kn);
+ return ret;
+}
+
static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
unsigned long fflags)
{
if (atomic_dec_and_test(&rdtgrp->waitcount) &&
(rdtgrp->flags & RDT_DELETED)) {
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+ rdtgroup_pseudo_lock_remove(rdtgrp);
kernfs_unbreak_active_protection(kn);
kernfs_put(rdtgrp->kn);
kfree(rdtgrp);
rdtgroup_default.mon.mon_data_kn = kn_mondata;
}
+ ret = rdt_pseudo_lock_init();
+ if (ret) {
+ dentry = ERR_PTR(ret);
+ goto out_mondata;
+ }
+
dentry = kernfs_mount(fs_type, flags, rdt_root,
RDTGROUP_SUPER_MAGIC, NULL);
if (IS_ERR(dentry))
- goto out_mondata;
+ goto out_psl;
if (rdt_alloc_capable)
static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
goto out;
+out_psl:
+ rdt_pseudo_lock_release();
out_mondata:
if (rdt_mon_capable)
kernfs_remove(kn_mondata);
if (rdtgrp == &rdtgroup_default)
continue;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+ rdtgroup_pseudo_lock_remove(rdtgrp);
+
/*
* Give any CPUs back to the default group. We cannot copy
* cpu_online_mask because a CPU might have executed the
reset_all_ctrls(r);
cdp_disable_all();
rmdir_all_sub();
+ rdt_pseudo_lock_release();
+ rdtgroup_default.mode = RDT_MODE_SHAREABLE;
static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
static_branch_disable_cpuslocked(&rdt_mon_enable_key);
static_branch_disable_cpuslocked(&rdt_enable_key);
return ret;
}
+/**
+ * cbm_ensure_valid - Enforce validity on provided CBM
+ * @_val: Candidate CBM
+ * @r: RDT resource to which the CBM belongs
+ *
+ * The provided CBM represents all cache portions available for use. This
+ * may be represented by a bitmap that does not consist of contiguous ones
+ * and thus be an invalid CBM.
+ * Here the provided CBM is forced to be a valid CBM by only considering
+ * the first set of contiguous bits as valid and clearing all bits.
+ * The intention here is to provide a valid default CBM with which a new
+ * resource group is initialized. The user can follow this with a
+ * modification to the CBM if the default does not satisfy the
+ * requirements.
+ */
+static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
+{
+ /*
+ * Convert the u32 _val to an unsigned long required by all the bit
+ * operations within this function. No more than 32 bits of this
+ * converted value can be accessed because all bit operations are
+ * additionally provided with cbm_len that is initialized during
+ * hardware enumeration using five bits from the EAX register and
+ * thus never can exceed 32 bits.
+ */
+ unsigned long *val = (unsigned long *)_val;
+ unsigned int cbm_len = r->cache.cbm_len;
+ unsigned long first_bit, zero_bit;
+
+ if (*val == 0)
+ return;
+
+ first_bit = find_first_bit(val, cbm_len);
+ zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+
+ /* Clear any remaining bits to ensure contiguous region */
+ bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+}
+
+/**
+ * rdtgroup_init_alloc - Initialize the new RDT group's allocations
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations. That is, all shareable and unused bits.
+ *
+ * All-zero CBM is invalid. If there are no more shareable bits available
+ * on any domain then the entire allocation will fail.
+ */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+ u32 used_b = 0, unused_b = 0;
+ u32 closid = rdtgrp->closid;
+ struct rdt_resource *r;
+ enum rdtgrp_mode mode;
+ struct rdt_domain *d;
+ int i, ret;
+ u32 *ctrl;
+
+ for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(d, &r->domains, list) {
+ d->have_new_ctrl = false;
+ d->new_ctrl = r->cache.shareable_bits;
+ used_b = r->cache.shareable_bits;
+ ctrl = d->ctrl_val;
+ for (i = 0; i < r->num_closid; i++, ctrl++) {
+ if (closid_allocated(i) && i != closid) {
+ mode = rdtgroup_mode_by_closid(i);
+ if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+ break;
+ used_b |= *ctrl;
+ if (mode == RDT_MODE_SHAREABLE)
+ d->new_ctrl |= *ctrl;
+ }
+ }
+ if (d->plr && d->plr->cbm > 0)
+ used_b |= d->plr->cbm;
+ unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+ unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+ d->new_ctrl |= unused_b;
+ /*
+ * Force the initial CBM to be valid, user can
+ * modify the CBM based on system availability.
+ */
+ cbm_ensure_valid(&d->new_ctrl, r);
+ if (bitmap_weight((unsigned long *) &d->new_ctrl,
+ r->cache.cbm_len) <
+ r->cache.min_cbm_bits) {
+ rdt_last_cmd_printf("no space on %s:%d\n",
+ r->name, d->id);
+ return -ENOSPC;
+ }
+ d->have_new_ctrl = true;
+ }
+ }
+
+ for_each_alloc_enabled_rdt_resource(r) {
+ ret = update_domains(r, rdtgrp->closid);
+ if (ret < 0) {
+ rdt_last_cmd_puts("failed to initialize allocations\n");
+ return ret;
+ }
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+ }
+
+ return 0;
+}
+
static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
struct kernfs_node *prgrp_kn,
const char *name, umode_t mode,
goto out_unlock;
}
+ if (rtype == RDTMON_GROUP &&
+ (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+ prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
+ ret = -EINVAL;
+ rdt_last_cmd_puts("pseudo-locking in progress\n");
+ goto out_unlock;
+ }
+
/* allocate the rdtgroup. */
rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
if (!rdtgrp) {
ret = 0;
rdtgrp->closid = closid;
+ ret = rdtgroup_init_alloc(rdtgrp);
+ if (ret < 0)
+ goto out_id_free;
+
list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
if (rdt_mon_capable) {
ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
if (ret) {
rdt_last_cmd_puts("kernfs subdir error\n");
- goto out_id_free;
+ goto out_del_list;
}
}
goto out_unlock;
+out_del_list:
+ list_del(&rdtgrp->rdtgroup_list);
out_id_free:
closid_free(closid);
- list_del(&rdtgrp->rdtgroup_list);
out_common_fail:
mkdir_rdt_prepare_clean(rdtgrp);
out_unlock:
return 0;
}
+static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
+ struct rdtgroup *rdtgrp)
+{
+ rdtgrp->flags = RDT_DELETED;
+ list_del(&rdtgrp->rdtgroup_list);
+
+ /*
+ * one extra hold on this, will drop when we kfree(rdtgrp)
+ * in rdtgroup_kn_unlock()
+ */
+ kernfs_get(kn);
+ kernfs_remove(rdtgrp->kn);
+ return 0;
+}
+
static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
cpumask_var_t tmpmask)
{
cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
update_closid_rmid(tmpmask, NULL);
- rdtgrp->flags = RDT_DELETED;
closid_free(rdtgrp->closid);
free_rmid(rdtgrp->mon.rmid);
*/
free_all_child_rdtgrp(rdtgrp);
- list_del(&rdtgrp->rdtgroup_list);
-
- /*
- * one extra hold on this, will drop when we kfree(rdtgrp)
- * in rdtgroup_kn_unlock()
- */
- kernfs_get(kn);
- kernfs_remove(rdtgrp->kn);
+ rdtgroup_ctrl_remove(kn, rdtgrp);
return 0;
}
* If the rdtgroup is a mon group and parent directory
* is a valid "mon_groups" directory, remove the mon group.
*/
- if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
- ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
- else if (rdtgrp->type == RDTMON_GROUP &&
- is_mon_groups(parent_kn, kn->name))
+ if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+ rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ ret = rdtgroup_ctrl_remove(kn, rdtgrp);
+ } else {
+ ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+ }
+ } else if (rdtgrp->type == RDTMON_GROUP &&
+ is_mon_groups(parent_kn, kn->name)) {
ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
- else
+ } else {
ret = -EPERM;
+ }
out:
rdtgroup_kn_unlock(kn);
int ret;
rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
- KERNFS_ROOT_CREATE_DEACTIVATED,
+ KERNFS_ROOT_CREATE_DEACTIVATED |
+ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
&rdtgroup_default);
if (IS_ERR(rdt_root))
return PTR_ERR(rdt_root);
if (ret)
goto cleanup_mountpoint;
+ /*
+ * Adding the resctrl debugfs directory here may not be ideal since
+ * it would let the resctrl debugfs directory appear on the debugfs
+ * filesystem before the resctrl filesystem is mounted.
+ * It may also be ok since that would enable debugging of RDT before
+ * resctrl is mounted.
+ * The reason why the debugfs directory is created here and not in
+ * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+ * during the debugfs directory creation also &sb->s_type->i_mutex_key
+ * (the lockdep class of inode->i_rwsem). Other filesystem
+ * interactions (eg. SyS_getdents) have the lock ordering:
+ * &sb->s_type->i_mutex_key --> &mm->mmap_sem
+ * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex
+ * is taken, thus creating dependency:
+ * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause
+ * issues considering the other two lock dependencies.
+ * By creating the debugfs directory here we avoid a dependency
+ * that may cause deadlock (even though file operations cannot
+ * occur until the filesystem is mounted, but I do not know how to
+ * tell lockdep that).
+ */
+ debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
+
return 0;
cleanup_mountpoint:
return ret;
}
+
+void __exit rdtgroup_exit(void)
+{
+ debugfs_remove_recursive(debugfs_resctrl);
+ unregister_filesystem(&rdt_fs_type);
+ sysfs_remove_mount_point(fs_kobj, "resctrl");
+ kernfs_destroy_root(rdt_root);
+}
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
USER
),
+ MCESEV(
+ PANIC, "Data load in unrecoverable area of kernel",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+ KERNEL
+ ),
#endif
MCESEV(
PANIC, "Action required: unknown MCACOD",
{
memset(m, 0, sizeof(struct mce));
m->cpu = m->extcpu = smp_processor_id();
- /* We hope get_seconds stays lockless */
- m->time = get_seconds();
+ /* need the internal __ version to avoid deadlocks */
+ m->time = __ktime_get_real_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
m->cpuid = cpuid_eax(1);
m->socketid = cpu_data(m->extcpu).phys_proc_id;
static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
- int i, ret = 0;
char *tmp;
+ int i;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(msr_ops.status(i));
- if (m->status & MCI_STATUS_VAL) {
- __set_bit(i, validp);
- if (quirk_no_way_out)
- quirk_no_way_out(i, m, regs);
- }
+ if (!(m->status & MCI_STATUS_VAL))
+ continue;
+
+ __set_bit(i, validp);
+ if (quirk_no_way_out)
+ quirk_no_way_out(i, m, regs);
if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ mce_read_aux(m, i);
*msg = tmp;
- ret = 1;
+ return 1;
}
}
- return ret;
+ return 0;
}
/*
}
#endif
+
+/*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ * skip those CPUs which remain looping in the 1st kernel - see
+ * crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+static bool __mc_check_crashing_cpu(int cpu)
+{
+ if (cpu_is_offline(cpu) ||
+ (crashing_cpu != -1 && crashing_cpu != cpu)) {
+ u64 mcgstatus;
+
+ mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+ if (mcgstatus & MCG_STATUS_RIPV) {
+ mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+ return true;
+ }
+ }
+ return false;
+}
+
+static void __mc_scan_banks(struct mce *m, struct mce *final,
+ unsigned long *toclear, unsigned long *valid_banks,
+ int no_way_out, int *worst)
+{
+ struct mca_config *cfg = &mca_cfg;
+ int severity, i;
+
+ for (i = 0; i < cfg->banks; i++) {
+ __clear_bit(i, toclear);
+ if (!test_bit(i, valid_banks))
+ continue;
+
+ if (!mce_banks[i].ctl)
+ continue;
+
+ m->misc = 0;
+ m->addr = 0;
+ m->bank = i;
+
+ m->status = mce_rdmsrl(msr_ops.status(i));
+ if (!(m->status & MCI_STATUS_VAL))
+ continue;
+
+ /*
+ * Corrected or non-signaled errors are handled by
+ * machine_check_poll(). Leave them alone, unless this panics.
+ */
+ if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+ !no_way_out)
+ continue;
+
+ /* Set taint even when machine check was not enabled. */
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+ severity = mce_severity(m, cfg->tolerant, NULL, true);
+
+ /*
+ * When machine check was for corrected/deferred handler don't
+ * touch, unless we're panicking.
+ */
+ if ((severity == MCE_KEEP_SEVERITY ||
+ severity == MCE_UCNA_SEVERITY) && !no_way_out)
+ continue;
+
+ __set_bit(i, toclear);
+
+ /* Machine check event was not enabled. Clear, but ignore. */
+ if (severity == MCE_NO_SEVERITY)
+ continue;
+
+ mce_read_aux(m, i);
+
+ /* assuming valid severity level != 0 */
+ m->severity = severity;
+
+ mce_log(m);
+
+ if (severity > *worst) {
+ *final = *m;
+ *worst = severity;
+ }
+ }
+
+ /* mce_clear_state will clear *final, save locally for use later */
+ *m = *final;
+}
+
/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
*/
void do_machine_check(struct pt_regs *regs, long error_code)
{
+ DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
+ DECLARE_BITMAP(toclear, MAX_NR_BANKS);
struct mca_config *cfg = &mca_cfg;
+ int cpu = smp_processor_id();
+ char *msg = "Unknown";
struct mce m, *final;
- int i;
int worst = 0;
- int severity;
/*
* Establish sequential order between the CPUs entering the machine
* check handler.
*/
int order = -1;
+
/*
* If no_way_out gets set, there is no safe way to recover from this
* MCE. If mca_cfg.tolerant is cranked up, we'll try anyway.
*/
int no_way_out = 0;
+
/*
* If kill_it gets set, there might be a way to recover from this
* error.
*/
int kill_it = 0;
- DECLARE_BITMAP(toclear, MAX_NR_BANKS);
- DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
- char *msg = "Unknown";
/*
* MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
* on Intel.
*/
int lmce = 1;
- int cpu = smp_processor_id();
-
- /*
- * Cases where we avoid rendezvous handler timeout:
- * 1) If this CPU is offline.
- *
- * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
- * skip those CPUs which remain looping in the 1st kernel - see
- * crash_nmi_callback().
- *
- * Note: there still is a small window between kexec-ing and the new,
- * kdump kernel establishing a new #MC handler where a broadcasted MCE
- * might not get handled properly.
- */
- if (cpu_is_offline(cpu) ||
- (crashing_cpu != -1 && crashing_cpu != cpu)) {
- u64 mcgstatus;
- mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
- if (mcgstatus & MCG_STATUS_RIPV) {
- mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
- return;
- }
- }
+ if (__mc_check_crashing_cpu(cpu))
+ return;
ist_enter(regs);
this_cpu_inc(mce_exception_count);
- if (!cfg->banks)
- goto out;
-
mce_gather_info(&m, regs);
m.tsc = rdtsc();
lmce = m.mcgstatus & MCG_STATUS_LMCES;
/*
+ * Local machine check may already know that we have to panic.
+ * Broadcast machine check begins rendezvous in mce_start()
* Go through all banks in exclusion of the other CPUs. This way we
* don't report duplicated events on shared banks because the first one
- * to see it will clear it. If this is a Local MCE, then no need to
- * perform rendezvous.
+ * to see it will clear it.
*/
- if (!lmce)
+ if (lmce) {
+ if (no_way_out)
+ mce_panic("Fatal local machine check", &m, msg);
+ } else {
order = mce_start(&no_way_out);
-
- for (i = 0; i < cfg->banks; i++) {
- __clear_bit(i, toclear);
- if (!test_bit(i, valid_banks))
- continue;
- if (!mce_banks[i].ctl)
- continue;
-
- m.misc = 0;
- m.addr = 0;
- m.bank = i;
-
- m.status = mce_rdmsrl(msr_ops.status(i));
- if ((m.status & MCI_STATUS_VAL) == 0)
- continue;
-
- /*
- * Non uncorrected or non signaled errors are handled by
- * machine_check_poll. Leave them alone, unless this panics.
- */
- if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
- !no_way_out)
- continue;
-
- /*
- * Set taint even when machine check was not enabled.
- */
- add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
- severity = mce_severity(&m, cfg->tolerant, NULL, true);
-
- /*
- * When machine check was for corrected/deferred handler don't
- * touch, unless we're panicing.
- */
- if ((severity == MCE_KEEP_SEVERITY ||
- severity == MCE_UCNA_SEVERITY) && !no_way_out)
- continue;
- __set_bit(i, toclear);
- if (severity == MCE_NO_SEVERITY) {
- /*
- * Machine check event was not enabled. Clear, but
- * ignore.
- */
- continue;
- }
-
- mce_read_aux(&m, i);
-
- /* assuming valid severity level != 0 */
- m.severity = severity;
-
- mce_log(&m);
-
- if (severity > worst) {
- *final = m;
- worst = severity;
- }
}
- /* mce_clear_state will clear *final, save locally for use later */
- m = *final;
+ __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst);
if (!no_way_out)
mce_clear_state(toclear);
no_way_out = worst >= MCE_PANIC_SEVERITY;
} else {
/*
- * Local MCE skipped calling mce_reign()
- * If we found a fatal error, we need to panic here.
+ * If there was a fatal machine check we should have
+ * already called mce_panic earlier in this function.
+ * Since we re-read the banks, we might have found
+ * something new. Check again to see if we found a
+ * fatal error. We call "mce_severity()" again to
+ * make sure we have the right "msg".
*/
- if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
- mce_panic("Machine check from unknown source",
- NULL, NULL);
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+ mce_severity(&m, cfg->tolerant, &msg, true);
+ mce_panic("Local fatal machine check!", &m, msg);
+ }
}
/*
if (worst > 0)
mce_report_event(regs);
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-out:
+
sync_core();
if (worst != MCE_AR_SEVERITY && !kill_it)
if (check_interval == old_check_interval)
return ret;
- if (check_interval < 1)
- check_interval = 1;
-
mutex_lock(&mce_sysfs_mutex);
mce_restart();
mutex_unlock(&mce_sysfs_mutex);
p = memdup_patch(data, size);
if (!p)
pr_err("Error allocating buffer %p\n", data);
- else
+ else {
list_replace(&iter->plist, &p->plist);
+ kfree(iter->data);
+ kfree(iter);
+ }
}
}
memset(line, 0, LINE_SIZE);
- length = strncpy_from_user(line, buf, LINE_SIZE - 1);
+ len = min_t(size_t, len, LINE_SIZE - 1);
+ length = strncpy_from_user(line, buf, len);
if (length < 0)
return length;
#include <asm/stacktrace.h>
#include <asm/unwind.h>
-#define OPCODE_BUFSIZE 64
-
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
static int die_counter;
*/
void show_opcodes(u8 *rip, const char *loglvl)
{
- unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+#define PROLOGUE_SIZE 42
+#define EPILOGUE_SIZE 21
+#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
u8 opcodes[OPCODE_BUFSIZE];
- u8 *ip;
- int i;
-
- printk("%sCode: ", loglvl);
-
- ip = (u8 *)rip - code_prologue;
- if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
- pr_cont("Bad RIP value.\n");
- return;
- }
- for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
- if (ip == rip)
- pr_cont("<%02x> ", opcodes[i]);
- else
- pr_cont("%02x ", opcodes[i]);
+ if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) {
+ printk("%sCode: Bad RIP value.\n", loglvl);
+ } else {
+ printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
+ __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
+ opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
}
- pr_cont("\n");
}
void show_ip(struct pt_regs *regs, const char *loglvl)
{
int i;
u64 end;
+ u64 addr = 0;
/*
* The bootstrap memblock region count maximum is 128 entries
struct e820_entry *entry = &e820_table->entries[i];
end = entry->addr + entry->size;
+ if (addr < entry->addr)
+ memblock_reserve(addr, entry->addr - addr);
+ addr = end;
if (end != (resource_size_t)end)
continue;
+ /*
+ * all !E820_TYPE_RAM ranges (including gap ranges) are put
+ * into memblock.reserved to make sure that struct pages in
+ * such regions are not left uninitialized after bootup.
+ */
if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
- continue;
-
- memblock_add(entry->addr, entry->size);
+ memblock_reserve(entry->addr, entry->size);
+ else
+ memblock_add(entry->addr, entry->size);
}
/* Throw away partial pages: */
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
#ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __initdata;
+unsigned int __pgtable_l5_enabled __ro_after_init;
unsigned int pgdir_shift __ro_after_init = 39;
EXPORT_SYMBOL(pgdir_shift);
unsigned int ptrs_per_p4d __ro_after_init = 1;
ENTRY(setup_once_ref)
.long setup_once
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#define PGD_ALIGN (2 * PAGE_SIZE)
+#define PTI_USER_PGD_FILL 1024
+#else
+#define PGD_ALIGN (PAGE_SIZE)
+#define PTI_USER_PGD_FILL 0
+#endif
/*
* BSS section
*/
__PAGE_ALIGNED_BSS
- .align PAGE_SIZE
+ .align PGD_ALIGN
#ifdef CONFIG_X86_PAE
.globl initial_pg_pmd
initial_pg_pmd:
initial_page_table:
.fill 1024,4,0
#endif
+ .align PGD_ALIGN
initial_pg_fixmap:
.fill 1024,4,0
-.globl empty_zero_page
-empty_zero_page:
- .fill 4096,1,0
.globl swapper_pg_dir
+ .align PGD_ALIGN
swapper_pg_dir:
.fill 1024,4,0
+ .fill PTI_USER_PGD_FILL,4,0
+.globl empty_zero_page
+empty_zero_page:
+ .fill 4096,1,0
EXPORT_SYMBOL(empty_zero_page)
/*
#ifdef CONFIG_X86_PAE
__PAGE_ALIGNED_DATA
/* Page-aligned for the benefit of paravirt? */
- .align PAGE_SIZE
+ .align PGD_ALIGN
ENTRY(initial_page_table)
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */
# if KPMDS == 3
* address given in m16:64.
*/
pushq $.Lafter_lret # put return address on stack for unwinder
- xorq %rbp, %rbp # clear frame pointer
+ xorl %ebp, %ebp # clear frame pointer
movq initial_code(%rip), %rax
pushq $__KERNEL_CS # set correct cs
pushq %rax # target address in negative space
set_dr_addr_mask(0, i);
}
-/*
- * Check for virtual address in kernel space.
- */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+static int arch_bp_generic_len(int x86_len)
{
- unsigned int len;
- unsigned long va;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
- va = info->address;
- len = bp->attr.bp_len;
-
- /*
- * We don't need to worry about va + len - 1 overflowing:
- * we already require that va is aligned to a multiple of len.
- */
- return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+ switch (x86_len) {
+ case X86_BREAKPOINT_LEN_1:
+ return HW_BREAKPOINT_LEN_1;
+ case X86_BREAKPOINT_LEN_2:
+ return HW_BREAKPOINT_LEN_2;
+ case X86_BREAKPOINT_LEN_4:
+ return HW_BREAKPOINT_LEN_4;
+#ifdef CONFIG_X86_64
+ case X86_BREAKPOINT_LEN_8:
+ return HW_BREAKPOINT_LEN_8;
+#endif
+ default:
+ return -EINVAL;
+ }
}
int arch_bp_generic_fields(int x86_len, int x86_type,
int *gen_len, int *gen_type)
{
+ int len;
+
/* Type */
switch (x86_type) {
case X86_BREAKPOINT_EXECUTE:
}
/* Len */
- switch (x86_len) {
- case X86_BREAKPOINT_LEN_1:
- *gen_len = HW_BREAKPOINT_LEN_1;
- break;
- case X86_BREAKPOINT_LEN_2:
- *gen_len = HW_BREAKPOINT_LEN_2;
- break;
- case X86_BREAKPOINT_LEN_4:
- *gen_len = HW_BREAKPOINT_LEN_4;
- break;
-#ifdef CONFIG_X86_64
- case X86_BREAKPOINT_LEN_8:
- *gen_len = HW_BREAKPOINT_LEN_8;
- break;
-#endif
- default:
+ len = arch_bp_generic_len(x86_len);
+ if (len < 0)
return -EINVAL;
- }
+ *gen_len = len;
return 0;
}
-
-static int arch_build_bp_info(struct perf_event *bp)
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+ unsigned long va;
+ int len;
- info->address = bp->attr.bp_addr;
+ va = hw->address;
+ len = arch_bp_generic_len(hw->len);
+ WARN_ON_ONCE(len < 0);
+
+ /*
+ * We don't need to worry about va + len - 1 overflowing:
+ * we already require that va is aligned to a multiple of len.
+ */
+ return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+}
+
+static int arch_build_bp_info(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
+{
+ hw->address = attr->bp_addr;
+ hw->mask = 0;
/* Type */
- switch (bp->attr.bp_type) {
+ switch (attr->bp_type) {
case HW_BREAKPOINT_W:
- info->type = X86_BREAKPOINT_WRITE;
+ hw->type = X86_BREAKPOINT_WRITE;
break;
case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
- info->type = X86_BREAKPOINT_RW;
+ hw->type = X86_BREAKPOINT_RW;
break;
case HW_BREAKPOINT_X:
/*
* acceptable for kprobes. On non-kprobes kernels, we don't
* allow kernel breakpoints at all.
*/
- if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+ if (attr->bp_addr >= TASK_SIZE_MAX) {
#ifdef CONFIG_KPROBES
- if (within_kprobe_blacklist(bp->attr.bp_addr))
+ if (within_kprobe_blacklist(attr->bp_addr))
return -EINVAL;
#else
return -EINVAL;
#endif
}
- info->type = X86_BREAKPOINT_EXECUTE;
+ hw->type = X86_BREAKPOINT_EXECUTE;
/*
* x86 inst breakpoints need to have a specific undefined len.
* But we still need to check userspace is not trying to setup
* an unsupported length, to get a range breakpoint for example.
*/
- if (bp->attr.bp_len == sizeof(long)) {
- info->len = X86_BREAKPOINT_LEN_X;
+ if (attr->bp_len == sizeof(long)) {
+ hw->len = X86_BREAKPOINT_LEN_X;
return 0;
}
default:
}
/* Len */
- info->mask = 0;
-
- switch (bp->attr.bp_len) {
+ switch (attr->bp_len) {
case HW_BREAKPOINT_LEN_1:
- info->len = X86_BREAKPOINT_LEN_1;
+ hw->len = X86_BREAKPOINT_LEN_1;
break;
case HW_BREAKPOINT_LEN_2:
- info->len = X86_BREAKPOINT_LEN_2;
+ hw->len = X86_BREAKPOINT_LEN_2;
break;
case HW_BREAKPOINT_LEN_4:
- info->len = X86_BREAKPOINT_LEN_4;
+ hw->len = X86_BREAKPOINT_LEN_4;
break;
#ifdef CONFIG_X86_64
case HW_BREAKPOINT_LEN_8:
- info->len = X86_BREAKPOINT_LEN_8;
+ hw->len = X86_BREAKPOINT_LEN_8;
break;
#endif
default:
/* AMD range breakpoint */
- if (!is_power_of_2(bp->attr.bp_len))
+ if (!is_power_of_2(attr->bp_len))
return -EINVAL;
- if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+ if (attr->bp_addr & (attr->bp_len - 1))
return -EINVAL;
if (!boot_cpu_has(X86_FEATURE_BPEXT))
* breakpoints, then we'll have to check for kprobe-blacklisted
* addresses anywhere in the range.
*/
- info->mask = bp->attr.bp_len - 1;
- info->len = X86_BREAKPOINT_LEN_1;
+ hw->mask = attr->bp_len - 1;
+ hw->len = X86_BREAKPOINT_LEN_1;
}
return 0;
/*
* Validate the arch-specific HW Breakpoint register settings
*/
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
unsigned int align;
int ret;
- ret = arch_build_bp_info(bp);
+ ret = arch_build_bp_info(bp, attr, hw);
if (ret)
return ret;
- switch (info->len) {
+ switch (hw->len) {
case X86_BREAKPOINT_LEN_1:
align = 0;
- if (info->mask)
- align = info->mask;
+ if (hw->mask)
+ align = hw->mask;
break;
case X86_BREAKPOINT_LEN_2:
align = 1;
* Check that the low-order bits of the address are appropriate
* for the alignment implied by len.
*/
- if (info->address & align)
+ if (hw->address & align)
return -EINVAL;
return 0;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/asm.h>
+#include <asm/export.h>
+#include <linux/linkage.h>
+
+/*
+ * unsigned long native_save_fl(void)
+ */
+ENTRY(native_save_fl)
+ pushf
+ pop %_ASM_AX
+ ret
+ENDPROC(native_save_fl)
+EXPORT_SYMBOL(native_save_fl)
+
+/*
+ * void native_restore_fl(unsigned long flags)
+ * %eax/%rdi: flags
+ */
+ENTRY(native_restore_fl)
+ push %_ASM_ARG1
+ popf
+ ret
+ENDPROC(native_restore_fl)
+EXPORT_SYMBOL(native_restore_fl)
BUG();
}
-static void __jump_label_transform(struct jump_entry *entry,
- enum jump_label_type type,
- void *(*poker)(void *, const void *, size_t),
- int init)
+static void __ref __jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ void *(*poker)(void *, const void *, size_t),
+ int init)
{
union jump_code_union code;
const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+ if (early_boot_irqs_disabled)
+ poker = text_poke_early;
+
if (type == JUMP_LABEL_JMP) {
if (init) {
/*
}
#endif
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
-{
- return 0;
-}
-#endif
#endif
#include "common.h"
-void jprobe_return_end(void);
-
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
- (u8 *) real;
if ((s64) (s32) newdisp != newdisp) {
pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
- pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
- src, real, insn->displacement.value);
return 0;
}
disp = (u8 *) dest + insn_offset_displacement(insn);
* stepping.
*/
regs->ip = (unsigned long)p->ainsn.insn;
- preempt_enable_no_resched();
return;
}
#endif
* Raise a BUG or we'll continue in an endless reentering loop
* and eventually a stack overflow.
*/
- printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
- p->addr);
+ pr_err("Unrecoverable kprobe detected.\n");
dump_kprobe(p);
BUG();
default:
addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
/*
- * We don't want to be preempted for the entire
- * duration of kprobe processing. We conditionally
- * re-enable preemption at the end of this function,
- * and also in reenter_kprobe() and setup_singlestep().
+ * We don't want to be preempted for the entire duration of kprobe
+ * processing. Since int3 and debug trap disables irqs and we clear
+ * IF while singlestepping, it must be no preemptible.
*/
- preempt_disable();
kcb = get_kprobe_ctlblk();
p = get_kprobe(addr);
/*
* If we have no pre-handler or it returned 0, we
* continue with normal processing. If we have a
- * pre-handler and it returned non-zero, it prepped
- * for calling the break_handler below on re-entry
- * for jprobe processing, so get out doing nothing
- * more here.
+ * pre-handler and it returned non-zero, that means
+ * user handler setup registers to exit to another
+ * instruction, we must skip the single stepping.
*/
if (!p->pre_handler || !p->pre_handler(p, regs))
setup_singlestep(p, regs, kcb, 0);
+ else
+ reset_current_kprobe();
return 1;
}
} else if (*addr != BREAKPOINT_INSTRUCTION) {
* the original instruction.
*/
regs->ip = (unsigned long)addr;
- preempt_enable_no_resched();
return 1;
- } else if (kprobe_running()) {
- p = __this_cpu_read(current_kprobe);
- if (p->break_handler && p->break_handler(p, regs)) {
- if (!skip_singlestep(p, regs, kcb))
- setup_singlestep(p, regs, kcb, 0);
- return 1;
- }
} /* else: not a kprobe fault; let the kernel handle it */
- preempt_enable_no_resched();
return 0;
}
NOKPROBE_SYMBOL(kprobe_int3_handler);
}
reset_current_kprobe();
out:
- preempt_enable_no_resched();
-
/*
* if somebody else is singlestepping across a probe point, flags
* will have TF set, in which case, continue the remaining processing
restore_previous_kprobe(kcb);
else
reset_current_kprobe();
- preempt_enable_no_resched();
} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
kcb->kprobe_status == KPROBE_HIT_SSDONE) {
/*
}
NOKPROBE_SYMBOL(kprobe_exceptions_notify);
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- unsigned long addr;
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- kcb->jprobe_saved_regs = *regs;
- kcb->jprobe_saved_sp = stack_addr(regs);
- addr = (unsigned long)(kcb->jprobe_saved_sp);
-
- /*
- * As Linus pointed out, gcc assumes that the callee
- * owns the argument space and could overwrite it, e.g.
- * tailcall optimization. So, to be absolutely safe
- * we also save and restore enough stack bytes to cover
- * the argument area.
- * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
- * raw stack chunk with redzones:
- */
- __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
- regs->ip = (unsigned long)(jp->entry);
-
- /*
- * jprobes use jprobe_return() which skips the normal return
- * path of the function, and this messes up the accounting of the
- * function graph tracer to get messed up.
- *
- * Pause function graph tracing while performing the jprobe function.
- */
- pause_graph_tracing();
- return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- /* Unpoison stack redzones in the frames we are going to jump over. */
- kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
-
- asm volatile (
-#ifdef CONFIG_X86_64
- " xchg %%rbx,%%rsp \n"
-#else
- " xchgl %%ebx,%%esp \n"
-#endif
- " int3 \n"
- " .globl jprobe_return_end\n"
- " jprobe_return_end: \n"
- " nop \n"::"b"
- (kcb->jprobe_saved_sp):"memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-NOKPROBE_SYMBOL(jprobe_return_end);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- u8 *addr = (u8 *) (regs->ip - 1);
- struct jprobe *jp = container_of(p, struct jprobe, kp);
- void *saved_sp = kcb->jprobe_saved_sp;
-
- if ((addr > (u8 *) jprobe_return) &&
- (addr < (u8 *) jprobe_return_end)) {
- if (stack_addr(regs) != saved_sp) {
- struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
- printk(KERN_ERR
- "current sp %p does not match saved sp %p\n",
- stack_addr(regs), saved_sp);
- printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
- show_regs(saved_regs);
- printk(KERN_ERR "Current registers\n");
- show_regs(regs);
- BUG();
- }
- /* It's OK to start function graph tracing again */
- unpause_graph_tracing();
- *regs = kcb->jprobe_saved_regs;
- __memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
- preempt_enable_no_resched();
- return 1;
- }
- return 0;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
bool arch_within_kprobe_blacklist(unsigned long addr)
{
bool is_in_entry_trampoline_section = false;
#include "common.h"
-static nokprobe_inline
-void __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb, unsigned long orig_ip)
-{
- /*
- * Emulate singlestep (and also recover regs->ip)
- * as if there is a 5byte nop
- */
- regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
- if (unlikely(p->post_handler)) {
- kcb->kprobe_status = KPROBE_HIT_SSDONE;
- p->post_handler(p, regs, 0);
- }
- __this_cpu_write(current_kprobe, NULL);
- if (orig_ip)
- regs->ip = orig_ip;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
-{
- if (kprobe_ftrace(p)) {
- __skip_singlestep(p, regs, kcb, 0);
- preempt_enable_no_resched();
- return 1;
- }
- return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
/* Ftrace callback handler for kprobes -- called under preepmt disabed */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct pt_regs *regs)
/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
regs->ip = ip + sizeof(kprobe_opcode_t);
- /* To emulate trap based kprobes, preempt_disable here */
- preempt_disable();
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (!p->pre_handler || !p->pre_handler(p, regs)) {
- __skip_singlestep(p, regs, kcb, orig_ip);
- preempt_enable_no_resched();
+ /*
+ * Emulate singlestep (and also recover regs->ip)
+ * as if there is a 5byte nop
+ */
+ regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ regs->ip = orig_ip;
}
/*
- * If pre_handler returns !0, it sets regs->ip and
- * resets current kprobe, and keep preempt count +1.
+ * If pre_handler returns !0, it changes regs->ip. We have to
+ * skip emulating post_handler.
*/
+ __this_cpu_write(current_kprobe, NULL);
}
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
if (!reenter)
reset_current_kprobe();
- preempt_enable_no_resched();
return 1;
}
return 0;
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
-#include <asm/kvm_guest.h>
static int kvmapf = 1;
early_param("no-steal-acc", parse_no_stealacc);
-static int kvmclock_vsyscall = 1;
-static int __init parse_no_kvmclock_vsyscall(char *arg)
-{
- kvmclock_vsyscall = 0;
- return 0;
-}
-
-early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
-
static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
static int has_steal_clock = 0;
for (;;) {
if (!n.halted)
- prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
if (hlist_unhashed(&n.link))
break;
if (n->halted)
smp_send_reschedule(n->cpu);
else if (swq_has_sleeper(&n->wq))
- swake_up(&n->wq);
+ swake_up_one(&n->wq);
}
static void apf_task_wake_all(void)
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
- if (kvmclock_vsyscall)
- kvm_setup_vsyscall_timeinfo();
-
#ifdef CONFIG_SMP
smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
.name = "KVM",
.detect = kvm_detect,
.type = X86_HYPER_KVM,
+ .init.init_platform = kvmclock_init,
.init.guest_late_init = kvm_guest_init,
.init.x2apic_available = kvm_para_available,
};
#include <asm/apic.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
-#include <linux/memblock.h>
+#include <linux/cpuhotplug.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
+#include <linux/mm.h>
+#include <asm/hypervisor.h>
#include <asm/mem_encrypt.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
#include <asm/kvmclock.h>
-static int kvmclock __ro_after_init = 1;
-static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static u64 kvm_sched_clock_offset;
+static int kvmclock __initdata = 1;
+static int kvmclock_vsyscall __initdata = 1;
+static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static u64 kvm_sched_clock_offset __ro_after_init;
-static int parse_no_kvmclock(char *arg)
+static int __init parse_no_kvmclock(char *arg)
{
kvmclock = 0;
return 0;
}
early_param("no-kvmclock", parse_no_kvmclock);
-/* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock *wall_clock;
+static int __init parse_no_kvmclock_vsyscall(char *arg)
+{
+ kvmclock_vsyscall = 0;
+ return 0;
+}
+early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
+
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE (sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define HVC_BOOT_ARRAY_SIZE \
+ (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
+
+static struct pvclock_vsyscall_time_info
+ hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock;
+static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+ return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+ return this_cpu_read(hv_clock_per_cpu);
+}
/*
* The wallclock is the time of day when we booted. Since then, some time may
*/
static void kvm_get_wallclock(struct timespec64 *now)
{
- struct pvclock_vcpu_time_info *vcpu_time;
- int low, high;
- int cpu;
-
- low = (int)slow_virt_to_phys(wall_clock);
- high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
-
- native_write_msr(msr_kvm_wall_clock, low, high);
-
- cpu = get_cpu();
-
- vcpu_time = &hv_clock[cpu].pvti;
- pvclock_read_wallclock(wall_clock, vcpu_time, now);
-
- put_cpu();
+ wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+ preempt_disable();
+ pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
+ preempt_enable();
}
static int kvm_set_wallclock(const struct timespec64 *now)
static u64 kvm_clock_read(void)
{
- struct pvclock_vcpu_time_info *src;
u64 ret;
- int cpu;
preempt_disable_notrace();
- cpu = smp_processor_id();
- src = &hv_clock[cpu].pvti;
- ret = pvclock_clocksource_read(src);
+ ret = pvclock_clocksource_read(this_cpu_pvti());
preempt_enable_notrace();
return ret;
}
kvm_sched_clock_offset = kvm_clock_read();
pv_time_ops.sched_clock = kvm_sched_clock_read;
- printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
- kvm_sched_clock_offset);
+ pr_info("kvm-clock: using sched offset of %llu cycles",
+ kvm_sched_clock_offset);
BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
- sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+ sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
}
/*
*/
static unsigned long kvm_get_tsc_khz(void)
{
- struct pvclock_vcpu_time_info *src;
- int cpu;
- unsigned long tsc_khz;
-
- cpu = get_cpu();
- src = &hv_clock[cpu].pvti;
- tsc_khz = pvclock_tsc_khz(src);
- put_cpu();
- return tsc_khz;
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+ return pvclock_tsc_khz(this_cpu_pvti());
}
-static void kvm_get_preset_lpj(void)
+static void __init kvm_get_preset_lpj(void)
{
unsigned long khz;
u64 lpj;
bool kvm_check_and_clear_guest_paused(void)
{
+ struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
bool ret = false;
- struct pvclock_vcpu_time_info *src;
- int cpu = smp_processor_id();
- if (!hv_clock)
+ if (!src)
return ret;
- src = &hv_clock[cpu].pvti;
- if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
- src->flags &= ~PVCLOCK_GUEST_STOPPED;
+ if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
+ src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
pvclock_touch_watchdogs();
ret = true;
}
-
return ret;
}
struct clocksource kvm_clock = {
- .name = "kvm-clock",
- .read = kvm_clock_get_cycles,
- .rating = 400,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .name = "kvm-clock",
+ .read = kvm_clock_get_cycles,
+ .rating = 400,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
EXPORT_SYMBOL_GPL(kvm_clock);
-int kvm_register_clock(char *txt)
+static void kvm_register_clock(char *txt)
{
- int cpu = smp_processor_id();
- int low, high, ret;
- struct pvclock_vcpu_time_info *src;
-
- if (!hv_clock)
- return 0;
+ struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
+ u64 pa;
- src = &hv_clock[cpu].pvti;
- low = (int)slow_virt_to_phys(src) | 1;
- high = ((u64)slow_virt_to_phys(src) >> 32);
- ret = native_write_msr_safe(msr_kvm_system_time, low, high);
- printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
- cpu, high, low, txt);
+ if (!src)
+ return;
- return ret;
+ pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
+ wrmsrl(msr_kvm_system_time, pa);
+ pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
}
static void kvm_save_sched_clock_state(void)
#ifdef CONFIG_X86_LOCAL_APIC
static void kvm_setup_secondary_clock(void)
{
- /*
- * Now that the first cpu already had this clocksource initialized,
- * we shouldn't fail.
- */
- WARN_ON(kvm_register_clock("secondary cpu clock"));
+ kvm_register_clock("secondary cpu clock");
}
#endif
native_machine_shutdown();
}
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
- phys_addr_t align)
+static int __init kvm_setup_vsyscall_timeinfo(void)
{
- phys_addr_t mem;
+#ifdef CONFIG_X86_64
+ u8 flags;
- mem = memblock_alloc(size, align);
- if (!mem)
+ if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
return 0;
- if (sev_active()) {
- if (early_set_memory_decrypted((unsigned long)__va(mem), size))
- goto e_free;
- }
+ flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+ if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+ return 0;
- return mem;
-e_free:
- memblock_free(mem, size);
+ kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
return 0;
}
+early_initcall(kvm_setup_vsyscall_timeinfo);
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
+static int kvmclock_setup_percpu(unsigned int cpu)
{
- if (sev_active())
- early_set_memory_encrypted((unsigned long)__va(addr), size);
+ struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);
+
+ /*
+ * The per cpu area setup replicates CPU0 data to all cpu
+ * pointers. So carefully check. CPU0 has been set up in init
+ * already.
+ */
+ if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
+ return 0;
+
+ /* Use the static page for the first CPUs, allocate otherwise */
+ if (cpu < HVC_BOOT_ARRAY_SIZE)
+ p = &hv_clock_boot[cpu];
+ else
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
- memblock_free(addr, size);
+ per_cpu(hv_clock_per_cpu, cpu) = p;
+ return p ? 0 : -ENOMEM;
}
void __init kvmclock_init(void)
{
- struct pvclock_vcpu_time_info *vcpu_time;
- unsigned long mem, mem_wall_clock;
- int size, cpu, wall_clock_size;
u8 flags;
- size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
- if (!kvm_para_available())
+ if (!kvm_para_available() || !kvmclock)
return;
- if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+ if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
- } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
- return;
-
- wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
- mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
- if (!mem_wall_clock)
- return;
-
- wall_clock = __va(mem_wall_clock);
- memset(wall_clock, 0, wall_clock_size);
-
- mem = kvm_memblock_alloc(size, PAGE_SIZE);
- if (!mem) {
- kvm_memblock_free(mem_wall_clock, wall_clock_size);
- wall_clock = NULL;
+ } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
return;
}
- hv_clock = __va(mem);
- memset(hv_clock, 0, size);
-
- if (kvm_register_clock("primary cpu clock")) {
- hv_clock = NULL;
- kvm_memblock_free(mem, size);
- kvm_memblock_free(mem_wall_clock, wall_clock_size);
- wall_clock = NULL;
+ if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
+ kvmclock_setup_percpu, NULL) < 0) {
return;
}
- printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+ pr_info("kvm-clock: Using msrs %x and %x",
msr_kvm_system_time, msr_kvm_wall_clock);
+ this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
+ kvm_register_clock("primary cpu clock");
+ pvclock_set_pvti_cpu0_va(hv_clock_boot);
+
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
- cpu = get_cpu();
- vcpu_time = &hv_clock[cpu].pvti;
- flags = pvclock_read_flags(vcpu_time);
-
+ flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
- put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
- x86_cpuinit.early_percpu_clock_init =
- kvm_setup_secondary_clock;
+ x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
#endif
x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
pv_info.name = "KVM";
}
-
-int __init kvm_setup_vsyscall_timeinfo(void)
-{
-#ifdef CONFIG_X86_64
- int cpu;
- u8 flags;
- struct pvclock_vcpu_time_info *vcpu_time;
- unsigned int size;
-
- if (!hv_clock)
- return 0;
-
- size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
- cpu = get_cpu();
-
- vcpu_time = &hv_clock[cpu].pvti;
- flags = pvclock_read_flags(vcpu_time);
-
- if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
- put_cpu();
- return 1;
- }
-
- pvclock_set_pvti_cpu0_va(hv_clock);
- put_cpu();
-
- kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
-#endif
- return 0;
-}
return new_ldt;
}
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+static void do_sanity_check(struct mm_struct *mm,
+ bool had_kernel_mapping,
+ bool had_user_mapping)
+{
+ if (mm->context.ldt) {
+ /*
+ * We already had an LDT. The top-level entry should already
+ * have been allocated and synchronized with the usermode
+ * tables.
+ */
+ WARN_ON(!had_kernel_mapping);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(!had_user_mapping);
+ } else {
+ /*
+ * This is the first time we're mapping an LDT for this process.
+ * Sync the pgd to the usermode tables.
+ */
+ WARN_ON(had_kernel_mapping);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(had_user_mapping);
+ }
+}
+
+#ifdef CONFIG_X86_PAE
+
+static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va)
+{
+ p4d_t *p4d;
+ pud_t *pud;
+
+ if (pgd->pgd == 0)
+ return NULL;
+
+ p4d = p4d_offset(pgd, va);
+ if (p4d_none(*p4d))
+ return NULL;
+
+ pud = pud_offset(p4d, va);
+ if (pud_none(*pud))
+ return NULL;
+
+ return pmd_offset(pud, va);
+}
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+ pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+ pmd_t *k_pmd, *u_pmd;
+
+ k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+ u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+
+ if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ set_pmd(u_pmd, *k_pmd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+ pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+ bool had_kernel, had_user;
+ pmd_t *k_pmd, *u_pmd;
+
+ k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+ u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+ had_kernel = (k_pmd->pmd != 0);
+ had_user = (u_pmd->pmd != 0);
+
+ do_sanity_check(mm, had_kernel, had_user);
+}
+
+#else /* !CONFIG_X86_PAE */
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+ pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+
+ if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+ pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ bool had_kernel = (pgd->pgd != 0);
+ bool had_user = (kernel_to_user_pgdp(pgd)->pgd != 0);
+
+ do_sanity_check(mm, had_kernel, had_user);
+}
+
+#endif /* CONFIG_X86_PAE */
+
/*
* If PTI is enabled, this maps the LDT into the kernelmode and
* usermode tables for the given mm.
static int
map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- bool is_vmalloc, had_top_level_entry;
unsigned long va;
+ bool is_vmalloc;
spinlock_t *ptl;
pgd_t *pgd;
int i;
*/
WARN_ON(ldt->slot != -1);
+ /* Check if the current mappings are sane */
+ sanity_check_ldt_mapping(mm);
+
/*
* Did we already have the top level entry allocated? We can't
* use pgd_none() for this because it doens't do anything on
* 4-level page table kernels.
*/
pgd = pgd_offset(mm, LDT_BASE_ADDR);
- had_top_level_entry = (pgd->pgd != 0);
is_vmalloc = is_vmalloc_addr(ldt->entries);
pte_unmap_unlock(ptep, ptl);
}
- if (mm->context.ldt) {
- /*
- * We already had an LDT. The top-level entry should already
- * have been allocated and synchronized with the usermode
- * tables.
- */
- WARN_ON(!had_top_level_entry);
- if (static_cpu_has(X86_FEATURE_PTI))
- WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
- } else {
- /*
- * This is the first time we're mapping an LDT for this process.
- * Sync the pgd to the usermode tables.
- */
- WARN_ON(had_top_level_entry);
- if (static_cpu_has(X86_FEATURE_PTI)) {
- WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
- set_pgd(kernel_to_user_pgdp(pgd), *pgd);
- }
- }
+ /* Propagate LDT mapping to the user page-table */
+ map_ldt_struct_to_user(mm);
va = (unsigned long)ldt_slot_va(slot);
flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
ldt->slot = slot;
-#endif
return 0;
}
+#else /* !CONFIG_PAGE_TABLE_ISOLATION */
+
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+ return 0;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
static void free_ldt_pgtables(struct mm_struct *mm)
{
#ifdef CONFIG_PAGE_TABLE_ISOLATION
struct mmu_gather tlb;
unsigned long start = LDT_BASE_ADDR;
- unsigned long end = start + (1UL << PGDIR_SHIFT);
+ unsigned long end = LDT_END_ADDR;
if (!static_cpu_has(X86_FEATURE_PTI))
return;
static void machine_kexec_free_page_tables(struct kimage *image)
{
- free_page((unsigned long)image->arch.pgd);
+ free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
static int machine_kexec_alloc_page_tables(struct kimage *image)
{
- image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+ image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ PGD_ALLOCATION_ORDER);
#ifdef CONFIG_X86_PAE
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
- if (tgt_clobbers & ~site_clobbers)
- return len; /* target would clobber too much for this site */
- if (len < 5)
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
return len; /* call too long for patch site */
+ }
b->opcode = 0xe8; /* call */
b->delta = delta;
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
- if (len < 5)
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
return len; /* call too long for patch site */
+ }
b->opcode = 0xe9; /* jmp */
b->delta = delta;
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
p->detect, q->detect);
/* Heavy handed way..*/
- x->depend = 0;
+ x->depend = NULL;
}
}
pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
- return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+ return PTR_ERR_OR_ZERO(pd);
}
device_initcall(add_pcspkr);
*/
.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
-#ifdef CONFIG_X86_64
/*
* .sp1 is cpu_current_top_of_stack. The init task never
* runs user code, but cpu_current_top_of_stack should still
* be well defined before the first context switch.
*/
.sp1 = TOP_OF_INIT_STACK,
-#endif
#ifdef CONFIG_X86_32
.ss0 = __KERNEL_DS,
* current_thread_info(). Refresh the SYSENTER configuration in
* case prev or next is vm86.
*/
- update_sp0(next_p);
+ update_task_stack(next_p);
refresh_sysenter_cs(next);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
/* Reload sp0. */
- update_sp0(next_p);
+ update_task_stack(next_p);
/*
* Now maybe reload the debug registers and handle I/O bitmaps
/* Skylake */
static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
{
- u32 capid0;
+ u32 capid0, capid5;
pci_read_config_dword(pdev, 0x84, &capid0);
+ pci_read_config_dword(pdev, 0x98, &capid5);
- if ((capid0 & 0xc0) == 0xc0)
+ /*
+ * CAPID0{7:6} indicate whether this is an advanced RAS SKU
+ * CAPID5{8:5} indicate that various NVDIMM usage modes are
+ * enabled, so memory machine check recovery is also enabled.
+ */
+ if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
static_branch_inc(&mcsafe_key);
+
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);
idt_setup_early_traps();
early_cpu_init();
+ arch_init_ideal_nops();
+ jump_label_init();
early_ioremap_init();
setup_olpc_ofw_pgd();
*/
init_hypervisor_platform();
+ tsc_early_init();
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
memblock_find_dma_reserve();
-#ifdef CONFIG_KVM_GUEST
- kvmclock_init();
-#endif
-
- tsc_early_delay_calibrate();
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
mcheck_init();
- arch_init_ideal_nops();
-
register_refined_jiffies(CLOCK_TICK_RATE);
#ifdef CONFIG_EFI
* Increment event counter and perform fixup for the pre-signal
* frame.
*/
- rseq_signal_deliver(regs);
+ rseq_signal_deliver(ksig, regs);
/* Set up the stack frame */
if (is_ia32_frame(ksig)) {
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
+ /*
+ * Initialize the CR4 shadow before doing anything that could
+ * try to read it.
+ */
+ cr4_init_shadow();
__flush_tlb_all();
#endif
load_current_idt();
#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-#define STACKTRACE_DUMP_ONCE(task) ({ \
- static bool __section(.data.unlikely) __dumped; \
- \
- if (!__dumped) { \
- __dumped = true; \
- WARN_ON(1); \
- show_stack(task, NULL); \
- } \
-})
-
static int __always_inline
__save_stack_trace_reliable(struct stack_trace *trace,
struct task_struct *task)
struct pt_regs *regs;
unsigned long addr;
- for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+ for (unwind_start(&state, task, NULL, NULL);
+ !unwind_done(&state) && !unwind_error(&state);
unwind_next_frame(&state)) {
regs = unwind_get_entry_regs(&state, NULL);
if (regs) {
+ /* Success path for user tasks */
+ if (user_mode(regs))
+ goto success;
+
/*
* Kernel mode registers on the stack indicate an
* in-kernel interrupt or exception (e.g., preemption
* or a page fault), which can make frame pointers
* unreliable.
*/
- if (!user_mode(regs))
- return -EINVAL;
- /*
- * The last frame contains the user mode syscall
- * pt_regs. Skip it and finish the unwind.
- */
- unwind_next_frame(&state);
- if (!unwind_done(&state)) {
- STACKTRACE_DUMP_ONCE(task);
+ if (IS_ENABLED(CONFIG_FRAME_POINTER))
return -EINVAL;
- }
- break;
}
addr = unwind_get_return_address(&state);
* generated code which __kernel_text_address() doesn't know
* about.
*/
- if (!addr) {
- STACKTRACE_DUMP_ONCE(task);
+ if (!addr)
return -EINVAL;
- }
if (save_stack_address(trace, addr, false))
return -EINVAL;
}
/* Check for stack corruption */
- if (unwind_error(&state)) {
- STACKTRACE_DUMP_ONCE(task);
+ if (unwind_error(&state))
+ return -EINVAL;
+
+ /* Success path for non-user tasks, i.e. kthreads and idle tasks */
+ if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
return -EINVAL;
- }
+success:
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
- return;
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
- if (!fixup_exception(regs, trapnr)) {
- task->thread.error_code = error_code;
- task->thread.trap_nr = trapnr;
+ if (fixup_exception(regs, trapnr))
+ return;
+
+ task->thread.error_code = error_code;
+ task->thread.trap_nr = trapnr;
+
+ if (notify_die(DIE_TRAP, str, regs, error_code,
+ trapnr, SIGFPE) != NOTIFY_STOP)
die(str, regs, error_code);
- }
return;
}
unsigned int __read_mostly tsc_khz;
EXPORT_SYMBOL(tsc_khz);
+#define KHZ 1000
+
/*
* TSC can be unstable due to cpufreq or due to unsynced TSCs
*/
static int __read_mostly tsc_unstable;
-/* native_sched_clock() is called before tsc_init(), so
- we must start with the TSC soft disabled to prevent
- erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
-static int __read_mostly tsc_disabled = -1;
-
static DEFINE_STATIC_KEY_FALSE(__use_tsc);
int tsc_clocksource_reliable;
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
*/
-static void cyc2ns_data_init(struct cyc2ns_data *data)
-{
- data->cyc2ns_mul = 0;
- data->cyc2ns_shift = 0;
- data->cyc2ns_offset = 0;
-}
-
-static void __init cyc2ns_init(int cpu)
-{
- struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
- cyc2ns_data_init(&c2n->data[0]);
- cyc2ns_data_init(&c2n->data[1]);
-
- seqcount_init(&c2n->seq);
-}
-
static inline unsigned long long cycles_2_ns(unsigned long long cyc)
{
struct cyc2ns_data data;
return ns;
}
-static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
{
unsigned long long ns_now;
struct cyc2ns_data data;
struct cyc2ns *c2n;
- unsigned long flags;
-
- local_irq_save(flags);
- sched_clock_idle_sleep_event();
-
- if (!khz)
- goto done;
ns_now = cycles_2_ns(tsc_now);
c2n->data[0] = data;
raw_write_seqcount_latch(&c2n->seq);
c2n->data[1] = data;
+}
+
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ sched_clock_idle_sleep_event();
+
+ if (khz)
+ __set_cyc2ns_scale(khz, cpu, tsc_now);
-done:
sched_clock_idle_wakeup_event();
local_irq_restore(flags);
}
+/*
+ * Initialize cyc2ns for boot cpu
+ */
+static void __init cyc2ns_init_boot_cpu(void)
+{
+ struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+
+ seqcount_init(&c2n->seq);
+ __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
+}
+
+/*
+ * Secondary CPUs do not run through tsc_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+static void __init cyc2ns_init_secondary_cpus(void)
+{
+ unsigned int cpu, this_cpu = smp_processor_id();
+ struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+ struct cyc2ns_data *data = c2n->data;
+
+ for_each_possible_cpu(cpu) {
+ if (cpu != this_cpu) {
+ seqcount_init(&c2n->seq);
+ c2n = per_cpu_ptr(&cyc2ns, cpu);
+ c2n->data[0] = data[0];
+ c2n->data[1] = data[1];
+ }
+ }
+}
+
/*
* Scheduler clock - returns current time in nanosec units.
*/
#ifdef CONFIG_X86_TSC
int __init notsc_setup(char *str)
{
- pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n");
- tsc_disabled = 1;
+ mark_tsc_unstable("boot parameter notsc");
return 1;
}
#else
return eax_base_mhz * 1000;
}
-/**
- * native_calibrate_cpu - calibrate the cpu on boot
+/*
+ * calibrate cpu using pit, hpet, and ptimer methods. They are available
+ * later in boot after acpi is initialized.
*/
-unsigned long native_calibrate_cpu(void)
+static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
{
u64 tsc1, tsc2, delta, ref1, ref2;
unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
- unsigned long flags, latch, ms, fast_calibrate;
+ unsigned long flags, latch, ms;
int hpet = is_hpet_enabled(), i, loopmin;
- fast_calibrate = cpu_khz_from_cpuid();
- if (fast_calibrate)
- return fast_calibrate;
-
- fast_calibrate = cpu_khz_from_msr();
- if (fast_calibrate)
- return fast_calibrate;
-
- local_irq_save(flags);
- fast_calibrate = quick_pit_calibrate();
- local_irq_restore(flags);
- if (fast_calibrate)
- return fast_calibrate;
-
/*
* Run 5 calibration loops to get the lowest frequency value
* (the best estimate). We use two different calibration modes
return tsc_pit_min;
}
+/**
+ * native_calibrate_cpu_early - can calibrate the cpu early in boot
+ */
+unsigned long native_calibrate_cpu_early(void)
+{
+ unsigned long flags, fast_calibrate = cpu_khz_from_cpuid();
+
+ if (!fast_calibrate)
+ fast_calibrate = cpu_khz_from_msr();
+ if (!fast_calibrate) {
+ local_irq_save(flags);
+ fast_calibrate = quick_pit_calibrate();
+ local_irq_restore(flags);
+ }
+ return fast_calibrate;
+}
+
+
+/**
+ * native_calibrate_cpu - calibrate the cpu
+ */
+static unsigned long native_calibrate_cpu(void)
+{
+ unsigned long tsc_freq = native_calibrate_cpu_early();
+
+ if (!tsc_freq)
+ tsc_freq = pit_hpet_ptimer_calibrate_cpu();
+
+ return tsc_freq;
+}
+
void recalibrate_cpu_khz(void)
{
#ifndef CONFIG_SMP
static int __init init_tsc_clocksource(void)
{
- if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
+ if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
return 0;
if (tsc_unstable)
*/
device_initcall(init_tsc_clocksource);
-void __init tsc_early_delay_calibrate(void)
+static bool __init determine_cpu_tsc_frequencies(bool early)
{
- unsigned long lpj;
-
- if (!boot_cpu_has(X86_FEATURE_TSC))
- return;
-
- cpu_khz = x86_platform.calibrate_cpu();
- tsc_khz = x86_platform.calibrate_tsc();
-
- tsc_khz = tsc_khz ? : cpu_khz;
- if (!tsc_khz)
- return;
-
- lpj = tsc_khz * 1000;
- do_div(lpj, HZ);
- loops_per_jiffy = lpj;
-}
-
-void __init tsc_init(void)
-{
- u64 lpj, cyc;
- int cpu;
-
- if (!boot_cpu_has(X86_FEATURE_TSC)) {
- setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
- return;
+ /* Make sure that cpu and tsc are not already calibrated */
+ WARN_ON(cpu_khz || tsc_khz);
+
+ if (early) {
+ cpu_khz = x86_platform.calibrate_cpu();
+ tsc_khz = x86_platform.calibrate_tsc();
+ } else {
+ /* We should not be here with non-native cpu calibration */
+ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
+ cpu_khz = pit_hpet_ptimer_calibrate_cpu();
}
- cpu_khz = x86_platform.calibrate_cpu();
- tsc_khz = x86_platform.calibrate_tsc();
-
/*
- * Trust non-zero tsc_khz as authorative,
+ * Trust non-zero tsc_khz as authoritative,
* and use it to sanity check cpu_khz,
* which will be off if system timer is off.
*/
else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz)
cpu_khz = tsc_khz;
- if (!tsc_khz) {
- mark_tsc_unstable("could not calculate TSC khz");
- setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
- return;
- }
+ if (tsc_khz == 0)
+ return false;
pr_info("Detected %lu.%03lu MHz processor\n",
- (unsigned long)cpu_khz / 1000,
- (unsigned long)cpu_khz % 1000);
+ (unsigned long)cpu_khz / KHZ,
+ (unsigned long)cpu_khz % KHZ);
if (cpu_khz != tsc_khz) {
pr_info("Detected %lu.%03lu MHz TSC",
- (unsigned long)tsc_khz / 1000,
- (unsigned long)tsc_khz % 1000);
+ (unsigned long)tsc_khz / KHZ,
+ (unsigned long)tsc_khz % KHZ);
}
+ return true;
+}
+
+static unsigned long __init get_loops_per_jiffy(void)
+{
+ unsigned long lpj = tsc_khz * KHZ;
+ do_div(lpj, HZ);
+ return lpj;
+}
+
+static void __init tsc_enable_sched_clock(void)
+{
/* Sanitize TSC ADJUST before cyc2ns gets initialized */
tsc_store_and_check_tsc_adjust(true);
+ cyc2ns_init_boot_cpu();
+ static_branch_enable(&__use_tsc);
+}
+
+void __init tsc_early_init(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_TSC))
+ return;
+ if (!determine_cpu_tsc_frequencies(true))
+ return;
+ loops_per_jiffy = get_loops_per_jiffy();
+ tsc_enable_sched_clock();
+}
+
+void __init tsc_init(void)
+{
/*
- * Secondary CPUs do not run through tsc_init(), so set up
- * all the scale factors for all CPUs, assuming the same
- * speed as the bootup CPU. (cpufreq notifiers will fix this
- * up if their speed diverges)
+ * native_calibrate_cpu_early can only calibrate using methods that are
+ * available early in boot.
*/
- cyc = rdtsc();
- for_each_possible_cpu(cpu) {
- cyc2ns_init(cpu);
- set_cyc2ns_scale(tsc_khz, cpu, cyc);
- }
+ if (x86_platform.calibrate_cpu == native_calibrate_cpu_early)
+ x86_platform.calibrate_cpu = native_calibrate_cpu;
- if (tsc_disabled > 0)
+ if (!boot_cpu_has(X86_FEATURE_TSC)) {
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
+ }
- /* now allow native_sched_clock() to use rdtsc */
+ if (!tsc_khz) {
+ /* We failed to determine frequencies earlier, try again */
+ if (!determine_cpu_tsc_frequencies(false)) {
+ mark_tsc_unstable("could not calculate TSC khz");
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+ return;
+ }
+ tsc_enable_sched_clock();
+ }
- tsc_disabled = 0;
- static_branch_enable(&__use_tsc);
+ cyc2ns_init_secondary_cpus();
if (!no_sched_irq_time)
enable_sched_clock_irqtime();
- lpj = ((u64)tsc_khz * 1000);
- do_div(lpj, HZ);
- lpj_fine = lpj;
-
+ lpj_fine = get_loops_per_jiffy();
use_tsc_delay();
check_system_tsc_reliable();
int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
const struct cpumask *mask = topology_core_cpumask(cpu);
- if (tsc_disabled || !constant_tsc || !mask)
+ if (!constant_tsc || !mask)
return 0;
sibling = cpumask_any_but(mask, cpu);
+// SPDX-License-Identifier: GPL-2.0
/*
- * tsc_msr.c - TSC frequency enumeration via MSR
+ * TSC frequency enumeration via MSR
*
- * Copyright (C) 2013 Intel Corporation
+ * Copyright (C) 2013, 2018 Intel Corporation
* Author: Bin Gao <bin.gao@intel.com>
- *
- * This file is released under the GPLv2.
*/
#include <linux/kernel.h>
-#include <asm/processor.h>
-#include <asm/setup.h>
+
#include <asm/apic.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/msr.h>
#include <asm/param.h>
+#include <asm/tsc.h>
#define MAX_NUM_FREQS 9
* field msr_plat does.
*/
struct freq_desc {
- u8 x86_family; /* CPU family */
- u8 x86_model; /* model */
u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
u32 freqs[MAX_NUM_FREQS];
};
-static struct freq_desc freq_desc_tables[] = {
- /* PNW */
- { 6, 0x27, 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } },
- /* CLV+ */
- { 6, 0x35, 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } },
- /* TNG - Intel Atom processor Z3400 series */
- { 6, 0x4a, 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } },
- /* VLV2 - Intel Atom processor E3000, Z3600, Z3700 series */
- { 6, 0x37, 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } },
- /* ANN - Intel Atom processor Z3500 series */
- { 6, 0x5a, 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } },
- /* AMT - Intel Atom processor X7-Z8000 and X5-Z8000 series */
- { 6, 0x4c, 1, { 83300, 100000, 133300, 116700,
- 80000, 93300, 90000, 88900, 87500 } },
+/*
+ * Penwell and Clovertrail use spread spectrum clock,
+ * so the freq number is not exactly the same as reported
+ * by MSR based on SDM.
+ */
+static const struct freq_desc freq_desc_pnw = {
+ 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
};
-static int match_cpu(u8 family, u8 model)
-{
- int i;
+static const struct freq_desc freq_desc_clv = {
+ 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+};
- for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) {
- if ((family == freq_desc_tables[i].x86_family) &&
- (model == freq_desc_tables[i].x86_model))
- return i;
- }
+static const struct freq_desc freq_desc_byt = {
+ 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+};
- return -1;
-}
+static const struct freq_desc freq_desc_cht = {
+ 1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+};
-/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-#define id_to_freq(cpu_index, freq_id) \
- (freq_desc_tables[cpu_index].freqs[freq_id])
+static const struct freq_desc freq_desc_tng = {
+ 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+};
+
+static const struct freq_desc freq_desc_ann = {
+ 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+};
+
+static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
+ INTEL_CPU_FAM6(ATOM_PENWELL, freq_desc_pnw),
+ INTEL_CPU_FAM6(ATOM_CLOVERVIEW, freq_desc_clv),
+ INTEL_CPU_FAM6(ATOM_SILVERMONT1, freq_desc_byt),
+ INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht),
+ INTEL_CPU_FAM6(ATOM_MERRIFIELD, freq_desc_tng),
+ INTEL_CPU_FAM6(ATOM_MOOREFIELD, freq_desc_ann),
+ {}
+};
/*
* MSR-based CPU/TSC frequency discovery for certain CPUs.
*/
unsigned long cpu_khz_from_msr(void)
{
- u32 lo, hi, ratio, freq_id, freq;
+ u32 lo, hi, ratio, freq;
+ const struct freq_desc *freq_desc;
+ const struct x86_cpu_id *id;
unsigned long res;
- int cpu_index;
-
- if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
- return 0;
- cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
- if (cpu_index < 0)
+ id = x86_match_cpu(tsc_msr_cpu_ids);
+ if (!id)
return 0;
- if (freq_desc_tables[cpu_index].msr_plat) {
+ freq_desc = (struct freq_desc *)id->driver_data;
+ if (freq_desc->msr_plat) {
rdmsr(MSR_PLATFORM_INFO, lo, hi);
ratio = (lo >> 8) & 0xff;
} else {
/* Get FSB FREQ ID */
rdmsr(MSR_FSB_FREQ, lo, hi);
- freq_id = lo & 0x7;
- freq = id_to_freq(cpu_index, freq_id);
+
+ /* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
+ freq = freq_desc->freqs[lo & 0x7];
/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
res = freq * ratio;
* whitelisted .o files which didn't get objtool generation.
*/
orc_a = cur_orc_table + (a - cur_orc_ip_table);
- return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+ return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
}
#ifdef CONFIG_MODULES
bool unwind_next_frame(struct unwind_state *state)
{
- unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+ unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
enum stack_type prev_type = state->stack_info.type;
struct orc_entry *orc;
bool indirect = false;
/* Don't let modules unload while we're reading their ORC data. */
preempt_disable();
- /* Have we reached the end? */
+ /* End-of-stack check for user tasks: */
if (state->regs && user_mode(state->regs))
- goto done;
+ goto the_end;
/*
* Find the orc_entry associated with the text address.
* calls and calls to noreturn functions.
*/
orc = orc_find(state->signal ? state->ip : state->ip - 1);
- if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
- goto done;
- orig_ip = state->ip;
+ if (!orc)
+ goto err;
+
+ /* End-of-stack check for kernel threads: */
+ if (orc->sp_reg == ORC_REG_UNDEFINED) {
+ if (!orc->end)
+ goto err;
+
+ goto the_end;
+ }
/* Find the previous frame's stack: */
switch (orc->sp_reg) {
if (!state->regs || !state->full_regs) {
orc_warn("missing regs for base reg R10 at ip %pB\n",
(void *)state->ip);
- goto done;
+ goto err;
}
sp = state->regs->r10;
break;
if (!state->regs || !state->full_regs) {
orc_warn("missing regs for base reg R13 at ip %pB\n",
(void *)state->ip);
- goto done;
+ goto err;
}
sp = state->regs->r13;
break;
if (!state->regs || !state->full_regs) {
orc_warn("missing regs for base reg DI at ip %pB\n",
(void *)state->ip);
- goto done;
+ goto err;
}
sp = state->regs->di;
break;
if (!state->regs || !state->full_regs) {
orc_warn("missing regs for base reg DX at ip %pB\n",
(void *)state->ip);
- goto done;
+ goto err;
}
sp = state->regs->dx;
break;
default:
orc_warn("unknown SP base reg %d for ip %pB\n",
orc->sp_reg, (void *)state->ip);
- goto done;
+ goto err;
}
if (indirect) {
if (!deref_stack_reg(state, sp, &sp))
- goto done;
+ goto err;
}
/* Find IP, SP and possibly regs: */
ip_p = sp - sizeof(long);
if (!deref_stack_reg(state, ip_p, &state->ip))
- goto done;
+ goto err;
state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
state->ip, (void *)ip_p);
if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
- goto done;
+ goto err;
}
state->regs = (struct pt_regs *)sp;
if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference iret registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
- goto done;
+ goto err;
}
state->regs = (void *)sp - IRET_FRAME_OFFSET;
case ORC_REG_PREV_SP:
if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
- goto done;
+ goto err;
break;
case ORC_REG_BP:
if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
- goto done;
+ goto err;
break;
default:
orc_warn("unknown BP base reg %d for ip %pB\n",
orc->bp_reg, (void *)orig_ip);
- goto done;
+ goto err;
}
/* Prevent a recursive loop due to bad ORC data: */
state->sp <= prev_sp) {
orc_warn("stack going in the wrong direction? ip=%pB\n",
(void *)orig_ip);
- goto done;
+ goto err;
}
preempt_enable();
return true;
-done:
+err:
+ state->error = true;
+
+the_end:
preempt_enable();
state->stack_info.type = STACK_TYPE_UNKNOWN;
return false;
insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
/* has the side-effect of processing the entire instruction */
insn_get_length(insn);
- if (WARN_ON_ONCE(!insn_complete(insn)))
+ if (!insn_complete(insn))
return -ENOEXEC;
if (is_prefix_bad(insn))
preempt_disable();
tsk->thread.sp0 = vm86->saved_sp0;
tsk->thread.sysenter_cs = __KERNEL_CS;
- update_sp0(tsk);
+ update_task_stack(tsk);
refresh_sysenter_cs(&tsk->thread);
vm86->saved_sp0 = 0;
preempt_enable();
refresh_sysenter_cs(&tsk->thread);
}
- update_sp0(tsk);
+ update_task_stack(tsk);
preempt_enable();
if (vm86->flags & VM86_SCREEN_BITMAP)
* so we can enable protection checks as well as retain 2MB large page
* mappings for kernel text.
*/
-#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE);
+#define X86_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE);
-#define X64_ALIGN_RODATA_END \
+#define X86_ALIGN_RODATA_END \
. = ALIGN(HPAGE_SIZE); \
- __end_rodata_hpage_align = .;
+ __end_rodata_hpage_align = .; \
+ __end_rodata_aligned = .;
#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
#else
-#define X64_ALIGN_RODATA_BEGIN
-#define X64_ALIGN_RODATA_END
+#define X86_ALIGN_RODATA_BEGIN
+#define X86_ALIGN_RODATA_END \
+ . = ALIGN(PAGE_SIZE); \
+ __end_rodata_aligned = .;
#define ALIGN_ENTRY_TEXT_BEGIN
#define ALIGN_ENTRY_TEXT_END
/* .text should occupy whole number of pages */
. = ALIGN(PAGE_SIZE);
- X64_ALIGN_RODATA_BEGIN
+ X86_ALIGN_RODATA_BEGIN
RO_DATA(PAGE_SIZE)
- X64_ALIGN_RODATA_END
+ X86_ALIGN_RODATA_END
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
static void default_nmi_init(void) { };
struct x86_platform_ops x86_platform __ro_after_init = {
- .calibrate_cpu = native_calibrate_cpu,
+ .calibrate_cpu = native_calibrate_cpu_early,
.calibrate_tsc = native_calibrate_tsc,
.get_wallclock = mach_get_cmos_time,
.set_wallclock = mach_set_rtc_mmss,
def_bool y
bool "AMD Secure Encrypted Virtualization (SEV) support"
depends on KVM_AMD && X86_64
- depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP
+ depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
---help---
Provides support for launching Encrypted VMs on AMD processors.
* using swait_active() is safe.
*/
if (swait_active(q))
- swake_up(q);
+ swake_up_one(q);
if (apic_lvtt_tscdeadline(apic))
ktimer->expired_tscdeadline = ktimer->tscdeadline;
if (cache->nobjs >= min)
return 0;
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
- page = (void *)__get_free_page(GFP_KERNEL);
+ page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
if (!page)
return -ENOMEM;
cache->objects[cache->nobjs++] = page;
MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
}
+static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
+}
+
+static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
+ CPU_BASED_MONITOR_TRAP_FLAG;
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
struct vcpu_vmx *vmx = to_vmx(vcpu);
#ifdef CONFIG_X86_64
int cpu = raw_smp_processor_id();
+ unsigned long fs_base, kernel_gs_base;
#endif
int i;
vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
#ifdef CONFIG_X86_64
- save_fsgs_for_kvm();
- vmx->host_state.fs_sel = current->thread.fsindex;
- vmx->host_state.gs_sel = current->thread.gsindex;
-#else
- savesegment(fs, vmx->host_state.fs_sel);
- savesegment(gs, vmx->host_state.gs_sel);
+ if (likely(is_64bit_mm(current->mm))) {
+ save_fsgs_for_kvm();
+ vmx->host_state.fs_sel = current->thread.fsindex;
+ vmx->host_state.gs_sel = current->thread.gsindex;
+ fs_base = current->thread.fsbase;
+ kernel_gs_base = current->thread.gsbase;
+ } else {
+#endif
+ savesegment(fs, vmx->host_state.fs_sel);
+ savesegment(gs, vmx->host_state.gs_sel);
+#ifdef CONFIG_X86_64
+ fs_base = read_msr(MSR_FS_BASE);
+ kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+ }
#endif
if (!(vmx->host_state.fs_sel & 7)) {
vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
savesegment(ds, vmx->host_state.ds_sel);
savesegment(es, vmx->host_state.es_sel);
- vmcs_writel(HOST_FS_BASE, current->thread.fsbase);
+ vmcs_writel(HOST_FS_BASE, fs_base);
vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu));
- vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+ vmx->msr_host_kernel_gs_base = kernel_gs_base;
if (is_long_mode(&vmx->vcpu))
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#else
vmcs_conf->order = get_order(vmcs_conf->size);
vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
- /* KVM supports Enlightened VMCS v1 only */
- if (static_branch_unlikely(&enable_evmcs))
- vmcs_conf->revision_id = KVM_EVMCS_VERSION;
- else
- vmcs_conf->revision_id = vmx_msr_low;
+ vmcs_conf->revision_id = vmx_msr_low;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
return NULL;
vmcs = page_address(pages);
memset(vmcs, 0, vmcs_config.size);
- vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
+
+ /* KVM supports Enlightened VMCS v1 only */
+ if (static_branch_unlikely(&enable_evmcs))
+ vmcs->revision_id = KVM_EVMCS_VERSION;
+ else
+ vmcs->revision_id = vmcs_config.revision_id;
+
return vmcs;
}
goto out_vmcs;
memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
-#if IS_ENABLED(CONFIG_HYPERV)
- if (static_branch_unlikely(&enable_evmcs) &&
+ if (IS_ENABLED(CONFIG_HYPERV) &&
+ static_branch_unlikely(&enable_evmcs) &&
(ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
struct hv_enlightened_vmcs *evmcs =
(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
evmcs->hv_enlightenments_control.msr_bitmap = 1;
}
-#endif
-
}
return 0;
return -ENOMEM;
}
+ /*
+ * When eVMCS is enabled, alloc_vmcs_cpu() sets
+ * vmcs->revision_id to KVM_EVMCS_VERSION instead of
+ * revision_id reported by MSR_IA32_VMX_BASIC.
+ *
+ * However, even though not explictly documented by
+ * TLFS, VMXArea passed as VMXON argument should
+ * still be marked with revision_id reported by
+ * physical CPU.
+ */
+ if (static_branch_unlikely(&enable_evmcs))
+ vmcs->revision_id = vmcs_config.revision_id;
+
per_cpu(vmxarea, cpu) = vmcs;
}
return 0;
HRTIMER_MODE_REL_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+ vmx->nested.vpid02 = allocate_vpid();
+
vmx->nested.vmxon = true;
return 0;
/* Emulate the VMPTRST instruction */
static int handle_vmptrst(struct kvm_vcpu *vcpu)
{
- unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
- gva_t vmcs_gva;
+ unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+ u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+ gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
struct x86_exception e;
+ gva_t gva;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, true, &vmcs_gva))
+ if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
return 1;
/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
- if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
- (void *)&to_vmx(vcpu)->nested.current_vmptr,
- sizeof(u64), &e)) {
+ if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr,
+ sizeof(gpa_t), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
goto free_vmcs;
}
- if (nested) {
+ if (nested)
nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
kvm_vcpu_apicv_active(&vmx->vcpu));
- vmx->nested.vpid02 = allocate_vpid();
- }
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
return &vmx->vcpu;
free_vmcs:
- free_vpid(vmx->nested.vpid02);
free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
kfree(vmx->guest_msrs);
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
+ /*
+ * From the Intel SDM, volume 3:
+ * Fields relevant to VM-entry event injection must be set properly.
+ * These fields are the VM-entry interruption-information field, the
+ * VM-entry exception error code, and the VM-entry instruction length.
+ */
+ if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
+ u32 intr_info = vmcs12->vm_entry_intr_info_field;
+ u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
+ u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
+ bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
+ bool should_have_error_code;
+ bool urg = nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_UNRESTRICTED_GUEST);
+ bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
+
+ /* VM-entry interruption-info field: interruption type */
+ if (intr_type == INTR_TYPE_RESERVED ||
+ (intr_type == INTR_TYPE_OTHER_EVENT &&
+ !nested_cpu_supports_monitor_trap_flag(vcpu)))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: vector */
+ if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
+ (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
+ (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: deliver error code */
+ should_have_error_code =
+ intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
+ x86_exception_has_error_code(vector);
+ if (has_error_code != should_have_error_code)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry exception error code */
+ if (has_error_code &&
+ vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: reserved bits */
+ if (intr_info & INTR_INFO_RESVD_BITS_MASK)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry instruction length */
+ switch (intr_type) {
+ case INTR_TYPE_SOFT_EXCEPTION:
+ case INTR_TYPE_SOFT_INTR:
+ case INTR_TYPE_PRIV_SW_EXCEPTION:
+ if ((vmcs12->vm_entry_instruction_len > 15) ||
+ (vmcs12->vm_entry_instruction_len == 0 &&
+ !nested_cpu_has_zero_length_injection(vcpu)))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ }
+ }
+
return 0;
}
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- u32 msr_entry_idx;
u32 exit_qual;
int r;
nested_get_vmcs12_pages(vcpu, vmcs12);
r = EXIT_REASON_MSR_LOAD_FAIL;
- msr_entry_idx = nested_vmx_load_msr(vcpu,
- vmcs12->vm_entry_msr_load_addr,
- vmcs12->vm_entry_msr_load_count);
- if (msr_entry_idx)
+ exit_qual = nested_vmx_load_msr(vcpu,
+ vmcs12->vm_entry_msr_load_addr,
+ vmcs12->vm_entry_msr_load_count);
+ if (exit_qual)
goto fail;
/*
MSR_F10H_DECFG,
MSR_IA32_UCODE_REV,
+ MSR_IA32_ARCH_CAPABILITIES,
};
static unsigned int num_msr_based_features;
{
switch (msr->index) {
case MSR_IA32_UCODE_REV:
- rdmsrl(msr->index, msr->data);
+ case MSR_IA32_ARCH_CAPABILITIES:
+ rdmsrl_safe(msr->index, &msr->data);
break;
default:
if (kvm_x86_ops->get_msr_feature(msr))
/*
* Make sure the user can only configure tsc_khz values that
* fit into a signed integer.
- * A min value is not calculated needed because it will always
+ * A min value is not calculated because it will always
* be 1 on all machines.
*/
u64 max = min(0x7fffffffULL,
#endif
}
+static inline bool x86_exception_has_error_code(unsigned int vector)
+{
+ static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
+ BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
+ BIT(PF_VECTOR) | BIT(AC_VECTOR);
+
+ return (1U << vector) & exception_has_error_code;
+}
+
static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
{
return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
/* Copy successful. Return zero */
.L_done_memcpy_trap:
- xorq %rax, %rax
+ xorl %eax, %eax
ret
ENDPROC(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
[END_OF_SPACE_NR] = { -1, NULL }
};
+#define INIT_PGD ((pgd_t *) &init_top_pgt)
+
#else /* CONFIG_X86_64 */
enum address_markers_idx {
VMALLOC_END_NR,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE_NR,
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ LDT_NR,
#endif
CPU_ENTRY_AREA_NR,
FIXADDR_START_NR,
[VMALLOC_END_NR] = { 0UL, "vmalloc() End" },
#ifdef CONFIG_HIGHMEM
[PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { 0UL, "LDT remap" },
#endif
[CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" },
[FIXADDR_START_NR] = { 0UL, "Fixmap area" },
[END_OF_SPACE_NR] = { -1, NULL }
};
+#define INIT_PGD (swapper_pg_dir)
+
#endif /* !CONFIG_X86_64 */
/* Multipliers for offsets within the PTEs */
static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
bool checkwx, bool dmesg)
{
-#ifdef CONFIG_X86_64
- pgd_t *start = (pgd_t *) &init_top_pgt;
-#else
- pgd_t *start = swapper_pg_dir;
-#endif
+ pgd_t *start = INIT_PGD;
pgprotval_t prot, eff;
int i;
struct pg_state st = {};
}
EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
-static void ptdump_walk_user_pgd_level_checkwx(void)
+void ptdump_walk_user_pgd_level_checkwx(void)
{
#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pgd_t *pgd = (pgd_t *) &init_top_pgt;
+ pgd_t *pgd = INIT_PGD;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!(__supported_pte_mask & _PAGE_NX) ||
+ !static_cpu_has(X86_FEATURE_PTI))
return;
pr_info("x86/mm: Checking user space page tables\n");
void ptdump_walk_pgd_level_checkwx(void)
{
ptdump_walk_pgd_level_core(NULL, NULL, true, false);
- ptdump_walk_user_pgd_level_checkwx();
}
static int __init pt_dump_init(void)
# endif
address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+ address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
#endif
return 0;
}
if (!(address >= VMALLOC_START && address < VMALLOC_END))
return -1;
- WARN_ON_ONCE(in_nmi());
-
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
return 0;
}
-static const char nx_warning[] = KERN_CRIT
-"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
-static const char smep_warning[] = KERN_CRIT
-"unable to execute userspace code (SMEP?) (uid: %d)\n";
-
static void
show_fault_oops(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
pte = lookup_address_in_pgd(pgd, address, &level);
if (pte && pte_present(*pte) && !pte_exec(*pte))
- printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
+ pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
+ from_kuid(&init_user_ns, current_uid()));
if (pte && pte_present(*pte) && pte_exec(*pte) &&
(pgd_flags(*pgd) & _PAGE_USER) &&
(__read_cr4() & X86_CR4_SMEP))
- printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
+ pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
+ from_kuid(&init_user_ns, current_uid()));
}
- printk(KERN_ALERT "BUG: unable to handle kernel ");
- if (address < PAGE_SIZE)
- printk(KERN_CONT "NULL pointer dereference");
- else
- printk(KERN_CONT "paging request");
-
- printk(KERN_CONT " at %px\n", (void *) address);
+ pr_alert("BUG: unable to handle kernel %s at %px\n",
+ address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
+ (void *)address);
dump_pagetable(address);
}
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (page_is_ram(pagenr)) {
+ if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE,
+ IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
+ != REGION_DISJOINT) {
/*
* For disallowed memory regions in the low 1MB range,
* request that the page be shown as all zeros.
}
}
+/*
+ * begin/end can be in the direct map or the "high kernel mapping"
+ * used for the kernel image only. free_init_pages() will do the
+ * right thing for either kind of address.
+ */
+void free_kernel_image_pages(void *begin, void *end)
+{
+ unsigned long begin_ul = (unsigned long)begin;
+ unsigned long end_ul = (unsigned long)end;
+ unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
+
+
+ free_init_pages("unused kernel image", begin_ul, end_ul);
+
+ /*
+ * PTI maps some of the kernel into userspace. For performance,
+ * this includes some kernel areas that do not contain secrets.
+ * Those areas might be adjacent to the parts of the kernel image
+ * being freed, which may contain secrets. Remove the "high kernel
+ * image mapping" for these freed areas, ensuring they are not even
+ * potentially vulnerable to Meltdown regardless of the specific
+ * optimizations PTI is currently using.
+ *
+ * The "noalias" prevents unmapping the direct map alias which is
+ * needed to access the freed pages.
+ *
+ * This is only valid for 64bit kernels. 32bit has only one mapping
+ * which can't be treated in this way for obvious reasons.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
+ set_memory_np_noalias(begin_ul, len_pages);
+}
+
void __ref free_initmem(void)
{
e820__reallocate_tables();
- free_init_pages("unused kernel",
- (unsigned long)(&__init_begin),
- (unsigned long)(&__init_end));
+ free_kernel_image_pages(&__init_begin, &__init_end);
}
#ifdef CONFIG_BLK_DEV_INITRD
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
- memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
sparse_memory_present_with_active_regions(0);
#ifdef CONFIG_FLATMEM
#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
- memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
}
#endif
set_memory_ro(start, (end-start) >> PAGE_SHIFT);
#endif
- free_init_pages("unused kernel",
- (unsigned long) __va(__pa_symbol(text_end)),
- (unsigned long) __va(__pa_symbol(rodata_start)));
- free_init_pages("unused kernel",
- (unsigned long) __va(__pa_symbol(rodata_end)),
- (unsigned long) __va(__pa_symbol(_sdata)));
+ free_kernel_image_pages((void *)text_end, (void *)rodata_start);
+ free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
debug_checkwx();
-
- /*
- * Do this after all of the manipulation of the
- * kernel text page tables are complete.
- */
- pti_clone_kernel_text();
}
int kern_addr_valid(unsigned long addr)
/* Amount of ram needed to start using large blocks */
#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+/* Adjustable memory block size */
+static unsigned long set_memory_block_size;
+int __init set_memory_block_size_order(unsigned int order)
+{
+ unsigned long size = 1UL << order;
+
+ if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE)
+ return -EINVAL;
+
+ set_memory_block_size = size;
+ return 0;
+}
+
static unsigned long probe_memory_block_size(void)
{
unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
unsigned long bz;
- /* If this is UV system, always set 2G block size */
- if (is_uv_system()) {
- bz = MAX_BLOCK_SIZE;
+ /* If memory block size has been set, then use it */
+ bz = set_memory_block_size;
+ if (bz)
goto done;
- }
/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
eb->nid = nid;
if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
- emu_nid_to_phys[nid] = nid;
+ emu_nid_to_phys[nid] = pb->nid;
pb->start += size;
if (pb->start >= pb->end) {
return end;
}
+static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
+{
+ unsigned long max_pfn = PHYS_PFN(max_addr);
+ unsigned long base_pfn = PHYS_PFN(base);
+ unsigned long hole_pfns = PHYS_PFN(hole);
+
+ return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
+}
+
/*
* Sets up fake nodes of `size' interleaved over physical nodes ranging from
* `addr' to `max_addr'.
*
* Returns zero on success or negative on error.
*/
-static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
struct numa_meminfo *pi,
- u64 addr, u64 max_addr, u64 size)
+ u64 addr, u64 max_addr, u64 size,
+ int nr_nodes, struct numa_memblk *pblk,
+ int nid)
{
nodemask_t physnode_mask = numa_nodes_parsed;
+ int i, ret, uniform = 0;
u64 min_size;
- int nid = 0;
- int i, ret;
- if (!size)
+ if ((!size && !nr_nodes) || (nr_nodes && !pblk))
return -1;
+
/*
- * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
- * increased accordingly if the requested size is too small. This
- * creates a uniform distribution of node sizes across the entire
- * machine (but not necessarily over physical nodes).
+ * In the 'uniform' case split the passed in physical node by
+ * nr_nodes, in the non-uniform case, ignore the passed in
+ * physical block and try to create nodes of at least size
+ * @size.
+ *
+ * In the uniform case, split the nodes strictly by physical
+ * capacity, i.e. ignore holes. In the non-uniform case account
+ * for holes and treat @size as a minimum floor.
*/
- min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
- min_size = max(min_size, FAKE_NODE_MIN_SIZE);
- if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
- min_size = (min_size + FAKE_NODE_MIN_SIZE) &
- FAKE_NODE_MIN_HASH_MASK;
+ if (!nr_nodes)
+ nr_nodes = MAX_NUMNODES;
+ else {
+ nodes_clear(physnode_mask);
+ node_set(pblk->nid, physnode_mask);
+ uniform = 1;
+ }
+
+ if (uniform) {
+ min_size = uniform_size(max_addr, addr, 0, nr_nodes);
+ size = min_size;
+ } else {
+ /*
+ * The limit on emulated nodes is MAX_NUMNODES, so the
+ * size per node is increased accordingly if the
+ * requested size is too small. This creates a uniform
+ * distribution of node sizes across the entire machine
+ * (but not necessarily over physical nodes).
+ */
+ min_size = uniform_size(max_addr, addr,
+ mem_hole_size(addr, max_addr), nr_nodes);
+ }
+ min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
if (size < min_size) {
pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
size >> 20, min_size >> 20);
size = min_size;
}
- size &= FAKE_NODE_MIN_HASH_MASK;
+ size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
/*
* Fill physical nodes with fake nodes of size until there is no memory
node_clear(i, physnode_mask);
continue;
}
+
start = pi->blk[phys_blk].start;
limit = pi->blk[phys_blk].end;
- end = find_end_of_node(start, limit, size);
+ if (uniform)
+ end = start + size;
+ else
+ end = find_end_of_node(start, limit, size);
/*
* If there won't be at least FAKE_NODE_MIN_SIZE of
* non-reserved memory in ZONE_DMA32 for the next node,
* next node, this one must extend to the end of the
* physical node.
*/
- if (limit - end - mem_hole_size(end, limit) < size)
+ if ((limit - end - mem_hole_size(end, limit) < size)
+ && !uniform)
end = limit;
ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
return ret;
}
}
- return 0;
+ return nid;
+}
+
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+ struct numa_meminfo *pi,
+ u64 addr, u64 max_addr, u64 size)
+{
+ return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
+ 0, NULL, NUMA_NO_NODE);
}
int __init setup_emu2phys_nid(int *dfl_phys_nid)
* the fixed node size. Otherwise, if it is just a single number N,
* split the system RAM into N fake nodes.
*/
- if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+ if (strchr(emu_cmdline, 'U')) {
+ nodemask_t physnode_mask = numa_nodes_parsed;
+ unsigned long n;
+ int nid = 0;
+
+ n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+ ret = -1;
+ for_each_node_mask(i, physnode_mask) {
+ ret = split_nodes_size_interleave_uniform(&ei, &pi,
+ pi.blk[i].start, pi.blk[i].end, 0,
+ n, &pi.blk[i], nid);
+ if (ret < 0)
+ break;
+ if (ret < n) {
+ pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
+ __func__, i, ret, n);
+ ret = -1;
+ break;
+ }
+ nid = ret;
+ }
+ } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
u64 size;
size = memparse(emu_cmdline, &emu_cmdline);
#define CPA_FLUSHTLB 1
#define CPA_ARRAY 2
#define CPA_PAGES_ARRAY 4
+#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
#ifdef CONFIG_PROC_FS
static unsigned long direct_pages_count[PG_LEVEL_NUM];
/* No alias checking for _NX bit modifications */
checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
+ /* Has caller explicitly disabled alias checking? */
+ if (in_flag & CPA_NO_CHECK_ALIAS)
+ checkalias = 0;
ret = __change_page_attr_set_clr(&cpa, checkalias);
return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
}
+int set_memory_np_noalias(unsigned long addr, int numpages)
+{
+ int cpa_flags = CPA_NO_CHECK_ALIAS;
+
+ return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+ __pgprot(_PAGE_PRESENT), 0,
+ cpa_flags, NULL);
+}
+
int set_memory_4k(unsigned long addr, int numpages)
{
return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
__pgprot(_PAGE_GLOBAL), 0);
}
+int set_memory_global(unsigned long addr, int numpages)
+{
+ return change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_GLOBAL), 0);
+}
+
static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
{
struct cpa_data cpa;
*/
#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD
+/*
+ * We allocate separate PMDs for the kernel part of the user page-table
+ * when PTI is enabled. We need them to map the per-process LDT into the
+ * user-space page-table.
+ */
+#define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \
+ KERNEL_PGD_PTRS : 0)
+
void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
{
paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS 0
-
+#define PREALLOCATED_USER_PMDS 0
#endif /* CONFIG_X86_PAE */
-static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
{
int i;
- for(i = 0; i < PREALLOCATED_PMDS; i++)
+ for (i = 0; i < count; i++)
if (pmds[i]) {
pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
free_page((unsigned long)pmds[i]);
}
}
-static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
{
int i;
bool failed = false;
if (mm == &init_mm)
gfp &= ~__GFP_ACCOUNT;
- for(i = 0; i < PREALLOCATED_PMDS; i++) {
+ for (i = 0; i < count; i++) {
pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
if (!pmd)
failed = true;
}
if (failed) {
- free_pmds(mm, pmds);
+ free_pmds(mm, pmds, count);
return -ENOMEM;
}
* preallocate which never got a corresponding vma will need to be
* freed manually.
*/
+static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
+{
+ pgd_t pgd = *pgdp;
+
+ if (pgd_val(pgd) != 0) {
+ pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+ *pgdp = native_make_pgd(0);
+
+ paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+ pmd_free(mm, pmd);
+ mm_dec_nr_pmds(mm);
+ }
+}
+
static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
{
int i;
- for(i = 0; i < PREALLOCATED_PMDS; i++) {
- pgd_t pgd = pgdp[i];
+ for (i = 0; i < PREALLOCATED_PMDS; i++)
+ mop_up_one_pmd(mm, &pgdp[i]);
- if (pgd_val(pgd) != 0) {
- pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pgdp[i] = native_make_pgd(0);
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
- paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
- pmd_free(mm, pmd);
- mm_dec_nr_pmds(mm);
- }
- }
+ pgdp = kernel_to_user_pgdp(pgdp);
+
+ for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
+ mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
+#endif
}
static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
}
}
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+ pgd_t *k_pgd, pmd_t *pmds[])
+{
+ pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
+ pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+ p4d_t *u_p4d;
+ pud_t *u_pud;
+ int i;
+
+ u_p4d = p4d_offset(u_pgd, 0);
+ u_pud = pud_offset(u_p4d, 0);
+
+ s_pgd += KERNEL_PGD_BOUNDARY;
+ u_pud += KERNEL_PGD_BOUNDARY;
+
+ for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
+ pmd_t *pmd = pmds[i];
+
+ memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
+ sizeof(pmd_t) * PTRS_PER_PMD);
+
+ pud_populate(mm, u_pud, pmd);
+ }
+
+}
+#else
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+ pgd_t *k_pgd, pmd_t *pmds[])
+{
+}
+#endif
/*
* Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
* assumes that pgd should be in one page.
*/
pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
SLAB_PANIC, NULL);
- if (!pgd_cache)
- return -ENOMEM;
-
return 0;
}
core_initcall(pgd_cache_init);
* We allocate one page for pgd.
*/
if (!SHARED_KERNEL_PMD)
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP,
+ PGD_ALLOCATION_ORDER);
/*
* Now PAE kernel is not running as a Xen domain. We can allocate
static inline void _pgd_free(pgd_t *pgd)
{
if (!SHARED_KERNEL_PMD)
- free_page((unsigned long)pgd);
+ free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
else
kmem_cache_free(pgd_cache, pgd);
}
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
+ pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
pmd_t *pmds[PREALLOCATED_PMDS];
pgd = _pgd_alloc();
mm->pgd = pgd;
- if (preallocate_pmds(mm, pmds) != 0)
+ if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
goto out_free_pgd;
- if (paravirt_pgd_alloc(mm) != 0)
+ if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
goto out_free_pmds;
+ if (paravirt_pgd_alloc(mm) != 0)
+ goto out_free_user_pmds;
+
/*
* Make sure that pre-populating the pmds is atomic with
* respect to anything walking the pgd_list, so that they
pgd_ctor(mm, pgd);
pgd_prepopulate_pmd(mm, pgd, pmds);
+ pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
spin_unlock(&pgd_lock);
return pgd;
+out_free_user_pmds:
+ free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
out_free_pmds:
- free_pmds(mm, pmds);
+ free_pmds(mm, pmds, PREALLOCATED_PMDS);
out_free_pgd:
_pgd_free(pgd);
out:
return 0;
}
+#ifdef CONFIG_X86_64
/**
* pud_free_pmd_page - Clear pud entry and free pmd page.
* @pud: Pointer to a PUD.
+ * @addr: Virtual address associated with pud.
*
- * Context: The pud range has been unmaped and TLB purged.
+ * Context: The pud range has been unmapped and TLB purged.
* Return: 1 if clearing the entry succeeded. 0 otherwise.
+ *
+ * NOTE: Callers must allow a single page allocation.
*/
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
- pmd_t *pmd;
+ pmd_t *pmd, *pmd_sv;
+ pte_t *pte;
int i;
if (pud_none(*pud))
return 1;
pmd = (pmd_t *)pud_page_vaddr(*pud);
+ pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
+ if (!pmd_sv)
+ return 0;
- for (i = 0; i < PTRS_PER_PMD; i++)
- if (!pmd_free_pte_page(&pmd[i]))
- return 0;
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ pmd_sv[i] = pmd[i];
+ if (!pmd_none(pmd[i]))
+ pmd_clear(&pmd[i]);
+ }
pud_clear(pud);
+
+ /* INVLPG to clear all paging-structure caches */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ if (!pmd_none(pmd_sv[i])) {
+ pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
+ free_page((unsigned long)pte);
+ }
+ }
+
+ free_page((unsigned long)pmd_sv);
free_page((unsigned long)pmd);
return 1;
/**
* pmd_free_pte_page - Clear pmd entry and free pte page.
* @pmd: Pointer to a PMD.
+ * @addr: Virtual address associated with pmd.
*
- * Context: The pmd range has been unmaped and TLB purged.
+ * Context: The pmd range has been unmapped and TLB purged.
* Return: 1 if clearing the entry succeeded. 0 otherwise.
*/
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
pte_t *pte;
pte = (pte_t *)pmd_page_vaddr(*pmd);
pmd_clear(pmd);
+
+ /* INVLPG to clear all paging-structure caches */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
free_page((unsigned long)pte);
return 1;
}
+
+#else /* !CONFIG_X86_64 */
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+ return pud_none(*pud);
+}
+
+/*
+ * Disable free page handling on x86-PAE. This assures that ioremap()
+ * does not update sync'd pmd entries. See vmalloc_sync_one().
+ */
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+ return pmd_none(*pmd);
+}
+
+#endif /* CONFIG_X86_64 */
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
#define __GFP_NOTRACK 0
#endif
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PMD
+#else
+#define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PTE
+#endif
+
static void __init pti_print_if_insecure(const char *reason)
{
if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
setup_force_cpu_cap(X86_FEATURE_PTI);
}
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
{
/*
* Changes to the high (kernel) portion of the kernelmode page
if (pgd_none(*pgd)) {
unsigned long new_p4d_page = __get_free_page(gfp);
- if (!new_p4d_page)
+ if (WARN_ON_ONCE(!new_p4d_page))
return NULL;
set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
{
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+ p4d_t *p4d;
pud_t *pud;
+ p4d = pti_user_pagetable_walk_p4d(address);
+ if (!p4d)
+ return NULL;
+
BUILD_BUG_ON(p4d_large(*p4d) != 0);
if (p4d_none(*p4d)) {
unsigned long new_pud_page = __get_free_page(gfp);
- if (!new_pud_page)
+ if (WARN_ON_ONCE(!new_pud_page))
return NULL;
set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
}
if (pud_none(*pud)) {
unsigned long new_pmd_page = __get_free_page(gfp);
- if (!new_pmd_page)
+ if (WARN_ON_ONCE(!new_pmd_page))
return NULL;
set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
return pmd_offset(pud, address);
}
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
/*
* Walk the shadow copy of the page tables (optionally) trying to allocate
* page table pages on the way down. Does not support large pages.
static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
{
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+ pmd_t *pmd;
pte_t *pte;
+ pmd = pti_user_pagetable_walk_pmd(address);
+ if (!pmd)
+ return NULL;
+
/* We can't do anything sensible if we hit a large mapping. */
if (pmd_large(*pmd)) {
WARN_ON(1);
return pte;
}
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
static void __init pti_setup_vsyscall(void)
{
pte_t *pte, *target_pte;
static void __init pti_setup_vsyscall(void) { }
#endif
+enum pti_clone_level {
+ PTI_CLONE_PMD,
+ PTI_CLONE_PTE,
+};
+
static void
-pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+ enum pti_clone_level level)
{
unsigned long addr;
* Clone the populated PMDs which cover start to end. These PMD areas
* can have holes.
*/
- for (addr = start; addr < end; addr += PMD_SIZE) {
+ for (addr = start; addr < end;) {
+ pte_t *pte, *target_pte;
pmd_t *pmd, *target_pmd;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
+ /* Overflow check */
+ if (addr < start)
+ break;
+
pgd = pgd_offset_k(addr);
if (WARN_ON(pgd_none(*pgd)))
return;
p4d = p4d_offset(pgd, addr);
if (WARN_ON(p4d_none(*p4d)))
return;
+
pud = pud_offset(p4d, addr);
- if (pud_none(*pud))
+ if (pud_none(*pud)) {
+ addr += PUD_SIZE;
continue;
+ }
+
pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd))
+ if (pmd_none(*pmd)) {
+ addr += PMD_SIZE;
continue;
+ }
- target_pmd = pti_user_pagetable_walk_pmd(addr);
- if (WARN_ON(!target_pmd))
- return;
-
- /*
- * Only clone present PMDs. This ensures only setting
- * _PAGE_GLOBAL on present PMDs. This should only be
- * called on well-known addresses anyway, so a non-
- * present PMD would be a surprise.
- */
- if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
- return;
-
- /*
- * Setting 'target_pmd' below creates a mapping in both
- * the user and kernel page tables. It is effectively
- * global, so set it as global in both copies. Note:
- * the X86_FEATURE_PGE check is not _required_ because
- * the CPU ignores _PAGE_GLOBAL when PGE is not
- * supported. The check keeps consistentency with
- * code that only set this bit when supported.
- */
- if (boot_cpu_has(X86_FEATURE_PGE))
- *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
-
- /*
- * Copy the PMD. That is, the kernelmode and usermode
- * tables will share the last-level page tables of this
- * address range
- */
- *target_pmd = pmd_clear_flags(*pmd, clear);
+ if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+ target_pmd = pti_user_pagetable_walk_pmd(addr);
+ if (WARN_ON(!target_pmd))
+ return;
+
+ /*
+ * Only clone present PMDs. This ensures only setting
+ * _PAGE_GLOBAL on present PMDs. This should only be
+ * called on well-known addresses anyway, so a non-
+ * present PMD would be a surprise.
+ */
+ if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+ return;
+
+ /*
+ * Setting 'target_pmd' below creates a mapping in both
+ * the user and kernel page tables. It is effectively
+ * global, so set it as global in both copies. Note:
+ * the X86_FEATURE_PGE check is not _required_ because
+ * the CPU ignores _PAGE_GLOBAL when PGE is not
+ * supported. The check keeps consistentency with
+ * code that only set this bit when supported.
+ */
+ if (boot_cpu_has(X86_FEATURE_PGE))
+ *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+ /*
+ * Copy the PMD. That is, the kernelmode and usermode
+ * tables will share the last-level page tables of this
+ * address range
+ */
+ *target_pmd = *pmd;
+
+ addr += PMD_SIZE;
+
+ } else if (level == PTI_CLONE_PTE) {
+
+ /* Walk the page-table down to the pte level */
+ pte = pte_offset_kernel(pmd, addr);
+ if (pte_none(*pte)) {
+ addr += PAGE_SIZE;
+ continue;
+ }
+
+ /* Only clone present PTEs */
+ if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+ return;
+
+ /* Allocate PTE in the user page-table */
+ target_pte = pti_user_pagetable_walk_pte(addr);
+ if (WARN_ON(!target_pte))
+ return;
+
+ /* Set GLOBAL bit in both PTEs */
+ if (boot_cpu_has(X86_FEATURE_PGE))
+ *pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+ /* Clone the PTE */
+ *target_pte = *pte;
+
+ addr += PAGE_SIZE;
+
+ } else {
+ BUG();
+ }
}
}
+#ifdef CONFIG_X86_64
/*
* Clone a single p4d (i.e. a top-level entry on 4-level systems and a
* next-level entry on 5-level systems.
pgd_t *kernel_pgd;
user_p4d = pti_user_pagetable_walk_p4d(addr);
+ if (!user_p4d)
+ return;
+
kernel_pgd = pgd_offset_k(addr);
kernel_p4d = p4d_offset(kernel_pgd, addr);
*user_p4d = *kernel_p4d;
pti_clone_p4d(CPU_ENTRY_AREA_BASE);
}
+#else /* CONFIG_X86_64 */
+
+/*
+ * On 32 bit PAE systems with 1GB of Kernel address space there is only
+ * one pgd/p4d for the whole kernel. Cloning that would map the whole
+ * address space into the user page-tables, making PTI useless. So clone
+ * the page-table on the PMD level to prevent that.
+ */
+static void __init pti_clone_user_shared(void)
+{
+ unsigned long start, end;
+
+ start = CPU_ENTRY_AREA_BASE;
+ end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+ pti_clone_pgtable(start, end, PTI_CLONE_PMD);
+}
+#endif /* CONFIG_X86_64 */
+
/*
* Clone the ESPFIX P4D into the user space visible page table
*/
/*
* Clone the populated PMDs of the entry and irqentry text and force it RO.
*/
-static void __init pti_clone_entry_text(void)
+static void pti_clone_entry_text(void)
{
- pti_clone_pmds((unsigned long) __entry_text_start,
- (unsigned long) __irqentry_text_end,
- _PAGE_RW);
+ pti_clone_pgtable((unsigned long) __entry_text_start,
+ (unsigned long) __irqentry_text_end,
+ PTI_CLONE_PMD);
}
/*
return true;
}
+/*
+ * This is the only user for these and it is not arch-generic
+ * like the other set_memory.h functions. Just extern them.
+ */
+extern int set_memory_nonglobal(unsigned long addr, int numpages);
+extern int set_memory_global(unsigned long addr, int numpages);
+
/*
* For some configurations, map all of kernel text into the user page
* tables. This reduces TLB misses, especially on non-PCID systems.
*/
-void pti_clone_kernel_text(void)
+static void pti_clone_kernel_text(void)
{
/*
* rodata is part of the kernel image and is normally
* clone the areas past rodata, they might contain secrets.
*/
unsigned long start = PFN_ALIGN(_text);
- unsigned long end = (unsigned long)__end_rodata_hpage_align;
+ unsigned long end_clone = (unsigned long)__end_rodata_aligned;
+ unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
if (!pti_kernel_image_global_ok())
return;
* pti_set_kernel_image_nonglobal() did to clear the
* global bit.
*/
- pti_clone_pmds(start, end, _PAGE_RW);
+ pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
+
+ /*
+ * pti_clone_pgtable() will set the global bit in any PMDs
+ * that it clones, but we also need to get any PTEs in
+ * the last level for areas that are not huge-page-aligned.
+ */
+
+ /* Set the global bit for normal non-__init kernel text: */
+ set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
}
-/*
- * This is the only user for it and it is not arch-generic like
- * the other set_memory.h functions. Just extern it.
- */
-extern int set_memory_nonglobal(unsigned long addr, int numpages);
void pti_set_kernel_image_nonglobal(void)
{
/*
unsigned long start = PFN_ALIGN(_text);
unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
- if (pti_kernel_image_global_ok())
- return;
-
+ /*
+ * This clears _PAGE_GLOBAL from the entire kernel image.
+ * pti_clone_kernel_text() map put _PAGE_GLOBAL back for
+ * areas that are mapped to userspace.
+ */
set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
}
pr_info("enabled\n");
+#ifdef CONFIG_X86_32
+ /*
+ * We check for X86_FEATURE_PCID here. But the init-code will
+ * clear the feature flag on 32 bit because the feature is not
+ * supported on 32 bit anyway. To print the warning we need to
+ * check with cpuid directly again.
+ */
+ if (cpuid_ecx(0x1) & BIT(17)) {
+ /* Use printk to work around pr_fmt() */
+ printk(KERN_WARNING "\n");
+ printk(KERN_WARNING "************************************************************\n");
+ printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n");
+ printk(KERN_WARNING "** **\n");
+ printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n");
+ printk(KERN_WARNING "** Your performance will increase dramatically if you **\n");
+ printk(KERN_WARNING "** switch to a 64-bit kernel! **\n");
+ printk(KERN_WARNING "** **\n");
+ printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n");
+ printk(KERN_WARNING "************************************************************\n");
+ }
+#endif
+
pti_clone_user_shared();
/* Undo all global bits from the init pagetables in head_64.S: */
pti_setup_espfix64();
pti_setup_vsyscall();
}
+
+/*
+ * Finalize the kernel mappings in the userspace page-table. Some of the
+ * mappings for the kernel image might have changed since pti_init()
+ * cloned them. This is because parts of the kernel image have been
+ * mapped RO and/or NX. These changes need to be cloned again to the
+ * userspace page-table.
+ */
+void pti_finalize(void)
+{
+ /*
+ * We need to clone everything (again) that maps parts of the
+ * kernel image.
+ */
+ pti_clone_entry_text();
+ pti_clone_kernel_text();
+
+ debug_checkwx_user();
+}
#include <linux/export.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
+#include <linux/gfp.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
* necessary invalidation by clearing out the 'ctx_id' which
* forces a TLB flush when the context is loaded.
*/
-void clear_asid_other(void)
+static void clear_asid_other(void)
{
u16 asid;
{
struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+ bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
unsigned cpu = smp_processor_id();
u64 next_tlb_gen;
+ bool need_flush;
+ u16 new_asid;
/*
* NB: The scheduler will call us with prev == next when switching
next->context.ctx_id);
/*
- * We don't currently support having a real mm loaded without
- * our cpu set in mm_cpumask(). We have all the bookkeeping
- * in place to figure out whether we would need to flush
- * if our cpu were cleared in mm_cpumask(), but we don't
- * currently use it.
+ * Even in lazy TLB mode, the CPU should stay set in the
+ * mm_cpumask. The TLB shootdown code can figure out from
+ * from cpu_tlbstate.is_lazy whether or not to send an IPI.
*/
if (WARN_ON_ONCE(real_prev != &init_mm &&
!cpumask_test_cpu(cpu, mm_cpumask(next))))
cpumask_set_cpu(cpu, mm_cpumask(next));
- return;
+ /*
+ * If the CPU is not in lazy TLB mode, we are just switching
+ * from one thread in a process to another thread in the same
+ * process. No TLB flush required.
+ */
+ if (!was_lazy)
+ return;
+
+ /*
+ * Read the tlb_gen to check whether a flush is needed.
+ * If the TLB is up to date, just use it.
+ * The barrier synchronizes with the tlb_gen increment in
+ * the TLB shootdown code.
+ */
+ smp_mb();
+ next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+ if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+ next_tlb_gen)
+ return;
+
+ /*
+ * TLB contents went out of date while we were in lazy
+ * mode. Fall through to the TLB switching code below.
+ */
+ new_asid = prev_asid;
+ need_flush = true;
} else {
- u16 new_asid;
- bool need_flush;
u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
/*
sync_current_stack_to_mm(next);
}
- /* Stop remote flushes for the previous mm */
- VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
- real_prev != &init_mm);
- cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+ /*
+ * Stop remote flushes for the previous mm.
+ * Skip kernel threads; we never send init_mm TLB flushing IPIs,
+ * but the bitmap manipulation can cause cache line contention.
+ */
+ if (real_prev != &init_mm) {
+ VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
+ mm_cpumask(real_prev)));
+ cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+ }
/*
* Start remote flushes and then read tlb_gen.
*/
- cpumask_set_cpu(cpu, mm_cpumask(next));
+ if (next != &init_mm)
+ cpumask_set_cpu(cpu, mm_cpumask(next));
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+ }
- if (need_flush) {
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- load_new_mm_cr3(next->pgd, new_asid, true);
-
- /*
- * NB: This gets called via leave_mm() in the idle path
- * where RCU functions differently. Tracing normally
- * uses RCU, so we need to use the _rcuidle variant.
- *
- * (There is no good reason for this. The idle code should
- * be rearranged to call this before rcu_idle_enter().)
- */
- trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
- } else {
- /* The new ASID is already up to date. */
- load_new_mm_cr3(next->pgd, new_asid, false);
-
- /* See above wrt _rcuidle. */
- trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
- }
+ if (need_flush) {
+ this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+ this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+ load_new_mm_cr3(next->pgd, new_asid, true);
/*
- * Record last user mm's context id, so we can avoid
- * flushing branch buffer with IBPB if we switch back
- * to the same user.
+ * NB: This gets called via leave_mm() in the idle path
+ * where RCU functions differently. Tracing normally
+ * uses RCU, so we need to use the _rcuidle variant.
+ *
+ * (There is no good reason for this. The idle code should
+ * be rearranged to call this before rcu_idle_enter().)
*/
- if (next != &init_mm)
- this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+ } else {
+ /* The new ASID is already up to date. */
+ load_new_mm_cr3(next->pgd, new_asid, false);
- this_cpu_write(cpu_tlbstate.loaded_mm, next);
- this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+ /* See above wrt _rcuidle. */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
+ /*
+ * Record last user mm's context id, so we can avoid
+ * flushing branch buffer with IBPB if we switch back
+ * to the same user.
+ */
+ if (next != &init_mm)
+ this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+ this_cpu_write(cpu_tlbstate.loaded_mm, next);
+ this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
load_mm_cr4(next);
switch_ldt(real_prev, next);
}
if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
return;
- if (tlb_defer_switch_to_init_mm()) {
- /*
- * There's a significant optimization that may be possible
- * here. We have accurate enough TLB flush tracking that we
- * don't need to maintain coherence of TLB per se when we're
- * lazy. We do, however, need to maintain coherence of
- * paging-structure caches. We could, in principle, leave our
- * old mm loaded and only switch to init_mm when
- * tlb_remove_page() happens.
- */
- this_cpu_write(cpu_tlbstate.is_lazy, true);
- } else {
- switch_mm(NULL, &init_mm, NULL);
- }
+ this_cpu_write(cpu_tlbstate.is_lazy, true);
}
/*
* paging-structure cache to avoid speculatively reading
* garbage into our TLB. Since switching to init_mm is barely
* slower than a minimal flush, just switch to init_mm.
+ *
+ * This should be rare, with native_flush_tlb_others skipping
+ * IPIs to lazy TLB mode CPUs.
*/
switch_mm_irqs_off(NULL, &init_mm, NULL);
return;
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
+ cpumask_var_t lazymask;
+ unsigned int cpu;
+
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
if (info->end == TLB_FLUSH_ALL)
trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
* that UV should be updated so that smp_call_function_many(),
* etc, are optimal on UV.
*/
- unsigned int cpu;
-
cpu = smp_processor_id();
cpumask = uv_flush_tlb_others(cpumask, info);
if (cpumask)
(void *)info, 1);
return;
}
- smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+ /*
+ * A temporary cpumask is used in order to skip sending IPIs
+ * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm).
+ * If the allocation fails, simply IPI every CPU in mm_cpumask.
+ */
+ if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) {
+ smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
+ return;
+ }
+
+ cpumask_copy(lazymask, cpumask);
+
+ for_each_cpu(cpu, lazymask) {
+ if (per_cpu(cpu_tlbstate.is_lazy, cpu))
+ cpumask_clear_cpu(cpu, lazymask);
+ }
+
+ smp_call_function_many(lazymask, flush_tlb_func_remote,
+ (void *)info, 1);
+
+ free_cpumask_var(lazymask);
}
/*
put_cpu();
}
+void tlb_flush_remove_tables_local(void *arg)
+{
+ struct mm_struct *mm = arg;
+
+ if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm &&
+ this_cpu_read(cpu_tlbstate.is_lazy)) {
+ /*
+ * We're in lazy mode. We need to at least flush our
+ * paging-structure cache to avoid speculatively reading
+ * garbage into our TLB. Since switching to init_mm is barely
+ * slower than a minimal flush, just switch to init_mm.
+ */
+ switch_mm_irqs_off(NULL, &init_mm, NULL);
+ }
+}
+
+static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
+ struct cpumask *lazy_cpus)
+{
+ int cpu;
+
+ for_each_cpu(cpu, mm_cpumask(mm)) {
+ if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
+ cpumask_set_cpu(cpu, lazy_cpus);
+ }
+}
+
+void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+ int cpu = get_cpu();
+ cpumask_var_t lazy_cpus;
+
+ if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) {
+ put_cpu();
+ return;
+ }
+
+ if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
+ /*
+ * If the cpumask allocation fails, do a brute force flush
+ * on all the CPUs that have this mm loaded.
+ */
+ smp_call_function_many(mm_cpumask(mm),
+ tlb_flush_remove_tables_local, (void *)mm, 1);
+ put_cpu();
+ return;
+ }
+
+ /*
+ * CPUs with !is_lazy either received a TLB flush IPI while the user
+ * pages in this address range were unmapped, or have context switched
+ * and reloaded %CR3 since then.
+ *
+ * Shootdown IPIs at page table freeing time only need to be sent to
+ * CPUs that may have out of date TLB contents.
+ */
+ mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
+ smp_call_function_many(lazy_cpus,
+ tlb_flush_remove_tables_local, (void *)mm, 1);
+ free_cpumask_var(lazy_cpus);
+ put_cpu();
+}
static void do_flush_tlb_all(void *info)
{
/* sub esp,STACK_SIZE */
EMIT2_off32(0x81, 0xEC, STACK_SIZE);
- /* sub ebp,SCRATCH_SIZE+4+12*/
- EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+ /* sub ebp,SCRATCH_SIZE+12*/
+ EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12);
/* xor ebx,ebx */
EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
/* mov edx,dword ptr [ebp+off]*/
EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
- /* add ebp,SCRATCH_SIZE+4+12*/
- EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+ /* add ebp,SCRATCH_SIZE+12*/
+ EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12);
/* mov ebx,dword ptr [ebp-12]*/
EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
- if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+ if (!pgd_present(*pgd))
continue;
for (i = 0; i < PTRS_PER_P4D; i++) {
p4d = p4d_offset(pgd,
pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
- if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+ if (!p4d_present(*p4d))
continue;
pud = (pud_t *)p4d_page_vaddr(*p4d);
if (!(md->attribute & EFI_MEMORY_WB))
flags |= _PAGE_PCD;
- if (sev_active())
+ if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO)
flags |= _PAGE_ENC;
pfn = md->phys_addr >> PAGE_SHIFT;
#ifdef CONFIG_EFI_MIXED
extern efi_status_t efi64_thunk(u32, ...);
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
#define runtime_service32(func) \
({ \
u32 table = (u32)(unsigned long)efi.systab; \
#define efi_thunk(f, ...) \
({ \
efi_status_t __s; \
- unsigned long __flags; \
u32 __func; \
\
- local_irq_save(__flags); \
arch_efi_call_virt_setup(); \
\
__func = runtime_service32(f); \
__s = efi64_thunk(__func, __VA_ARGS__); \
\
arch_efi_call_virt_teardown(); \
- local_irq_restore(__flags); \
\
__s; \
})
{
efi_status_t status;
u32 phys_tm, phys_tc;
+ unsigned long flags;
spin_lock(&rtc_lock);
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_tm = virt_to_phys_or_null(tm);
phys_tc = virt_to_phys_or_null(tc);
status = efi_thunk(get_time, phys_tm, phys_tc);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
spin_unlock(&rtc_lock);
return status;
{
efi_status_t status;
u32 phys_tm;
+ unsigned long flags;
spin_lock(&rtc_lock);
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_time, phys_tm);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
spin_unlock(&rtc_lock);
return status;
{
efi_status_t status;
u32 phys_enabled, phys_pending, phys_tm;
+ unsigned long flags;
spin_lock(&rtc_lock);
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_enabled = virt_to_phys_or_null(enabled);
phys_pending = virt_to_phys_or_null(pending);
status = efi_thunk(get_wakeup_time, phys_enabled,
phys_pending, phys_tm);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
spin_unlock(&rtc_lock);
return status;
{
efi_status_t status;
u32 phys_tm;
+ unsigned long flags;
spin_lock(&rtc_lock);
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_wakeup_time, enabled, phys_tm);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
spin_unlock(&rtc_lock);
return status;
efi_status_t status;
u32 phys_name, phys_vendor, phys_attr;
u32 phys_data_size, phys_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_data_size = virt_to_phys_or_null(data_size);
phys_vendor = virt_to_phys_or_null(vendor);
status = efi_thunk(get_variable, phys_name, phys_vendor,
phys_attr, phys_data_size, phys_data);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
return status;
}
{
u32 phys_name, phys_vendor, phys_data;
efi_status_t status;
+ unsigned long flags;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
+
+ phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_data = virt_to_phys_or_null_size(data, data_size);
+
+ /* If data_size is > sizeof(u32) we've got problems */
+ status = efi_thunk(set_variable, phys_name, phys_vendor,
+ attr, data_size, phys_data);
+
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+ return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+ u32 attr, unsigned long data_size,
+ void *data)
+{
+ u32 phys_name, phys_vendor, phys_data;
+ efi_status_t status;
+ unsigned long flags;
+
+ if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+ return EFI_NOT_READY;
phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
phys_vendor = virt_to_phys_or_null(vendor);
status = efi_thunk(set_variable, phys_name, phys_vendor,
attr, data_size, phys_data);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
return status;
}
{
efi_status_t status;
u32 phys_name_size, phys_name, phys_vendor;
+ unsigned long flags;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_name_size = virt_to_phys_or_null(name_size);
phys_vendor = virt_to_phys_or_null(vendor);
status = efi_thunk(get_next_variable, phys_name_size,
phys_name, phys_vendor);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
return status;
}
{
efi_status_t status;
u32 phys_count;
+ unsigned long flags;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_count = virt_to_phys_or_null(count);
status = efi_thunk(get_next_high_mono_count, phys_count);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
return status;
}
unsigned long data_size, efi_char16_t *data)
{
u32 phys_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
phys_data = virt_to_phys_or_null_size(data, data_size);
efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
}
static efi_status_t
{
efi_status_t status;
u32 phys_storage, phys_remaining, phys_max;
+ unsigned long flags;
+
+ if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+ return EFI_UNSUPPORTED;
+
+ spin_lock_irqsave(&efi_runtime_lock, flags);
+
+ phys_storage = virt_to_phys_or_null(storage_space);
+ phys_remaining = virt_to_phys_or_null(remaining_space);
+ phys_max = virt_to_phys_or_null(max_variable_size);
+
+ status = efi_thunk(query_variable_info, attr, phys_storage,
+ phys_remaining, phys_max);
+
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+ return status;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space,
+ u64 *remaining_space,
+ u64 *max_variable_size)
+{
+ efi_status_t status;
+ u32 phys_storage, phys_remaining, phys_max;
+ unsigned long flags;
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
+ if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+ return EFI_NOT_READY;
+
phys_storage = virt_to_phys_or_null(storage_space);
phys_remaining = virt_to_phys_or_null(remaining_space);
phys_max = virt_to_phys_or_null(max_variable_size);
status = efi_thunk(query_variable_info, attr, phys_storage,
phys_remaining, phys_max);
+ spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
return status;
}
efi.get_variable = efi_thunk_get_variable;
efi.get_next_variable = efi_thunk_get_next_variable;
efi.set_variable = efi_thunk_set_variable;
+ efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking;
efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
efi.reset_system = efi_thunk_reset_system;
efi.query_variable_info = efi_thunk_query_variable_info;
+ efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking;
efi.update_capsule = efi_thunk_update_capsule;
efi.query_capsule_caps = efi_thunk_query_capsule_caps;
}
*/
void efi_delete_dummy_variable(void)
{
- efi.set_variable((efi_char16_t *)efi_dummy_name,
- &EFI_DUMMY_GUID,
- EFI_VARIABLE_NON_VOLATILE |
- EFI_VARIABLE_BOOTSERVICE_ACCESS |
- EFI_VARIABLE_RUNTIME_ACCESS,
- 0, NULL);
+ efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name,
+ &EFI_DUMMY_GUID,
+ EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL);
}
/*
int num_entries;
void *new;
- if (efi_mem_desc_lookup(addr, &md)) {
+ if (efi_mem_desc_lookup(addr, &md) ||
+ md.type != EFI_BOOT_SERVICES_DATA) {
pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
return;
}
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfld.o pwr.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o
# SFI specific code
ifdef CONFIG_X86_INTEL_MID
#include <asm/apb_timer.h>
#include <asm/reboot.h>
-#include "intel_mid_weak_decls.h"
-
/*
* the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
* cmdline option x86_intel_mid_timer can be used to override the configuration
enum intel_mid_timer_options intel_mid_timer_options;
-/* intel_mid_ops to store sub arch ops */
-static struct intel_mid_ops *intel_mid_ops;
-/* getter function for sub arch ops*/
-static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT;
enum intel_mid_cpu_type __intel_mid_cpu_chip;
EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
}
-static unsigned long __init intel_mid_calibrate_tsc(void)
-{
- return 0;
-}
-
static void __init intel_mid_setup_bp_timer(void)
{
apbt_time_init();
case 0x3C:
case 0x4A:
__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER;
+ x86_platform.legacy.rtc = 1;
break;
case 0x27:
default:
break;
}
- if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops))
- intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
- else {
- intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
- pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
- }
-
out:
- if (intel_mid_ops->arch_setup)
- intel_mid_ops->arch_setup();
-
/*
* Intel MID platforms are using explicitly defined regulators.
*
x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
- x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
x86_init.pci.arch_init = intel_mid_pci_init;
+++ /dev/null
-/*
- * intel_mid_weak_decls.h: Weak declarations of intel-mid.c
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-
-/* For every CPU addition a new get_<cpuname>_ops interface needs
- * to be added.
- */
-extern void *get_penwell_ops(void);
-extern void *get_cloverview_ops(void);
-extern void *get_tangier_ops(void);
+++ /dev/null
-/*
- * mfld.c: Intel Medfield platform setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-#include <asm/intel_mid_vrtc.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init mfld_calibrate_tsc(void)
-{
- unsigned long fast_calibrate;
- u32 lo, hi, ratio, fsb;
-
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
- ratio = (hi >> 8) & 0x1f;
- pr_debug("ratio is %d\n", ratio);
- if (!ratio) {
- pr_err("read a zero ratio, should be incorrect!\n");
- pr_err("force tsc ratio to 16 ...\n");
- ratio = 16;
- }
- rdmsr(MSR_FSB_FREQ, lo, hi);
- if ((lo & 0x7) == 0x7)
- fsb = FSB_FREQ_83SKU;
- else
- fsb = FSB_FREQ_100SKU;
- fast_calibrate = ratio * fsb;
- pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
- lapic_timer_frequency = fsb * 1000 / HZ;
-
- /*
- * TSC on Intel Atom SoCs is reliable and of known frequency.
- * See tsc_msr.c for details.
- */
- setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
- setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
- return fast_calibrate;
-}
-
-static void __init penwell_arch_setup(void)
-{
- x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-}
-
-static struct intel_mid_ops penwell_ops = {
- .arch_setup = penwell_arch_setup,
-};
-
-void *get_penwell_ops(void)
-{
- return &penwell_ops;
-}
-
-void *get_cloverview_ops(void)
-{
- return &penwell_ops;
-}
+++ /dev/null
-/*
- * Intel Merrifield platform specific setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init tangier_calibrate_tsc(void)
-{
- unsigned long fast_calibrate;
- u32 lo, hi, ratio, fsb, bus_freq;
-
- /* *********************** */
- /* Compute TSC:Ratio * FSB */
- /* *********************** */
-
- /* Compute Ratio */
- rdmsr(MSR_PLATFORM_INFO, lo, hi);
- pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo);
-
- ratio = (lo >> 8) & 0xFF;
- pr_debug("ratio is %d\n", ratio);
- if (!ratio) {
- pr_err("Read a zero ratio, force tsc ratio to 4 ...\n");
- ratio = 4;
- }
-
- /* Compute FSB */
- rdmsr(MSR_FSB_FREQ, lo, hi);
- pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n",
- hi, lo);
-
- bus_freq = lo & 0x7;
- pr_debug("bus_freq = 0x%x\n", bus_freq);
-
- if (bus_freq == 0)
- fsb = FSB_FREQ_100SKU;
- else if (bus_freq == 1)
- fsb = FSB_FREQ_100SKU;
- else if (bus_freq == 2)
- fsb = FSB_FREQ_133SKU;
- else if (bus_freq == 3)
- fsb = FSB_FREQ_167SKU;
- else if (bus_freq == 4)
- fsb = FSB_FREQ_83SKU;
- else if (bus_freq == 5)
- fsb = FSB_FREQ_400SKU;
- else if (bus_freq == 6)
- fsb = FSB_FREQ_267SKU;
- else if (bus_freq == 7)
- fsb = FSB_FREQ_333SKU;
- else {
- BUG();
- pr_err("Invalid bus_freq! Setting to minimal value!\n");
- fsb = FSB_FREQ_100SKU;
- }
-
- /* TSC = FSB Freq * Resolved HFM Ratio */
- fast_calibrate = ratio * fsb;
- pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate);
-
- /* ************************************ */
- /* Calculate Local APIC Timer Frequency */
- /* ************************************ */
- lapic_timer_frequency = (fsb * 1000) / HZ;
-
- pr_debug("Setting lapic_timer_frequency = %d\n",
- lapic_timer_frequency);
-
- /*
- * TSC on Intel Atom SoCs is reliable and of known frequency.
- * See tsc_msr.c for details.
- */
- setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
- setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
- return fast_calibrate;
-}
-
-static void __init tangier_arch_setup(void)
-{
- x86_platform.calibrate_tsc = tangier_calibrate_tsc;
- x86_platform.legacy.rtc = 1;
-}
-
-/* tangier arch ops */
-static struct intel_mid_ops tangier_ops = {
- .arch_setup = tangier_arch_setup,
-};
-
-void *get_tangier_ops(void)
-{
- return &tangier_ops;
-}
return PTR_ERR(pdev);
pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
- if (IS_ERR(pdev))
- return PTR_ERR(pdev);
- return 0;
+ return PTR_ERR_OR_ZERO(pdev);
}
static int olpc_xo1_ec_probe(struct platform_device *pdev)
*tunables[cnt].tunp = val;
continue;
}
- if (q == p)
- break;
}
return 0;
}
/* Saved in save_processor_state. */
lgdt saved_context_gdt_desc(%rax)
- xorq %rax, %rax
+ xorl %eax, %eax
/* tell the hibernation core that we've just restored the memory */
movq %rax, in_suspend(%rip)
targets += $(purgatory-y)
PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
$(call if_changed_rule,cc_o_c)
LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
"__tracedata_(start|end)|"
"__(start|stop)_notes|"
"__end_rodata|"
+ "__end_rodata_aligned|"
"__initramfs_start|"
"(jiffies|jiffies_64)|"
#if ELF_BITS == 64
if (!FIXADDR_USER_START)
return 0;
- gate_vma.vm_mm = NULL;
+ vma_init(&gate_vma, NULL);
gate_vma.vm_start = FIXADDR_USER_START;
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
-targets += vdso-syms.lds
-extra-$(VDSO64-y) += vdso-syms.lds
-
-#
-# Match symbols in the DSO that look like VDSO*; produce a file of constants.
-#
-sed-vdsosym := -e 's/^00*/0/' \
- -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p'
-quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
- $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@
-endef
-
-$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
- $(call if_changed,vdsosym)
-
#
# The DSO images are built using a special linker script.
#
__read_mostly int xen_have_vector_callback;
EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+/*
+ * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
+ * before clearing the bss.
+ */
+uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+EXPORT_SYMBOL(xen_start_flags);
+
/*
* Point at some empty memory to start with. We map the real shared_info
* page as soon as fixmap is up and running.
version >> 16, version & 0xffff, extra.extraversion,
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
+
+static void __init xen_pv_init_platform(void)
+{
+ set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+ HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+
+ /* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */
+ xen_vcpu_info_reset(0);
+
+ /* pvclock is in shared info area */
+ xen_init_time_ops();
+}
+
+static void __init xen_pv_guest_late_init(void)
+{
+#ifndef CONFIG_SMP
+ /* Setup shared vcpu info for non-smp configurations */
+ xen_setup_vcpu_info_placement();
+#endif
+}
+
/* Check if running on Xen version (major, minor) or later */
bool
xen_running_on_version_or_later(unsigned int major, unsigned int minor)
xen_write_msr_safe(msr, low, high);
}
-void xen_setup_shared_info(void)
-{
- set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
-
- HYPERVISOR_shared_info =
- (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
- xen_setup_mfn_list_list();
-
- if (system_state == SYSTEM_BOOTING) {
-#ifndef CONFIG_SMP
- /*
- * In UP this is as good a place as any to set up shared info.
- * Limit this to boot only, at restore vcpu setup is done via
- * xen_vcpu_restore().
- */
- xen_setup_vcpu_info_placement();
-#endif
- /*
- * Now that shared info is set up we can start using routines
- * that point to pvclock area.
- */
- xen_init_time_ops();
- }
-}
-
/* This is called once we have the cpu_possible_mask */
-void __ref xen_setup_vcpu_info_placement(void)
+void __init xen_setup_vcpu_info_placement(void)
{
int cpu;
return;
xen_domain_type = XEN_PV_DOMAIN;
+ xen_start_flags = xen_start_info->flags;
xen_setup_features();
- xen_setup_machphys_mapping();
-
/* Install Xen paravirt ops */
pv_info = xen_info;
pv_init_ops.patch = paravirt_patch_default;
pv_cpu_ops = xen_cpu_ops;
+ xen_init_irq_ops();
+
+ /*
+ * Setup xen_vcpu early because it is needed for
+ * local_irq_disable(), irqs_disabled(), e.g. in printk().
+ *
+ * Don't do the full vcpu_info placement stuff until we have
+ * the cpu_possible_mask and a non-dummy shared_info.
+ */
+ xen_vcpu_info_reset(0);
x86_platform.get_nmi_reason = xen_get_nmi_reason;
x86_init.irqs.intr_mode_init = x86_init_noop;
x86_init.oem.arch_setup = xen_arch_setup;
x86_init.oem.banner = xen_banner;
+ x86_init.hyper.init_platform = xen_pv_init_platform;
+ x86_init.hyper.guest_late_init = xen_pv_guest_late_init;
/*
* Set up some pagetable state before starting to set any ptes.
*/
+ xen_setup_machphys_mapping();
xen_init_mmu_ops();
/* Prevent unwanted bits from being set in PTEs. */
__supported_pte_mask &= ~_PAGE_GLOBAL;
+ __default_kernel_pte_mask &= ~_PAGE_GLOBAL;
/*
* Prevent page tables from being allocated in highmem, even
get_cpu_cap(&boot_cpu_data);
x86_configure_nx();
- xen_init_irq_ops();
-
/* Let's presume PV guests always boot on vCPU with id 0. */
per_cpu(xen_vcpu_id, 0) = 0;
- /*
- * Setup xen_vcpu early because idt_setup_early_handler needs it for
- * local_irq_disable(), irqs_disabled().
- *
- * Don't do the full vcpu_info placement stuff until we have
- * the cpu_possible_mask and a non-dummy shared_info.
- */
- xen_vcpu_info_reset(0);
-
idt_setup_early_handler();
xen_init_capabilities();
}
xen_pvh = 1;
+ xen_start_flags = pvh_start_info.flags;
msr = cpuid_ebx(xen_cpuid_base() + 2);
pfn = __pa(hypercall_page);
void __init xen_init_irq_ops(void)
{
- /* For PVH we use default pv_irq_ops settings. */
- if (!xen_feature(XENFEAT_hvm_callback_vector))
- pv_irq_ops = xen_irq_ops;
+ pv_irq_ops = xen_irq_ops;
x86_init.irqs.intr_init = xen_init_IRQ;
}
* We roundup to the PMD, which means that if anybody at this stage is
* using the __ka address of xen_start_info or
* xen_start_info->shared_info they are in going to crash. Fortunatly
- * we have already revectored in xen_setup_kernel_pagetable and in
- * xen_setup_shared_info.
+ * we have already revectored in xen_setup_kernel_pagetable.
*/
size = roundup(size, PMD_SIZE);
/* Remap memory freed due to conflicts with E820 map */
xen_remap_memory();
-
- xen_setup_shared_info();
+ xen_setup_mfn_list_list();
}
static void xen_write_cr2(unsigned long cr2)
{
#include <xen/interface/vcpu.h>
#include <xen/interface/xenpmu.h>
+#include <asm/spec-ctrl.h>
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
cpu_data(cpu).x86_max_cores = 1;
set_cpu_sibling_map(cpu);
+ speculative_store_bypass_ht_init();
+
xen_setup_cpu_clockevents();
notify_cpu_starting(cpu);
}
set_cpu_sibling_map(0);
+ speculative_store_bypass_ht_init();
+
xen_pmu_init(0);
if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))
void xen_pv_post_suspend(int suspend_cancelled)
{
xen_build_mfn_list_list();
-
- xen_setup_shared_info();
+ set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+ HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+ xen_setup_mfn_list_list();
if (suspend_cancelled) {
xen_start_info->store_mfn =
/* Xen may fire a timer up to this many ns early */
#define TIMER_SLOP 100000
+static u64 xen_sched_clock_offset __read_mostly;
+
/* Get the TSC speed from Xen */
static unsigned long xen_tsc_khz(void)
{
return pvclock_tsc_khz(info);
}
-u64 xen_clocksource_read(void)
+static u64 xen_clocksource_read(void)
{
struct pvclock_vcpu_time_info *src;
u64 ret;
return xen_clocksource_read();
}
+static u64 xen_sched_clock(void)
+{
+ return xen_clocksource_read() - xen_sched_clock_offset;
+}
+
static void xen_read_wallclock(struct timespec64 *ts)
{
struct shared_info *s = HYPERVISOR_shared_info;
}
static const struct pv_time_ops xen_time_ops __initconst = {
- .sched_clock = xen_clocksource_read,
+ .sched_clock = xen_sched_clock,
.steal_clock = xen_steal_clock,
};
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
}
-void __ref xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
{
+ xen_sched_clock_offset = xen_clocksource_read();
pv_time_ops = xen_time_ops;
x86_init.timers.timer_init = xen_time_init;
return;
if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
- printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
- "disable pv timer\n");
+ pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
return;
}
+ xen_sched_clock_offset = xen_clocksource_read();
pv_time_ops = xen_time_ops;
x86_init.timers.setup_percpu_clockev = xen_time_init;
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
extern struct shared_info *HYPERVISOR_shared_info;
void xen_setup_mfn_list_list(void);
-void xen_setup_shared_info(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_setup_timer(int cpu);
void xen_setup_runstate_info(int cpu);
void xen_teardown_timer(int cpu);
-u64 xen_clocksource_read(void);
void xen_setup_cpu_clockevents(void);
void xen_save_time_memory_area(void);
void xen_restore_time_memory_area(void);
-void __ref xen_init_time_ops(void);
-void __init xen_hvm_init_time_ops(void);
+void xen_init_time_ops(void);
+void xen_hvm_init_time_ops(void);
irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
select GENERIC_SCHED_CLOCK
select GENERIC_STRNCPY_FROM_USER if KASAN
select HAVE_ARCH_KASAN if MMU
- select HAVE_CC_STACKPROTECTOR
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_EXIT_THREAD
select HAVE_MEMBLOCK
select HAVE_OPROFILE
select HAVE_PERF_EVENTS
+ select HAVE_STACKPROTECTOR
select IRQ_DOMAIN
select MODULES_USE_ELF_RELA
select NO_BOOTMEM
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1,(v))
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1,(v))
-
-/**
- * atomic_dec_return - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0)
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0)
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0)
-
#define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
#endif /* __KERNEL__ */
#endif /* _XTENSA_ATOMIC_H */
*
* Pages can get remapped. Because this might change the 'color' of that page,
* we have to flush the cache before the PTE is changed.
- * (see also Documentation/cachetlb.txt)
+ * (see also Documentation/core-api/cachetlb.rst)
*/
#if defined(CONFIG_MMU) && \
__invalidate_icache_range(start,(end) - (start)); \
} while (0)
-/* This is not required, see Documentation/cachetlb.txt */
+/* This is not required, see Documentation/core-api/cachetlb.rst */
#define flush_icache_page(vma,page) do { } while (0)
#define flush_dcache_mmap_lock(mapping) do { } while (0)
u16 type;
};
+struct perf_event_attr;
struct perf_event;
struct pt_regs;
struct task_struct;
int hw_breakpoint_slots(int type);
-int arch_check_bp_in_kernelspace(struct perf_event *bp);
-int arch_validate_hwbkpt_settings(struct perf_event *bp);
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw);
int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
}
}
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
{
unsigned int len;
unsigned long va;
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- va = info->address;
- len = bp->attr.bp_len;
+ va = hw->address;
+ len = hw->len;
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
/*
* Construct an arch_hw_breakpoint from a perf_event.
*/
-static int arch_build_bp_info(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
/* Type */
- switch (bp->attr.bp_type) {
+ switch (attr->bp_type) {
case HW_BREAKPOINT_X:
- info->type = XTENSA_BREAKPOINT_EXECUTE;
+ hw->type = XTENSA_BREAKPOINT_EXECUTE;
break;
case HW_BREAKPOINT_R:
- info->type = XTENSA_BREAKPOINT_LOAD;
+ hw->type = XTENSA_BREAKPOINT_LOAD;
break;
case HW_BREAKPOINT_W:
- info->type = XTENSA_BREAKPOINT_STORE;
+ hw->type = XTENSA_BREAKPOINT_STORE;
break;
case HW_BREAKPOINT_RW:
- info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
+ hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
break;
default:
return -EINVAL;
}
/* Len */
- info->len = bp->attr.bp_len;
- if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len))
+ hw->len = attr->bp_len;
+ if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len))
return -EINVAL;
/* Address */
- info->address = bp->attr.bp_addr;
- if (info->address & (info->len - 1))
+ hw->address = attr->bp_addr;
+ if (hw->address & (hw->len - 1))
return -EINVAL;
return 0;
}
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
-{
- int ret;
-
- /* Build the arch_hw_breakpoint. */
- ret = arch_build_bp_info(bp);
- return ret;
-}
-
int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data)
{
one needs to mount and use blkio cgroup controller for creating
cgroups and specifying per device IO rate policies.
- See Documentation/cgroups/blkio-controller.txt for more information.
+ See Documentation/cgroup-v1/blkio-controller.txt for more information.
config BLK_DEV_THROTTLING_LOW
bool "Block throttling .low limit interface support (EXPERIMENTAL)"
EXPORT_SYMBOL(bio_add_page);
/**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
* @bio: bio to add pages to
* @iter: iov iterator describing the region to be mapped
*
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
* pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
*/
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
- unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+ unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
- size_t offset, diff;
+ size_t offset;
ssize_t size;
size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
if (unlikely(size <= 0))
return size ? size : -EFAULT;
- nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+ idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
/*
* Deep magic below: We need to walk the pinned pages backwards
bio->bi_iter.bi_size += size;
bio->bi_vcnt += nr_pages;
- diff = (nr_pages * PAGE_SIZE - offset) - size;
- while (nr_pages--) {
- bv[nr_pages].bv_page = pages[nr_pages];
- bv[nr_pages].bv_len = PAGE_SIZE;
- bv[nr_pages].bv_offset = 0;
+ while (idx--) {
+ bv[idx].bv_page = pages[idx];
+ bv[idx].bv_len = PAGE_SIZE;
+ bv[idx].bv_offset = 0;
}
bv[0].bv_offset += offset;
bv[0].bv_len -= offset;
- if (diff)
- bv[bio->bi_vcnt - 1].bv_len -= diff;
+ bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
iov_iter_advance(iter, size);
return 0;
}
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+ unsigned short orig_vcnt = bio->bi_vcnt;
+
+ do {
+ int ret = __bio_iov_iter_get_pages(bio, iter);
+
+ if (unlikely(ret))
+ return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+ } while (iov_iter_count(iter) && !bio_full(bio));
+
+ return 0;
+}
EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
static void submit_bio_wait_endio(struct bio *bio)
if (!bio_integrity_endio(bio))
return;
- if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
- bio->bi_next = NULL;
-
/*
* Need to have a real endio function for chained bios, otherwise
* various corner cases will break (like stacking block devices that
bio_integrity_trim(split);
bio_advance(bio, split->bi_iter.bi_size);
+ bio->bi_iter.bi_done = 0;
if (bio_flagged(bio, BIO_TRACE_COMPLETION))
bio_set_flag(split, BIO_TRACE_COMPLETION);
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- /*
- * XXX this code looks suspicious - it's not consistent with advancing
- * req->bio in caller
- */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
}
if (part->policy && op_is_write(bio_op(bio))) {
char b[BDEVNAME_SIZE];
- printk(KERN_ERR
+ WARN_ONCE(1,
"generic_make_request: Trying to write "
"to read-only block-device %s (partno %d)\n",
bio_devname(bio, b), part->partno);
- return true;
+ /* Older lvm-tools actually trigger this */
+ return false;
}
return false;
struct bio *bio = req->bio;
unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
- if (bio_bytes == bio->bi_iter.bi_size) {
+ if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next;
- bio->bi_next = NULL;
- }
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
dst->cpu = src->cpu;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
+ if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+ dst->rq_flags |= RQF_SPECIAL_PAYLOAD;
+ dst->special_vec = src->special_vec;
+ }
dst->nr_phys_segments = src->nr_phys_segments;
dst->ioprio = src->ioprio;
dst->extra_len = src->extra_len;
static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
{
- if (WARN_ON_ONCE((unsigned int)rq_state >
+ if (WARN_ON_ONCE((unsigned int)rq_state >=
ARRAY_SIZE(blk_mq_rq_state_name_array)))
return "(?)";
return blk_mq_rq_state_name_array[rq_state];
* test and set the bit before assining ->rqs[].
*/
rq = tags->rqs[bitnr];
- if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
+ if (rq && blk_mq_request_started(rq))
iter_data->fn(rq, iter_data->data, reserved);
return true;
}
EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
- int (fn)(void *, struct request *))
-{
- int i, j, ret = 0;
-
- if (WARN_ON_ONCE(!fn))
- goto out;
-
- for (i = 0; i < set->nr_hw_queues; i++) {
- struct blk_mq_tags *tags = set->tags[i];
-
- if (!tags)
- continue;
-
- for (j = 0; j < tags->nr_tags; j++) {
- if (!tags->static_rqs[j])
- continue;
-
- ret = fn(data, tags->static_rqs[j]);
- if (ret)
- goto out;
- }
- }
-
-out:
- return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tagset_iter);
-
void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
void *priv)
{
bool shared = false;
int cpu;
- if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
- MQ_RQ_IN_FLIGHT)
+ if (!blk_mq_mark_complete(rq))
return;
-
if (rq->internal_tag != -1)
blk_mq_sched_completed_request(rq);
if (blk_mq_request_started(rq)) {
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+ rq->rq_flags &= ~RQF_TIMED_OUT;
if (q->dma_drain_size && blk_rq_bytes(rq))
rq->nr_phys_segments--;
}
static void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
+ req->rq_flags |= RQF_TIMED_OUT;
if (req->q->mq_ops->timeout) {
enum blk_eh_timer_return ret;
if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
return false;
+ if (rq->rq_flags & RQF_TIMED_OUT)
+ return false;
deadline = blk_rq_deadline(rq);
if (time_after_eq(jiffies, deadline))
#define BLK_MQ_RESOURCE_DELAY 3 /* ms units */
+/*
+ * Returns true if we did some work AND can potentially do more.
+ */
bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
bool got_budget)
{
blk_mq_run_hw_queue(hctx, true);
else if (needs_restart && (ret == BLK_STS_RESOURCE))
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
+
+ return false;
}
+ /*
+ * If the host/device is unable to accept more work, inform the
+ * caller of that.
+ */
+ if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+ return false;
+
return (queued + errors) != 0;
}
mutex_lock(&set->tag_list_lock);
list_del_rcu(&q->tag_set_list);
- INIT_LIST_HEAD(&q->tag_set_list);
if (list_is_singular(&set->tag_list)) {
/* just transitioned to unshared */
set->flags &= ~BLK_MQ_F_TAG_SHARED;
blk_mq_update_tag_set_depth(set, false);
}
mutex_unlock(&set->tag_list_lock);
-
synchronize_rcu();
+ INIT_LIST_HEAD(&q->tag_set_list);
}
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
local_irq_restore(flags);
}
+EXPORT_SYMBOL(__blk_complete_request);
/**
* blk_complete_request - end I/O on a request
*/
q->queue_tags = tags;
queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
- INIT_LIST_HEAD(&q->tag_busy_list);
return 0;
}
EXPORT_SYMBOL(blk_queue_init_tags);
rq->tag = tag;
bqt->tag_index[tag] = rq;
blk_start_request(rq);
- list_add(&rq->queuelist, &q->tag_busy_list);
return 0;
}
EXPORT_SYMBOL(blk_queue_start_tag);
-
-/**
- * blk_queue_invalidate_tags - invalidate all pending tags
- * @q: the request queue for the device
- *
- * Description:
- * Hardware conditions may dictate a need to stop all pending requests.
- * In this case, we will safely clear the block side of the tag queue and
- * readd all requests to the request queue in the right order.
- **/
-void blk_queue_invalidate_tags(struct request_queue *q)
-{
- struct list_head *tmp, *n;
-
- lockdep_assert_held(q->queue_lock);
-
- list_for_each_safe(tmp, n, &q->tag_busy_list)
- blk_requeue_request(q, list_entry_rq(tmp));
-}
-EXPORT_SYMBOL(blk_queue_invalidate_tags);
if (!req->timeout)
req->timeout = q->rq_timeout;
+ req->rq_flags &= ~RQF_TIMED_OUT;
blk_rq_set_deadline(req, jiffies + req->timeout);
/*
} else if (hdr->din_xfer_len) {
ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp),
hdr->din_xfer_len, GFP_KERNEL);
- } else {
- ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL);
}
if (ret)
struct bsg_device *bd;
unsigned char buf[32];
+ lockdep_assert_held(&bsg_mutex);
+
if (!blk_get_queue(rq))
return ERR_PTR(-ENXIO);
bsg_set_block(bd, file);
atomic_set(&bd->ref_count, 1);
- mutex_lock(&bsg_mutex);
hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
bsg_dbg(bd, "bound to <%s>, max queue %d\n",
format_dev_t(buf, inode->i_rdev), bd->max_queue);
- mutex_unlock(&bsg_mutex);
return bd;
}
{
struct bsg_device *bd;
- mutex_lock(&bsg_mutex);
+ lockdep_assert_held(&bsg_mutex);
hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
if (bd->queue == q) {
}
bd = NULL;
found:
- mutex_unlock(&bsg_mutex);
return bd;
}
*/
mutex_lock(&bsg_mutex);
bcd = idr_find(&bsg_minor_idr, iminor(inode));
- mutex_unlock(&bsg_mutex);
- if (!bcd)
- return ERR_PTR(-ENODEV);
+ if (!bcd) {
+ bd = ERR_PTR(-ENODEV);
+ goto out_unlock;
+ }
bd = __bsg_get_device(iminor(inode), bcd->queue);
- if (bd)
- return bd;
-
- bd = bsg_add_device(inode, bcd->queue, file);
+ if (!bd)
+ bd = bsg_add_device(inode, bcd->queue, file);
+out_unlock:
+ mutex_unlock(&bsg_mutex);
return bd;
}
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
If this option is unchanged from its default "certs/signing_key.pem",
then the kernel will automatically generate the private key and
- certificate as described in Documentation/module-signing.txt
+ certificate as described in Documentation/admin-guide/module-signing.rst
config SYSTEM_TRUSTED_KEYRING
bool "Provide system-wide ring of trusted keys"
#include <linux/kernel.h>
-extern const char __initdata *const blacklist_hashes[];
+extern const char __initconst *const blacklist_hashes[];
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
+/**
+ * af_alg_poll - poll system call handler
+ */
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct af_alg_ctx *ctx = ask->private;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
if (!ctx->more || ctx->used)
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
-EXPORT_SYMBOL_GPL(af_alg_poll_mask);
+EXPORT_SYMBOL_GPL(af_alg_poll);
/**
* af_alg_alloc_areq - allocate struct af_alg_async_req
/* make one iovec available as scatterlist */
err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen);
- if (err < 0)
+ if (err < 0) {
+ rsgl->sg_num_bytes = 0;
return err;
+ }
/* chain the new scatterlist with previous one */
if (areq->last_rsgl)
.sendmsg = aead_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = aead_recvmsg,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static int aead_check_key(struct socket *sock)
.sendmsg = aead_sendmsg_nokey,
.sendpage = aead_sendpage_nokey,
.recvmsg = aead_recvmsg_nokey,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static void *aead_bind(const char *name, u32 type, u32 mask)
.sendmsg = skcipher_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = skcipher_recvmsg,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static int skcipher_check_key(struct socket *sock)
.sendmsg = skcipher_sendmsg_nokey,
.sendpage = skcipher_sendpage_nokey,
.recvmsg = skcipher_recvmsg_nokey,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static void *skcipher_bind(const char *name, u32 type, u32 mask)
/* Asymmetric public-key cryptography key type
*
- * See Documentation/security/asymmetric-keys.txt
+ * See Documentation/crypto/asymmetric-keys.txt
*
* Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
/* Signature verification with an asymmetric key
*
- * See Documentation/security/asymmetric-keys.txt
+ * See Documentation/crypto/asymmetric-keys.txt
*
* Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
return -EINVAL;
}
+ if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0) {
+ /* Discard the BIT STRING metadata */
+ if (vlen < 1 || *(const u8 *)value != 0)
+ return -EBADMSG;
+
+ value++;
+ vlen--;
+ }
+
ctx->cert->raw_sig = value;
ctx->cert->raw_sig_size = vlen;
return 0;
union morus640_block_in tail;
memcpy(tail.bytes, src, size);
+ memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
- crypto_morus640_load_a(&m, src);
+ crypto_morus640_load_a(&m, tail.bytes);
crypto_morus640_core(state, &m);
crypto_morus640_store_a(tail.bytes, &m);
memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
st[24] ^= bc[ 4];
}
-static void __optimize("O3") keccakf(u64 st[25])
+static void keccakf(u64 st[25])
{
int round;
#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
#include <linux/pwm.h>
+#include <linux/suspend.h>
#include <linux/delay.h>
#include "internal.h"
#define LPSS_GPIODEF0_DMA_LLP BIT(13)
static DEFINE_MUTEX(lpss_iosf_mutex);
+static bool lpss_iosf_d3_entered;
static void lpss_iosf_enter_d3_state(void)
{
iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
LPSS_IOSF_GPIODEF0, value1, mask1);
+
+ lpss_iosf_d3_entered = true;
+
exit:
mutex_unlock(&lpss_iosf_mutex);
}
mutex_lock(&lpss_iosf_mutex);
+ if (!lpss_iosf_d3_entered)
+ goto exit;
+
+ lpss_iosf_d3_entered = false;
+
iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE,
LPSS_IOSF_GPIODEF0, value1, mask1);
iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE,
LPSS_IOSF_PMCSR, value2, mask2);
+exit:
mutex_unlock(&lpss_iosf_mutex);
}
* wrong status for devices being about to be powered off. See
* lpss_iosf_enter_d3_state() for further information.
*/
- if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+ if (acpi_target_system_state() == ACPI_STATE_S0 &&
+ lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
lpss_iosf_enter_d3_state();
return ret;
return_ACPI_STATUS(status);
}
- /*
- * 1) Disable all GPEs
- * 2) Enable all wakeup GPEs
- */
+ /* Disable all GPEs */
status = acpi_hw_disable_all_gpes();
if (ACPI_FAILURE(status)) {
return_ACPI_STATUS(status);
}
+ /*
+ * If the target sleep state is S5, clear all GPEs and fixed events too
+ */
+ if (sleep_state == ACPI_STATE_S5) {
+ status = acpi_hw_clear_acpi_status();
+ if (ACPI_FAILURE(status)) {
+ return_ACPI_STATUS(status);
+ }
+ }
acpi_gbl_system_awake_and_running = FALSE;
+ /* Enable all wakeup GPEs */
status = acpi_hw_enable_all_wakeup_gpes();
if (ACPI_FAILURE(status)) {
return_ACPI_STATUS(status);
status =
acpi_ps_create_op(walk_state, aml_op_start, &op);
if (ACPI_FAILURE(status)) {
+ /*
+ * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by
+ * executing it as a control method. However, if we encounter
+ * an error while loading the table, we need to keep trying to
+ * load the table rather than aborting the table load. Set the
+ * status to AE_OK to proceed with the table load.
+ */
+ if ((walk_state->
+ parse_flags & ACPI_PARSE_MODULE_LEVEL)
+ && status == AE_ALREADY_EXISTS) {
+ status = AE_OK;
+ }
if (status == AE_CTRL_PARSE_CONTINUE) {
continue;
}
acpi_ps_next_parse_state(walk_state, op, status);
if (status == AE_CTRL_PENDING) {
status = AE_OK;
+ } else
+ if ((walk_state->
+ parse_flags & ACPI_PARSE_MODULE_LEVEL)
+ && status != AE_CTRL_TRANSFER
+ && ACPI_FAILURE(status)) {
+ /*
+ * ACPI_PARSE_MODULE_LEVEL flag means that we are currently
+ * loading a table by executing it as a control method.
+ * However, if we encounter an error while loading the table,
+ * we need to keep trying to load the table rather than
+ * aborting the table load (setting the status to AE_OK
+ * continues the table load). If we get a failure at this
+ * point, it means that the dispatcher got an error while
+ * processing Op (most likely an AML operand error) or a
+ * control method was called from module level and the
+ * dispatcher returned AE_CTRL_TRANSFER. In the latter case,
+ * leave the status alone, there's nothing wrong with it.
+ */
+ status = AE_OK;
}
}
switch (lookup_status) {
case AE_ALREADY_EXISTS:
- acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+ acpi_os_printf(ACPI_MSG_BIOS_ERROR);
message = "Failure creating";
break;
case AE_NOT_FOUND:
- acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+ acpi_os_printf(ACPI_MSG_BIOS_ERROR);
message = "Could not resolve";
break;
default:
- acpi_os_printf("\n" ACPI_MSG_ERROR);
+ acpi_os_printf(ACPI_MSG_ERROR);
message = "Failure resolving";
break;
}
*/
pr_err("extension failed to load: %s", hook->name);
__battery_hook_unregister(hook, 0);
- return;
+ goto end;
}
}
pr_info("new extension: %s\n", hook->name);
+end:
mutex_unlock(&hook_mutex);
}
EXPORT_SYMBOL_GPL(battery_hook_register);
*/
static void battery_hook_add_battery(struct acpi_battery *battery)
{
- struct acpi_battery_hook *hook_node;
+ struct acpi_battery_hook *hook_node, *tmp;
mutex_lock(&hook_mutex);
INIT_LIST_HEAD(&battery->list);
* when a battery gets hotplugged or initialized
* during the battery module initialization.
*/
- list_for_each_entry(hook_node, &battery_hook_list, list) {
+ list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) {
if (hook_node->add_battery(battery->bat)) {
/*
* The notification of the extensions has failed, to
* prevent further errors we will unload the extension.
*/
- __battery_hook_unregister(hook_node, 0);
pr_err("error in extension, unloading: %s",
hook_node->name);
+ __battery_hook_unregister(hook_node, 0);
}
}
mutex_unlock(&hook_mutex);
}
}
+static const struct dmi_system_id acpi_ec_no_wakeup[] = {
+ {
+ .ident = "Thinkpad X1 Carbon 6th",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
+ },
+ },
+ { },
+};
+
int __init acpi_ec_init(void)
{
int result;
if (result)
return result;
+ /*
+ * Disable EC wakeup on following systems to prevent periodic
+ * wakeup from EC GPE.
+ */
+ if (dmi_check_system(acpi_ec_no_wakeup)) {
+ ec_no_wakeup = true;
+ pr_debug("Disabling EC wakeup on suspend-to-idle\n");
+ }
+
/* Drivers must be started after acpi_ec_query_init() */
dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
/*
const guid_t *guid;
int rc, i;
+ if (cmd_rc)
+ *cmd_rc = -EINVAL;
func = cmd;
if (cmd == ND_CMD_CALL) {
call_pkg = buf;
* If we return an error (like elsewhere) then caller wouldn't
* be able to rely upon data returned to make calculation.
*/
+ if (cmd_rc)
+ *cmd_rc = 0;
return 0;
}
mutex_lock(&acpi_desc->init_mutex);
rc = sprintf(buf, "%d%s", acpi_desc->scrub_count,
- work_busy(&acpi_desc->dwork.work)
+ acpi_desc->scrub_busy
&& !acpi_desc->cancel ? "+\n" : "\n");
mutex_unlock(&acpi_desc->init_mutex);
}
return 0;
}
+static void __sched_ars(struct acpi_nfit_desc *acpi_desc, unsigned int tmo)
+{
+ lockdep_assert_held(&acpi_desc->init_mutex);
+
+ acpi_desc->scrub_busy = 1;
+ /* note this should only be set from within the workqueue */
+ if (tmo)
+ acpi_desc->scrub_tmo = tmo;
+ queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
+}
+
+static void sched_ars(struct acpi_nfit_desc *acpi_desc)
+{
+ __sched_ars(acpi_desc, 0);
+}
+
+static void notify_ars_done(struct acpi_nfit_desc *acpi_desc)
+{
+ lockdep_assert_held(&acpi_desc->init_mutex);
+
+ acpi_desc->scrub_busy = 0;
+ acpi_desc->scrub_count++;
+ if (acpi_desc->scrub_count_state)
+ sysfs_notify_dirent(acpi_desc->scrub_count_state);
+}
+
static void acpi_nfit_scrub(struct work_struct *work)
{
struct acpi_nfit_desc *acpi_desc;
mutex_lock(&acpi_desc->init_mutex);
query_rc = acpi_nfit_query_poison(acpi_desc);
tmo = __acpi_nfit_scrub(acpi_desc, query_rc);
- if (tmo) {
- queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
- acpi_desc->scrub_tmo = tmo;
- } else {
- acpi_desc->scrub_count++;
- if (acpi_desc->scrub_count_state)
- sysfs_notify_dirent(acpi_desc->scrub_count_state);
- }
+ if (tmo)
+ __sched_ars(acpi_desc, tmo);
+ else
+ notify_ars_done(acpi_desc);
memset(acpi_desc->ars_status, 0, acpi_desc->max_ars);
mutex_unlock(&acpi_desc->init_mutex);
}
break;
}
- queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+ sched_ars(acpi_desc);
return 0;
}
}
}
if (scheduled) {
- queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+ sched_ars(acpi_desc);
dev_dbg(dev, "ars_scan triggered\n");
}
mutex_unlock(&acpi_desc->init_mutex);
unsigned int max_ars;
unsigned int scrub_count;
unsigned int scrub_mode;
+ unsigned int scrub_busy:1;
unsigned int cancel:1;
unsigned long dimm_cmd_force_en;
unsigned long bus_cmd_force_en;
#include <linux/uaccess.h>
#include <linux/io-64-nonatomic-lo-hi.h>
+#include "acpica/accommon.h"
+#include "acpica/acnamesp.h"
#include "internal.h"
#define _COMPONENT ACPI_OS_SERVICES
}
EXPORT_SYMBOL(acpi_check_region);
+static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level,
+ void *_res, void **return_value)
+{
+ struct acpi_mem_space_context **mem_ctx;
+ union acpi_operand_object *handler_obj;
+ union acpi_operand_object *region_obj2;
+ union acpi_operand_object *region_obj;
+ struct resource *res = _res;
+ acpi_status status;
+
+ region_obj = acpi_ns_get_attached_object(handle);
+ if (!region_obj)
+ return AE_OK;
+
+ handler_obj = region_obj->region.handler;
+ if (!handler_obj)
+ return AE_OK;
+
+ if (region_obj->region.space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY)
+ return AE_OK;
+
+ if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE))
+ return AE_OK;
+
+ region_obj2 = acpi_ns_get_secondary_object(region_obj);
+ if (!region_obj2)
+ return AE_OK;
+
+ mem_ctx = (void *)®ion_obj2->extra.region_context;
+
+ if (!(mem_ctx[0]->address >= res->start &&
+ mem_ctx[0]->address < res->end))
+ return AE_OK;
+
+ status = handler_obj->address_space.setup(region_obj,
+ ACPI_REGION_DEACTIVATE,
+ NULL, (void **)mem_ctx);
+ if (ACPI_SUCCESS(status))
+ region_obj->region.flags &= ~(AOPOBJ_SETUP_COMPLETE);
+
+ return status;
+}
+
+/**
+ * acpi_release_memory - Release any mappings done to a memory region
+ * @handle: Handle to namespace node
+ * @res: Memory resource
+ * @level: A level that terminates the search
+ *
+ * Walks through @handle and unmaps all SystemMemory Operation Regions that
+ * overlap with @res and that have already been activated (mapped).
+ *
+ * This is a helper that allows drivers to place special requirements on memory
+ * region that may overlap with operation regions, primarily allowing them to
+ * safely map the region as non-cached memory.
+ *
+ * The unmapped Operation Regions will be automatically remapped next time they
+ * are called, so the drivers do not need to do anything else.
+ */
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+ u32 level)
+{
+ if (!(res->flags & IORESOURCE_MEM))
+ return AE_TYPE;
+
+ return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
+ acpi_deactivate_mem_region, NULL, res, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_release_memory);
+
/*
* Let drivers know whether the resource checks are effective
*/
if (cpu_node) {
cpu_node = acpi_find_processor_package_id(table, cpu_node,
level, flag);
- /* Only the first level has a guaranteed id */
- if (level == 0)
+ /*
+ * As per specification if the processor structure represents
+ * an actual processor, then ACPI processor ID must be valid.
+ * For processor containers ACPI_PPTT_ACPI_PROCESSOR_ID_VALID
+ * should be set if the UID is valid
+ */
+ if (level == 0 ||
+ cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID)
return cpu_node->acpi_processor_id;
return ACPI_PTR_DIFF(cpu_node, table);
}
config SATA_HIGHBANK
tristate "Calxeda Highbank SATA support"
- depends on HAS_DMA
depends on ARCH_HIGHBANK || COMPILE_TEST
help
This option enables support for the Calxeda Highbank SoC's
config SATA_MV
tristate "Marvell SATA support"
- depends on HAS_DMA
depends on PCI || ARCH_DOVE || ARCH_MV78XX0 || \
ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST
select GENERIC_PHY
{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
+ { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */
/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
return strcmp(buf, dmi->driver_data) < 0;
}
+static bool ahci_broken_lpm(struct pci_dev *pdev)
+{
+ static const struct dmi_system_id sysids[] = {
+ /* Various Lenovo 50 series have LPM issues with older BIOSen */
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X250"),
+ },
+ .driver_data = "20180406", /* 1.31 */
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L450"),
+ },
+ .driver_data = "20180420", /* 1.28 */
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T450s"),
+ },
+ .driver_data = "20180315", /* 1.33 */
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
+ },
+ /*
+ * Note date based on release notes, 2.35 has been
+ * reported to be good, but I've been unable to get
+ * a hold of the reporter to get the DMI BIOS date.
+ * TODO: fix this.
+ */
+ .driver_data = "20180310", /* 2.35 */
+ },
+ { } /* terminate list */
+ };
+ const struct dmi_system_id *dmi = dmi_first_match(sysids);
+ int year, month, date;
+ char buf[9];
+
+ if (!dmi)
+ return false;
+
+ dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
+ snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
+
+ return strcmp(buf, dmi->driver_data) < 0;
+}
+
static bool ahci_broken_online(struct pci_dev *pdev)
{
#define ENCODE_BUSDEVFN(bus, slot, func) \
"quirky BIOS, skipping spindown on poweroff\n");
}
+ if (ahci_broken_lpm(pdev)) {
+ pi.flags |= ATA_FLAG_NO_LPM;
+ dev_warn(&pdev->dev,
+ "BIOS update required for Link Power Management support\n");
+ }
+
if (ahci_broken_suspend(pdev)) {
hpriv->flags |= AHCI_HFLAG_NO_SUSPEND;
dev_warn(&pdev->dev,
*
* Return: 0 on success; Error code otherwise.
*/
-int ahci_mvebu_stop_engine(struct ata_port *ap)
+static int ahci_mvebu_stop_engine(struct ata_port *ap)
{
void __iomem *port_mmio = ahci_port_base(ap);
u32 tmp, port_fbs;
#include <linux/kernel.h>
#include <linux/gfp.h>
#include <linux/module.h>
+#include <linux/nospec.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
/* get the slot number from the message */
pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
- if (pmp < EM_MAX_SLOTS)
+ if (pmp < EM_MAX_SLOTS) {
+ pmp = array_index_nospec(pmp, EM_MAX_SLOTS);
emp = &pp->em_priv[pmp];
- else
+ } else {
return -EINVAL;
+ }
/* mask off the activity bits if we are in sw_activity
* mode, user should turn off sw_activity before setting
(id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
dev->horkage |= ATA_HORKAGE_NOLPM;
+ if (ap->flags & ATA_FLAG_NO_LPM)
+ dev->horkage |= ATA_HORKAGE_NOLPM;
+
if (dev->horkage & ATA_HORKAGE_NOLPM) {
ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
struct ata_queued_cmd *qc;
- for (i = 0; i < ATA_MAX_QUEUE; i++) {
- qc = __ata_qc_from_tag(ap, i);
+ ata_qc_for_each_raw(ap, qc, i) {
if (qc->flags & ATA_QCFLAG_ACTIVE &&
qc->scsicmd == scmd)
break;
static int ata_eh_nr_in_flight(struct ata_port *ap)
{
+ struct ata_queued_cmd *qc;
unsigned int tag;
int nr = 0;
/* count only non-internal commands */
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- if (ata_tag_internal(tag))
- continue;
- if (ata_qc_from_tag(ap, tag))
+ ata_qc_for_each(ap, qc, tag) {
+ if (qc)
nr++;
}
goto out_unlock;
if (cnt == ap->fastdrain_cnt) {
+ struct ata_queued_cmd *qc;
unsigned int tag;
/* No progress during the last interval, tag all
* in-flight qcs as timed out and freeze the port.
*/
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
+ ata_qc_for_each(ap, qc, tag) {
if (qc)
qc->err_mask |= AC_ERR_TIMEOUT;
}
static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
{
+ struct ata_queued_cmd *qc;
int tag, nr_aborted = 0;
WARN_ON(!ap->ops->error_handler);
ata_eh_set_pending(ap, 0);
/* include internal tag in iteration */
- for (tag = 0; tag <= ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
-
+ ata_qc_for_each_with_internal(ap, qc, tag) {
if (qc && (!link || qc->dev->link == link)) {
qc->flags |= ATA_QCFLAG_FAILED;
ata_qc_complete(qc);
return;
/* has LLDD analyzed already? */
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- qc = __ata_qc_from_tag(ap, tag);
-
+ ata_qc_for_each_raw(ap, qc, tag) {
if (!(qc->flags & ATA_QCFLAG_FAILED))
continue;
{
struct ata_port *ap = link->ap;
struct ata_eh_context *ehc = &link->eh_context;
+ struct ata_queued_cmd *qc;
struct ata_device *dev;
unsigned int all_err_mask = 0, eflags = 0;
int tag, nr_failed = 0, nr_quiet = 0;
all_err_mask |= ehc->i.err_mask;
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+ ata_qc_for_each_raw(ap, qc, tag) {
if (!(qc->flags & ATA_QCFLAG_FAILED) ||
ata_dev_phys_link(qc->dev) != link)
continue;
{
struct ata_port *ap = link->ap;
struct ata_eh_context *ehc = &link->eh_context;
+ struct ata_queued_cmd *qc;
const char *frozen, *desc;
char tries_buf[6] = "";
int tag, nr_failed = 0;
if (ehc->i.desc[0] != '\0')
desc = ehc->i.desc;
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+ ata_qc_for_each_raw(ap, qc, tag) {
if (!(qc->flags & ATA_QCFLAG_FAILED) ||
ata_dev_phys_link(qc->dev) != link ||
((qc->flags & ATA_QCFLAG_QUIET) &&
ehc->i.serror & SERR_DEV_XCHG ? "DevExch " : "");
#endif
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
+ ata_qc_for_each_raw(ap, qc, tag) {
struct ata_taskfile *cmd = &qc->tf, *res = &qc->result_tf;
char data_buf[20] = "";
char cdb_buf[70] = "";
*/
void ata_eh_finish(struct ata_port *ap)
{
+ struct ata_queued_cmd *qc;
int tag;
/* retry or finish qcs */
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+ ata_qc_for_each_raw(ap, qc, tag) {
if (!(qc->flags & ATA_QCFLAG_FAILED))
continue;
*/
goto invalid_param_len;
}
- if (block > dev->n_sectors)
- goto out_of_range;
all = cdb[14] & 0x1;
+ if (all) {
+ /*
+ * Ignore the block address (zone ID) as defined by ZBC.
+ */
+ block = 0;
+ } else if (block >= dev->n_sectors) {
+ /*
+ * Block must be a valid zone ID (a zone start LBA).
+ */
+ fp = 2;
+ goto invalid_fld;
+ }
if (ata_ncq_enabled(qc->dev) &&
ata_fpdma_zac_mgmt_out_supported(qc->dev)) {
invalid_fld:
ata_scsi_set_invalid_field(qc->dev, scmd, fp, 0xff);
return 1;
- out_of_range:
- /* "Logical Block Address out of range" */
- ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x21, 0x00);
- return 1;
invalid_param_len:
/* "Parameter list length error" */
ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x1a, 0x0);
{
/* We let libATA core do actual (queue) tag allocation */
- /* all non NCQ/queued commands should have tag#0 */
- if (ata_tag_internal(tag)) {
- DPRINTK("mapping internal cmds to tag#0\n");
- return 0;
- }
-
if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) {
DPRINTK("tag %d invalid : out of range\n", tag);
return 0;
/* Workaround for data length mismatch errata */
if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) {
- for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
- qc = ata_qc_from_tag(ap, tag);
+ ata_qc_for_each_with_internal(ap, qc, tag) {
if (qc && ata_is_atapi(qc->tf.protocol)) {
u32 hcontrol;
/* Set HControl[27] to clear error registers */
struct ata_port *ap = ata_shost_to_port(sdev->host);
struct nv_adma_port_priv *pp = ap->private_data;
struct nv_adma_port_priv *port0, *port1;
- struct scsi_device *sdev0, *sdev1;
struct pci_dev *pdev = to_pci_dev(ap->host->dev);
unsigned long segment_boundary, flags;
unsigned short sg_tablesize;
port0 = ap->host->ports[0]->private_data;
port1 = ap->host->ports[1]->private_data;
- sdev0 = ap->host->ports[0]->link.device[0].sdev;
- sdev1 = ap->host->ports[1]->link.device[0].sdev;
if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
(port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
/*
skb_queue_head_init(&iadev->rx_dma_q);
iadev->rx_free_desc_qhead = NULL;
- iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL);
+ iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL);
if (!iadev->rx_open) {
printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n",
dev->number);
return -EFAULT;
if (pool < 0 || pool > ZATM_LAST_POOL)
return -EINVAL;
+ pool = array_index_nospec(pool,
+ ZATM_LAST_POOL + 1);
if (copy_from_user(&info,
&((struct zatm_pool_req __user *) arg)->info,
sizeof(info))) return -EFAULT;
topology.o container.o property.o cacheinfo.o \
devcon.o
obj-$(CONFIG_DEVTMPFS) += devtmpfs.o
-obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
obj-y += power/
-obj-$(CONFIG_HAS_DMA) += dma-mapping.o
-obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_ISA_BUS_API) += isa.o
obj-y += firmware_loader/
obj-$(CONFIG_NUMA) += node.o
link->rpm_active = true;
}
pm_runtime_new_link(consumer);
+ /*
+ * If the link is being added by the consumer driver at probe
+ * time, balance the decrementation of the supplier's runtime PM
+ * usage counter after consumer probe in driver_probe_device().
+ */
+ if (consumer->links.status == DL_DEV_PROBING)
+ pm_runtime_get_noresume(supplier);
}
get_device(supplier);
link->supplier = supplier;
switch (consumer->links.status) {
case DL_DEV_PROBING:
/*
- * Balance the decrementation of the supplier's
- * runtime PM usage counter after consumer probe
- * in driver_probe_device().
+ * Some callers expect the link creation during
+ * consumer driver probe to resume the supplier
+ * even without DL_FLAG_RPM_ACTIVE.
*/
if (flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_get_sync(supplier);
+ pm_runtime_resume(supplier);
link->status = DL_STATE_CONSUMER_PROBE;
break;
goto probe_failed;
}
- /*
- * Ensure devices are listed in devices_kset in correct order
- * It's important to move Dev to the end of devices_kset before
- * calling .probe, because it could be recursive and parent Dev
- * should always go first
- */
- devices_kset_move_last(dev);
-
if (dev->bus->probe) {
ret = dev->bus->probe(dev);
if (ret)
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Coherent per-device memory handling.
- * Borrowed from i386
- */
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-
-struct dma_coherent_mem {
- void *virt_base;
- dma_addr_t device_base;
- unsigned long pfn_base;
- int size;
- int flags;
- unsigned long *bitmap;
- spinlock_t spinlock;
- bool use_dev_dma_pfn_offset;
-};
-
-static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
-
-static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
-{
- if (dev && dev->dma_mem)
- return dev->dma_mem;
- return NULL;
-}
-
-static inline dma_addr_t dma_get_device_base(struct device *dev,
- struct dma_coherent_mem * mem)
-{
- if (mem->use_dev_dma_pfn_offset)
- return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
- else
- return mem->device_base;
-}
-
-static int dma_init_coherent_memory(
- phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
- struct dma_coherent_mem **mem)
-{
- struct dma_coherent_mem *dma_mem = NULL;
- void __iomem *mem_base = NULL;
- int pages = size >> PAGE_SHIFT;
- int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
- int ret;
-
- if (!size) {
- ret = -EINVAL;
- goto out;
- }
-
- mem_base = memremap(phys_addr, size, MEMREMAP_WC);
- if (!mem_base) {
- ret = -EINVAL;
- goto out;
- }
- dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
- if (!dma_mem) {
- ret = -ENOMEM;
- goto out;
- }
- dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
- if (!dma_mem->bitmap) {
- ret = -ENOMEM;
- goto out;
- }
-
- dma_mem->virt_base = mem_base;
- dma_mem->device_base = device_addr;
- dma_mem->pfn_base = PFN_DOWN(phys_addr);
- dma_mem->size = pages;
- dma_mem->flags = flags;
- spin_lock_init(&dma_mem->spinlock);
-
- *mem = dma_mem;
- return 0;
-
-out:
- kfree(dma_mem);
- if (mem_base)
- memunmap(mem_base);
- return ret;
-}
-
-static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
-{
- if (!mem)
- return;
-
- memunmap(mem->virt_base);
- kfree(mem->bitmap);
- kfree(mem);
-}
-
-static int dma_assign_coherent_memory(struct device *dev,
- struct dma_coherent_mem *mem)
-{
- if (!dev)
- return -ENODEV;
-
- if (dev->dma_mem)
- return -EBUSY;
-
- dev->dma_mem = mem;
- return 0;
-}
-
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
- dma_addr_t device_addr, size_t size, int flags)
-{
- struct dma_coherent_mem *mem;
- int ret;
-
- ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags, &mem);
- if (ret)
- return ret;
-
- ret = dma_assign_coherent_memory(dev, mem);
- if (ret)
- dma_release_coherent_memory(mem);
- return ret;
-}
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
- struct dma_coherent_mem *mem = dev->dma_mem;
-
- if (!mem)
- return;
- dma_release_coherent_memory(mem);
- dev->dma_mem = NULL;
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
- dma_addr_t device_addr, size_t size)
-{
- struct dma_coherent_mem *mem = dev->dma_mem;
- unsigned long flags;
- int pos, err;
-
- size += device_addr & ~PAGE_MASK;
-
- if (!mem)
- return ERR_PTR(-EINVAL);
-
- spin_lock_irqsave(&mem->spinlock, flags);
- pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
- err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
- spin_unlock_irqrestore(&mem->spinlock, flags);
-
- if (err != 0)
- return ERR_PTR(err);
- return mem->virt_base + (pos << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
-
-static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
- ssize_t size, dma_addr_t *dma_handle)
-{
- int order = get_order(size);
- unsigned long flags;
- int pageno;
- void *ret;
-
- spin_lock_irqsave(&mem->spinlock, flags);
-
- if (unlikely(size > (mem->size << PAGE_SHIFT)))
- goto err;
-
- pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
- if (unlikely(pageno < 0))
- goto err;
-
- /*
- * Memory was found in the coherent area.
- */
- *dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
- ret = mem->virt_base + (pageno << PAGE_SHIFT);
- spin_unlock_irqrestore(&mem->spinlock, flags);
- memset(ret, 0, size);
- return ret;
-err:
- spin_unlock_irqrestore(&mem->spinlock, flags);
- return NULL;
-}
-
-/**
- * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool
- * @dev: device from which we allocate memory
- * @size: size of requested memory area
- * @dma_handle: This will be filled with the correct dma handle
- * @ret: This pointer will be filled with the virtual address
- * to allocated area.
- *
- * This function should be only called from per-arch dma_alloc_coherent()
- * to support allocation from per-device coherent memory pools.
- *
- * Returns 0 if dma_alloc_coherent should continue with allocating from
- * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
- */
-int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
- dma_addr_t *dma_handle, void **ret)
-{
- struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
-
- if (!mem)
- return 0;
-
- *ret = __dma_alloc_from_coherent(mem, size, dma_handle);
- if (*ret)
- return 1;
-
- /*
- * In the case where the allocation can not be satisfied from the
- * per-device area, try to fall back to generic memory if the
- * constraints allow it.
- */
- return mem->flags & DMA_MEMORY_EXCLUSIVE;
-}
-EXPORT_SYMBOL(dma_alloc_from_dev_coherent);
-
-void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle)
-{
- if (!dma_coherent_default_memory)
- return NULL;
-
- return __dma_alloc_from_coherent(dma_coherent_default_memory, size,
- dma_handle);
-}
-
-static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
- int order, void *vaddr)
-{
- if (mem && vaddr >= mem->virt_base && vaddr <
- (mem->virt_base + (mem->size << PAGE_SHIFT))) {
- int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
- unsigned long flags;
-
- spin_lock_irqsave(&mem->spinlock, flags);
- bitmap_release_region(mem->bitmap, page, order);
- spin_unlock_irqrestore(&mem->spinlock, flags);
- return 1;
- }
- return 0;
-}
-
-/**
- * dma_release_from_dev_coherent() - free memory to device coherent memory pool
- * @dev: device from which the memory was allocated
- * @order: the order of pages allocated
- * @vaddr: virtual address of allocated pages
- *
- * This checks whether the memory was allocated from the per-device
- * coherent memory pool and if so, releases that memory.
- *
- * Returns 1 if we correctly released the memory, or 0 if the caller should
- * proceed with releasing memory from generic pools.
- */
-int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr)
-{
- struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
-
- return __dma_release_from_coherent(mem, order, vaddr);
-}
-EXPORT_SYMBOL(dma_release_from_dev_coherent);
-
-int dma_release_from_global_coherent(int order, void *vaddr)
-{
- if (!dma_coherent_default_memory)
- return 0;
-
- return __dma_release_from_coherent(dma_coherent_default_memory, order,
- vaddr);
-}
-
-static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
- struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
-{
- if (mem && vaddr >= mem->virt_base && vaddr + size <=
- (mem->virt_base + (mem->size << PAGE_SHIFT))) {
- unsigned long off = vma->vm_pgoff;
- int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
- int user_count = vma_pages(vma);
- int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
- *ret = -ENXIO;
- if (off < count && user_count <= count - off) {
- unsigned long pfn = mem->pfn_base + start + off;
- *ret = remap_pfn_range(vma, vma->vm_start, pfn,
- user_count << PAGE_SHIFT,
- vma->vm_page_prot);
- }
- return 1;
- }
- return 0;
-}
-
-/**
- * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool
- * @dev: device from which the memory was allocated
- * @vma: vm_area for the userspace memory
- * @vaddr: cpu address returned by dma_alloc_from_dev_coherent
- * @size: size of the memory buffer allocated
- * @ret: result from remap_pfn_range()
- *
- * This checks whether the memory was allocated from the per-device
- * coherent memory pool and if so, maps that memory to the provided vma.
- *
- * Returns 1 if @vaddr belongs to the device coherent pool and the caller
- * should return @ret, or 0 if they should proceed with mapping memory from
- * generic areas.
- */
-int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
- void *vaddr, size_t size, int *ret)
-{
- struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
-
- return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
-}
-EXPORT_SYMBOL(dma_mmap_from_dev_coherent);
-
-int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
- size_t size, int *ret)
-{
- if (!dma_coherent_default_memory)
- return 0;
-
- return __dma_mmap_from_coherent(dma_coherent_default_memory, vma,
- vaddr, size, ret);
-}
-
-/*
- * Support for reserved memory regions defined in device tree
- */
-#ifdef CONFIG_OF_RESERVED_MEM
-#include <linux/of.h>
-#include <linux/of_fdt.h>
-#include <linux/of_reserved_mem.h>
-
-static struct reserved_mem *dma_reserved_default_memory __initdata;
-
-static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
-{
- struct dma_coherent_mem *mem = rmem->priv;
- int ret;
-
- if (!mem) {
- ret = dma_init_coherent_memory(rmem->base, rmem->base,
- rmem->size,
- DMA_MEMORY_EXCLUSIVE, &mem);
- if (ret) {
- pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
- &rmem->base, (unsigned long)rmem->size / SZ_1M);
- return ret;
- }
- }
- mem->use_dev_dma_pfn_offset = true;
- rmem->priv = mem;
- dma_assign_coherent_memory(dev, mem);
- return 0;
-}
-
-static void rmem_dma_device_release(struct reserved_mem *rmem,
- struct device *dev)
-{
- if (dev)
- dev->dma_mem = NULL;
-}
-
-static const struct reserved_mem_ops rmem_dma_ops = {
- .device_init = rmem_dma_device_init,
- .device_release = rmem_dma_device_release,
-};
-
-static int __init rmem_dma_setup(struct reserved_mem *rmem)
-{
- unsigned long node = rmem->fdt_node;
-
- if (of_get_flat_dt_prop(node, "reusable", NULL))
- return -EINVAL;
-
-#ifdef CONFIG_ARM
- if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
- pr_err("Reserved memory: regions without no-map are not yet supported\n");
- return -EINVAL;
- }
-
- if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
- WARN(dma_reserved_default_memory,
- "Reserved memory: region for default DMA coherent area is redefined\n");
- dma_reserved_default_memory = rmem;
- }
-#endif
-
- rmem->ops = &rmem_dma_ops;
- pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
- &rmem->base, (unsigned long)rmem->size / SZ_1M);
- return 0;
-}
-
-static int __init dma_init_reserved_memory(void)
-{
- const struct reserved_mem_ops *ops;
- int ret;
-
- if (!dma_reserved_default_memory)
- return -ENOMEM;
-
- ops = dma_reserved_default_memory->ops;
-
- /*
- * We rely on rmem_dma_device_init() does not propagate error of
- * dma_assign_coherent_memory() for "NULL" device.
- */
- ret = ops->device_init(dma_reserved_default_memory, NULL);
-
- if (!ret) {
- dma_coherent_default_memory = dma_reserved_default_memory->priv;
- pr_info("DMA: default coherent area is set\n");
- }
-
- return ret;
-}
-
-core_initcall(dma_init_reserved_memory);
-
-RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Contiguous Memory Allocator for DMA mapping framework
- * Copyright (c) 2010-2011 by Samsung Electronics.
- * Written by:
- * Marek Szyprowski <m.szyprowski@samsung.com>
- * Michal Nazarewicz <mina86@mina86.com>
- */
-
-#define pr_fmt(fmt) "cma: " fmt
-
-#ifdef CONFIG_CMA_DEBUG
-#ifndef DEBUG
-# define DEBUG
-#endif
-#endif
-
-#include <asm/page.h>
-#include <asm/dma-contiguous.h>
-
-#include <linux/memblock.h>
-#include <linux/err.h>
-#include <linux/sizes.h>
-#include <linux/dma-contiguous.h>
-#include <linux/cma.h>
-
-#ifdef CONFIG_CMA_SIZE_MBYTES
-#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
-#else
-#define CMA_SIZE_MBYTES 0
-#endif
-
-struct cma *dma_contiguous_default_area;
-
-/*
- * Default global CMA area size can be defined in kernel's .config.
- * This is useful mainly for distro maintainers to create a kernel
- * that works correctly for most supported systems.
- * The size can be set in bytes or as a percentage of the total memory
- * in the system.
- *
- * Users, who want to set the size of global CMA area for their system
- * should use cma= kernel parameter.
- */
-static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
-static phys_addr_t size_cmdline = -1;
-static phys_addr_t base_cmdline;
-static phys_addr_t limit_cmdline;
-
-static int __init early_cma(char *p)
-{
- pr_debug("%s(%s)\n", __func__, p);
- size_cmdline = memparse(p, &p);
- if (*p != '@')
- return 0;
- base_cmdline = memparse(p + 1, &p);
- if (*p != '-') {
- limit_cmdline = base_cmdline + size_cmdline;
- return 0;
- }
- limit_cmdline = memparse(p + 1, &p);
-
- return 0;
-}
-early_param("cma", early_cma);
-
-#ifdef CONFIG_CMA_SIZE_PERCENTAGE
-
-static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
-{
- struct memblock_region *reg;
- unsigned long total_pages = 0;
-
- /*
- * We cannot use memblock_phys_mem_size() here, because
- * memblock_analyze() has not been called yet.
- */
- for_each_memblock(memory, reg)
- total_pages += memblock_region_memory_end_pfn(reg) -
- memblock_region_memory_base_pfn(reg);
-
- return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
-}
-
-#else
-
-static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
-{
- return 0;
-}
-
-#endif
-
-/**
- * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
- * @limit: End address of the reserved memory (optional, 0 for any).
- *
- * This function reserves memory from early allocator. It should be
- * called by arch specific code once the early allocator (memblock or bootmem)
- * has been activated and all other subsystems have already allocated/reserved
- * memory.
- */
-void __init dma_contiguous_reserve(phys_addr_t limit)
-{
- phys_addr_t selected_size = 0;
- phys_addr_t selected_base = 0;
- phys_addr_t selected_limit = limit;
- bool fixed = false;
-
- pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
-
- if (size_cmdline != -1) {
- selected_size = size_cmdline;
- selected_base = base_cmdline;
- selected_limit = min_not_zero(limit_cmdline, limit);
- if (base_cmdline + size_cmdline == limit_cmdline)
- fixed = true;
- } else {
-#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
- selected_size = size_bytes;
-#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
- selected_size = cma_early_percent_memory();
-#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
- selected_size = min(size_bytes, cma_early_percent_memory());
-#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
- selected_size = max(size_bytes, cma_early_percent_memory());
-#endif
- }
-
- if (selected_size && !dma_contiguous_default_area) {
- pr_debug("%s: reserving %ld MiB for global area\n", __func__,
- (unsigned long)selected_size / SZ_1M);
-
- dma_contiguous_reserve_area(selected_size, selected_base,
- selected_limit,
- &dma_contiguous_default_area,
- fixed);
- }
-}
-
-/**
- * dma_contiguous_reserve_area() - reserve custom contiguous area
- * @size: Size of the reserved area (in bytes),
- * @base: Base address of the reserved area optional, use 0 for any
- * @limit: End address of the reserved memory (optional, 0 for any).
- * @res_cma: Pointer to store the created cma region.
- * @fixed: hint about where to place the reserved area
- *
- * This function reserves memory from early allocator. It should be
- * called by arch specific code once the early allocator (memblock or bootmem)
- * has been activated and all other subsystems have already allocated/reserved
- * memory. This function allows to create custom reserved areas for specific
- * devices.
- *
- * If @fixed is true, reserve contiguous area at exactly @base. If false,
- * reserve in range from @base to @limit.
- */
-int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
- phys_addr_t limit, struct cma **res_cma,
- bool fixed)
-{
- int ret;
-
- ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
- "reserved", res_cma);
- if (ret)
- return ret;
-
- /* Architecture specific contiguous memory fixup. */
- dma_contiguous_early_fixup(cma_get_base(*res_cma),
- cma_get_size(*res_cma));
-
- return 0;
-}
-
-/**
- * dma_alloc_from_contiguous() - allocate pages from contiguous area
- * @dev: Pointer to device for which the allocation is performed.
- * @count: Requested number of pages.
- * @align: Requested alignment of pages (in PAGE_SIZE order).
- * @gfp_mask: GFP flags to use for this allocation.
- *
- * This function allocates memory buffer for specified device. It uses
- * device specific contiguous memory area if available or the default
- * global one. Requires architecture specific dev_get_cma_area() helper
- * function.
- */
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
- unsigned int align, gfp_t gfp_mask)
-{
- if (align > CONFIG_CMA_ALIGNMENT)
- align = CONFIG_CMA_ALIGNMENT;
-
- return cma_alloc(dev_get_cma_area(dev), count, align, gfp_mask);
-}
-
-/**
- * dma_release_from_contiguous() - release allocated pages
- * @dev: Pointer to device for which the pages were allocated.
- * @pages: Allocated pages.
- * @count: Number of allocated pages.
- *
- * This function releases memory allocated by dma_alloc_from_contiguous().
- * It returns false when provided pages do not belong to contiguous area and
- * true otherwise.
- */
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
- int count)
-{
- return cma_release(dev_get_cma_area(dev), pages, count);
-}
-
-/*
- * Support for reserved memory regions defined in device tree
- */
-#ifdef CONFIG_OF_RESERVED_MEM
-#include <linux/of.h>
-#include <linux/of_fdt.h>
-#include <linux/of_reserved_mem.h>
-
-#undef pr_fmt
-#define pr_fmt(fmt) fmt
-
-static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
-{
- dev_set_cma_area(dev, rmem->priv);
- return 0;
-}
-
-static void rmem_cma_device_release(struct reserved_mem *rmem,
- struct device *dev)
-{
- dev_set_cma_area(dev, NULL);
-}
-
-static const struct reserved_mem_ops rmem_cma_ops = {
- .device_init = rmem_cma_device_init,
- .device_release = rmem_cma_device_release,
-};
-
-static int __init rmem_cma_setup(struct reserved_mem *rmem)
-{
- phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
- phys_addr_t mask = align - 1;
- unsigned long node = rmem->fdt_node;
- struct cma *cma;
- int err;
-
- if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
- of_get_flat_dt_prop(node, "no-map", NULL))
- return -EINVAL;
-
- if ((rmem->base & mask) || (rmem->size & mask)) {
- pr_err("Reserved memory: incorrect alignment of CMA region\n");
- return -EINVAL;
- }
-
- err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma);
- if (err) {
- pr_err("Reserved memory: unable to setup CMA region\n");
- return err;
- }
- /* Architecture specific contiguous memory fixup. */
- dma_contiguous_early_fixup(rmem->base, rmem->size);
-
- if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
- dma_contiguous_set_default(cma);
-
- rmem->ops = &rmem_cma_ops;
- rmem->priv = cma;
-
- pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
- &rmem->base, (unsigned long)rmem->size / SZ_1M);
-
- return 0;
-}
-RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * drivers/base/dma-mapping.c - arch-independent dma-mapping routines
- *
- * Copyright (c) 2006 SUSE Linux Products GmbH
- * Copyright (c) 2006 Tejun Heo <teheo@suse.de>
- */
-
-#include <linux/acpi.h>
-#include <linux/dma-mapping.h>
-#include <linux/export.h>
-#include <linux/gfp.h>
-#include <linux/of_device.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-/*
- * Managed DMA API
- */
-struct dma_devres {
- size_t size;
- void *vaddr;
- dma_addr_t dma_handle;
- unsigned long attrs;
-};
-
-static void dmam_release(struct device *dev, void *res)
-{
- struct dma_devres *this = res;
-
- dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
- this->attrs);
-}
-
-static int dmam_match(struct device *dev, void *res, void *match_data)
-{
- struct dma_devres *this = res, *match = match_data;
-
- if (this->vaddr == match->vaddr) {
- WARN_ON(this->size != match->size ||
- this->dma_handle != match->dma_handle);
- return 1;
- }
- return 0;
-}
-
-/**
- * dmam_alloc_coherent - Managed dma_alloc_coherent()
- * @dev: Device to allocate coherent memory for
- * @size: Size of allocation
- * @dma_handle: Out argument for allocated DMA handle
- * @gfp: Allocation flags
- *
- * Managed dma_alloc_coherent(). Memory allocated using this function
- * will be automatically released on driver detach.
- *
- * RETURNS:
- * Pointer to allocated memory on success, NULL on failure.
- */
-void *dmam_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp)
-{
- struct dma_devres *dr;
- void *vaddr;
-
- dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
- if (!dr)
- return NULL;
-
- vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp);
- if (!vaddr) {
- devres_free(dr);
- return NULL;
- }
-
- dr->vaddr = vaddr;
- dr->dma_handle = *dma_handle;
- dr->size = size;
-
- devres_add(dev, dr);
-
- return vaddr;
-}
-EXPORT_SYMBOL(dmam_alloc_coherent);
-
-/**
- * dmam_free_coherent - Managed dma_free_coherent()
- * @dev: Device to free coherent memory for
- * @size: Size of allocation
- * @vaddr: Virtual address of the memory to free
- * @dma_handle: DMA handle of the memory to free
- *
- * Managed dma_free_coherent().
- */
-void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
-{
- struct dma_devres match_data = { size, vaddr, dma_handle };
-
- dma_free_coherent(dev, size, vaddr, dma_handle);
- WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
-}
-EXPORT_SYMBOL(dmam_free_coherent);
-
-/**
- * dmam_alloc_attrs - Managed dma_alloc_attrs()
- * @dev: Device to allocate non_coherent memory for
- * @size: Size of allocation
- * @dma_handle: Out argument for allocated DMA handle
- * @gfp: Allocation flags
- * @attrs: Flags in the DMA_ATTR_* namespace.
- *
- * Managed dma_alloc_attrs(). Memory allocated using this function will be
- * automatically released on driver detach.
- *
- * RETURNS:
- * Pointer to allocated memory on success, NULL on failure.
- */
-void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- struct dma_devres *dr;
- void *vaddr;
-
- dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
- if (!dr)
- return NULL;
-
- vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
- if (!vaddr) {
- devres_free(dr);
- return NULL;
- }
-
- dr->vaddr = vaddr;
- dr->dma_handle = *dma_handle;
- dr->size = size;
- dr->attrs = attrs;
-
- devres_add(dev, dr);
-
- return vaddr;
-}
-EXPORT_SYMBOL(dmam_alloc_attrs);
-
-#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
-
-static void dmam_coherent_decl_release(struct device *dev, void *res)
-{
- dma_release_declared_memory(dev);
-}
-
-/**
- * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory()
- * @dev: Device to declare coherent memory for
- * @phys_addr: Physical address of coherent memory to be declared
- * @device_addr: Device address of coherent memory to be declared
- * @size: Size of coherent memory to be declared
- * @flags: Flags
- *
- * Managed dma_declare_coherent_memory().
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
- dma_addr_t device_addr, size_t size, int flags)
-{
- void *res;
- int rc;
-
- res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL);
- if (!res)
- return -ENOMEM;
-
- rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size,
- flags);
- if (!rc)
- devres_add(dev, res);
- else
- devres_free(res);
-
- return rc;
-}
-EXPORT_SYMBOL(dmam_declare_coherent_memory);
-
-/**
- * dmam_release_declared_memory - Managed dma_release_declared_memory().
- * @dev: Device to release declared coherent memory for
- *
- * Managed dmam_release_declared_memory().
- */
-void dmam_release_declared_memory(struct device *dev)
-{
- WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL));
-}
-EXPORT_SYMBOL(dmam_release_declared_memory);
-
-#endif
-
-/*
- * Create scatter-list for the already allocated DMA buffer.
- */
-int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t handle, size_t size)
-{
- struct page *page = virt_to_page(cpu_addr);
- int ret;
-
- ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
- if (unlikely(ret))
- return ret;
-
- sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
- return 0;
-}
-EXPORT_SYMBOL(dma_common_get_sgtable);
-
-/*
- * Create userspace mapping for the DMA-coherent memory.
- */
-int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
- int ret = -ENXIO;
-#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
- unsigned long user_count = vma_pages(vma);
- unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long off = vma->vm_pgoff;
-
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
- if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
- return ret;
-
- if (off < count && user_count <= (count - off))
- ret = remap_pfn_range(vma, vma->vm_start,
- page_to_pfn(virt_to_page(cpu_addr)) + off,
- user_count << PAGE_SHIFT,
- vma->vm_page_prot);
-#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
-
- return ret;
-}
-EXPORT_SYMBOL(dma_common_mmap);
-
-#ifdef CONFIG_MMU
-static struct vm_struct *__dma_common_pages_remap(struct page **pages,
- size_t size, unsigned long vm_flags, pgprot_t prot,
- const void *caller)
-{
- struct vm_struct *area;
-
- area = get_vm_area_caller(size, vm_flags, caller);
- if (!area)
- return NULL;
-
- if (map_vm_area(area, prot, pages)) {
- vunmap(area->addr);
- return NULL;
- }
-
- return area;
-}
-
-/*
- * remaps an array of PAGE_SIZE pages into another vm_area
- * Cannot be used in non-sleeping contexts
- */
-void *dma_common_pages_remap(struct page **pages, size_t size,
- unsigned long vm_flags, pgprot_t prot,
- const void *caller)
-{
- struct vm_struct *area;
-
- area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
- if (!area)
- return NULL;
-
- area->pages = pages;
-
- return area->addr;
-}
-
-/*
- * remaps an allocated contiguous region into another vm_area.
- * Cannot be used in non-sleeping contexts
- */
-
-void *dma_common_contiguous_remap(struct page *page, size_t size,
- unsigned long vm_flags,
- pgprot_t prot, const void *caller)
-{
- int i;
- struct page **pages;
- struct vm_struct *area;
-
- pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
- if (!pages)
- return NULL;
-
- for (i = 0; i < (size >> PAGE_SHIFT); i++)
- pages[i] = nth_page(page, i);
-
- area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
-
- kfree(pages);
-
- if (!area)
- return NULL;
- return area->addr;
-}
-
-/*
- * unmaps a range previously mapped by dma_common_*_remap
- */
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
-{
- struct vm_struct *area = find_vm_area(cpu_addr);
-
- if (!area || (area->flags & vm_flags) != vm_flags) {
- WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
- return;
- }
-
- unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
- vunmap(cpu_addr);
-}
-#endif
-
-/*
- * enables DMA API use for a device
- */
-int dma_configure(struct device *dev)
-{
- if (dev->bus->dma_configure)
- return dev->bus->dma_configure(dev);
- return 0;
-}
-
-void dma_deconfigure(struct device *dev)
-{
- of_dma_deconfigure(dev);
- acpi_dma_deconfigure(dev);
-}
}
static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
- unsigned int index)
+ unsigned int index, bool power_on)
{
struct of_phandle_args pd_args;
struct generic_pm_domain *pd;
dev->pm_domain->detach = genpd_dev_pm_detach;
dev->pm_domain->sync = genpd_dev_pm_sync;
- genpd_lock(pd);
- ret = genpd_power_on(pd, 0);
- genpd_unlock(pd);
+ if (power_on) {
+ genpd_lock(pd);
+ ret = genpd_power_on(pd, 0);
+ genpd_unlock(pd);
+ }
if (ret)
genpd_remove_device(pd, dev);
"#power-domain-cells") != 1)
return 0;
- return __genpd_dev_pm_attach(dev, dev->of_node, 0);
+ return __genpd_dev_pm_attach(dev, dev->of_node, 0, true);
}
EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
}
/* Try to attach the device to the PM domain at the specified index. */
- ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index);
+ ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index, false);
if (ret < 1) {
device_unregister(genpd_dev);
return ret ? ERR_PTR(ret) : NULL;
}
- pm_runtime_set_active(genpd_dev);
pm_runtime_enable(genpd_dev);
+ genpd_queue_power_off_work(dev_to_genpd(genpd_dev));
return genpd_dev;
}
* power domain corresponding to a DT node's "required-opps" property.
*
* @dev: Device for which the performance-state needs to be found.
- * @opp_node: DT node where the "required-opps" property is present. This can be
+ * @np: DT node where the "required-opps" property is present. This can be
* the device node itself (if it doesn't have an OPP table) or a node
* within the OPP table of a device (if device has an OPP table).
- * @state: Pointer to return performance state.
*
* Returns performance state corresponding to the "required-opps" property of
* a DT node. This calls platform specific genpd->opp_to_performance_state()
* Returns performance state on success and 0 on failure.
*/
unsigned int of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node)
+ struct device_node *np)
{
struct generic_pm_domain *genpd;
struct dev_pm_opp *opp;
genpd_lock(genpd);
- opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+ opp = of_dev_pm_opp_find_required_opp(&genpd->dev, np);
if (IS_ERR(opp)) {
dev_err(dev, "Failed to find required OPP: %ld\n",
PTR_ERR(opp));
_drbd_start_io_acct(device, req);
/* process discards always from our submitter thread */
- if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
- (bio_op(bio) & REQ_OP_DISCARD))
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD)
goto queue_for_submitter_thread;
if (rw == WRITE && req->private_bio && req->i.size
what = COMPLETED_OK;
}
- bio_put(req->private_bio);
req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status));
+ bio_put(bio);
/* not req_mod(), we need irqsave here! */
spin_lock_irqsave(&device->resource->req_lock, flags);
arg = (unsigned long) compat_ptr(arg);
case LOOP_SET_FD:
case LOOP_CHANGE_FD:
+ case LOOP_SET_BLOCK_SIZE:
err = lo_ioctl(bdev, mode, cmd, arg);
break;
default:
#define NBD_HAS_CONFIG_REF 4
#define NBD_BOUND 5
#define NBD_DESTROY_ON_DISCONNECT 6
+#define NBD_DISCONNECT_ON_CLOSE 7
struct nbd_config {
u32 flags;
struct task_struct *task_setup;
};
+#define NBD_CMD_REQUEUED 1
+
struct nbd_cmd {
struct nbd_device *nbd;
+ struct mutex lock;
int index;
int cookie;
- struct completion send_complete;
blk_status_t status;
+ unsigned long flags;
+ u32 cmd_cookie;
};
#if IS_ENABLED(CONFIG_DEBUG_FS)
static void nbd_connect_reply(struct genl_info *info, int index);
static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
static void nbd_dead_link_work(struct work_struct *work);
+static void nbd_disconnect_and_put(struct nbd_device *nbd);
static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
return disk_to_dev(nbd->disk);
}
+static void nbd_requeue_cmd(struct nbd_cmd *cmd)
+{
+ struct request *req = blk_mq_rq_from_pdu(cmd);
+
+ if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags))
+ blk_mq_requeue_request(req, true);
+}
+
+#define NBD_COOKIE_BITS 32
+
+static u64 nbd_cmd_handle(struct nbd_cmd *cmd)
+{
+ struct request *req = blk_mq_rq_from_pdu(cmd);
+ u32 tag = blk_mq_unique_tag(req);
+ u64 cookie = cmd->cmd_cookie;
+
+ return (cookie << NBD_COOKIE_BITS) | tag;
+}
+
+static u32 nbd_handle_to_tag(u64 handle)
+{
+ return (u32)handle;
+}
+
+static u32 nbd_handle_to_cookie(u64 handle)
+{
+ return (u32)(handle >> NBD_COOKIE_BITS);
+}
+
static const char *nbdcmd_to_ascii(int cmd)
{
switch (cmd) {
}
config = nbd->config;
+ if (!mutex_trylock(&cmd->lock))
+ return BLK_EH_RESET_TIMER;
+
if (config->num_connections > 1) {
dev_err_ratelimited(nbd_to_dev(nbd),
"Connection timed out, retrying (%d/%d alive)\n",
nbd_mark_nsock_dead(nbd, nsock, 1);
mutex_unlock(&nsock->tx_lock);
}
- blk_mq_requeue_request(req, true);
+ mutex_unlock(&cmd->lock);
+ nbd_requeue_cmd(cmd);
nbd_config_put(nbd);
return BLK_EH_DONE;
}
}
set_bit(NBD_TIMEDOUT, &config->runtime_flags);
cmd->status = BLK_STS_IOERR;
+ mutex_unlock(&cmd->lock);
sock_shutdown(nbd);
nbd_config_put(nbd);
done:
struct iov_iter from;
unsigned long size = blk_rq_bytes(req);
struct bio *bio;
+ u64 handle;
u32 type;
u32 nbd_cmd_flags = 0;
- u32 tag = blk_mq_unique_tag(req);
int sent = nsock->sent, skip = 0;
iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
goto send_pages;
}
iov_iter_advance(&from, sent);
+ } else {
+ cmd->cmd_cookie++;
}
cmd->index = index;
cmd->cookie = nsock->cookie;
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
request.len = htonl(size);
}
- memcpy(request.handle, &tag, sizeof(tag));
+ handle = nbd_cmd_handle(cmd);
+ memcpy(request.handle, &handle, sizeof(handle));
dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
req, nbdcmd_to_ascii(type),
nsock->pending = req;
nsock->sent = sent;
}
+ set_bit(NBD_CMD_REQUEUED, &cmd->flags);
return BLK_STS_RESOURCE;
}
dev_err_ratelimited(disk_to_dev(nbd->disk),
*/
nsock->pending = req;
nsock->sent = sent;
+ set_bit(NBD_CMD_REQUEUED, &cmd->flags);
return BLK_STS_RESOURCE;
}
dev_err(disk_to_dev(nbd->disk),
struct nbd_reply reply;
struct nbd_cmd *cmd;
struct request *req = NULL;
+ u64 handle;
u16 hwq;
u32 tag;
struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
struct iov_iter to;
+ int ret = 0;
reply.magic = 0;
iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
return ERR_PTR(-EPROTO);
}
- memcpy(&tag, reply.handle, sizeof(u32));
-
+ memcpy(&handle, reply.handle, sizeof(handle));
+ tag = nbd_handle_to_tag(handle);
hwq = blk_mq_unique_tag_to_hwq(tag);
if (hwq < nbd->tag_set.nr_hw_queues)
req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq],
return ERR_PTR(-ENOENT);
}
cmd = blk_mq_rq_to_pdu(req);
+
+ mutex_lock(&cmd->lock);
+ if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
+ dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
+ req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
+ ret = -ENOENT;
+ goto out;
+ }
+ if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
+ dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
+ req);
+ ret = -ENOENT;
+ goto out;
+ }
if (ntohl(reply.error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
ntohl(reply.error));
cmd->status = BLK_STS_IOERR;
- return cmd;
+ goto out;
}
dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
if (nbd_disconnected(config) ||
config->num_connections <= 1) {
cmd->status = BLK_STS_IOERR;
- return cmd;
+ goto out;
}
- return ERR_PTR(-EIO);
+ ret = -EIO;
+ goto out;
}
dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
req, bvec.bv_len);
}
- } else {
- /* See the comment in nbd_queue_rq. */
- wait_for_completion(&cmd->send_complete);
}
- return cmd;
+out:
+ mutex_unlock(&cmd->lock);
+ return ret ? ERR_PTR(ret) : cmd;
}
static void recv_work(struct work_struct *work)
*/
blk_mq_start_request(req);
if (unlikely(nsock->pending && nsock->pending != req)) {
- blk_mq_requeue_request(req, true);
+ nbd_requeue_cmd(cmd);
ret = 0;
goto out;
}
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Request send failed, requeueing\n");
nbd_mark_nsock_dead(nbd, nsock, 1);
- blk_mq_requeue_request(req, true);
+ nbd_requeue_cmd(cmd);
ret = 0;
}
out:
* that the server is misbehaving (or there was an error) before we're
* done sending everything over the wire.
*/
- init_completion(&cmd->send_complete);
+ mutex_lock(&cmd->lock);
+ clear_bit(NBD_CMD_REQUEUED, &cmd->flags);
/* We can be called directly from the user space process, which means we
* could possibly have signals pending so our sendmsg will fail. In
ret = BLK_STS_IOERR;
else if (!ret)
ret = BLK_STS_OK;
- complete(&cmd->send_complete);
+ mutex_unlock(&cmd->lock);
return ret;
}
static void nbd_release(struct gendisk *disk, fmode_t mode)
{
struct nbd_device *nbd = disk->private_data;
+ struct block_device *bdev = bdget_disk(disk, 0);
+
+ if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+ bdev->bd_openers == 0)
+ nbd_disconnect_and_put(nbd);
+
nbd_config_put(nbd);
nbd_put(nbd);
}
{
struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq);
cmd->nbd = set->driver_data;
+ cmd->flags = 0;
+ mutex_init(&cmd->lock);
return 0;
}
&config->runtime_flags);
put_dev = true;
}
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
return ret;
}
+static void nbd_disconnect_and_put(struct nbd_device *nbd)
+{
+ mutex_lock(&nbd->config_lock);
+ nbd_disconnect(nbd);
+ nbd_clear_sock(nbd);
+ mutex_unlock(&nbd->config_lock);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
+}
+
static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
{
struct nbd_device *nbd;
nbd_put(nbd);
return 0;
}
- mutex_lock(&nbd->config_lock);
- nbd_disconnect(nbd);
- nbd_clear_sock(nbd);
- mutex_unlock(&nbd->config_lock);
- if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
- &nbd->config->runtime_flags))
- nbd_config_put(nbd);
+ nbd_disconnect_and_put(nbd);
nbd_config_put(nbd);
nbd_put(nbd);
return 0;
struct nbd_device *nbd = NULL;
struct nbd_config *config;
int index;
- int ret = -EINVAL;
+ int ret = 0;
bool put_dev = false;
if (!netlink_capable(skb, CAP_SYS_ADMIN))
!nbd->task_recv) {
dev_err(nbd_to_dev(nbd),
"not configured, cannot reconfigure\n");
+ ret = -EINVAL;
goto out;
}
&config->runtime_flags))
refcount_inc(&nbd->refs);
}
+
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ } else {
+ clear_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
{
pr_info("null: rq %p timed out\n", rq);
- blk_mq_complete_request(rq);
+ __blk_complete_request(rq);
return BLK_EH_DONE;
}
{
unsigned int counter;
- counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+ counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
if (counter <= (unsigned int)INT_MAX)
return (int)counter;
static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
{
unsigned int num_osd_ops = obj_req->osd_req->r_num_ops;
+ int ret;
dout("%s obj_req %p bytes %u\n", __func__, obj_req, bytes);
rbd_assert(obj_req->osd_req->r_ops[0].op == CEPH_OSD_OP_STAT);
if (!obj_req->osd_req)
return -ENOMEM;
+ ret = osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
+ "copyup");
+ if (ret)
+ return ret;
+
/*
* Only send non-zero copyup data to save some I/O and network
* bandwidth -- zero copyup data is equivalent to the object not
dout("%s obj_req %p detected zeroes\n", __func__, obj_req);
bytes = 0;
}
-
- osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
- "copyup");
osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0,
obj_req->copyup_bvecs,
obj_req->copyup_bvec_count,
{
dout("%s rbd_dev %p\n", __func__, rbd_dev);
- cancel_delayed_work_sync(&rbd_dev->watch_dwork);
cancel_work_sync(&rbd_dev->acquired_lock_work);
cancel_work_sync(&rbd_dev->released_lock_work);
cancel_delayed_work_sync(&rbd_dev->lock_dwork);
rbd_dev->watch_state = RBD_WATCH_STATE_UNREGISTERED;
mutex_unlock(&rbd_dev->watch_mutex);
+ cancel_delayed_work_sync(&rbd_dev->watch_dwork);
ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
}
zram->backing_dev = NULL;
zram->old_block_size = 0;
zram->bdev = NULL;
-
+ zram->disk->queue->backing_dev_info->capabilities |=
+ BDI_CAP_SYNCHRONOUS_IO;
kvfree(zram->bitmap);
zram->bitmap = NULL;
}
zram->backing_dev = backing_dev;
zram->bitmap = bitmap;
zram->nr_pages = nr_pages;
+ /*
+ * With writeback feature, zram does asynchronous IO so it's no longer
+ * synchronous device so let's remove synchronous io flag. Othewise,
+ * upper layer(e.g., swap) could wait IO completion rather than
+ * (submit and return), which will cause system sluggish.
+ * Furthermore, when the IO function returns(e.g., swap_readpage),
+ * upper layer expects IO was done so it could deallocate the page
+ * freely but in fact, IO is going on so finally could cause
+ * use-after-free when the IO is really done.
+ */
+ zram->disk->queue->backing_dev_info->capabilities &=
+ ~BDI_CAP_SYNCHRONOUS_IO;
up_write(&zram->init_lock);
pr_info("setup backing device %s\n", file_name);
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/unaligned/le_struct.h>
+#include <asm/unaligned.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
const char *name;
int nr_fck = 0, nr_ick = 0, i, error = 0;
- ddata->clock_roles = devm_kzalloc(ddata->dev,
- sizeof(*ddata->clock_roles) *
+ ddata->clock_roles = devm_kcalloc(ddata->dev,
SYSC_MAX_CLOCKS,
+ sizeof(*ddata->clock_roles),
GFP_KERNEL);
if (!ddata->clock_roles)
return -ENOMEM;
return -EINVAL;
}
- ddata->clocks = devm_kzalloc(ddata->dev,
- sizeof(*ddata->clocks) * ddata->nr_clocks,
+ ddata->clocks = devm_kcalloc(ddata->dev,
+ ddata->nr_clocks, sizeof(*ddata->clocks),
GFP_KERNEL);
if (!ddata->clocks)
return -ENOMEM;
corresponding drivers into the kernel.
To compile this driver as a module, choose M here and read
- <file:Documentation/parport.txt>. The module will be called lp.
+ <file:Documentation/admin-guide/parport.rst>. The module will be called lp.
If you have several parallel ports, you can specify which ports to
use with the "lp" kernel command line option. (Try "man bootparam"
#include "agp.h"
-static int alpha_core_agp_vm_fault(struct vm_fault *vmf)
+static vm_fault_t alpha_core_agp_vm_fault(struct vm_fault *vmf)
{
alpha_agp_info *agp = agp_bridge->dev_private_data;
dma_addr_t dma_addr;
/* Address to map to */
pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp);
- aperturebase = tmp << 25;
+ aperturebase = (u64)tmp << 25;
aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK);
enable_gart_translation(hammer, gatt_table);
pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order);
nb_order = (nb_order >> 1) & 7;
pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base);
- nb_aper = nb_base << 25;
+ nb_aper = (u64)nb_base << 25;
/* Northbridge seems to contain crap. Try the AGP bridge. */
void hwrng_unregister(struct hwrng *rng)
{
+ int err;
+
mutex_lock(&rng_mutex);
list_del(&rng->list);
- if (current_rng == rng)
- enable_best_rng();
+ if (current_rng == rng) {
+ err = enable_best_rng();
+ if (err) {
+ drop_current_rng();
+ cur_rng_set_by_user = 0;
+ }
+ }
if (list_empty(&rng_list)) {
mutex_unlock(&rng_mutex);
return 0;
out_err:
- ipmi_unregister_smi(new_smi->intf);
- new_smi->intf = NULL;
+ if (new_smi->intf) {
+ ipmi_unregister_smi(new_smi->intf);
+ new_smi->intf = NULL;
+ }
kfree(init_name);
int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc)
{
unsigned long flags;
- int ret = 0;
+ int ret = -ENODATA;
u8 status;
spin_lock_irqsave(&kcs_bmc->lock, flags);
- if (!kcs_bmc->running) {
- kcs_force_abort(kcs_bmc);
- ret = -ENODEV;
- goto out_unlock;
- }
-
- status = read_status(kcs_bmc) & (KCS_STATUS_IBF | KCS_STATUS_CMD_DAT);
-
- switch (status) {
- case KCS_STATUS_IBF | KCS_STATUS_CMD_DAT:
- kcs_bmc_handle_cmd(kcs_bmc);
- break;
-
- case KCS_STATUS_IBF:
- kcs_bmc_handle_data(kcs_bmc);
- break;
+ status = read_status(kcs_bmc);
+ if (status & KCS_STATUS_IBF) {
+ if (!kcs_bmc->running)
+ kcs_force_abort(kcs_bmc);
+ else if (status & KCS_STATUS_CMD_DAT)
+ kcs_bmc_handle_cmd(kcs_bmc);
+ else
+ kcs_bmc_handle_data(kcs_bmc);
- default:
- ret = -ENODATA;
- break;
+ ret = 0;
}
-out_unlock:
spin_unlock_irqrestore(&kcs_bmc->lock, flags);
return ret;
#endif
if (vma->vm_flags & VM_SHARED)
return shmem_zero_setup(vma);
+ vma_set_anonymous(vma);
return 0;
}
/*
* Static global variables
*/
-static DECLARE_WAIT_QUEUE_HEAD(random_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
/* should we wake readers? */
if (entropy_bits >= random_read_wakeup_bits &&
- wq_has_sleeper(&random_wait)) {
- wake_up_interruptible_poll(&random_wait, POLLIN);
+ wq_has_sleeper(&random_read_wait)) {
+ wake_up_interruptible(&random_read_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
}
/* If the input pool is getting full, send some
trace_debit_entropy(r->name, 8 * ibytes);
if (ibytes &&
(r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
- wake_up_interruptible_poll(&random_wait, POLLOUT);
+ wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
if (nonblock)
return -EAGAIN;
- wait_event_interruptible(random_wait,
+ wait_event_interruptible(random_read_wait,
ENTROPY_BITS(&input_pool) >=
random_read_wakeup_bits);
if (signal_pending(current))
return ret;
}
-static struct wait_queue_head *
-random_get_poll_head(struct file *file, __poll_t events)
-{
- return &random_wait;
-}
-
static __poll_t
-random_poll_mask(struct file *file, __poll_t events)
+random_poll(struct file *file, poll_table * wait)
{
- __poll_t mask = 0;
+ __poll_t mask;
+ poll_wait(file, &random_read_wait, wait);
+ poll_wait(file, &random_write_wait, wait);
+ mask = 0;
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
{
size_t bytes;
- __u32 buf[16];
+ __u32 t, buf[16];
const char __user *p = buffer;
while (count > 0) {
+ int b, i = 0;
+
bytes = min(count, sizeof(buf));
if (copy_from_user(&buf, p, bytes))
return -EFAULT;
+ for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) {
+ if (!arch_get_random_int(&t))
+ break;
+ buf[i] ^= t;
+ }
+
count -= bytes;
p += bytes;
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
- .get_poll_head = random_get_poll_head,
- .poll_mask = random_poll_mask,
+ .poll = random_poll,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
* We'll be woken up again once below random_write_wakeup_thresh,
* or when the calling thread is about to terminate.
*/
- wait_event_interruptible(random_wait, kthread_should_stop() ||
+ wait_event_interruptible(random_write_wait, kthread_should_stop() ||
ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
mix_pool_bytes(poolp, buffer, count);
credit_entropy_bits(poolp, entropy);
obj-$(CONFIG_ARCH_STI) += st/
obj-$(CONFIG_ARCH_STRATIX10) += socfpga/
obj-$(CONFIG_ARCH_SUNXI) += sunxi/
-obj-$(CONFIG_ARCH_SUNXI) += sunxi-ng/
+obj-$(CONFIG_SUNXI_CCU) += sunxi-ng/
obj-$(CONFIG_ARCH_TEGRA) += tegra/
obj-y += ti/
obj-$(CONFIG_CLK_UNIPHIER) += uniphier/
#define ASPEED_MPLL_PARAM 0x20
#define ASPEED_HPLL_PARAM 0x24
#define AST2500_HPLL_BYPASS_EN BIT(20)
-#define AST2400_HPLL_STRAPPED BIT(18)
+#define AST2400_HPLL_PROGRAMMED BIT(18)
#define AST2400_HPLL_BYPASS_EN BIT(17)
#define ASPEED_MISC_CTRL 0x2c
#define UART_DIV13_EN BIT(12)
[ASPEED_CLK_GATE_GCLK] = { 1, 7, "gclk-gate", NULL, 0 }, /* 2D engine */
[ASPEED_CLK_GATE_MCLK] = { 2, -1, "mclk-gate", "mpll", CLK_IS_CRITICAL }, /* SDRAM */
[ASPEED_CLK_GATE_VCLK] = { 3, 6, "vclk-gate", NULL, 0 }, /* Video Capture */
- [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", 0 }, /* PCIe/PCI */
- [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, 0 }, /* DAC */
+ [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", CLK_IS_CRITICAL }, /* PCIe/PCI */
+ [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, CLK_IS_CRITICAL }, /* DAC */
[ASPEED_CLK_GATE_REFCLK] = { 6, -1, "refclk-gate", "clkin", CLK_IS_CRITICAL },
[ASPEED_CLK_GATE_USBPORT2CLK] = { 7, 3, "usb-port2-gate", NULL, 0 }, /* USB2.0 Host port 2 */
[ASPEED_CLK_GATE_LCLK] = { 8, 5, "lclk-gate", NULL, 0 }, /* LPC */
{
struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
u32 clk = BIT(gate->clock_idx);
+ u32 rst = BIT(gate->reset_idx);
u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk;
u32 reg;
+ /*
+ * If the IP is in reset, treat the clock as not enabled,
+ * this happens with some clocks such as the USB one when
+ * coming from cold reset. Without this, aspeed_clk_enable()
+ * will fail to lift the reset.
+ */
+ if (gate->reset_idx >= 0) {
+ regmap_read(gate->map, ASPEED_RESET_CTRL, ®);
+ if (reg & rst)
+ return 0;
+ }
+
regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®);
return ((reg & clk) == enval) ? 1 : 0;
static void __init aspeed_ast2400_cc(struct regmap *map)
{
struct clk_hw *hw;
- u32 val, freq, div;
+ u32 val, div, clkin, hpll;
+ const u16 hpll_rates[][4] = {
+ {384, 360, 336, 408},
+ {400, 375, 350, 425},
+ };
+ int rate;
/*
* CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by
* strapping
*/
regmap_read(map, ASPEED_STRAP, &val);
- if (val & CLKIN_25MHZ_EN)
- freq = 25000000;
- else if (val & AST2400_CLK_SOURCE_SEL)
- freq = 48000000;
- else
- freq = 24000000;
- hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq);
- pr_debug("clkin @%u MHz\n", freq / 1000000);
+ rate = (val >> 8) & 3;
+ if (val & CLKIN_25MHZ_EN) {
+ clkin = 25000000;
+ hpll = hpll_rates[1][rate];
+ } else if (val & AST2400_CLK_SOURCE_SEL) {
+ clkin = 48000000;
+ hpll = hpll_rates[0][rate];
+ } else {
+ clkin = 24000000;
+ hpll = hpll_rates[0][rate];
+ }
+ hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin);
+ pr_debug("clkin @%u MHz\n", clkin / 1000000);
/*
* High-speed PLL clock derived from the crystal. This the CPU clock,
- * and we assume that it is enabled
+ * and we assume that it is enabled. It can be configured through the
+ * HPLL_PARAM register, or set to a specified frequency by strapping.
*/
regmap_read(map, ASPEED_HPLL_PARAM, &val);
- WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured");
- aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val);
+ if (val & AST2400_HPLL_PROGRAMMED)
+ hw = aspeed_ast2400_calc_pll("hpll", val);
+ else
+ hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0,
+ hpll * 1000000);
+
+ aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw;
/*
* Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK)
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
- * Standard functionality for the common clock API. See Documentation/clk.txt
+ * Standard functionality for the common clock API. See Documentation/driver-api/clk.rst
*/
#include <linux/clk.h>
#include <linux/pm_runtime.h>
#include <linux/sched.h>
#include <linux/clkdev.h>
-#include <linux/stringify.h>
#include "clk.h"
unsigned long flag;
const char *name;
} clk_flags[] = {
-#define ENTRY(f) { f, __stringify(f) }
+#define ENTRY(f) { f, #f }
ENTRY(CLK_SET_RATE_GATE),
ENTRY(CLK_SET_PARENT_GATE),
ENTRY(CLK_SET_RATE_PARENT),
goto out;
}
- /* check that clk_ops are sane. See Documentation/clk.txt */
+ /* check that clk_ops are sane. See Documentation/driver-api/clk.rst */
if (core->ops->set_rate &&
!((core->ops->round_rate || core->ops->determine_rate) &&
core->ops->recalc_rate)) {
struct clk *clk;
int rc;
- if (index < 0)
- return ERR_PTR(-EINVAL);
-
rc = of_parse_phandle_with_args(np, "clocks", "#clock-cells", index,
&clkspec);
if (rc)
const char *dev_id = dev ? dev_name(dev) : NULL;
struct clk *clk;
- if (dev) {
+ if (dev && dev->of_node) {
clk = __of_clk_get_by_name(dev->of_node, dev_id, con_id);
if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
return clk;
usb1 = da8xx_cfgchip_register_usb1_clk48(dev, regmap);
if (IS_ERR(usb1)) {
- if (PTR_ERR(usb0) == -EPROBE_DEFER)
+ if (PTR_ERR(usb1) == -EPROBE_DEFER)
return -EPROBE_DEFER;
dev_warn(dev, "Failed to register usb1_clk48 (%ld)\n",
#ifdef CONFIG_ARCH_DAVINCI_DM355
extern const struct davinci_psc_init_data dm355_psc_init_data;
#endif
-#ifdef CONFIG_ARCH_DAVINCI_DM356
+#ifdef CONFIG_ARCH_DAVINCI_DM365
extern const struct davinci_psc_init_data dm365_psc_init_data;
#endif
#ifdef CONFIG_ARCH_DAVINCI_DM644x
/**
* struct ingenic_clk - private data for a clock
- * @hw: see Documentation/clk.txt
+ * @hw: see Documentation/driver-api/clk.rst
* @cgu: a pointer to the CGU data
* @idx: the index of this clock in cgu->clock_info
*/
struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
unsigned long divider;
- divider = meson_parm_read(clk->map, &adiv->div);
+ divider = meson_parm_read(clk->map, &adiv->div) + 1;
return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
}
.ops = &clk_regmap_gate_ops,
.parent_names = (const char *[]){ "fclk_div2_div" },
.num_parents = 1,
+ .flags = CLK_IS_CRITICAL,
},
};
#define CLK_SEL 0x10
#define CLK_DIS 0x14
+#define ARMADA_37XX_DVFS_LOAD_1 1
#define LOAD_LEVEL_NR 4
#define ARMADA_37XX_NB_L0L1 0x18
return -EINVAL;
}
+/*
+ * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz
+ * respectively) to L0 frequency (1.2 Ghz) requires a significant
+ * amount of time to let VDD stabilize to the appropriate
+ * voltage. This amount of time is large enough that it cannot be
+ * covered by the hardware countdown register. Due to this, the CPU
+ * might start operating at L0 before the voltage is stabilized,
+ * leading to CPU stalls.
+ *
+ * To work around this problem, we prevent switching directly from the
+ * L2/L3 frequencies to the L0 frequency, and instead switch to the L1
+ * frequency in-between. The sequence therefore becomes:
+ * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ)
+ * 2. Sleep 20ms for stabling VDD voltage
+ * 3. Then switch from L1(600MHZ) to L0(1200Mhz).
+ */
+static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base)
+{
+ unsigned int cur_level;
+
+ if (rate != 1200 * 1000 * 1000)
+ return;
+
+ regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level);
+ cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
+ if (cur_level <= ARMADA_37XX_DVFS_LOAD_1)
+ return;
+
+ regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD,
+ ARMADA_37XX_NB_CPU_LOAD_MASK,
+ ARMADA_37XX_DVFS_LOAD_1);
+ msleep(20);
+}
+
static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
*/
reg = ARMADA_37XX_NB_CPU_LOAD;
mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
+
+ clk_pm_cpu_set_rate_wa(rate, base);
+
regmap_update_bits(base, reg, mask, load_level);
return rate;
static struct clk_branch gcc_ufs_tx_symbol_0_clk = {
.halt_reg = 0x75018,
+ .halt_check = BRANCH_HALT_SKIP,
.clkr = {
.enable_reg = 0x75018,
.enable_mask = BIT(0),
.name = "mmagic_bimc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = ALWAYS_ON,
};
static struct gdsc mmagic_video_gdsc = {
# SPDX-License-Identifier: GPL-2.0
# Common objects
-lib-$(CONFIG_SUNXI_CCU) += ccu_common.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_mmc_timing.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_reset.o
+obj-y += ccu_common.o
+obj-y += ccu_mmc_timing.o
+obj-y += ccu_reset.o
# Base clock types
-lib-$(CONFIG_SUNXI_CCU) += ccu_div.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_frac.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_gate.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_mux.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_mult.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_phase.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_sdm.o
+obj-y += ccu_div.o
+obj-y += ccu_frac.o
+obj-y += ccu_gate.o
+obj-y += ccu_mux.o
+obj-y += ccu_mult.o
+obj-y += ccu_phase.o
+obj-y += ccu_sdm.o
# Multi-factor clocks
-lib-$(CONFIG_SUNXI_CCU) += ccu_nk.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_nkm.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_nkmp.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_nm.o
-lib-$(CONFIG_SUNXI_CCU) += ccu_mp.o
+obj-y += ccu_nk.o
+obj-y += ccu_nkm.o
+obj-y += ccu_nkmp.o
+obj-y += ccu_nm.o
+obj-y += ccu_mp.o
# SoC support
obj-$(CONFIG_SUN50I_A64_CCU) += ccu-sun50i-a64.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-de.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-usb.o
-
-# The lib-y file goals is supposed to work only in arch/*/lib or lib/. In our
-# case, we want to use that goal, but even though lib.a will be properly
-# generated, it will not be linked in, eventually resulting in a linker error
-# for missing symbols.
-#
-# We can work around that by explicitly adding lib.a to the obj-y goal. This is
-# an undocumented behaviour, but works well for now.
-obj-$(CONFIG_SUNXI_CCU) += lib.a
obj-$(CONFIG_FSL_FTM_TIMER) += fsl_ftm_timer.o
obj-$(CONFIG_VF_PIT_TIMER) += vf_pit_timer.o
obj-$(CONFIG_CLKSRC_QCOM) += qcom-timer.o
-obj-$(CONFIG_MTK_TIMER) += mtk_timer.o
+obj-$(CONFIG_MTK_TIMER) += timer-mediatek.o
obj-$(CONFIG_CLKSRC_PISTACHIO) += time-pistachio.o
obj-$(CONFIG_CLKSRC_TI_32K) += timer-ti-32k.o
obj-$(CONFIG_CLKSRC_NPS) += timer-nps.o
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->name = "arch_mem_timer";
clk->rating = 400;
- clk->cpumask = cpu_all_mask;
+ clk->cpumask = cpu_possible_mask;
if (arch_timer_mem_use_virtual) {
clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
+++ /dev/null
-/*
- * Mediatek SoCs General-Purpose Timer handling.
- *
- * Copyright (C) 2014 Matthias Brugger
- *
- * Matthias Brugger <matthias.bgg@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-#include <linux/slab.h>
-
-#define GPT_IRQ_EN_REG 0x00
-#define GPT_IRQ_ENABLE(val) BIT((val) - 1)
-#define GPT_IRQ_ACK_REG 0x08
-#define GPT_IRQ_ACK(val) BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val) (0x10 * (val))
-#define TIMER_CTRL_OP(val) (((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT (0)
-#define TIMER_CTRL_OP_REPEAT (1)
-#define TIMER_CTRL_OP_FREERUN (3)
-#define TIMER_CTRL_CLEAR (2)
-#define TIMER_CTRL_ENABLE (1)
-#define TIMER_CTRL_DISABLE (0)
-
-#define TIMER_CLK_REG(val) (0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val) (((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M (0)
-#define TIMER_CLK_SRC_RTC32K (1)
-#define TIMER_CLK_DIV1 (0x0)
-#define TIMER_CLK_DIV2 (0x1)
-
-#define TIMER_CNT_REG(val) (0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val) (0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT 1
-#define GPT_CLK_SRC 2
-
-struct mtk_clock_event_device {
- void __iomem *gpt_base;
- u32 ticks_per_jiffy;
- struct clock_event_device dev;
-};
-
-static void __iomem *gpt_sched_reg __read_mostly;
-
-static u64 notrace mtk_read_sched_clock(void)
-{
- return readl_relaxed(gpt_sched_reg);
-}
-
-static inline struct mtk_clock_event_device *to_mtk_clk(
- struct clock_event_device *c)
-{
- return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
-{
- u32 val;
-
- val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
- writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
- TIMER_CTRL_REG(timer));
-}
-
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
- unsigned long delay, u8 timer)
-{
- writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
-}
-
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
- bool periodic, u8 timer)
-{
- u32 val;
-
- /* Acknowledge interrupt */
- writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
-
- val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-
- /* Clear 2 bit timer operation mode field */
- val &= ~TIMER_CTRL_OP(0x3);
-
- if (periodic)
- val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
- else
- val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
-
- writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
- evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
-{
- mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
- return 0;
-}
-
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
-{
- struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
- mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
- mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
- mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
- return 0;
-}
-
-static int mtk_clkevt_next_event(unsigned long event,
- struct clock_event_device *clk)
-{
- struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
- mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
- mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
- mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
-
- return 0;
-}
-
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
-{
- struct mtk_clock_event_device *evt = dev_id;
-
- /* Acknowledge timer0 irq */
- writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
- evt->dev.event_handler(&evt->dev);
-
- return IRQ_HANDLED;
-}
-
-static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
-{
- writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
- evt->gpt_base + TIMER_CTRL_REG(timer));
-
- writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
- evt->gpt_base + TIMER_CLK_REG(timer));
-
- writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
-
- writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
- evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
-{
- u32 val;
-
- /* Disable all interrupts */
- writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
-
- /* Acknowledge all spurious pending interrupts */
- writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
-
- val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
- writel(val | GPT_IRQ_ENABLE(timer),
- evt->gpt_base + GPT_IRQ_EN_REG);
-}
-
-static int __init mtk_timer_init(struct device_node *node)
-{
- struct mtk_clock_event_device *evt;
- struct resource res;
- unsigned long rate = 0;
- struct clk *clk;
-
- evt = kzalloc(sizeof(*evt), GFP_KERNEL);
- if (!evt)
- return -ENOMEM;
-
- evt->dev.name = "mtk_tick";
- evt->dev.rating = 300;
- evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
- evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
- evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
- evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
- evt->dev.tick_resume = mtk_clkevt_shutdown;
- evt->dev.set_next_event = mtk_clkevt_next_event;
- evt->dev.cpumask = cpu_possible_mask;
-
- evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
- if (IS_ERR(evt->gpt_base)) {
- pr_err("Can't get resource\n");
- goto err_kzalloc;
- }
-
- evt->dev.irq = irq_of_parse_and_map(node, 0);
- if (evt->dev.irq <= 0) {
- pr_err("Can't parse IRQ\n");
- goto err_mem;
- }
-
- clk = of_clk_get(node, 0);
- if (IS_ERR(clk)) {
- pr_err("Can't get timer clock\n");
- goto err_irq;
- }
-
- if (clk_prepare_enable(clk)) {
- pr_err("Can't prepare clock\n");
- goto err_clk_put;
- }
- rate = clk_get_rate(clk);
-
- if (request_irq(evt->dev.irq, mtk_timer_interrupt,
- IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
- pr_err("failed to setup irq %d\n", evt->dev.irq);
- goto err_clk_disable;
- }
-
- evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
- /* Configure clock source */
- mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
- clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
- node->name, rate, 300, 32, clocksource_mmio_readl_up);
- gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
- sched_clock_register(mtk_read_sched_clock, 32, rate);
-
- /* Configure clock event */
- mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
- clockevents_config_and_register(&evt->dev, rate, 0x3,
- 0xffffffff);
-
- mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
- return 0;
-
-err_clk_disable:
- clk_disable_unprepare(clk);
-err_clk_put:
- clk_put(clk);
-err_irq:
- irq_dispose_mapping(evt->dev.irq);
-err_mem:
- iounmap(evt->gpt_base);
- of_address_to_resource(node, 0, &res);
- release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
- kfree(evt);
-
- return -EINVAL;
-}
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
return ret;
}
- tegra_clockevent.cpumask = cpu_all_mask;
+ tegra_clockevent.cpumask = cpu_possible_mask;
tegra_clockevent.irq = tegra_timer_irq.irq;
clockevents_config_and_register(&tegra_clockevent, 1000000,
0x1, 0x1fffffff);
else
clk_prepare_enable(clk);
- return register_persistent_clock(NULL, tegra_read_persistent_clock64);
+ return register_persistent_clock(tegra_read_persistent_clock64);
}
TIMER_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
.set_state_oneshot = atcpit100_clkevt_set_oneshot,
.tick_resume = atcpit100_clkevt_shutdown,
.set_next_event = atcpit100_clkevt_next_event,
- .cpumask = cpu_all_mask,
+ .cpumask = cpu_possible_mask,
},
.of_irq = {
event_dev->set_state_shutdown = keystone_shutdown;
event_dev->set_state_periodic = keystone_set_periodic;
event_dev->set_state_oneshot = keystone_shutdown;
- event_dev->cpumask = cpu_all_mask;
+ event_dev->cpumask = cpu_possible_mask;
event_dev->owner = THIS_MODULE;
event_dev->name = TIMER_NAME;
event_dev->irq = irq;
--- /dev/null
+/*
+ * Mediatek SoCs General-Purpose Timer handling.
+ *
+ * Copyright (C) 2014 Matthias Brugger
+ *
+ * Matthias Brugger <matthias.bgg@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include "timer-of.h"
+
+#define TIMER_CLK_EVT (1)
+#define TIMER_CLK_SRC (2)
+
+#define TIMER_SYNC_TICKS (3)
+
+/* gpt */
+#define GPT_IRQ_EN_REG 0x00
+#define GPT_IRQ_ENABLE(val) BIT((val) - 1)
+#define GPT_IRQ_ACK_REG 0x08
+#define GPT_IRQ_ACK(val) BIT((val) - 1)
+
+#define GPT_CTRL_REG(val) (0x10 * (val))
+#define GPT_CTRL_OP(val) (((val) & 0x3) << 4)
+#define GPT_CTRL_OP_ONESHOT (0)
+#define GPT_CTRL_OP_REPEAT (1)
+#define GPT_CTRL_OP_FREERUN (3)
+#define GPT_CTRL_CLEAR (2)
+#define GPT_CTRL_ENABLE (1)
+#define GPT_CTRL_DISABLE (0)
+
+#define GPT_CLK_REG(val) (0x04 + (0x10 * (val)))
+#define GPT_CLK_SRC(val) (((val) & 0x1) << 4)
+#define GPT_CLK_SRC_SYS13M (0)
+#define GPT_CLK_SRC_RTC32K (1)
+#define GPT_CLK_DIV1 (0x0)
+#define GPT_CLK_DIV2 (0x1)
+
+#define GPT_CNT_REG(val) (0x08 + (0x10 * (val)))
+#define GPT_CMP_REG(val) (0x0C + (0x10 * (val)))
+
+/* system timer */
+#define SYST_BASE (0x40)
+
+#define SYST_CON (SYST_BASE + 0x0)
+#define SYST_VAL (SYST_BASE + 0x4)
+
+#define SYST_CON_REG(to) (timer_of_base(to) + SYST_CON)
+#define SYST_VAL_REG(to) (timer_of_base(to) + SYST_VAL)
+
+/*
+ * SYST_CON_EN: Clock enable. Shall be set to
+ * - Start timer countdown.
+ * - Allow timeout ticks being updated.
+ * - Allow changing interrupt functions.
+ *
+ * SYST_CON_IRQ_EN: Set to allow interrupt.
+ *
+ * SYST_CON_IRQ_CLR: Set to clear interrupt.
+ */
+#define SYST_CON_EN BIT(0)
+#define SYST_CON_IRQ_EN BIT(1)
+#define SYST_CON_IRQ_CLR BIT(4)
+
+static void __iomem *gpt_sched_reg __read_mostly;
+
+static void mtk_syst_ack_irq(struct timer_of *to)
+{
+ /* Clear and disable interrupt */
+ writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
+}
+
+static irqreturn_t mtk_syst_handler(int irq, void *dev_id)
+{
+ struct clock_event_device *clkevt = dev_id;
+ struct timer_of *to = to_timer_of(clkevt);
+
+ mtk_syst_ack_irq(to);
+ clkevt->event_handler(clkevt);
+
+ return IRQ_HANDLED;
+}
+
+static int mtk_syst_clkevt_next_event(unsigned long ticks,
+ struct clock_event_device *clkevt)
+{
+ struct timer_of *to = to_timer_of(clkevt);
+
+ /* Enable clock to allow timeout tick update later */
+ writel(SYST_CON_EN, SYST_CON_REG(to));
+
+ /*
+ * Write new timeout ticks. Timer shall start countdown
+ * after timeout ticks are updated.
+ */
+ writel(ticks, SYST_VAL_REG(to));
+
+ /* Enable interrupt */
+ writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to));
+
+ return 0;
+}
+
+static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+ /* Disable timer */
+ writel(0, SYST_CON_REG(to_timer_of(clkevt)));
+
+ return 0;
+}
+
+static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt)
+{
+ return mtk_syst_clkevt_shutdown(clkevt);
+}
+
+static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt)
+{
+ return 0;
+}
+
+static u64 notrace mtk_gpt_read_sched_clock(void)
+{
+ return readl_relaxed(gpt_sched_reg);
+}
+
+static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer)
+{
+ u32 val;
+
+ val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+ writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) +
+ GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_setup(struct timer_of *to,
+ unsigned long delay, u8 timer)
+{
+ writel(delay, timer_of_base(to) + GPT_CMP_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_start(struct timer_of *to,
+ bool periodic, u8 timer)
+{
+ u32 val;
+
+ /* Acknowledge interrupt */
+ writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+ val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+
+ /* Clear 2 bit timer operation mode field */
+ val &= ~GPT_CTRL_OP(0x3);
+
+ if (periodic)
+ val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT);
+ else
+ val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
+
+ writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
+ timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
+{
+ mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT);
+
+ return 0;
+}
+
+static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
+{
+ struct timer_of *to = to_timer_of(clk);
+
+ mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+ mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT);
+ mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT);
+
+ return 0;
+}
+
+static int mtk_gpt_clkevt_next_event(unsigned long event,
+ struct clock_event_device *clk)
+{
+ struct timer_of *to = to_timer_of(clk);
+
+ mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+ mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT);
+ mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT);
+
+ return 0;
+}
+
+static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+ struct timer_of *to = to_timer_of(clkevt);
+
+ /* Acknowledge timer0 irq */
+ writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG);
+ clkevt->event_handler(clkevt);
+
+ return IRQ_HANDLED;
+}
+
+static void
+__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option)
+{
+ writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
+ timer_of_base(to) + GPT_CTRL_REG(timer));
+
+ writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
+ timer_of_base(to) + GPT_CLK_REG(timer));
+
+ writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer));
+
+ writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
+ timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer)
+{
+ u32 val;
+
+ /* Disable all interrupts */
+ writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG);
+
+ /* Acknowledge all spurious pending interrupts */
+ writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+ val = readl(timer_of_base(to) + GPT_IRQ_EN_REG);
+ writel(val | GPT_IRQ_ENABLE(timer),
+ timer_of_base(to) + GPT_IRQ_EN_REG);
+}
+
+static struct timer_of to = {
+ .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+ .clkevt = {
+ .name = "mtk-clkevt",
+ .rating = 300,
+ .cpumask = cpu_possible_mask,
+ },
+
+ .of_irq = {
+ .flags = IRQF_TIMER | IRQF_IRQPOLL,
+ },
+};
+
+static int __init mtk_syst_init(struct device_node *node)
+{
+ int ret;
+
+ to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT;
+ to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown;
+ to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot;
+ to.clkevt.tick_resume = mtk_syst_clkevt_resume;
+ to.clkevt.set_next_event = mtk_syst_clkevt_next_event;
+ to.of_irq.handler = mtk_syst_handler;
+
+ ret = timer_of_init(node, &to);
+ if (ret)
+ goto err;
+
+ clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+ TIMER_SYNC_TICKS, 0xffffffff);
+
+ return 0;
+err:
+ timer_of_cleanup(&to);
+ return ret;
+}
+
+static int __init mtk_gpt_init(struct device_node *node)
+{
+ int ret;
+
+ to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+ to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+ to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+ to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+ to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown;
+ to.clkevt.set_next_event = mtk_gpt_clkevt_next_event;
+ to.of_irq.handler = mtk_gpt_interrupt;
+
+ ret = timer_of_init(node, &to);
+ if (ret)
+ goto err;
+
+ /* Configure clock source */
+ mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+ clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC),
+ node->name, timer_of_rate(&to), 300, 32,
+ clocksource_mmio_readl_up);
+ gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC);
+ sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to));
+
+ /* Configure clock event */
+ mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+ clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+ TIMER_SYNC_TICKS, 0xffffffff);
+
+ mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
+
+ return 0;
+err:
+ timer_of_cleanup(&to);
+ return ret;
+}
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
+TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
return 0;
}
+static struct timer_of suspend_to = {
+ .flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+ return ~(u64)readl_relaxed(timer_of_base(&suspend_to) +
+ TIMER_VALUE_SHDW_LO) & cs->mask;
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+ sprd_timer_update_counter(timer_of_base(&suspend_to),
+ TIMER_VALUE_LO_MASK);
+ sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE);
+
+ return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+ sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+ .name = "sprd_suspend_timer",
+ .rating = 200,
+ .read = sprd_suspend_timer_read,
+ .enable = sprd_suspend_timer_enable,
+ .disable = sprd_suspend_timer_disable,
+ .mask = CLOCKSOURCE_MASK(32),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+ int ret;
+
+ ret = timer_of_init(np, &suspend_to);
+ if (ret)
+ return ret;
+
+ clocksource_register_hz(&suspend_clocksource,
+ timer_of_rate(&suspend_to));
+
+ return 0;
+}
+
TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+ sprd_suspend_timer_init);
to->private_data = kzalloc(sizeof(struct stm32_timer_private),
GFP_KERNEL);
- if (!to->private_data)
+ if (!to->private_data) {
+ ret = -ENOMEM;
goto deinit;
+ }
rstc = of_reset_control_get(node, NULL);
if (!IS_ERR(rstc)) {
.rating = 250,
.read = ti_32k_read_cycles,
.mask = CLOCKSOURCE_MASK(32),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
- CLOCK_SOURCE_SUSPEND_NONSTOP,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
},
};
timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
timer->clkevt.tick_resume = zevio_timer_set_oneshot;
timer->clkevt.rating = 200;
- timer->clkevt.cpumask = cpu_all_mask;
+ timer->clkevt.cpumask = cpu_possible_mask;
timer->clkevt.features = CLOCK_EVT_FEAT_ONESHOT;
timer->clkevt.irq = irqnr;
static struct pstate_funcs pstate_funcs __read_mostly;
static int hwp_active __read_mostly;
+static int hwp_mode_bdw __read_mostly;
static bool per_cpu_limits __read_mostly;
static bool hwp_boost __read_mostly;
#ifdef CONFIG_ACPI
-static bool intel_pstate_get_ppc_enable_status(void)
+static bool intel_pstate_acpi_pm_profile_server(void)
{
if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
return true;
+ return false;
+}
+
+static bool intel_pstate_get_ppc_enable_status(void)
+{
+ if (intel_pstate_acpi_pm_profile_server())
+ return true;
+
return acpi_ppc;
}
static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
{
}
+
+static inline bool intel_pstate_acpi_pm_profile_server(void)
+{
+ return false;
+}
#endif
static inline void update_turbo_state(void)
cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
cpu->pstate.scaling = pstate_funcs.get_scaling();
cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
- cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+
+ if (hwp_active && !hwp_mode_bdw) {
+ unsigned int phy_max, current_max;
+
+ intel_pstate_get_hwp_max(cpu->cpu, &phy_max, ¤t_max);
+ cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
+ } else {
+ cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+ }
if (pstate_funcs.get_aperf_mperf_shift)
cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
intel_pstate_hwp_enable(cpu);
id = x86_match_cpu(intel_pstate_hwp_boost_ids);
- if (id)
+ if (id && intel_pstate_acpi_pm_profile_server())
hwp_boost = true;
}
return true;
}
+static bool __init intel_pstate_no_acpi_pcch(void)
+{
+ acpi_status status;
+ acpi_handle handle;
+
+ status = acpi_get_handle(NULL, "\\_SB", &handle);
+ if (ACPI_FAILURE(status))
+ return true;
+
+ return !acpi_has_method(handle, "PCCH");
+}
+
static bool __init intel_pstate_has_acpi_ppc(void)
{
int i;
switch (plat_info[idx].data) {
case PSS:
- return intel_pstate_no_acpi_pss();
+ if (!intel_pstate_no_acpi_pss())
+ return false;
+
+ return intel_pstate_no_acpi_pcch();
case PPC:
return intel_pstate_has_acpi_ppc() && !force_load;
}
static inline void intel_pstate_request_control_from_smm(void) {}
#endif /* CONFIG_ACPI */
+#define INTEL_PSTATE_HWP_BROADWELL 0x01
+
+#define ICPU_HWP(model, hwp_mode) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode }
+
static const struct x86_cpu_id hwp_support_ids[] __initconst = {
- { X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+ ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL),
+ ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL),
+ ICPU_HWP(X86_MODEL_ANY, 0),
{}
};
static int __init intel_pstate_init(void)
{
+ const struct x86_cpu_id *id;
int rc;
if (no_load)
return -ENODEV;
- if (x86_match_cpu(hwp_support_ids)) {
+ id = x86_match_cpu(hwp_support_ids);
+ if (id) {
copy_cpu_funcs(&core_funcs);
if (!no_hwp) {
hwp_active++;
+ hwp_mode_bdw = id->driver_data;
intel_pstate.attr = hwp_cpufreq_attrs;
goto hwp_cpu_matched;
}
} else {
- const struct x86_cpu_id *id;
-
id = x86_match_cpu(intel_pstate_cpu_ids);
if (!id)
return -ENODEV;
{
int ret;
+ /* Skip initialization if another cpufreq driver is there. */
+ if (cpufreq_get_current_driver())
+ return 0;
+
if (acpi_disabled)
return 0;
NUM_OF_MSM8996_VERSIONS,
};
+struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+
static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
{
size_t len;
static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
{
struct opp_table *opp_tables[NR_CPUS] = {0};
- struct platform_device *cpufreq_dt_pdev;
enum _msm8996_version msm8996_version;
struct nvmem_cell *speedbin_nvmem;
struct device_node *np;
int ret;
cpu_dev = get_cpu_device(0);
- if (NULL == cpu_dev)
- ret = -ENODEV;
+ if (!cpu_dev)
+ return -ENODEV;
msm8996_version = qcom_cpufreq_kryo_get_msm_id();
if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
}
np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
- if (IS_ERR(np))
- return PTR_ERR(np);
+ if (!np)
+ return -ENOENT;
ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
if (!ret) {
speedbin = nvmem_cell_read(speedbin_nvmem, &len);
nvmem_cell_put(speedbin_nvmem);
+ if (IS_ERR(speedbin))
+ return PTR_ERR(speedbin);
switch (msm8996_version) {
case MSM8996_V3:
BUG();
break;
}
+ kfree(speedbin);
for_each_possible_cpu(cpu) {
cpu_dev = get_cpu_device(cpu);
return ret;
}
+static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
+{
+ platform_device_unregister(cpufreq_dt_pdev);
+ return 0;
+}
+
static struct platform_driver qcom_cpufreq_kryo_driver = {
.probe = qcom_cpufreq_kryo_probe,
+ .remove = qcom_cpufreq_kryo_remove,
.driver = {
.name = "qcom-cpufreq-kryo",
},
static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
{ .compatible = "qcom,apq8096", },
{ .compatible = "qcom,msm8996", },
+ {}
};
/*
if (unlikely(ret < 0))
return ret;
- ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
- "qcom-cpufreq-kryo", -1, NULL, 0));
+ kryo_cpufreq_pdev = platform_device_register_simple(
+ "qcom-cpufreq-kryo", -1, NULL, 0);
+ ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev);
if (0 == ret)
return 0;
}
module_init(qcom_cpufreq_kryo_init);
+static void __init qcom_cpufreq_kryo_exit(void)
+{
+ platform_device_unregister(kryo_cpufreq_pdev);
+ platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+}
+module_exit(qcom_cpufreq_kryo_exit);
+
MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
MODULE_LICENSE("GPL v2");
tp->urg_data = 0;
if ((avail + offset) >= skb->len) {
- if (likely(skb))
- chtls_free_skb(sk, skb);
- buffers_freed++;
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
tp->copied_seq += skb->len;
hws->rcvpld = skb->hdr_len;
} else {
tp->copied_seq += hws->rcvpld;
}
+ chtls_free_skb(sk, skb);
+ buffers_freed++;
hws->copied_seq = 0;
if (copied >= target &&
!skb_peek(&sk->sk_receive_queue))
return;
}
+ count -= initial;
+
if (initial)
asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */
: "+S"(input), "+D"(output)
asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */
: "+S"(input), "+D"(output)
- : "d"(control_word), "b"(key), "c"(count - initial));
+ : "d"(control_word), "b"(key), "c"(count));
}
static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
if (count < cbc_fetch_blocks)
return cbc_crypt(input, output, key, iv, control_word, count);
+ count -= initial;
+
if (initial)
asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */
: "+S" (input), "+D" (output), "+a" (iv)
asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */
: "+S" (input), "+D" (output), "+a" (iv)
- : "d" (control_word), "b" (key), "c" (count-initial));
+ : "d" (control_word), "b" (key), "c" (count));
return iv;
}
/* prevent private mappings from being established */
if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
- dev_info(dev, "%s: %s: fail, attempted private mapping\n",
+ dev_info_ratelimited(dev,
+ "%s: %s: fail, attempted private mapping\n",
current->comm, func);
return -EINVAL;
}
mask = dax_region->align - 1;
if (vma->vm_start & mask || vma->vm_end & mask) {
- dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
+ dev_info_ratelimited(dev,
+ "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
current->comm, func, vma->vm_start, vma->vm_end,
mask);
return -EINVAL;
if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
&& (vma->vm_flags & VM_DONTCOPY) == 0) {
- dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+ dev_info_ratelimited(dev,
+ "%s: %s: fail, dax range requires MADV_DONTFORK\n",
current->comm, func);
return -EINVAL;
}
if (!vma_is_dax(vma)) {
- dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+ dev_info_ratelimited(dev,
+ "%s: %s: fail, vma is not DAX capable\n",
current->comm, func);
return -EINVAL;
}
{
struct dax_device *dax_dev;
bool dax_enabled = false;
+ struct request_queue *q;
pgoff_t pgoff;
int err, id;
void *kaddr;
return false;
}
+ q = bdev_get_queue(bdev);
+ if (!q || !blk_queue_dax(q)) {
+ pr_debug("%s: error: request queue doesn't support dax\n",
+ bdevname(bdev, buf));
+ return false;
+ }
+
err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
if (err) {
pr_debug("%s: error: unaligned partition for dax\n",
* Each device has a channels list, which runs unlocked but is never modified
* once the device is registered, it's just setup by the driver.
*
- * See Documentation/dmaengine.txt for more details
+ * See Documentation/driver-api/dmaengine for more details
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
struct k3_dma_dev *d = ofdma->of_dma_data;
unsigned int request = dma_spec->args[0];
- if (request > d->dma_requests)
+ if (request >= d->dma_requests)
return NULL;
return dma_get_slave_channel(&(d->chans[request].vc.chan));
pd->src_addr_widths = PL330_DMA_BUSWIDTHS;
pd->dst_addr_widths = PL330_DMA_BUSWIDTHS;
pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
- pd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+ pd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
1 : PL330_MAX_BURST);
od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS;
od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS;
od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
- od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+ if (__dma_omap15xx(od->plat->dma_attr))
+ od->ddev.residue_granularity =
+ DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+ else
+ od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */
od->ddev.dev = &pdev->dev;
INIT_LIST_HEAD(&od->ddev.channels);
DEFINE_DMI_ATTR_WITH_SHOW(product_version, 0444, DMI_PRODUCT_VERSION);
DEFINE_DMI_ATTR_WITH_SHOW(product_serial, 0400, DMI_PRODUCT_SERIAL);
DEFINE_DMI_ATTR_WITH_SHOW(product_uuid, 0400, DMI_PRODUCT_UUID);
+DEFINE_DMI_ATTR_WITH_SHOW(product_sku, 0444, DMI_PRODUCT_SKU);
DEFINE_DMI_ATTR_WITH_SHOW(product_family, 0444, DMI_PRODUCT_FAMILY);
DEFINE_DMI_ATTR_WITH_SHOW(board_vendor, 0444, DMI_BOARD_VENDOR);
DEFINE_DMI_ATTR_WITH_SHOW(board_name, 0444, DMI_BOARD_NAME);
ADD_DMI_ATTR(product_serial, DMI_PRODUCT_SERIAL);
ADD_DMI_ATTR(product_uuid, DMI_PRODUCT_UUID);
ADD_DMI_ATTR(product_family, DMI_PRODUCT_FAMILY);
+ ADD_DMI_ATTR(product_sku, DMI_PRODUCT_SKU);
ADD_DMI_ATTR(board_vendor, DMI_BOARD_VENDOR);
ADD_DMI_ATTR(board_name, DMI_BOARD_NAME);
ADD_DMI_ATTR(board_version, DMI_BOARD_VERSION);
dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6);
dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7);
dmi_save_uuid(dm, DMI_PRODUCT_UUID, 8);
+ dmi_save_ident(dm, DMI_PRODUCT_SKU, 25);
dmi_save_ident(dm, DMI_PRODUCT_FAMILY, 26);
break;
case 2: /* Base Board Information */
config EFI_ARMSTUB
bool
+config EFI_ARMSTUB_DTB_LOADER
+ bool "Enable the DTB loader"
+ depends on EFI_ARMSTUB
+ help
+ Select this config option to add support for the dtb= command
+ line parameter, allowing a device tree blob to be loaded into
+ memory from the EFI System Partition by the stub.
+
+ The device tree is typically provided by the platform or by
+ the bootloader, so this option is mostly for development
+ purposes only.
+
config EFI_BOOTLOADER_CONTROL
tristate "EFI Bootloader Control"
depends on EFI_VARS
* uses its own memory map instead.
*/
memblock_dump_all();
- memblock_remove(0, (phys_addr_t)ULLONG_MAX);
+ memblock_remove(0, PHYS_ADDR_MAX);
for_each_efi_memory_desc(md) {
paddr = md->phys_addr;
{
static atomic64_t seq;
- if (!atomic64_read(&seq))
- atomic64_set(&seq, ((u64)get_seconds()) << 32);
+ if (!atomic64_read(&seq)) {
+ time64_t time = ktime_get_real_seconds();
+
+ /*
+ * This code is unlikely to still be needed in year 2106,
+ * but just in case, let's use a few more bits for timestamps
+ * after y2038 to be sure they keep increasing monotonically
+ * for the next few hundred years...
+ */
+ if (time < 0x80000000)
+ atomic64_set(&seq, (ktime_get_real_seconds()) << 32);
+ else
+ atomic64_set(&seq, 0x8000000000000000ull |
+ ktime_get_real_seconds() << 24);
+ }
return atomic64_inc_return(&seq);
}
else
goto err_section_too_small;
#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
- } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) {
+ } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata);
printk("%ssection_type: ARM processor error\n", newpfx);
return 0;
}
-static inline u64 generic_id(unsigned long timestamp,
- unsigned int part, int count)
+static inline u64 generic_id(u64 timestamp, unsigned int part, int count)
{
- return ((u64) timestamp * 100 + part) * 1000 + count;
+ return (timestamp * 100 + part) * 1000 + count;
}
static int efi_pstore_read_func(struct efivar_entry *entry,
int i;
int cnt;
unsigned int part;
- unsigned long time, size;
+ unsigned long size;
+ u64 time;
if (efi_guidcmp(entry->var.VendorGuid, vendor))
return 0;
for (i = 0; i < DUMP_NAME_LEN; i++)
name[i] = entry->var.VariableName[i];
- if (sscanf(name, "dump-type%u-%u-%d-%lu-%c",
+ if (sscanf(name, "dump-type%u-%u-%d-%llu-%c",
&record->type, &part, &cnt, &time, &data_type) == 5) {
record->id = generic_id(time, part, cnt);
record->part = part;
else
record->compressed = false;
record->ecc_notice_size = 0;
- } else if (sscanf(name, "dump-type%u-%u-%d-%lu",
+ } else if (sscanf(name, "dump-type%u-%u-%d-%llu",
&record->type, &part, &cnt, &time) == 4) {
record->id = generic_id(time, part, cnt);
record->part = part;
record->time.tv_nsec = 0;
record->compressed = false;
record->ecc_notice_size = 0;
- } else if (sscanf(name, "dump-type%u-%u-%lu",
+ } else if (sscanf(name, "dump-type%u-%u-%llu",
&record->type, &part, &time) == 3) {
/*
* Check if an old format,
/* Since we copy the entire length of name, make sure it is wiped. */
memset(name, 0, sizeof(name));
- snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu-%c",
+ snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lld-%c",
record->type, record->part, record->count,
- record->time.tv_sec, record->compressed ? 'C' : 'D');
+ (long long)record->time.tv_sec,
+ record->compressed ? 'C' : 'D');
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
char name[DUMP_NAME_LEN];
int ret;
- snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu",
+ snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lld",
record->type, record->part, record->count,
- record->time.tv_sec);
+ (long long)record->time.tv_sec);
ret = efi_pstore_erase_name(name);
if (ret != -ENOENT)
return ret;
- snprintf(name, sizeof(name), "dump-type%u-%u-%lu",
- record->type, record->part, record->time.tv_sec);
+ snprintf(name, sizeof(name), "dump-type%u-%u-%lld",
+ record->type, record->part, (long long)record->time.tv_sec);
ret = efi_pstore_erase_name(name);
return ret;
.mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem),
.page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
.mmlist = LIST_HEAD_INIT(efi_mm.mmlist),
+ .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0},
};
+struct workqueue_struct *efi_rts_wq;
+
static bool disable_runtime;
static int __init setup_noefi(char *arg)
{
if (!efi_enabled(EFI_BOOT))
return 0;
+ /*
+ * Since we process only one efi_runtime_service() at a time, an
+ * ordered workqueue (which creates only one execution context)
+ * should suffice all our needs.
+ */
+ efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+ if (!efi_rts_wq) {
+ pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ return 0;
+ }
+
/* We register the efi directory at /sys/firmware/efi */
efi_kobj = kobject_create_and_add("efi", firmware_kobj);
if (!efi_kobj) {
* and if so, populate the supplied memory descriptor with the appropriate
* data.
*/
-int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
{
efi_memory_desc_t *md;
u64 size;
u64 end;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_DATA &&
- md->type != EFI_RUNTIME_SERVICES_DATA) {
- continue;
- }
-
size = md->num_pages << EFI_PAGE_SHIFT;
end = md->phys_addr + size;
if (phys_addr >= md->phys_addr && phys_addr < end) {
return;
rc = efi_mem_desc_lookup(efi.esrt, &md);
- if (rc < 0) {
+ if (rc < 0 ||
+ (!(md.attribute & EFI_MEMORY_RUNTIME) &&
+ md.type != EFI_BOOT_SERVICES_DATA &&
+ md.type != EFI_RUNTIME_SERVICES_DATA)) {
pr_warn("ESRT header is not in the memory map.\n");
return;
}
end = esrt_data + size;
pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
- efi_mem_reserve(esrt_data, esrt_data_size);
+ if (md.type == EFI_BOOT_SERVICES_DATA)
+ efi_mem_reserve(esrt_data, esrt_data_size);
pr_debug("esrt-init: loaded.\n");
}
static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
- void *__image, void **__fh)
-{
- efi_file_io_interface_t *io;
- efi_loaded_image_t *image = __image;
- efi_file_handle_t *fh;
- efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
- efi_status_t status;
- void *handle = (void *)(unsigned long)image->device_handle;
-
- status = sys_table_arg->boottime->handle_protocol(handle,
- &fs_proto, (void **)&io);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
- return status;
- }
-
- status = io->open_volume(io, &fh);
- if (status != EFI_SUCCESS)
- efi_printk(sys_table_arg, "Failed to open volume\n");
-
- *__fh = fh;
- return status;
-}
-
void efi_char16_printk(efi_system_table_t *sys_table_arg,
efi_char16_t *str)
{
* 'dtb=' unless UEFI Secure Boot is disabled. We assume that secure
* boot is enabled if we can't determine its state.
*/
- if (secure_boot != efi_secureboot_mode_disabled &&
- strstr(cmdline_ptr, "dtb=")) {
- pr_efi(sys_table, "Ignoring DTB from command line.\n");
+ if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
+ secure_boot != efi_secureboot_mode_disabled) {
+ if (strstr(cmdline_ptr, "dtb="))
+ pr_efi(sys_table, "Ignoring DTB from command line.\n");
} else {
status = handle_cmdline_files(sys_table, image, cmdline_ptr,
"dtb=",
return efi_call_proto(efi_file_handle, close, handle);
}
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+ efi_loaded_image_t *image,
+ efi_file_handle_t **__fh)
+{
+ efi_file_io_interface_t *io;
+ efi_file_handle_t *fh;
+ efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+ efi_status_t status;
+ void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image,
+ device_handle,
+ image);
+
+ status = efi_call_early(handle_protocol, handle,
+ &fs_proto, (void **)&io);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+ return status;
+ }
+
+ status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh);
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table_arg, "Failed to open volume\n");
+ else
+ *__fh = fh;
+
+ return status;
+}
+
/*
* Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
* option, e.g. efi=nochunk.
/* Only open the volume once. */
if (!i) {
- status = efi_open_volume(sys_table_arg, image,
- (void **)&fh);
+ status = efi_open_volume(sys_table_arg, image, &fh);
if (status != EFI_SUCCESS)
goto free_files;
}
void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
- void **__fh);
-
unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
efi_status_t status;
- efi_physical_addr_t log_location, log_last_entry;
+ efi_physical_addr_t log_location = 0, log_last_entry = 0;
struct linux_efi_tpm_eventlog *log_tbl = NULL;
unsigned long first_entry_addr, last_entry_addr;
size_t log_size, last_entry_size;
/*
* runtime-wrappers.c - Runtime Services function call wrappers
*
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
* Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* Split off from arch/x86/platform/efi/efi.c
#include <linux/mutex.h>
#include <linux/semaphore.h>
#include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
#include <asm/efi.h>
/*
#define __efi_call_virt(f, args...) \
__efi_call_virt_pointer(efi.systab->runtime, f, args)
+/* efi_runtime_service() function identifiers */
+enum efi_rts_ids {
+ GET_TIME,
+ SET_TIME,
+ GET_WAKEUP_TIME,
+ SET_WAKEUP_TIME,
+ GET_VARIABLE,
+ GET_NEXT_VARIABLE,
+ SET_VARIABLE,
+ QUERY_VARIABLE_INFO,
+ GET_NEXT_HIGH_MONO_COUNT,
+ UPDATE_CAPSULE,
+ QUERY_CAPSULE_CAPS,
+};
+
+/*
+ * efi_runtime_work: Details of EFI Runtime Service work
+ * @arg<1-5>: EFI Runtime Service function arguments
+ * @status: Status of executing EFI Runtime Service
+ * @efi_rts_id: EFI Runtime Service function identifier
+ * @efi_rts_comp: Struct used for handling completions
+ */
+struct efi_runtime_work {
+ void *arg1;
+ void *arg2;
+ void *arg3;
+ void *arg4;
+ void *arg5;
+ efi_status_t status;
+ struct work_struct work;
+ enum efi_rts_ids efi_rts_id;
+ struct completion efi_rts_comp;
+};
+
+/*
+ * efi_queue_work: Queue efi_runtime_service() and wait until it's done
+ * @rts: efi_runtime_service() function identifier
+ * @rts_arg<1-5>: efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5) \
+({ \
+ struct efi_runtime_work efi_rts_work; \
+ efi_rts_work.status = EFI_ABORTED; \
+ \
+ init_completion(&efi_rts_work.efi_rts_comp); \
+ INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \
+ efi_rts_work.arg1 = _arg1; \
+ efi_rts_work.arg2 = _arg2; \
+ efi_rts_work.arg3 = _arg3; \
+ efi_rts_work.arg4 = _arg4; \
+ efi_rts_work.arg5 = _arg5; \
+ efi_rts_work.efi_rts_id = _rts; \
+ \
+ /* \
+ * queue_work() returns 0 if work was already on queue, \
+ * _ideally_ this should never happen. \
+ */ \
+ if (queue_work(efi_rts_wq, &efi_rts_work.work)) \
+ wait_for_completion(&efi_rts_work.efi_rts_comp); \
+ else \
+ pr_err("Failed to queue work to efi_rts_wq.\n"); \
+ \
+ efi_rts_work.status; \
+})
+
void efi_call_virt_check_flags(unsigned long flags, const char *call)
{
unsigned long cur_flags, mismatch;
*/
static DEFINE_SEMAPHORE(efi_runtime_lock);
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+ struct efi_runtime_work *efi_rts_work;
+ void *arg1, *arg2, *arg3, *arg4, *arg5;
+ efi_status_t status = EFI_NOT_FOUND;
+
+ efi_rts_work = container_of(work, struct efi_runtime_work, work);
+ arg1 = efi_rts_work->arg1;
+ arg2 = efi_rts_work->arg2;
+ arg3 = efi_rts_work->arg3;
+ arg4 = efi_rts_work->arg4;
+ arg5 = efi_rts_work->arg5;
+
+ switch (efi_rts_work->efi_rts_id) {
+ case GET_TIME:
+ status = efi_call_virt(get_time, (efi_time_t *)arg1,
+ (efi_time_cap_t *)arg2);
+ break;
+ case SET_TIME:
+ status = efi_call_virt(set_time, (efi_time_t *)arg1);
+ break;
+ case GET_WAKEUP_TIME:
+ status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+ (efi_bool_t *)arg2, (efi_time_t *)arg3);
+ break;
+ case SET_WAKEUP_TIME:
+ status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+ (efi_time_t *)arg2);
+ break;
+ case GET_VARIABLE:
+ status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+ (efi_guid_t *)arg2, (u32 *)arg3,
+ (unsigned long *)arg4, (void *)arg5);
+ break;
+ case GET_NEXT_VARIABLE:
+ status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+ (efi_char16_t *)arg2,
+ (efi_guid_t *)arg3);
+ break;
+ case SET_VARIABLE:
+ status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+ (efi_guid_t *)arg2, *(u32 *)arg3,
+ *(unsigned long *)arg4, (void *)arg5);
+ break;
+ case QUERY_VARIABLE_INFO:
+ status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+ (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+ break;
+ case GET_NEXT_HIGH_MONO_COUNT:
+ status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+ break;
+ case UPDATE_CAPSULE:
+ status = efi_call_virt(update_capsule,
+ (efi_capsule_header_t **)arg1,
+ *(unsigned long *)arg2,
+ *(unsigned long *)arg3);
+ break;
+ case QUERY_CAPSULE_CAPS:
+ status = efi_call_virt(query_capsule_caps,
+ (efi_capsule_header_t **)arg1,
+ *(unsigned long *)arg2, (u64 *)arg3,
+ (int *)arg4);
+ break;
+ default:
+ /*
+ * Ideally, we should never reach here because a caller of this
+ * function should have put the right efi_runtime_service()
+ * function identifier into efi_rts_work->efi_rts_id
+ */
+ pr_err("Requested executing invalid EFI Runtime Service.\n");
+ }
+ efi_rts_work->status = status;
+ complete(&efi_rts_work->efi_rts_comp);
+}
+
static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
efi_status_t status;
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(get_time, tm, tc);
+ status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(set_time, tm);
+ status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+ status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+ NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(set_wakeup_time, enabled, tm);
+ status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+ NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(get_variable, name, vendor, attr, data_size,
- data);
+ status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size,
+ data);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(get_next_variable, name_size, name, vendor);
+ status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor,
+ NULL, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(set_variable, name, vendor, attr, data_size,
- data);
+ status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size,
+ data);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(query_variable_info, attr, storage_space,
- remaining_space, max_variable_size);
+ status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space,
+ remaining_space, max_variable_size, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(get_next_high_mono_count, count);
+ status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+ NULL, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(update_capsule, capsules, count, sg_list);
+ status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list,
+ NULL, NULL);
up(&efi_runtime_lock);
return status;
}
if (down_interruptible(&efi_runtime_lock))
return EFI_ABORTED;
- status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
- reset_type);
+ status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count,
+ max_size, reset_type, NULL);
up(&efi_runtime_lock);
return status;
}
mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name,
&altera_cvp_ops, conf);
- if (!mgr)
- return -ENOMEM;
+ if (!mgr) {
+ ret = -ENOMEM;
+ goto err_unmap;
+ }
pci_set_drvdata(pdev, mgr);
fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node);
fwspec.param_count = 2;
fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET;
- fwspec.param[1] = IRQ_TYPE_NONE;
+ /*
+ * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH
+ * temporarily. Anyway, ->irq_set_type() will override it later.
+ */
+ fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH;
return irq_create_fwspec_mapping(&fwspec);
}
struct acpi_gpio_event {
struct list_head node;
+ struct list_head initial_sync_list;
acpi_handle handle;
unsigned int pin;
unsigned int irq;
struct list_head events;
};
+static LIST_HEAD(acpi_gpio_initial_sync_list);
+static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock);
+
static int acpi_gpiochip_find(struct gpio_chip *gc, void *data)
{
if (!gc->parent)
return gpiochip_get_desc(chip, pin);
}
+static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event)
+{
+ mutex_lock(&acpi_gpio_initial_sync_list_lock);
+ list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list);
+ mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
+static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event)
+{
+ mutex_lock(&acpi_gpio_initial_sync_list_lock);
+ if (!list_empty(&event->initial_sync_list))
+ list_del_init(&event->initial_sync_list);
+ mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
static irqreturn_t acpi_gpio_irq_handler(int irq, void *data)
{
struct acpi_gpio_event *event = data;
irq_handler_t handler = NULL;
struct gpio_desc *desc;
unsigned long irqflags;
- int ret, pin, irq;
+ int ret, pin, irq, value;
if (!acpi_gpio_get_irq_resource(ares, &agpio))
return AE_OK;
gpiod_direction_input(desc);
+ value = gpiod_get_value(desc);
+
ret = gpiochip_lock_as_irq(chip, pin);
if (ret) {
dev_err(chip->parent, "Failed to lock GPIO as interrupt\n");
event->irq = irq;
event->pin = pin;
event->desc = desc;
+ INIT_LIST_HEAD(&event->initial_sync_list);
ret = request_threaded_irq(event->irq, NULL, handler, irqflags,
"ACPI:Event", event);
enable_irq_wake(irq);
list_add_tail(&event->node, &acpi_gpio->events);
+
+ /*
+ * Make sure we trigger the initial state of the IRQ when using RISING
+ * or FALLING. Note we run the handlers on late_init, the AML code
+ * may refer to OperationRegions from other (builtin) drivers which
+ * may be probed after us.
+ */
+ if (handler == acpi_gpio_irq_handler &&
+ (((irqflags & IRQF_TRIGGER_RISING) && value == 1) ||
+ ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)))
+ acpi_gpio_add_to_initial_sync_list(event);
+
return AE_OK;
fail_free_event:
list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
struct gpio_desc *desc;
+ acpi_gpio_del_from_initial_sync_list(event);
+
if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
disable_irq_wake(event->irq);
return con_id == NULL;
}
+
+/* Sync the initial state of handlers after all builtin drivers have probed */
+static int acpi_gpio_initial_sync(void)
+{
+ struct acpi_gpio_event *event, *ep;
+
+ mutex_lock(&acpi_gpio_initial_sync_list_lock);
+ list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list,
+ initial_sync_list) {
+ acpi_evaluate_object(event->handle, NULL, NULL, NULL);
+ list_del_init(&event->initial_sync_list);
+ }
+ mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+
+ return 0;
+}
+/* We must use _sync so that this runs after the first deferred_probe run */
+late_initcall_sync(acpi_gpio_initial_sync);
* Note that active low is the default.
*/
if (IS_ENABLED(CONFIG_REGULATOR) &&
- (of_device_is_compatible(np, "reg-fixed-voltage") ||
+ (of_device_is_compatible(np, "regulator-fixed") ||
+ of_device_is_compatible(np, "reg-fixed-voltage") ||
of_device_is_compatible(np, "regulator-gpio"))) {
/*
* The regulator GPIO handles are specified such that the
struct amdgpu_irq_src;
struct amdgpu_fpriv;
struct amdgpu_bo_va_mapping;
+struct amdgpu_atif;
enum amdgpu_cp_irq {
AMDGPU_CP_IRQ_GFX_EOP = 0,
/*
* ACPI
*/
-struct amdgpu_atif_notification_cfg {
- bool enabled;
- int command_code;
-};
-
-struct amdgpu_atif_notifications {
- bool display_switch;
- bool expansion_mode_change;
- bool thermal_state;
- bool forced_power_state;
- bool system_power_state;
- bool display_conf_change;
- bool px_gfx_switch;
- bool brightness_change;
- bool dgpu_display_event;
-};
-
-struct amdgpu_atif_functions {
- bool system_params;
- bool sbios_requests;
- bool select_active_disp;
- bool lid_state;
- bool get_tv_standard;
- bool set_tv_standard;
- bool get_panel_expansion_mode;
- bool set_panel_expansion_mode;
- bool temperature_change;
- bool graphics_device_types;
-};
-
-struct amdgpu_atif {
- struct amdgpu_atif_notifications notifications;
- struct amdgpu_atif_functions functions;
- struct amdgpu_atif_notification_cfg notification_cfg;
- struct amdgpu_encoder *encoder_for_bl;
-};
-
struct amdgpu_atcs_functions {
bool get_ext_state;
bool pcie_perf_req;
#if defined(CONFIG_DEBUG_FS)
struct dentry *debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
#endif
- struct amdgpu_atif atif;
+ struct amdgpu_atif *atif;
struct amdgpu_atcs atcs;
struct mutex srbm_mutex;
/* GRBM index mutex. Protects concurrent access to GRBM index */
static inline bool amdgpu_has_atpx(void) { return false; }
#endif
+#if defined(CONFIG_VGA_SWITCHEROO) && defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void);
+#else
+static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
+#endif
+
/*
* KMS
*/
#define ACP_I2S_COMP2_CAP_REG_OFFSET 0xa8
#define ACP_I2S_COMP1_PLAY_REG_OFFSET 0x6c
#define ACP_I2S_COMP2_PLAY_REG_OFFSET 0x68
+#define ACP_BT_PLAY_REGS_START 0x14970
+#define ACP_BT_PLAY_REGS_END 0x14a24
+#define ACP_BT_COMP1_REG_OFFSET 0xac
+#define ACP_BT_COMP2_REG_OFFSET 0xa8
#define mmACP_PGFSM_RETAIN_REG 0x51c9
#define mmACP_PGFSM_CONFIG_REG 0x51ca
#define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE 0x000000FF
#define ACP_TIMEOUT_LOOP 0x000000FF
-#define ACP_DEVS 3
+#define ACP_DEVS 4
#define ACP_SRC_ID 162
enum {
if (adev->acp.acp_cell == NULL)
return -ENOMEM;
- adev->acp.acp_res = kcalloc(4, sizeof(struct resource), GFP_KERNEL);
-
+ adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
if (adev->acp.acp_res == NULL) {
kfree(adev->acp.acp_cell);
return -ENOMEM;
}
- i2s_pdata = kcalloc(2, sizeof(struct i2s_platform_data), GFP_KERNEL);
+ i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
if (i2s_pdata == NULL) {
kfree(adev->acp.acp_res);
kfree(adev->acp.acp_cell);
i2s_pdata[1].i2s_reg_comp1 = ACP_I2S_COMP1_CAP_REG_OFFSET;
i2s_pdata[1].i2s_reg_comp2 = ACP_I2S_COMP2_CAP_REG_OFFSET;
+ i2s_pdata[2].quirks = DW_I2S_QUIRK_COMP_REG_OFFSET;
+ switch (adev->asic_type) {
+ case CHIP_STONEY:
+ i2s_pdata[2].quirks |= DW_I2S_QUIRK_16BIT_IDX_OVERRIDE;
+ break;
+ default:
+ break;
+ }
+
+ i2s_pdata[2].cap = DWC_I2S_PLAY | DWC_I2S_RECORD;
+ i2s_pdata[2].snd_rates = SNDRV_PCM_RATE_8000_96000;
+ i2s_pdata[2].i2s_reg_comp1 = ACP_BT_COMP1_REG_OFFSET;
+ i2s_pdata[2].i2s_reg_comp2 = ACP_BT_COMP2_REG_OFFSET;
+
adev->acp.acp_res[0].name = "acp2x_dma";
adev->acp.acp_res[0].flags = IORESOURCE_MEM;
adev->acp.acp_res[0].start = acp_base;
adev->acp.acp_res[2].start = acp_base + ACP_I2S_CAP_REGS_START;
adev->acp.acp_res[2].end = acp_base + ACP_I2S_CAP_REGS_END;
- adev->acp.acp_res[3].name = "acp2x_dma_irq";
- adev->acp.acp_res[3].flags = IORESOURCE_IRQ;
- adev->acp.acp_res[3].start = amdgpu_irq_create_mapping(adev, 162);
- adev->acp.acp_res[3].end = adev->acp.acp_res[3].start;
+ adev->acp.acp_res[3].name = "acp2x_dw_bt_i2s_play_cap";
+ adev->acp.acp_res[3].flags = IORESOURCE_MEM;
+ adev->acp.acp_res[3].start = acp_base + ACP_BT_PLAY_REGS_START;
+ adev->acp.acp_res[3].end = acp_base + ACP_BT_PLAY_REGS_END;
+
+ adev->acp.acp_res[4].name = "acp2x_dma_irq";
+ adev->acp.acp_res[4].flags = IORESOURCE_IRQ;
+ adev->acp.acp_res[4].start = amdgpu_irq_create_mapping(adev, 162);
+ adev->acp.acp_res[4].end = adev->acp.acp_res[4].start;
adev->acp.acp_cell[0].name = "acp_audio_dma";
- adev->acp.acp_cell[0].num_resources = 4;
+ adev->acp.acp_cell[0].num_resources = 5;
adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0];
adev->acp.acp_cell[0].platform_data = &adev->asic_type;
adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type);
adev->acp.acp_cell[2].platform_data = &i2s_pdata[1];
adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data);
+ adev->acp.acp_cell[3].name = "designware-i2s";
+ adev->acp.acp_cell[3].num_resources = 1;
+ adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3];
+ adev->acp.acp_cell[3].platform_data = &i2s_pdata[2];
+ adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data);
+
r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
ACP_DEVS);
if (r)
val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
-
return 0;
}
#include "amd_acpi.h"
#include "atom.h"
+struct amdgpu_atif_notification_cfg {
+ bool enabled;
+ int command_code;
+};
+
+struct amdgpu_atif_notifications {
+ bool display_switch;
+ bool expansion_mode_change;
+ bool thermal_state;
+ bool forced_power_state;
+ bool system_power_state;
+ bool display_conf_change;
+ bool px_gfx_switch;
+ bool brightness_change;
+ bool dgpu_display_event;
+};
+
+struct amdgpu_atif_functions {
+ bool system_params;
+ bool sbios_requests;
+ bool select_active_disp;
+ bool lid_state;
+ bool get_tv_standard;
+ bool set_tv_standard;
+ bool get_panel_expansion_mode;
+ bool set_panel_expansion_mode;
+ bool temperature_change;
+ bool graphics_device_types;
+};
+
+struct amdgpu_atif {
+ acpi_handle handle;
+
+ struct amdgpu_atif_notifications notifications;
+ struct amdgpu_atif_functions functions;
+ struct amdgpu_atif_notification_cfg notification_cfg;
+ struct amdgpu_encoder *encoder_for_bl;
+};
+
/* Call the ATIF method
*/
/**
* Executes the requested ATIF function (all asics).
* Returns a pointer to the acpi output buffer.
*/
-static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
- struct acpi_buffer *params)
+static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
+ int function,
+ struct acpi_buffer *params)
{
acpi_status status;
union acpi_object atif_arg_elements[2];
atif_arg_elements[1].integer.value = 0;
}
- status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer);
+ status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
+ &buffer);
/* Fail only if calling the method fails and ATIF is supported */
if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
* (all asics).
* returns 0 on success, error on failure.
*/
-static int amdgpu_atif_verify_interface(acpi_handle handle,
- struct amdgpu_atif *atif)
+static int amdgpu_atif_verify_interface(struct amdgpu_atif *atif)
{
union acpi_object *info;
struct atif_verify_interface output;
size_t size;
int err = 0;
- info = amdgpu_atif_call(handle, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
+ info = amdgpu_atif_call(atif, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
if (!info)
return -EIO;
return err;
}
+static acpi_handle amdgpu_atif_probe_handle(acpi_handle dhandle)
+{
+ acpi_handle handle = NULL;
+ char acpi_method_name[255] = { 0 };
+ struct acpi_buffer buffer = { sizeof(acpi_method_name), acpi_method_name };
+ acpi_status status;
+
+ /* For PX/HG systems, ATIF and ATPX are in the iGPU's namespace, on dGPU only
+ * systems, ATIF is in the dGPU's namespace.
+ */
+ status = acpi_get_handle(dhandle, "ATIF", &handle);
+ if (ACPI_SUCCESS(status))
+ goto out;
+
+ if (amdgpu_has_atpx()) {
+ status = acpi_get_handle(amdgpu_atpx_get_dhandle(), "ATIF",
+ &handle);
+ if (ACPI_SUCCESS(status))
+ goto out;
+ }
+
+ DRM_DEBUG_DRIVER("No ATIF handle found\n");
+ return NULL;
+out:
+ acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+ DRM_DEBUG_DRIVER("Found ATIF handle %s\n", acpi_method_name);
+ return handle;
+}
+
/**
* amdgpu_atif_get_notification_params - determine notify configuration
*
* where n is specified in the result if a notifier is used.
* Returns 0 on success, error on failure.
*/
-static int amdgpu_atif_get_notification_params(acpi_handle handle,
- struct amdgpu_atif_notification_cfg *n)
+static int amdgpu_atif_get_notification_params(struct amdgpu_atif *atif)
{
union acpi_object *info;
+ struct amdgpu_atif_notification_cfg *n = &atif->notification_cfg;
struct atif_system_params params;
size_t size;
int err = 0;
- info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS, NULL);
+ info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS,
+ NULL);
if (!info) {
err = -EIO;
goto out;
* (all asics).
* Returns 0 on success, error on failure.
*/
-static int amdgpu_atif_get_sbios_requests(acpi_handle handle,
- struct atif_sbios_requests *req)
+static int amdgpu_atif_get_sbios_requests(struct amdgpu_atif *atif,
+ struct atif_sbios_requests *req)
{
union acpi_object *info;
size_t size;
int count = 0;
- info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS, NULL);
+ info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS,
+ NULL);
if (!info)
return -EIO;
* Returns NOTIFY code
*/
static int amdgpu_atif_handler(struct amdgpu_device *adev,
- struct acpi_bus_event *event)
+ struct acpi_bus_event *event)
{
- struct amdgpu_atif *atif = &adev->atif;
+ struct amdgpu_atif *atif = adev->atif;
struct atif_sbios_requests req;
- acpi_handle handle;
int count;
DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
return NOTIFY_DONE;
- if (!atif->notification_cfg.enabled ||
+ if (!atif ||
+ !atif->notification_cfg.enabled ||
event->type != atif->notification_cfg.command_code)
/* Not our event */
return NOTIFY_DONE;
/* Check pending SBIOS requests */
- handle = ACPI_HANDLE(&adev->pdev->dev);
- count = amdgpu_atif_get_sbios_requests(handle, &req);
+ count = amdgpu_atif_get_sbios_requests(atif, &req);
if (count <= 0)
return NOTIFY_DONE;
*/
int amdgpu_acpi_init(struct amdgpu_device *adev)
{
- acpi_handle handle;
- struct amdgpu_atif *atif = &adev->atif;
+ acpi_handle handle, atif_handle;
+ struct amdgpu_atif *atif;
struct amdgpu_atcs *atcs = &adev->atcs;
int ret;
DRM_DEBUG_DRIVER("Call to ATCS verify_interface failed: %d\n", ret);
}
+ /* Probe for ATIF, and initialize it if found */
+ atif_handle = amdgpu_atif_probe_handle(handle);
+ if (!atif_handle)
+ goto out;
+
+ atif = kzalloc(sizeof(*atif), GFP_KERNEL);
+ if (!atif) {
+ DRM_WARN("Not enough memory to initialize ATIF\n");
+ goto out;
+ }
+ atif->handle = atif_handle;
+
/* Call the ATIF method */
- ret = amdgpu_atif_verify_interface(handle, atif);
+ ret = amdgpu_atif_verify_interface(atif);
if (ret) {
DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
+ kfree(atif);
goto out;
}
+ adev->atif = atif;
if (atif->notifications.brightness_change) {
struct drm_encoder *tmp;
}
if (atif->functions.system_params) {
- ret = amdgpu_atif_get_notification_params(handle,
- &atif->notification_cfg);
+ ret = amdgpu_atif_get_notification_params(atif);
if (ret) {
DRM_DEBUG_DRIVER("Call to GET_SYSTEM_PARAMS failed: %d\n",
ret);
void amdgpu_acpi_fini(struct amdgpu_device *adev)
{
unregister_acpi_notifier(&adev->acpi_nb);
+ if (adev->atif)
+ kfree(adev->atif);
}
mem_info->local_mem_size_public,
mem_info->local_mem_size_private);
- if (amdgpu_emu_mode == 1) {
- mem_info->mem_clk_max = 100;
- return;
- }
-
if (amdgpu_sriov_vf(adev))
mem_info->mem_clk_max = adev->clock.default_mclk / 100;
- else
+ else if (adev->powerplay.pp_funcs)
mem_info->mem_clk_max = amdgpu_dpm_get_mclk(adev, false) / 100;
+ else
+ mem_info->mem_clk_max = 100;
}
uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
/* the sclk is in quantas of 10kHz */
- if (amdgpu_emu_mode == 1)
- return 100;
-
if (amdgpu_sriov_vf(adev))
return adev->clock.default_sclk / 100;
-
- return amdgpu_dpm_get_sclk(adev, false) / 100;
+ else if (adev->powerplay.pp_funcs)
+ return amdgpu_dpm_get_sclk(adev, false) / 100;
+ else
+ return 100;
}
void get_cu_info(struct kgd_dev *kgd, struct kfd_cu_info *cu_info)
return amdgpu_atpx_priv.atpx.dgpu_req_power_for_displays;
}
+#if defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void) {
+ return amdgpu_atpx_priv.dhandle;
+}
+#endif
+
/**
* amdgpu_atpx_call - call an ATPX method
*
{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
- { 0x1002, 0x67DF, 0x1028, 0x0774, AMDGPU_PX_QUIRK_FORCE_ATPX },
+ { 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0, 0, 0, 0, 0 },
};
struct amdgpu_bo_list_entry *e;
struct list_head duplicates;
unsigned i, tries = 10;
+ struct amdgpu_bo *gds;
+ struct amdgpu_bo *gws;
+ struct amdgpu_bo *oa;
int r;
INIT_LIST_HEAD(&p->validated);
amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
p->bytes_moved_vis);
+
if (p->bo_list) {
- struct amdgpu_bo *gds = p->bo_list->gds_obj;
- struct amdgpu_bo *gws = p->bo_list->gws_obj;
- struct amdgpu_bo *oa = p->bo_list->oa_obj;
struct amdgpu_vm *vm = &fpriv->vm;
unsigned i;
+ gds = p->bo_list->gds_obj;
+ gws = p->bo_list->gws_obj;
+ oa = p->bo_list->oa_obj;
for (i = 0; i < p->bo_list->num_entries; i++) {
struct amdgpu_bo *bo = p->bo_list->array[i].robj;
p->bo_list->array[i].bo_va = amdgpu_vm_bo_find(vm, bo);
}
+ } else {
+ gds = p->adev->gds.gds_gfx_bo;
+ gws = p->adev->gds.gws_gfx_bo;
+ oa = p->adev->gds.oa_gfx_bo;
+ }
- if (gds) {
- p->job->gds_base = amdgpu_bo_gpu_offset(gds);
- p->job->gds_size = amdgpu_bo_size(gds);
- }
- if (gws) {
- p->job->gws_base = amdgpu_bo_gpu_offset(gws);
- p->job->gws_size = amdgpu_bo_size(gws);
- }
- if (oa) {
- p->job->oa_base = amdgpu_bo_gpu_offset(oa);
- p->job->oa_size = amdgpu_bo_size(oa);
- }
+ if (gds) {
+ p->job->gds_base = amdgpu_bo_gpu_offset(gds);
+ p->job->gds_size = amdgpu_bo_size(gds);
+ }
+ if (gws) {
+ p->job->gws_base = amdgpu_bo_gpu_offset(gws);
+ p->job->gws_size = amdgpu_bo_size(gws);
+ }
+ if (oa) {
+ p->job->oa_base = amdgpu_bo_gpu_offset(oa);
+ p->job->oa_size = amdgpu_bo_size(oa);
}
if (!r && p->uf_entry.robj) {
r = amdgpu_bo_vm_update_pte(p);
if (r)
return r;
+
+ r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
+ if (r)
+ return r;
}
return amdgpu_cs_sync_rings(p);
}
}
}
+
+ if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
+ /* enable gfx powergating */
+ amdgpu_device_ip_set_powergating_state(adev,
+ AMD_IP_BLOCK_TYPE_GFX,
+ AMD_PG_STATE_GATE);
+ /* enable gfxoff */
+ amdgpu_device_ip_set_powergating_state(adev,
+ AMD_IP_BLOCK_TYPE_SMC,
+ AMD_PG_STATE_GATE);
+ }
+
return 0;
}
switch (asic_type) {
#if defined(CONFIG_DRM_AMD_DC)
case CHIP_BONAIRE:
- case CHIP_HAWAII:
case CHIP_KAVERI:
case CHIP_KABINI:
case CHIP_MULLINS:
+ /*
+ * We have systems in the wild with these ASICs that require
+ * LVDS and VGA support which is not supported with DC.
+ *
+ * Fallback to the non-DC driver here by default so as not to
+ * cause regressions.
+ */
+ return amdgpu_dc > 0;
+ case CHIP_HAWAII:
case CHIP_CARRIZO:
case CHIP_STONEY:
case CHIP_POLARIS10:
if (r)
return r;
+ /* Make sure IB tests flushed */
+ flush_delayed_work(&adev->late_init_work);
+
/* blat the mode back in */
if (fbcon) {
if (!amdgpu_device_has_dc_support(adev)) {
struct amdgpu_device *adev = ring->adev;
uint64_t index;
- if (ring != &adev->uvd.inst[ring->me].ring) {
+ if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
} else {
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#include "amdgpu.h"
+#include "amdgpu_display.h"
void amdgpu_gem_object_free(struct drm_gem_object *gobj)
{
/* create a gem object to contain this object in */
if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
+ if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
+ /* if gds bo is created from user space, it must be
+ * passed to bo list
+ */
+ DRM_ERROR("GDS bo cannot be per-vm-bo\n");
+ return -EINVAL;
+ }
flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
if (args->in.domains == AMDGPU_GEM_DOMAIN_GDS)
size = size << AMDGPU_GDS_SHIFT;
struct amdgpu_device *adev = dev->dev_private;
struct drm_gem_object *gobj;
uint32_t handle;
+ u32 domain;
int r;
args->pitch = amdgpu_align_pitch(adev, args->width,
DIV_ROUND_UP(args->bpp, 8), 0);
args->size = (u64)args->pitch * args->height;
args->size = ALIGN(args->size, PAGE_SIZE);
-
- r = amdgpu_gem_object_create(adev, args->size, 0,
- AMDGPU_GEM_DOMAIN_VRAM,
+ domain = amdgpu_bo_get_preferred_pin_domain(adev,
+ amdgpu_display_supported_domains(adev));
+ r = amdgpu_gem_object_create(adev, args->size, 0, domain,
AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
false, NULL, &gobj);
if (r)
if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
+ /* wrap the last IB with fence */
+ if (job && job->uf_addr) {
+ amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
+ fence_flags | AMDGPU_FENCE_FLAG_64BIT);
+ }
+
r = amdgpu_fence_emit(ring, f, fence_flags);
if (r) {
dev_err(adev->dev, "failed to emit fence (%d)\n", r);
if (ring->funcs->insert_end)
ring->funcs->insert_end(ring);
- /* wrap the last IB with fence */
- if (job && job->uf_addr) {
- amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
- fence_flags | AMDGPU_FENCE_FLAG_64BIT);
- }
-
if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
amdgpu_ring_patch_cond_exec(ring, patch_offset);
/* This assumes only APU display buffers are pinned with (VRAM|GTT).
* See function amdgpu_display_supported_domains()
*/
- if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
- domain = AMDGPU_GEM_DOMAIN_VRAM;
- if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD)
- domain = AMDGPU_GEM_DOMAIN_GTT;
- }
+ domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
if (bo->pin_count) {
uint32_t mem_type = bo->tbo.mem.mem_type;
domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
adev->vram_pin_size += amdgpu_bo_size(bo);
- if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
- adev->invisible_pin_size += amdgpu_bo_size(bo);
+ adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
adev->gart_pin_size += amdgpu_bo_size(bo);
}
bo->pin_count--;
if (bo->pin_count)
return 0;
- for (i = 0; i < bo->placement.num_placement; i++) {
- bo->placements[i].lpfn = 0;
- bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
- }
- r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
- if (unlikely(r)) {
- dev_err(adev->dev, "%p validate failed for unpin\n", bo);
- goto error;
- }
if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
adev->vram_pin_size -= amdgpu_bo_size(bo);
- if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
- adev->invisible_pin_size -= amdgpu_bo_size(bo);
+ adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
adev->gart_pin_size -= amdgpu_bo_size(bo);
}
-error:
+ for (i = 0; i < bo->placement.num_placement; i++) {
+ bo->placements[i].lpfn = 0;
+ bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
+ }
+ r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+ if (unlikely(r))
+ dev_err(adev->dev, "%p validate failed for unpin\n", bo);
+
return r;
}
return bo->tbo.offset;
}
+
+uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+ uint32_t domain)
+{
+ if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
+ domain = AMDGPU_GEM_DOMAIN_VRAM;
+ if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD)
+ domain = AMDGPU_GEM_DOMAIN_GTT;
+ }
+ return domain;
+}
struct reservation_object *resv,
struct dma_fence **fence,
bool direct);
-
+uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+ uint32_t domain);
/*
* sub allocation
if (!amdgpu_device_has_dc_support(adev)) {
mutex_lock(&adev->pm.mutex);
amdgpu_dpm_get_active_displays(adev);
- adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtcs;
+ adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
+u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
unsigned version_major, version_minor, family_id;
int i, j, r;
- INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler);
+ INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler);
switch (adev->asic_type) {
#ifdef CONFIG_DRM_AMDGPU_CIK
void *ptr;
int i, j;
+ cancel_delayed_work_sync(&adev->uvd.idle_work);
+
for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
if (adev->uvd.inst[j].vcpu_bo == NULL)
continue;
- cancel_delayed_work_sync(&adev->uvd.inst[j].idle_work);
-
/* only valid for physical mode */
if (adev->asic_type < CHIP_POLARIS10) {
for (i = 0; i < adev->uvd.max_handles; ++i)
static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
{
struct amdgpu_device *adev =
- container_of(work, struct amdgpu_device, uvd.inst->idle_work.work);
+ container_of(work, struct amdgpu_device, uvd.idle_work.work);
unsigned fences = 0, i, j;
for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
AMD_CG_STATE_GATE);
}
} else {
- schedule_delayed_work(&adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+ schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
}
}
if (amdgpu_sriov_vf(adev))
return;
- set_clocks = !cancel_delayed_work_sync(&adev->uvd.inst->idle_work);
+ set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
if (set_clocks) {
if (adev->pm.dpm_enabled) {
amdgpu_dpm_enable_uvd(adev, true);
void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
{
if (!amdgpu_sriov_vf(ring->adev))
- schedule_delayed_work(&ring->adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+ schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
}
/**
void *saved_bo;
atomic_t handles[AMDGPU_MAX_UVD_HANDLES];
struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES];
- struct delayed_work idle_work;
struct amdgpu_ring ring;
struct amdgpu_ring ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
struct amdgpu_irq_src irq;
bool address_64_bit;
bool use_ctx_buf;
struct amdgpu_uvd_inst inst[AMDGPU_MAX_UVD_INSTANCES];
+ struct delayed_work idle_work;
};
int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
{
- struct amdgpu_ring *ring;
- struct drm_sched_rq *rq;
unsigned long bo_size;
const char *fw_name;
const struct common_firmware_header *hdr;
- unsigned version_major, version_minor, family_id;
+ unsigned char fw_check;
int r;
INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
}
hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
- family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
- version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
- version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
- DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
- version_major, version_minor, family_id);
+ adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
+
+ /* Bit 20-23, it is encode major and non-zero for new naming convention.
+ * This field is part of version minor and DRM_DISABLED_FLAG in old naming
+ * convention. Since the l:wq!atest version minor is 0x5B and DRM_DISABLED_FLAG
+ * is zero in old naming convention, this field is always zero so far.
+ * These four bits are used to tell which naming convention is present.
+ */
+ fw_check = (le32_to_cpu(hdr->ucode_version) >> 20) & 0xf;
+ if (fw_check) {
+ unsigned int dec_ver, enc_major, enc_minor, vep, fw_rev;
+
+ fw_rev = le32_to_cpu(hdr->ucode_version) & 0xfff;
+ enc_minor = (le32_to_cpu(hdr->ucode_version) >> 12) & 0xff;
+ enc_major = fw_check;
+ dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf;
+ vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf;
+ DRM_INFO("Found VCN firmware Version ENC: %hu.%hu DEC: %hu VEP: %hu Revision: %hu\n",
+ enc_major, enc_minor, dec_ver, vep, fw_rev);
+ } else {
+ unsigned int version_major, version_minor, family_id;
+ family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
+ version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
+ version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+ DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
+ version_major, version_minor, family_id);
+ }
bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
+ AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
return r;
}
- ring = &adev->vcn.ring_dec;
- rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
- r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_dec,
- rq, NULL);
- if (r != 0) {
- DRM_ERROR("Failed setting up VCN dec run queue.\n");
- return r;
- }
-
- ring = &adev->vcn.ring_enc[0];
- rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
- r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_enc,
- rq, NULL);
- if (r != 0) {
- DRM_ERROR("Failed setting up VCN enc run queue.\n");
- return r;
- }
-
return 0;
}
kfree(adev->vcn.saved_bo);
- drm_sched_entity_fini(&adev->vcn.ring_dec.sched, &adev->vcn.entity_dec);
-
- drm_sched_entity_fini(&adev->vcn.ring_enc[0].sched, &adev->vcn.entity_enc);
-
amdgpu_bo_free_kernel(&adev->vcn.vcpu_bo,
&adev->vcn.gpu_addr,
(void **)&adev->vcn.cpu_addr);
}
static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
- struct amdgpu_bo *bo, bool direct,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
struct amdgpu_device *adev = ring->adev;
}
ib->length_dw = 16;
- if (direct) {
- r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
- job->fence = dma_fence_get(f);
- if (r)
- goto err_free;
+ r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+ job->fence = dma_fence_get(f);
+ if (r)
+ goto err_free;
- amdgpu_job_free(job);
- } else {
- r = amdgpu_job_submit(job, ring, &adev->vcn.entity_dec,
- AMDGPU_FENCE_OWNER_UNDEFINED, &f);
- if (r)
- goto err_free;
- }
+ amdgpu_job_free(job);
amdgpu_bo_fence(bo, f, false);
amdgpu_bo_unreserve(bo);
for (i = 14; i < 1024; ++i)
msg[i] = cpu_to_le32(0x0);
- return amdgpu_vcn_dec_send_msg(ring, bo, true, fence);
+ return amdgpu_vcn_dec_send_msg(ring, bo, fence);
}
static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
- bool direct, struct dma_fence **fence)
+ struct dma_fence **fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_bo *bo = NULL;
for (i = 6; i < 1024; ++i)
msg[i] = cpu_to_le32(0x0);
- return amdgpu_vcn_dec_send_msg(ring, bo, direct, fence);
+ return amdgpu_vcn_dec_send_msg(ring, bo, fence);
}
int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
goto error;
}
- r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, true, &fence);
+ r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, &fence);
if (r) {
DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
goto error;
struct amdgpu_ring ring_dec;
struct amdgpu_ring ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
struct amdgpu_irq_src irq;
- struct drm_sched_entity entity_dec;
- struct drm_sched_entity entity_enc;
unsigned num_enc_rings;
};
return;
list_add_tail(&base->bo_list, &bo->va);
+ if (bo->tbo.type == ttm_bo_type_kernel)
+ list_move(&base->vm_status, &vm->relocated);
+
if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
return;
pt->parent = amdgpu_bo_ref(parent->base.bo);
amdgpu_vm_bo_base_init(&entry->base, vm, pt);
- list_move(&entry->base.vm_status, &vm->relocated);
}
if (level < AMDGPU_VM_PTB) {
uint64_t count;
max_entries = min(max_entries, 16ull * 1024ull);
- for (count = 1; count < max_entries; ++count) {
+ for (count = 1;
+ count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+ ++count) {
uint64_t idx = pfn + count;
if (pages_addr[idx] !=
dma_addr = pages_addr;
} else {
addr = pages_addr[pfn];
- max_entries = count;
+ max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
}
} else if (flags & AMDGPU_PTE_VALID) {
if (r)
return r;
- pfn += last - start + 1;
+ pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
if (nodes && nodes->size == pfn) {
pfn = 0;
++nodes;
before->last = saddr - 1;
before->offset = tmp->offset;
before->flags = tmp->flags;
- list_add(&before->list, &tmp->list);
+ before->bo_va = tmp->bo_va;
+ list_add(&before->list, &tmp->bo_va->invalids);
}
/* Remember mapping split at the end */
after->offset = tmp->offset;
after->offset += after->start - tmp->start;
after->flags = tmp->flags;
- list_add(&after->list, &tmp->list);
+ after->bo_va = tmp->bo_va;
+ list_add(&after->list, &tmp->bo_va->invalids);
}
list_del(&tmp->list);
adev->gmc.visible_vram_size : end) - start;
}
+/**
+ * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size
+ *
+ * @bo: &amdgpu_bo buffer object (must be in VRAM)
+ *
+ * Returns:
+ * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM.
+ */
+u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
+{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ struct ttm_mem_reg *mem = &bo->tbo.mem;
+ struct drm_mm_node *nodes = mem->mm_node;
+ unsigned pages = mem->num_pages;
+ u64 usage = 0;
+
+ if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size)
+ return 0;
+
+ if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
+ return amdgpu_bo_size(bo);
+
+ while (nodes && pages) {
+ usage += nodes->size << PAGE_SHIFT;
+ usage -= amdgpu_vram_mgr_vis_size(adev, nodes);
+ pages -= nodes->size;
+ ++nodes;
+ }
+
+ return usage;
+}
+
/**
* amdgpu_vram_mgr_new - allocate new ranges
*
num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node);
}
- nodes = kcalloc(num_nodes, sizeof(*nodes), GFP_KERNEL);
+ nodes = kvmalloc_array(num_nodes, sizeof(*nodes),
+ GFP_KERNEL | __GFP_ZERO);
if (!nodes)
return -ENOMEM;
drm_mm_remove_node(&nodes[i]);
spin_unlock(&mgr->lock);
- kfree(nodes);
+ kvfree(nodes);
return r == -ENOSPC ? 0 : r;
}
atomic64_sub(usage, &mgr->usage);
atomic64_sub(vis_usage, &mgr->vis_usage);
- kfree(mem->mm_node);
+ kvfree(mem->mm_node);
mem->mm_node = NULL;
}
int fb_channel_number;
fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
- if (fb_channel_number > ARRAY_SIZE(df_v3_6_channel_number))
+ if (fb_channel_number >= ARRAY_SIZE(df_v3_6_channel_number))
fb_channel_number = 0;
return df_v3_6_channel_number[fb_channel_number];
static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
{
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_DCC_CONFIG, 0x0f000080, 0x04000080),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_2, 0x0f000000, 0x0a000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xf3e777ff, 0x22014042),
int indirect_offset,
int list_size,
int *unique_indirect_regs,
- int *unique_indirect_reg_count,
+ int unique_indirect_reg_count,
int *indirect_start_offsets,
- int *indirect_start_offsets_count)
+ int *indirect_start_offsets_count,
+ int max_start_offsets_count)
{
int idx;
for (; indirect_offset < list_size; indirect_offset++) {
+ WARN_ON(*indirect_start_offsets_count >= max_start_offsets_count);
indirect_start_offsets[*indirect_start_offsets_count] = indirect_offset;
*indirect_start_offsets_count = *indirect_start_offsets_count + 1;
indirect_offset += 2;
/* look for the matching indice */
- for (idx = 0; idx < *unique_indirect_reg_count; idx++) {
+ for (idx = 0; idx < unique_indirect_reg_count; idx++) {
if (unique_indirect_regs[idx] ==
register_list_format[indirect_offset] ||
!unique_indirect_regs[idx])
break;
}
- BUG_ON(idx >= *unique_indirect_reg_count);
+ BUG_ON(idx >= unique_indirect_reg_count);
if (!unique_indirect_regs[idx])
unique_indirect_regs[idx] = register_list_format[indirect_offset];
adev->gfx.rlc.reg_list_format_direct_reg_list_length,
adev->gfx.rlc.reg_list_format_size_bytes >> 2,
unique_indirect_regs,
- &unique_indirect_reg_count,
+ unique_indirect_reg_count,
indirect_start_offsets,
- &indirect_start_offsets_count);
+ &indirect_start_offsets_count,
+ ARRAY_SIZE(indirect_start_offsets));
/* enable auto inc in case it is disabled */
tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL));
if (r)
return r;
- r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_GFX,
- AMD_PG_STATE_GATE);
- if (r)
- return r;
-
return 0;
}
#define smnMP1_FIRMWARE_FLAGS 0x3010028
+static uint32_t sos_old_versions[] = {1517616, 1510592, 1448594, 1446554};
+
static int
psp_v3_1_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type *type)
{
return ret;
}
+static bool psp_v3_1_match_version(struct amdgpu_device *adev, uint32_t ver)
+{
+ int i;
+
+ if (ver == adev->psp.sos_fw_version)
+ return true;
+
+ /*
+ * Double check if the latest four legacy versions.
+ * If yes, it is still the right version.
+ */
+ for (i = 0; i < sizeof(sos_old_versions) / sizeof(uint32_t); i++) {
+ if (sos_old_versions[i] == adev->psp.sos_fw_version)
+ return true;
+ }
+
+ return false;
+}
+
static int psp_v3_1_bootloader_load_sos(struct psp_context *psp)
{
int ret;
unsigned int psp_gfxdrv_command_reg = 0;
struct amdgpu_device *adev = psp->adev;
- uint32_t sol_reg;
+ uint32_t sol_reg, ver;
/* Check sOS sign of life register to confirm sys driver and sOS
* are already been loaded.
RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81),
0, true);
+ ver = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58);
+ if (!psp_v3_1_match_version(adev, ver))
+ DRM_WARN("SOS version doesn't match\n");
+
return ret;
}
AMD_CG_SUPPORT_BIF_MGCG |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_MGCG |
+ AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_ROM_MGCG |
AMD_CG_SUPPORT_VCE_MGCG |
AMD_CG_SUPPORT_UVD_MGCG;
.emit_frame_size =
4 + /* vce_v3_0_emit_pipeline_sync */
6, /* amdgpu_vce_ring_emit_fence x1 no user fence */
- .emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
+ .emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
.emit_ib = amdgpu_vce_ring_emit_ib,
.emit_fence = amdgpu_vce_ring_emit_fence,
.test_ring = amdgpu_vce_ring_test_ring,
6 + /* vce_v3_0_emit_vm_flush */
4 + /* vce_v3_0_emit_pipeline_sync */
6 + 6, /* amdgpu_vce_ring_emit_fence x2 vm fence */
- .emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
+ .emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
.emit_ib = vce_v3_0_ring_emit_ib,
.emit_vm_flush = vce_v3_0_emit_vm_flush,
.emit_pipeline_sync = vce_v3_0_emit_pipeline_sync,
return 0;
}
-bool vcn_v1_0_is_idle(void *handle)
+static bool vcn_v1_0_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == 0x2);
}
-int vcn_v1_0_wait_for_idle(void *handle)
+static int vcn_v1_0_wait_for_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int ret = 0;
#include <linux/moduleparam.h>
#include <linux/version.h>
#include <linux/types.h>
+#include <linux/pm_runtime.h>
#include <drm/drmP.h>
#include <drm/drm_atomic.h>
{
uint32_t bpc = connector->display_info.bpc;
- /* Limited color depth to 8bit
- * TODO: Still need to handle deep color
- */
- if (bpc > 8)
- bpc = 8;
-
switch (bpc) {
case 0:
/* Temporary Work around, DRM don't parse color depth for
return color_space;
}
+static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+{
+ if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+ return;
+
+ timing_out->display_color_depth--;
+}
+
+static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
+ const struct drm_display_info *info)
+{
+ int normalized_clk;
+ if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+ return;
+ do {
+ normalized_clk = timing_out->pix_clk_khz;
+ /* YCbCr 4:2:0 requires additional adjustment of 1/2 */
+ if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+ normalized_clk /= 2;
+ /* Adjusting pix clock following on HDMI spec based on colour depth */
+ switch (timing_out->display_color_depth) {
+ case COLOR_DEPTH_101010:
+ normalized_clk = (normalized_clk * 30) / 24;
+ break;
+ case COLOR_DEPTH_121212:
+ normalized_clk = (normalized_clk * 36) / 24;
+ break;
+ case COLOR_DEPTH_161616:
+ normalized_clk = (normalized_clk * 48) / 24;
+ break;
+ default:
+ return;
+ }
+ if (normalized_clk <= info->max_tmds_clock)
+ return;
+ reduce_mode_colour_depth(timing_out);
+
+ } while (timing_out->display_color_depth > COLOR_DEPTH_888);
+
+}
/*****************************************************************************/
static void
const struct drm_connector *connector)
{
struct dc_crtc_timing *timing_out = &stream->timing;
+ const struct drm_display_info *info = &connector->display_info;
memset(timing_out, 0, sizeof(struct dc_crtc_timing));
timing_out->v_border_top = 0;
timing_out->v_border_bottom = 0;
/* TODO: un-hardcode */
-
- if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
+ if (drm_mode_is_420_only(info, mode_in)
+ && stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+ timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+ else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444;
else
stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
+ if (stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+ adjust_colour_depth_from_display_info(timing_out, info);
}
static void fill_audio_info(struct audio_info *audio_info,
}
}
-static int create_fake_sink(struct amdgpu_dm_connector *aconnector)
+static struct dc_sink *
+create_fake_sink(struct amdgpu_dm_connector *aconnector)
{
- struct dc_sink *sink = NULL;
struct dc_sink_init_data sink_init_data = { 0 };
-
+ struct dc_sink *sink = NULL;
sink_init_data.link = aconnector->dc_link;
sink_init_data.sink_signal = aconnector->dc_link->connector_signal;
sink = dc_sink_create(&sink_init_data);
if (!sink) {
DRM_ERROR("Failed to create sink!\n");
- return -ENOMEM;
+ return NULL;
}
-
sink->sink_signal = SIGNAL_TYPE_VIRTUAL;
- aconnector->fake_enable = true;
-
- aconnector->dc_sink = sink;
- aconnector->dc_link->local_sink = sink;
- return 0;
+ return sink;
}
static void set_multisync_trigger_params(
struct dc_stream_state *stream = NULL;
struct drm_display_mode mode = *drm_mode;
bool native_mode_found = false;
-
+ struct dc_sink *sink = NULL;
if (aconnector == NULL) {
DRM_ERROR("aconnector is NULL!\n");
return stream;
return stream;
}
- if (create_fake_sink(aconnector))
+ sink = create_fake_sink(aconnector);
+ if (!sink)
return stream;
+ } else {
+ sink = aconnector->dc_sink;
}
- stream = dc_create_stream_for_sink(aconnector->dc_sink);
+ stream = dc_create_stream_for_sink(sink);
if (stream == NULL) {
DRM_ERROR("Failed to create stream for sink!\n");
- return stream;
+ goto finish;
}
list_for_each_entry(preferred_mode, &aconnector->base.modes, head) {
fill_audio_info(
&stream->audio_info,
drm_connector,
- aconnector->dc_sink);
+ sink);
update_stream_signal(stream);
if (dm_state && dm_state->freesync_capable)
stream->ignore_msa_timing_param = true;
+finish:
+ if (sink && sink->sink_signal == SIGNAL_TYPE_VIRTUAL)
+ dc_sink_release(sink);
return stream;
}
struct dm_connector_state *state =
to_dm_connector_state(connector->state);
+ if (connector->state)
+ __drm_atomic_helper_connector_destroy_state(connector->state);
+
kfree(state);
state = kzalloc(sizeof(*state), GFP_KERNEL);
state->underscan_hborder = 0;
state->underscan_vborder = 0;
- connector->state = &state->base;
- connector->state->connector = connector;
+ __drm_atomic_helper_connector_reset(connector, &state->base);
}
}
}
}
- /* It's a hack for s3 since in 4.9 kernel filter out cursor buffer
- * prepare and cleanup in drm_atomic_helper_prepare_planes
- * and drm_atomic_helper_cleanup_planes because fb doens't in s3.
- * IN 4.10 kernel this code should be removed and amdgpu_device_suspend
- * code touching fram buffers should be avoided for DC.
- */
- if (plane->type == DRM_PLANE_TYPE_CURSOR) {
- struct amdgpu_crtc *acrtc = to_amdgpu_crtc(new_state->crtc);
-
- acrtc->cursor_bo = obj;
- }
return 0;
}
if (acrtc->base.state->event)
prepare_flip_isr(acrtc);
+ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
surface_updates->surface = dc_stream_get_status(acrtc_state->stream)->plane_states[0];
surface_updates->flip_addr = &addr;
-
dc_commit_updates_for_stream(adev->dm.dc,
surface_updates,
1,
__func__,
addr.address.grph.addr.high_part,
addr.address.grph.addr.low_part);
-
-
- spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
}
/*
struct drm_connector *connector;
struct drm_connector_state *old_con_state, *new_con_state;
struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+ int crtc_disable_count = 0;
drm_atomic_helper_update_legacy_modeset_state(dev, state);
if (dm_old_crtc_state->stream)
remove_stream(adev, acrtc, dm_old_crtc_state->stream);
+ pm_runtime_get_noresume(dev->dev);
+
acrtc->enabled = true;
acrtc->hw_mode = new_crtc_state->mode;
crtc->hwmode = new_crtc_state->mode;
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
bool modeset_needed;
+ if (old_crtc_state->active && !new_crtc_state->active)
+ crtc_disable_count++;
+
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
modeset_needed = modeset_required(
drm_atomic_helper_wait_for_flip_done(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
+
+ /* Finally, drop a runtime PM reference for each newly disabled CRTC,
+ * so we can put the GPU into runtime suspend if we're not driving any
+ * displays anymore
+ */
+ for (i = 0; i < crtc_disable_count; i++)
+ pm_runtime_put_autosuspend(dev->dev);
+ pm_runtime_mark_last_busy(dev->dev);
}
return 0;
}
+ if (acrtc->otg_inst == -1)
+ return 0;
+
irq_source = dal_irq_type + acrtc->otg_inst;
st = (state == AMDGPU_IRQ_STATE_ENABLE);
enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
I2C_MOT_TRUE : I2C_MOT_FALSE;
enum ddc_result res;
- uint32_t read_bytes = msg->size;
+ ssize_t read_bytes;
if (WARN_ON(msg->size > 16))
return -E2BIG;
switch (msg->request & ~DP_AUX_I2C_MOT) {
case DP_AUX_NATIVE_READ:
- res = dal_ddc_service_read_dpcd_data(
+ read_bytes = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
false,
I2C_MOT_UNDEF,
msg->address,
msg->buffer,
- msg->size,
- &read_bytes);
- break;
+ msg->size);
+ return read_bytes;
case DP_AUX_NATIVE_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
msg->size);
break;
case DP_AUX_I2C_READ:
- res = dal_ddc_service_read_dpcd_data(
+ read_bytes = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
true,
mot,
msg->address,
msg->buffer,
- msg->size,
- &read_bytes);
- break;
+ msg->size);
+ return read_bytes;
case DP_AUX_I2C_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
r == DDC_RESULT_SUCESSFULL);
#endif
- if (res != DDC_RESULT_SUCESSFULL)
- return -EIO;
- return read_bytes;
+ return msg->size;
}
static enum drm_connector_status
}
}
+static void pp_to_dc_clock_levels_with_latency(
+ const struct pp_clock_levels_with_latency *pp_clks,
+ struct dm_pp_clock_levels_with_latency *clk_level_info,
+ enum dm_pp_clock_type dc_clk_type)
+{
+ uint32_t i;
+
+ if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+ DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+ DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+ pp_clks->num_levels,
+ DM_PP_MAX_CLOCK_LEVELS);
+
+ clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+ } else
+ clk_level_info->num_levels = pp_clks->num_levels;
+
+ DRM_DEBUG("DM_PPLIB: values for %s clock\n",
+ DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+ for (i = 0; i < clk_level_info->num_levels; i++) {
+ DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+ /* translate 10kHz to kHz */
+ clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
+ clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
+ }
+}
+
bool dm_pp_get_clock_levels_by_type(
const struct dc_context *ctx,
enum dm_pp_clock_type clk_type,
enum dm_pp_clock_type clk_type,
struct dm_pp_clock_levels_with_latency *clk_level_info)
{
- /* TODO: to be implemented */
- return false;
+ struct amdgpu_device *adev = ctx->driver_context;
+ void *pp_handle = adev->powerplay.pp_handle;
+ struct pp_clock_levels_with_latency pp_clks = { 0 };
+ const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+ if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
+ return false;
+
+ if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
+ dc_to_pp_clock_type(clk_type),
+ &pp_clks))
+ return false;
+
+ pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
+
+ return true;
}
bool dm_pp_get_clock_levels_by_type_with_voltage(
return min_clamp;
}
+unsigned int dc_fixpt_u3d19(struct fixed31_32 arg)
+{
+ return ux_dy(arg.value, 3, 19);
+}
+
unsigned int dc_fixpt_u2d19(struct fixed31_32 arg)
{
return ux_dy(arg.value, 2, 19);
return ret;
}
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len,
- uint32_t *read)
+ uint32_t len)
{
struct aux_payload read_payload = {
.i2c_over_aux = i2c,
.mot = mot
};
- *read = 0;
-
if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
BREAK_TO_DEBUGGER();
return DDC_RESULT_FAILED_INVALID_OPERATION;
ddc->ctx->i2caux,
ddc->ddc_pin,
&command)) {
- *read = command.payloads->length;
- return DDC_RESULT_SUCESSFULL;
+ return (ssize_t)command.payloads->length;
}
return DDC_RESULT_FAILED_OPERATION;
struct dc_link *link,
union hpd_irq_data *irq_data)
{
+ static enum dc_status retval;
+
/* The HW reads 16 bytes from 200h on HPD,
* but if we get an AUX_DEFER, the HW cannot retry
* and this causes the CTS tests 4.3.2.1 - 3.2.4 to
* fail, so we now explicitly read 6 bytes which is
* the req from the above mentioned test cases.
+ *
+ * For DP 1.4 we need to read those from 2002h range.
*/
- return core_link_read_dpcd(
- link,
- DP_SINK_COUNT,
- irq_data->raw,
- sizeof(union hpd_irq_data));
+ if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14)
+ retval = core_link_read_dpcd(
+ link,
+ DP_SINK_COUNT,
+ irq_data->raw,
+ sizeof(union hpd_irq_data));
+ else {
+ /* Read 2 bytes at this location,... */
+ retval = core_link_read_dpcd(
+ link,
+ DP_SINK_COUNT_ESI,
+ irq_data->raw,
+ 2);
+
+ if (retval != DC_OK)
+ return retval;
+
+ /* ... then read remaining 4 at the other location */
+ retval = core_link_read_dpcd(
+ link,
+ DP_LANE0_1_STATUS_ESI,
+ &irq_data->raw[2],
+ 4);
+ }
+
+ return retval;
}
static bool allow_hpd_rx_irq(const struct dc_link *link)
dp_retrain_link_dp_test(link, &link_settings, false);
}
-/* TODO hbr2 compliance eye output is unstable
+/* TODO Raven hbr2 compliance eye output is unstable
* (toggling on and off) with debugger break
* This caueses intermittent PHY automation failure
* Need to look into the root cause */
-static uint8_t force_tps4_for_cp2520 = 1;
-
static void dp_test_send_phy_test_pattern(struct dc_link *link)
{
union phy_test_pattern dpcd_test_pattern;
break;
case PHY_TEST_PATTERN_CP2520_1:
/* CP2520 pattern is unstable, temporarily use TPS4 instead */
- test_pattern = (force_tps4_for_cp2520 == 1) ?
+ test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
DP_TEST_PATTERN_TRAINING_PATTERN4 :
DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
break;
case PHY_TEST_PATTERN_CP2520_2:
/* CP2520 pattern is unstable, temporarily use TPS4 instead */
- test_pattern = (force_tps4_for_cp2520 == 1) ?
+ test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
DP_TEST_PATTERN_TRAINING_PATTERN4 :
DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
break;
static bool retrieve_link_cap(struct dc_link *link)
{
- uint8_t dpcd_data[DP_TRAINING_AUX_RD_INTERVAL - DP_DPCD_REV + 1];
+ uint8_t dpcd_data[DP_ADAPTER_CAP - DP_DPCD_REV + 1];
union down_stream_port_count down_strm_port_count;
union edp_configuration_cap edp_config_cap;
bool is_apu;
bool dual_link_dvi;
bool post_blend_color_processing;
+ bool force_dp_tps4_for_cp2520;
};
struct dc_dcc_surface_param {
.mem_input_is_flip_pending = dce_mi_is_flip_pending
};
+static struct mem_input_funcs dce112_mi_funcs = {
+ .mem_input_program_display_marks = dce112_mi_program_display_marks,
+ .allocate_mem_input = dce_mi_allocate_dmif,
+ .free_mem_input = dce_mi_free_dmif,
+ .mem_input_program_surface_flip_and_addr =
+ dce_mi_program_surface_flip_and_addr,
+ .mem_input_program_pte_vm = dce_mi_program_pte_vm,
+ .mem_input_program_surface_config =
+ dce_mi_program_surface_config,
+ .mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
+
+static struct mem_input_funcs dce120_mi_funcs = {
+ .mem_input_program_display_marks = dce120_mi_program_display_marks,
+ .allocate_mem_input = dce_mi_allocate_dmif,
+ .free_mem_input = dce_mi_free_dmif,
+ .mem_input_program_surface_flip_and_addr =
+ dce_mi_program_surface_flip_and_addr,
+ .mem_input_program_pte_vm = dce_mi_program_pte_vm,
+ .mem_input_program_surface_config =
+ dce_mi_program_surface_config,
+ .mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
void dce_mem_input_construct(
struct dce_mem_input *dce_mi,
const struct dce_mem_input_mask *mi_mask)
{
dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
- dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks;
+ dce_mi->base.funcs = &dce112_mi_funcs;
}
void dce120_mem_input_construct(
const struct dce_mem_input_mask *mi_mask)
{
dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
- dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks;
+ dce_mi->base.funcs = &dce120_mi_funcs;
}
uint32_t max_retries = 50;
/*we need turn on clock before programming AFMT block*/
- REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
+ if (REG(AFMT_CNTL))
+ REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
if (REG(AFMT_VBI_PACKET_CONTROL1)) {
if (packet_index >= 8)
const uint32_t *content =
(const uint32_t *) &info_frame->avi.sb[0];
/*we need turn on clock before programming AFMT block*/
- REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
+ if (REG(AFMT_CNTL))
+ REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
REG_WRITE(AFMT_AVI_INFO0, content[0]);
struct dc *dc,
struct dc_state *context)
{
- /* TODO implement when needed but for now hardcode max value*/
- context->bw.dce.dispclk_khz = 681000;
- context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+ int i;
+ bool at_least_one_pipe = false;
+
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ if (context->res_ctx.pipe_ctx[i].stream)
+ at_least_one_pipe = true;
+ }
+
+ if (at_least_one_pipe) {
+ /* TODO implement when needed but for now hardcode max value*/
+ context->bw.dce.dispclk_khz = 681000;
+ context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+ } else {
+ context->bw.dce.dispclk_khz = 0;
+ context->bw.dce.yclk_khz = 0;
+ }
return true;
}
frame_count = dm_read_reg(ctx, mmCRTC_STATUS_FRAME_COUNT);
- for (retry = 100; retry > 0; retry--) {
+ for (retry = 10000; retry > 0; retry--) {
if (frame_count != dm_read_reg(ctx, mmCRTC_STATUS_FRAME_COUNT))
break;
- msleep(1);
+ udelay(10);
}
if (!retry)
dm_error("Frame count did not increase for 100ms.\n");
uint32_t addr = mmFBC_STATUS;
uint32_t value;
- while (counter < 10) {
+ while (counter < 1000) {
value = dm_read_reg(cp110->base.ctx, addr);
if (get_reg_field_value(
value,
FBC_STATUS,
FBC_ENABLE_STATUS) == enabled)
break;
- msleep(10);
+ udelay(100);
counter++;
}
/*don't free audio if it is from retrain or internal disable stream*/
if (option == FREE_ACQUIRED_RESOURCE && dc->caps.dynamic_audio == true) {
/*we have to dynamic arbitrate the audio endpoints*/
- pipe_ctx->stream_res.audio = NULL;
/*we free the resource, need reset is_audio_acquired*/
update_audio_usage(&dc->current_state->res_ctx, dc->res_pool, pipe_ctx->stream_res.audio, false);
+ pipe_ctx->stream_res.audio = NULL;
}
/* TODO: notify audio driver for if audio modes list changed
#define IDENTITY_RATIO(ratio) (dc_fixpt_u2d19(ratio) == (1 << 19))
-
-bool dpp_get_optimal_number_of_taps(
+static bool dpp_get_optimal_number_of_taps(
struct dpp *dpp,
struct scaler_data *scl_data,
const struct scaling_taps *in_taps)
enum ipp_degamma_mode mode);
void dpp1_set_degamma_pwl(struct dpp *dpp_base,
- const struct pwl_params *params);
+ const struct pwl_params *params);
-bool dpp_get_optimal_number_of_taps(
- struct dpp *dpp,
- struct scaler_data *scl_data,
- const struct scaling_taps *in_taps);
void dpp_read_state(struct dpp *dpp_base,
struct dcn_dpp_state *s);
uint32_t init_int = 0;
REG_SET(SCL_HORZ_FILTER_SCALE_RATIO, 0,
- SCL_H_SCALE_RATIO, dc_fixpt_u2d19(data->ratios.horz) << 5);
+ SCL_H_SCALE_RATIO, dc_fixpt_u3d19(data->ratios.horz) << 5);
REG_SET(SCL_VERT_FILTER_SCALE_RATIO, 0,
- SCL_V_SCALE_RATIO, dc_fixpt_u2d19(data->ratios.vert) << 5);
+ SCL_V_SCALE_RATIO, dc_fixpt_u3d19(data->ratios.vert) << 5);
REG_SET(SCL_HORZ_FILTER_SCALE_RATIO_C, 0,
- SCL_H_SCALE_RATIO_C, dc_fixpt_u2d19(data->ratios.horz_c) << 5);
+ SCL_H_SCALE_RATIO_C, dc_fixpt_u3d19(data->ratios.horz_c) << 5);
REG_SET(SCL_VERT_FILTER_SCALE_RATIO_C, 0,
- SCL_V_SCALE_RATIO_C, dc_fixpt_u2d19(data->ratios.vert_c) << 5);
+ SCL_V_SCALE_RATIO_C, dc_fixpt_u3d19(data->ratios.vert_c) << 5);
/*
* 0.24 format for fraction, first five bits zeroed
if (address->grph_stereo.right_addr.quad_part == 0)
break;
- REG_UPDATE_4(DCSURF_SURFACE_CONTROL,
+ REG_UPDATE_8(DCSURF_SURFACE_CONTROL,
PRIMARY_SURFACE_TMZ, address->tmz_surface,
PRIMARY_SURFACE_TMZ_C, address->tmz_surface,
PRIMARY_META_SURFACE_TMZ, address->tmz_surface,
- PRIMARY_META_SURFACE_TMZ_C, address->tmz_surface);
+ PRIMARY_META_SURFACE_TMZ_C, address->tmz_surface,
+ SECONDARY_SURFACE_TMZ, address->tmz_surface,
+ SECONDARY_SURFACE_TMZ_C, address->tmz_surface,
+ SECONDARY_META_SURFACE_TMZ, address->tmz_surface,
+ SECONDARY_META_SURFACE_TMZ_C, address->tmz_surface);
if (address->grph_stereo.right_meta_addr.quad_part != 0) {
uint32_t dcc_ind_64b_blk = independent_64b_blks ? 1 : 0;
struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
- REG_UPDATE_2(DCSURF_SURFACE_CONTROL,
+ REG_UPDATE_4(DCSURF_SURFACE_CONTROL,
PRIMARY_SURFACE_DCC_EN, dcc_en,
- PRIMARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk);
+ PRIMARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk,
+ SECONDARY_SURFACE_DCC_EN, dcc_en,
+ SECONDARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk);
}
void hubp1_program_surface_config(
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_META_SURFACE_TMZ_C, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_EN, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, PRIMARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_TMZ, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_TMZ_C, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ_C, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
type SECONDARY_META_SURFACE_TMZ_C;\
type PRIMARY_SURFACE_DCC_EN;\
type PRIMARY_SURFACE_DCC_IND_64B_BLK;\
+ type SECONDARY_SURFACE_DCC_EN;\
+ type SECONDARY_SURFACE_DCC_IND_64B_BLK;\
type DET_BUF_PLANE1_BASE_ADDRESS;\
type CROSSBAR_SRC_CB_B;\
type CROSSBAR_SRC_CR_R;\
dc->caps.max_slave_planes = 1;
dc->caps.is_apu = true;
dc->caps.post_blend_color_processing = false;
+ /* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */
+ dc->caps.force_dp_tps4_for_cp2520 = true;
if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
dc->debug = debug_defaults_drv;
REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
DP_COMPONENT_PIXEL_DEPTH_12BPC);
break;
+ case COLOR_DEPTH_161616:
+ REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+ DP_COMPONENT_PIXEL_DEPTH_16BPC);
+ break;
default:
REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
DP_COMPONENT_PIXEL_DEPTH_6BPC);
uint8_t *read_buf,
uint32_t read_size);
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len,
- uint32_t *read);
+ uint32_t len);
enum ddc_result dal_ddc_service_write_dpcd_data(
struct ddc_service *ddc,
* fractional
*/
+unsigned int dc_fixpt_u3d19(struct fixed31_32 arg);
+
unsigned int dc_fixpt_u2d19(struct fixed31_32 arg);
unsigned int dc_fixpt_u0d19(struct fixed31_32 arg);
/* DF_CS_AON0_DramBaseAddress0 */
#define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal__SHIFT 0x0
#define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT 0x1
-#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan__SHIFT 0x4
-#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel__SHIFT 0x8
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan__SHIFT 0x2
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel__SHIFT 0x9
#define DF_CS_UMC_AON0_DramBaseAddress0__DramBaseAddr__SHIFT 0xc
#define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal_MASK 0x00000001L
#define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn_MASK 0x00000002L
-#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan_MASK 0x000000F0L
-#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel_MASK 0x00000700L
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan_MASK 0x0000003CL
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel_MASK 0x00000E00L
#define DF_CS_UMC_AON0_DramBaseAddress0__DramBaseAddr_MASK 0xFFFFF000L
#endif
uint8_t acggfxclkspreadpercent;
uint16_t acggfxclkspreadfreq;
- uint32_t boardreserved[10];
+ uint8_t Vr2_I2C_address;
+ uint8_t padding_vr2[3];
+
+ uint32_t boardreserved[9];
};
/*
SMU11_SYSPLL3_1_ID = 6,
};
-
enum atom_smu11_syspll0_clock_id {
- SMU11_SYSPLL0_SOCCLK_ID = 0, // SOCCLK
- SMU11_SYSPLL0_MP0CLK_ID = 1, // MP0CLK
- SMU11_SYSPLL0_DCLK_ID = 2, // DCLK
- SMU11_SYSPLL0_VCLK_ID = 3, // VCLK
- SMU11_SYSPLL0_ECLK_ID = 4, // ECLK
+ SMU11_SYSPLL0_ECLK_ID = 0, // ECLK
+ SMU11_SYSPLL0_SOCCLK_ID = 1, // SOCCLK
+ SMU11_SYSPLL0_MP0CLK_ID = 2, // MP0CLK
+ SMU11_SYSPLL0_DCLK_ID = 3, // DCLK
+ SMU11_SYSPLL0_VCLK_ID = 4, // VCLK
SMU11_SYSPLL0_DCEFCLK_ID = 5, // DCEFCLK
};
-
enum atom_smu11_syspll1_0_clock_id {
SMU11_SYSPLL1_0_UCLKA_ID = 0, // UCLK_a
};
{
struct amdgpu_device *adev = handle;
struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
- int ret;
if (hwmgr && hwmgr->pm_en) {
mutex_lock(&hwmgr->smu_lock);
if (adev->pm.smu_prv_buffer_size != 0)
pp_reserve_vram_for_smu(adev);
- if (hwmgr->hwmgr_func->gfx_off_control &&
- (hwmgr->feature_mask & PP_GFXOFF_MASK)) {
- ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr, true);
- if (ret)
- pr_err("gfx off enabling failed!\n");
- }
-
return 0;
}
}
if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
- pr_info("%s was not implemented.\n", __func__);
+ pr_debug("%s was not implemented.\n", __func__);
return 0;
}
if (skip)
return 0;
- if (!hwmgr->ps)
- /*
- * for vega12/vega20 which does not support power state manager
- * DAL clock limits should also be honoured
- */
- phm_apply_clock_adjust_rules(hwmgr);
-
phm_pre_display_configuration_changed(hwmgr);
phm_display_configuration_changed(hwmgr);
if (hwmgr->ps)
power_state_management(hwmgr, new_ps);
+ else
+ /*
+ * for vega12/vega20 which does not support power state manager
+ * DAL clock limits should also be honoured
+ */
+ phm_apply_clock_adjust_rules(hwmgr);
phm_notify_smc_display_config_after_ps_adjustment(hwmgr);
uint32_t ix;
parameters.clk_id = id;
+ parameters.syspll_id = 0;
parameters.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ;
+ parameters.dfsdid = 0;
ix = GetIndexIntoMasterCmdTable(getsmuclockinfo);
return -EINVAL;
output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)¶meters;
- *frequency = output->atom_smu_outputclkfreq.smu_clock_freq_hz / 10000;
+ *frequency = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000;
return 0;
}
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_2(struct pp_hwmgr *hwmgr,
+ struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+ struct atom_firmware_info_v3_2 *fw_info)
+{
+ uint32_t frequency = 0;
+
+ boot_values->ulRevision = fw_info->firmware_revision;
+ boot_values->ulGfxClk = fw_info->bootup_sclk_in10khz;
+ boot_values->ulUClk = fw_info->bootup_mclk_in10khz;
+ boot_values->usVddc = fw_info->bootup_vddc_mv;
+ boot_values->usVddci = fw_info->bootup_vddci_mv;
+ boot_values->usMvddc = fw_info->bootup_mvddc_mv;
+ boot_values->usVddGfx = fw_info->bootup_vddgfx_mv;
+ boot_values->ucCoolingID = fw_info->coolingsolution_id;
+ boot_values->ulSocClk = 0;
+ boot_values->ulDCEFClk = 0;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_SOCCLK_ID, &frequency))
+ boot_values->ulSocClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCEFCLK_ID, &frequency))
+ boot_values->ulDCEFClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_ECLK_ID, &frequency))
+ boot_values->ulEClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_VCLK_ID, &frequency))
+ boot_values->ulVClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCLK_ID, &frequency))
+ boot_values->ulDClk = frequency;
+}
+
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_1(struct pp_hwmgr *hwmgr,
+ struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+ struct atom_firmware_info_v3_1 *fw_info)
+{
+ uint32_t frequency = 0;
+
+ boot_values->ulRevision = fw_info->firmware_revision;
+ boot_values->ulGfxClk = fw_info->bootup_sclk_in10khz;
+ boot_values->ulUClk = fw_info->bootup_mclk_in10khz;
+ boot_values->usVddc = fw_info->bootup_vddc_mv;
+ boot_values->usVddci = fw_info->bootup_vddci_mv;
+ boot_values->usMvddc = fw_info->bootup_mvddc_mv;
+ boot_values->usVddGfx = fw_info->bootup_vddgfx_mv;
+ boot_values->ucCoolingID = fw_info->coolingsolution_id;
+ boot_values->ulSocClk = 0;
+ boot_values->ulDCEFClk = 0;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_SOCCLK_ID, &frequency))
+ boot_values->ulSocClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCEFCLK_ID, &frequency))
+ boot_values->ulDCEFClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_ECLK_ID, &frequency))
+ boot_values->ulEClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_VCLK_ID, &frequency))
+ boot_values->ulVClk = frequency;
+
+ if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCLK_ID, &frequency))
+ boot_values->ulDClk = frequency;
+}
+
int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
struct pp_atomfwctrl_bios_boot_up_values *boot_values)
{
- struct atom_firmware_info_v3_1 *info = NULL;
+ struct atom_firmware_info_v3_2 *fwinfo_3_2;
+ struct atom_firmware_info_v3_1 *fwinfo_3_1;
+ struct atom_common_table_header *info = NULL;
uint16_t ix;
ix = GetIndexIntoMasterDataTable(firmwareinfo);
- info = (struct atom_firmware_info_v3_1 *)
+ info = (struct atom_common_table_header *)
smu_atom_get_data_table(hwmgr->adev,
ix, NULL, NULL, NULL);
return -EINVAL;
}
- boot_values->ulRevision = info->firmware_revision;
- boot_values->ulGfxClk = info->bootup_sclk_in10khz;
- boot_values->ulUClk = info->bootup_mclk_in10khz;
- boot_values->usVddc = info->bootup_vddc_mv;
- boot_values->usVddci = info->bootup_vddci_mv;
- boot_values->usMvddc = info->bootup_mvddc_mv;
- boot_values->usVddGfx = info->bootup_vddgfx_mv;
- boot_values->ucCoolingID = info->coolingsolution_id;
- boot_values->ulSocClk = 0;
- boot_values->ulDCEFClk = 0;
+ if ((info->format_revision == 3) && (info->content_revision == 2)) {
+ fwinfo_3_2 = (struct atom_firmware_info_v3_2 *)info;
+ pp_atomfwctrl_copy_vbios_bootup_values_3_2(hwmgr,
+ boot_values, fwinfo_3_2);
+ } else if ((info->format_revision == 3) && (info->content_revision == 1)) {
+ fwinfo_3_1 = (struct atom_firmware_info_v3_1 *)info;
+ pp_atomfwctrl_copy_vbios_bootup_values_3_1(hwmgr,
+ boot_values, fwinfo_3_1);
+ } else {
+ pr_info("Fw info table revision does not match!");
+ return -EINVAL;
+ }
return 0;
}
param->acggfxclkspreadpercent = info->acggfxclkspreadpercent;
param->acggfxclkspreadfreq = info->acggfxclkspreadfreq;
+ param->Vr2_I2C_address = info->Vr2_I2C_address;
+
return 0;
}
uint32_t ulUClk;
uint32_t ulSocClk;
uint32_t ulDCEFClk;
+ uint32_t ulEClk;
+ uint32_t ulVClk;
+ uint32_t ulDClk;
uint16_t usVddc;
uint16_t usVddci;
uint16_t usMvddc;
uint8_t acggfxclkspreadenabled;
uint8_t acggfxclkspreadpercent;
uint16_t acggfxclkspreadfreq;
+
+ uint8_t Vr2_I2C_address;
};
int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
hwmgr->platform_descriptor.maxOverdriveVDDC = 0;
hwmgr->platform_descriptor.overdriveVDDCStep = 0;
- if (hwmgr->platform_descriptor.overdriveLimit.engineClock == 0 \
- || hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0) {
- hwmgr->od_enabled = false;
- pr_debug("OverDrive feature not support by VBIOS\n");
- }
-
return 0;
}
powerplay_table,
(const ATOM_FIRMWARE_INFO_V2_1 *)fw_info);
- if (hwmgr->platform_descriptor.overdriveLimit.engineClock == 0
- && hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0) {
- hwmgr->od_enabled = false;
- pr_debug("OverDrive feature not support by VBIOS\n");
- }
-
return result;
}
static int smu10_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
- struct pp_display_clock_request *clock_req);
+ struct pp_display_clock_request *clock_req)
+{
+ struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+ enum amd_pp_clock_type clk_type = clock_req->clock_type;
+ uint32_t clk_freq = clock_req->clock_freq_in_khz / 1000;
+ PPSMC_Msg msg;
+ switch (clk_type) {
+ case amd_pp_dcf_clock:
+ if (clk_freq == smu10_data->dcf_actual_hard_min_freq)
+ return 0;
+ msg = PPSMC_MSG_SetHardMinDcefclkByFreq;
+ smu10_data->dcf_actual_hard_min_freq = clk_freq;
+ break;
+ case amd_pp_soc_clock:
+ msg = PPSMC_MSG_SetHardMinSocclkByFreq;
+ break;
+ case amd_pp_f_clock:
+ if (clk_freq == smu10_data->f_actual_hard_min_freq)
+ return 0;
+ smu10_data->f_actual_hard_min_freq = clk_freq;
+ msg = PPSMC_MSG_SetHardMinFclkByFreq;
+ break;
+ default:
+ pr_info("[DisplayClockVoltageRequest]Invalid Clock Type!");
+ return -EINVAL;
+ }
+ smum_send_msg_to_smc_with_parameter(hwmgr, msg, clk_freq);
+
+ return 0;
+}
static struct smu10_power_state *cast_smu10_ps(struct pp_hw_power_state *hw_ps)
{
static int smu10_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
{
- return smu10_disable_gfx_off(hwmgr);
+ return 0;
}
static int smu10_enable_gfx_off(struct pp_hwmgr *hwmgr)
static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
{
- return smu10_enable_gfx_off(hwmgr);
+ return 0;
}
static int smu10_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
case amd_pp_soc_clock:
pclk_vol_table = pinfo->vdd_dep_on_socclk;
break;
+ case amd_pp_disp_clock:
+ pclk_vol_table = pinfo->vdd_dep_on_dispclk;
+ break;
+ case amd_pp_phy_clock:
+ pclk_vol_table = pinfo->vdd_dep_on_phyclk;
+ break;
default:
return -EINVAL;
}
return 0;
}
-static int smu10_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
- struct pp_display_clock_request *clock_req)
-{
- struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
- enum amd_pp_clock_type clk_type = clock_req->clock_type;
- uint32_t clk_freq = clock_req->clock_freq_in_khz / 1000;
- PPSMC_Msg msg;
- switch (clk_type) {
- case amd_pp_dcf_clock:
- if (clk_freq == smu10_data->dcf_actual_hard_min_freq)
- return 0;
- msg = PPSMC_MSG_SetHardMinDcefclkByFreq;
- smu10_data->dcf_actual_hard_min_freq = clk_freq;
- break;
- case amd_pp_soc_clock:
- msg = PPSMC_MSG_SetHardMinSocclkByFreq;
- break;
- case amd_pp_f_clock:
- if (clk_freq == smu10_data->f_actual_hard_min_freq)
- return 0;
- smu10_data->f_actual_hard_min_freq = clk_freq;
- msg = PPSMC_MSG_SetHardMinFclkByFreq;
- break;
- default:
- pr_info("[DisplayClockVoltageRequest]Invalid Clock Type!");
- return -EINVAL;
- }
-
- smum_send_msg_to_smc_with_parameter(hwmgr, msg, clk_freq);
-
- return 0;
-}
static int smu10_get_max_high_clocks(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks)
{
.set_mmhub_powergating_by_smu = smu10_set_mmhub_powergating_by_smu,
.smus_notify_pwe = smu10_smus_notify_pwe,
.gfx_off_control = smu10_gfx_off_control,
+ .display_clock_voltage_request = smu10_display_clock_voltage_request,
};
int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
data->dpm_table.sclk_table.count++;
}
}
-
+ if (hwmgr->platform_descriptor.overdriveLimit.engineClock == 0)
+ hwmgr->platform_descriptor.overdriveLimit.engineClock = dep_sclk_table->entries[i-1].clk;
/* Initialize Mclk DPM table based on allow Mclk values */
data->dpm_table.mclk_table.count = 0;
for (i = 0; i < dep_mclk_table->count; i++) {
}
}
+ if (hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0)
+ hwmgr->platform_descriptor.overdriveLimit.memoryClock = dep_mclk_table->entries[i-1].clk;
return 0;
}
static int smu7_generate_dpm_level_enable_mask(
struct pp_hwmgr *hwmgr, const void *input)
{
- int result;
+ int result = 0;
const struct phm_set_power_state_input *states =
(const struct phm_set_power_state_input *)input;
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
const struct smu7_power_state *smu7_ps =
cast_const_phw_smu7_power_state(states->pnew_state);
- result = smu7_trim_dpm_states(hwmgr, smu7_ps);
+ /*skip the trim if od is enabled*/
+ if (!hwmgr->od_enabled)
+ result = smu7_trim_dpm_states(hwmgr, smu7_ps);
+
if (result)
return result;
odn_table->min_vddc = dep_table[0]->entries[0].vddc;
i = od_table[2]->count - 1;
- od_table[2]->entries[i].clk = hwmgr->platform_descriptor.overdriveLimit.memoryClock;
- od_table[2]->entries[i].vddc = odn_table->max_vddc;
+ od_table[2]->entries[i].clk = hwmgr->platform_descriptor.overdriveLimit.memoryClock > od_table[2]->entries[i].clk ?
+ hwmgr->platform_descriptor.overdriveLimit.memoryClock :
+ od_table[2]->entries[i].clk;
+ od_table[2]->entries[i].vddc = odn_table->max_vddc > od_table[2]->entries[i].vddc ?
+ odn_table->max_vddc :
+ od_table[2]->entries[i].vddc;
return 0;
}
vega10_setup_default_single_dpm_table(hwmgr,
dpm_table,
dep_gfx_table);
+ if (hwmgr->platform_descriptor.overdriveLimit.engineClock == 0)
+ hwmgr->platform_descriptor.overdriveLimit.engineClock =
+ dpm_table->dpm_levels[dpm_table->count-1].value;
vega10_init_dpm_state(&(dpm_table->dpm_state));
/* Initialize Mclk DPM table based on allow Mclk values */
vega10_setup_default_single_dpm_table(hwmgr,
dpm_table,
dep_mclk_table);
+ if (hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0)
+ hwmgr->platform_descriptor.overdriveLimit.memoryClock =
+ dpm_table->dpm_levels[dpm_table->count-1].value;
+
vega10_init_dpm_state(&(dpm_table->dpm_state));
data->dpm_table.eclk_table.count = 0;
static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
{
struct amdgpu_device *adev = hwmgr->adev;
- int result;
+ int result = 0;
uint32_t num_se = 0;
uint32_t count, data;
for (count = 0; count < num_se; count++) {
data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT);
WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
- result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
+ result = vega10_program_didt_config_registers(hwmgr, PSMSEEDCStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCStallDelayConfig_Vega10, VEGA10_CONFIGREG_DIDT);
result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCCtrlResetConfig_Vega10, VEGA10_CONFIGREG_DIDT);
result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCCtrlConfig_Vega10, VEGA10_CONFIGREG_DIDT);
hwmgr->platform_descriptor.maxOverdriveVDDC = 0;
hwmgr->platform_descriptor.overdriveVDDCStep = 0;
- if (hwmgr->platform_descriptor.overdriveLimit.engineClock == 0 ||
- hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0) {
- hwmgr->od_enabled = false;
- pr_debug("OverDrive feature not support by VBIOS\n");
- }
-
return 0;
}
data->registry_data.disallowed_features = 0x0;
data->registry_data.od_state_in_dc_support = 0;
+ data->registry_data.thermal_support = 1;
data->registry_data.skip_baco_hardware = 0;
data->registry_data.log_avfs_param = 0;
data->vbios_boot_state.soc_clock = boot_up_values.ulSocClk;
data->vbios_boot_state.dcef_clock = boot_up_values.ulDCEFClk;
data->vbios_boot_state.uc_cooling_id = boot_up_values.ucCoolingID;
+ data->vbios_boot_state.eclock = boot_up_values.ulEClk;
+ data->vbios_boot_state.dclock = boot_up_values.ulDClk;
+ data->vbios_boot_state.vclock = boot_up_values.ulVClk;
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetMinDeepSleepDcefclk,
(uint32_t)(data->vbios_boot_state.dcef_clock / 100));
uint32_t mem_clock;
uint32_t soc_clock;
uint32_t dcef_clock;
+ uint32_t eclock;
+ uint32_t dclock;
+ uint32_t vclock;
};
#define DPMTABLE_OD_UPDATE_SCLK 0x00000001
ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
}
+ ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
+
return 0;
}
uint8_t AcgGfxclkSpreadPercent;
uint16_t AcgGfxclkSpreadFreq;
- uint32_t BoardReserved[10];
+ uint8_t Vr2_I2C_address;
+ uint8_t padding_vr2[3];
+
+ uint32_t BoardReserved[9];
uint32_t MmHubPadding[7];
uint32_t fw_to_load;
int result = 0;
struct SMU_DRAMData_TOC *toc;
+ uint32_t num_entries = 0;
if (!hwmgr->reload_fw) {
pr_info("skip reloading...\n");
}
toc = (struct SMU_DRAMData_TOC *)smu_data->header;
- toc->num_entries = 0;
toc->structure_version = 1;
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
+ UCODE_ID_RLC_G, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_CE, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_PFP, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_ME, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_MEC, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
+ UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
+ UCODE_ID_SDMA0, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+ UCODE_ID_SDMA1, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
if (!hwmgr->not_vf)
PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
- UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
+ UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]),
"Failed to Get Firmware Entry.", return -EINVAL);
+ toc->num_entries = num_entries;
smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
static void malidp_fini(struct drm_device *drm)
{
- drm_atomic_helper_shutdown(drm);
drm_mode_config_cleanup(drm);
}
malidp_de_irq_fini(drm);
drm->irq_enabled = false;
irq_init_fail:
+ drm_atomic_helper_shutdown(drm);
component_unbind_all(dev, drm);
bind_fail:
of_node_put(malidp->crtc.port);
malidp_se_irq_fini(drm);
malidp_de_irq_fini(drm);
drm->irq_enabled = false;
+ drm_atomic_helper_shutdown(drm);
component_unbind_all(dev, drm);
of_node_put(malidp->crtc.port);
malidp->crtc.port = NULL;
.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
},
.se_irq_map = {
- .irq_mask = MALIDP500_SE_IRQ_CONF_MODE,
+ .irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
+ MALIDP500_SE_IRQ_GLOBAL,
.vsync_irq = 0,
},
.dc_irq_map = {
/* Layer specific register offsets */
#define MALIDP_LAYER_FORMAT 0x000
+#define LAYER_FORMAT_MASK 0x3f
#define MALIDP_LAYER_CONTROL 0x004
#define LAYER_ENABLE (1 << 0)
#define LAYER_FLOWCFG_MASK 7
if (state->rotation & MALIDP_ROTATED_MASK) {
int val;
- val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_h,
- state->crtc_w,
+ val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_w,
+ state->crtc_h,
fb->format->format);
if (val < 0)
return val;
dest_w = plane->state->crtc_w;
dest_h = plane->state->crtc_h;
- malidp_hw_write(mp->hwdev, ms->format, mp->layer->base);
+ val = malidp_hw_read(mp->hwdev, mp->layer->base);
+ val = (val & ~LAYER_FORMAT_MASK) | ms->format;
+ malidp_hw_write(mp->hwdev, val, mp->layer->base);
for (i = 0; i < ms->n_planes; i++) {
/* calculate the offset for the layer's plane registers */
u32 v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
/*
- * This is rediculous - rather than writing bits to clear, we
- * have to set the actual status register value. This is racy.
+ * Reading the ISR appears to clear bits provided CLEAN_SPU_IRQ_ISR
+ * is set. Writing has some other effect to acknowledge the IRQ -
+ * without this, we only get a single IRQ.
*/
writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
{
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+ unsigned long flags;
+ spin_lock_irqsave(&dcrtc->irq_lock, flags);
armada_drm_crtc_enable_irq(dcrtc, VSYNC_IRQ_ENA);
+ spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
return 0;
}
static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc)
{
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+ unsigned long flags;
+ spin_lock_irqsave(&dcrtc->irq_lock, flags);
armada_drm_crtc_disable_irq(dcrtc, VSYNC_IRQ_ENA);
+ spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
}
static const struct drm_crtc_funcs armada_crtc_funcs = {
CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1);
writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+ readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
ret = devm_request_irq(dev, irq, armada_drm_irq, 0, "armada_drm_crtc",
CFG_ALPHAM_GRA = 0x1 << 16,
CFG_ALPHAM_CFG = 0x2 << 16,
CFG_ALPHA_MASK = 0xff << 8,
+#define CFG_ALPHA(x) ((x) << 8)
CFG_PIXCMD_MASK = 0xff,
};
uint16_t contrast;
uint16_t saturation;
uint32_t colorkey_mode;
+ uint32_t colorkey_enable;
};
struct armada_ovl_plane {
writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
spin_lock_irq(&dcrtc->irq_lock);
- armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA,
- CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
- dcrtc->base + LCD_SPU_DMA_CTRL1);
-
- armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG);
+ armada_updatel(prop->colorkey_mode,
+ CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+ dcrtc->base + LCD_SPU_DMA_CTRL1);
+ if (dcrtc->variant->has_spu_adv_reg)
+ armada_updatel(prop->colorkey_enable,
+ ADV_GRACOLORKEY | ADV_VIDCOLORKEY,
+ dcrtc->base + LCD_SPU_ADV_REG);
spin_unlock_irq(&dcrtc->irq_lock);
}
dplane->prop.colorkey_vb |= K2B(val);
update_attr = true;
} else if (property == priv->colorkey_mode_prop) {
- dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK;
- dplane->prop.colorkey_mode |= CFG_CKMODE(val);
+ if (val == CKMODE_DISABLE) {
+ dplane->prop.colorkey_mode =
+ CFG_CKMODE(CKMODE_DISABLE) |
+ CFG_ALPHAM_CFG | CFG_ALPHA(255);
+ dplane->prop.colorkey_enable = 0;
+ } else {
+ dplane->prop.colorkey_mode =
+ CFG_CKMODE(val) |
+ CFG_ALPHAM_GRA | CFG_ALPHA(0);
+ dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
+ }
update_attr = true;
} else if (property == priv->brightness_prop) {
dplane->prop.brightness = val - 256;
dplane->prop.colorkey_yr = 0xfefefe00;
dplane->prop.colorkey_ug = 0x01010100;
dplane->prop.colorkey_vb = 0x01010100;
- dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB);
+ dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
+ CFG_ALPHAM_GRA | CFG_ALPHA(0);
+ dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
dplane->prop.brightness = 0;
dplane->prop.contrast = 0x4000;
dplane->prop.saturation = 0x4000;
return ret;
}
- if (desc->layout.xstride && desc->layout.pstride) {
+ if (desc->layout.xstride[0] && desc->layout.pstride[0]) {
int ret;
ret = drm_plane_create_rotation_property(&plane->base,
else
status = connector_status_disconnected;
+ /*
+ * The bridge resets its registers on unplug. So when we get a plug
+ * event and we're already supposed to be powered, cycle the bridge to
+ * restore its state.
+ */
+ if (status == connector_status_connected &&
+ adv7511->connector.status == connector_status_disconnected &&
+ adv7511->powered) {
+ regcache_mark_dirty(adv7511->regmap);
+ adv7511_power_on(adv7511);
+ }
+
if (adv7511->connector.status != status) {
adv7511->connector.status = status;
if (status == connector_status_disconnected)
#include <drm/bridge/mhl.h>
#include <drm/drm_crtc.h>
#include <drm/drm_edid.h>
+#include <drm/drm_encoder.h>
#include <linux/clk.h>
#include <linux/delay.h>
#define SII8620_BURST_BUF_LEN 288
#define VAL_RX_HDMI_CTRL2_DEFVAL VAL_RX_HDMI_CTRL2_IDLE_CNT(3)
-#define MHL1_MAX_LCLK 225000
-#define MHL3_MAX_LCLK 600000
+
+#define MHL1_MAX_PCLK 75000
+#define MHL1_MAX_PCLK_PP_MODE 150000
+#define MHL3_MAX_PCLK 200000
+#define MHL3_MAX_PCLK_PP_MODE 300000
enum sii8620_mode {
CM_DISCONNECTED,
struct regulator_bulk_data supplies[2];
struct mutex lock; /* context lock, protects fields below */
int error;
- int pixel_clock;
unsigned int use_packed_pixel:1;
- int video_code;
enum sii8620_mode mode;
enum sii8620_sink_type sink_type;
u8 cbus_status;
u8 xstat[MHL_XDS_SIZE];
u8 devcap[MHL_DCAP_SIZE];
u8 xdevcap[MHL_XDC_SIZE];
- u8 avif[HDMI_INFOFRAME_SIZE(AVI)];
+ bool feature_complete;
+ bool devcap_read;
+ bool sink_detected;
struct edid *edid;
unsigned int gen2_write_burst:1;
enum sii8620_mt_state mt_state;
}
}
-static void sii8620_sink_detected(struct sii8620 *ctx, int ret)
+static void sii8620_identify_sink(struct sii8620 *ctx)
{
static const char * const sink_str[] = {
[SINK_NONE] = "NONE",
char sink_name[20];
struct device *dev = ctx->dev;
- if (ret < 0)
+ if (!ctx->sink_detected || !ctx->devcap_read)
return;
sii8620_fetch_edid(ctx);
sii8620_mhl_disconnected(ctx);
return;
}
+ sii8620_set_upstream_edid(ctx);
if (drm_detect_hdmi_monitor(ctx->edid))
ctx->sink_type = SINK_HDMI;
sink_str[ctx->sink_type], sink_name);
}
-static void sii8620_hsic_init(struct sii8620 *ctx)
-{
- if (!sii8620_is_mhl3(ctx))
- return;
-
- sii8620_write(ctx, REG_FCGC,
- BIT_FCGC_HSIC_HOSTMODE | BIT_FCGC_HSIC_ENABLE);
- sii8620_setbits(ctx, REG_HRXCTRL3,
- BIT_HRXCTRL3_HRX_STAY_RESET | BIT_HRXCTRL3_STATUS_EN, ~0);
- sii8620_setbits(ctx, REG_TTXNUMB, MSK_TTXNUMB_TTX_NUMBPS, 4);
- sii8620_setbits(ctx, REG_TRXCTRL, BIT_TRXCTRL_TRX_FROM_SE_COC, ~0);
- sii8620_setbits(ctx, REG_HTXCTRL, BIT_HTXCTRL_HTX_DRVCONN1, 0);
- sii8620_setbits(ctx, REG_KEEPER, MSK_KEEPER_MODE, VAL_KEEPER_MODE_HOST);
- sii8620_write_seq_static(ctx,
- REG_TDMLLCTL, 0,
- REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST |
- BIT_UTSRST_KEEPER_SRST | BIT_UTSRST_FC_SRST,
- REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST,
- REG_HRXINTL, 0xff,
- REG_HRXINTH, 0xff,
- REG_TTXINTL, 0xff,
- REG_TTXINTH, 0xff,
- REG_TRXINTL, 0xff,
- REG_TRXINTH, 0xff,
- REG_HTXINTL, 0xff,
- REG_HTXINTH, 0xff,
- REG_FCINTR0, 0xff,
- REG_FCINTR1, 0xff,
- REG_FCINTR2, 0xff,
- REG_FCINTR3, 0xff,
- REG_FCINTR4, 0xff,
- REG_FCINTR5, 0xff,
- REG_FCINTR6, 0xff,
- REG_FCINTR7, 0xff
- );
-}
-
-static void sii8620_edid_read(struct sii8620 *ctx, int ret)
-{
- if (ret < 0)
- return;
-
- sii8620_set_upstream_edid(ctx);
- sii8620_hsic_init(ctx);
- sii8620_enable_hpd(ctx);
-}
-
static void sii8620_mr_devcap(struct sii8620 *ctx)
{
u8 dcap[MHL_DCAP_SIZE];
dcap[MHL_DCAP_ADOPTER_ID_H], dcap[MHL_DCAP_ADOPTER_ID_L],
dcap[MHL_DCAP_DEVICE_ID_H], dcap[MHL_DCAP_DEVICE_ID_L]);
sii8620_update_array(ctx->devcap, dcap, MHL_DCAP_SIZE);
+ ctx->devcap_read = true;
+ sii8620_identify_sink(ctx);
}
static void sii8620_mr_xdevcap(struct sii8620 *ctx)
static void sii8620_fetch_edid(struct sii8620 *ctx)
{
u8 lm_ddc, ddc_cmd, int3, cbus;
+ unsigned long timeout;
int fetched, i;
int edid_len = EDID_LENGTH;
u8 *edid;
REG_DDC_CMD, ddc_cmd | VAL_DDC_CMD_ENH_DDC_READ_NO_ACK
);
- do {
- int3 = sii8620_readb(ctx, REG_INTR3);
+ int3 = 0;
+ timeout = jiffies + msecs_to_jiffies(200);
+ for (;;) {
cbus = sii8620_readb(ctx, REG_CBUS_STATUS);
-
- if (int3 & BIT_DDC_CMD_DONE)
- break;
-
- if (!(cbus & BIT_CBUS_STATUS_CBUS_CONNECTED)) {
+ if (~cbus & BIT_CBUS_STATUS_CBUS_CONNECTED) {
+ kfree(edid);
+ edid = NULL;
+ goto end;
+ }
+ if (int3 & BIT_DDC_CMD_DONE) {
+ if (sii8620_readb(ctx, REG_DDC_DOUT_CNT)
+ >= FETCH_SIZE)
+ break;
+ } else {
+ int3 = sii8620_readb(ctx, REG_INTR3);
+ }
+ if (time_is_before_jiffies(timeout)) {
+ ctx->error = -ETIMEDOUT;
+ dev_err(ctx->dev, "timeout during EDID read\n");
kfree(edid);
edid = NULL;
goto end;
}
- } while (1);
-
- sii8620_readb(ctx, REG_DDC_STATUS);
- while (sii8620_readb(ctx, REG_DDC_DOUT_CNT) < FETCH_SIZE)
usleep_range(10, 20);
+ }
sii8620_read_buf(ctx, REG_DDC_DATA, edid + fetched, FETCH_SIZE);
if (fetched + FETCH_SIZE == EDID_LENGTH) {
ret = regulator_bulk_enable(ARRAY_SIZE(ctx->supplies), ctx->supplies);
if (ret)
return ret;
+
usleep_range(10000, 20000);
- return clk_prepare_enable(ctx->clk_xtal);
+ ret = clk_prepare_enable(ctx->clk_xtal);
+ if (ret)
+ return ret;
+
+ msleep(100);
+ gpiod_set_value(ctx->gpio_reset, 0);
+ msleep(100);
+
+ return 0;
}
static int sii8620_hw_off(struct sii8620 *ctx)
return regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies);
}
-static void sii8620_hw_reset(struct sii8620 *ctx)
-{
- usleep_range(10000, 20000);
- gpiod_set_value(ctx->gpio_reset, 0);
- usleep_range(5000, 20000);
- gpiod_set_value(ctx->gpio_reset, 1);
- usleep_range(10000, 20000);
- gpiod_set_value(ctx->gpio_reset, 0);
- msleep(300);
-}
-
static void sii8620_cbus_reset(struct sii8620 *ctx)
{
sii8620_write(ctx, REG_PWD_SRST, BIT_PWD_SRST_CBUS_RST
BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED,
ctx->use_packed_pixel ? ~0 : 0);
} else {
- if (ctx->use_packed_pixel)
+ if (ctx->use_packed_pixel) {
sii8620_write_seq_static(ctx,
REG_VID_MODE, BIT_VID_MODE_M1080P,
REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1,
REG_MHLTX_CTL6, 0x60
);
- else
+ } else {
sii8620_write_seq_static(ctx,
REG_VID_MODE, 0,
REG_MHL_TOP_CTL, 1,
REG_MHLTX_CTL6, 0xa0
);
+ }
}
if (ctx->use_packed_pixel)
- out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL) |
- BIT_TPI_OUTPUT_CSCMODE709;
+ out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL);
else
out_fmt = VAL_TPI_FORMAT(RGB, FULL);
return frm_len;
}
-static void sii8620_set_infoframes(struct sii8620 *ctx)
+static void sii8620_set_infoframes(struct sii8620 *ctx,
+ struct drm_display_mode *mode)
{
struct mhl3_infoframe mhl_frm;
union hdmi_infoframe frm;
u8 buf[31];
int ret;
+ ret = drm_hdmi_avi_infoframe_from_display_mode(&frm.avi,
+ mode,
+ true);
+ if (ctx->use_packed_pixel)
+ frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
+
+ if (!ret)
+ ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
+ if (ret > 0)
+ sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
+
if (!sii8620_is_mhl3(ctx) || !ctx->use_packed_pixel) {
sii8620_write(ctx, REG_TPI_SC,
BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI);
- sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, ctx->avif + 3,
- ARRAY_SIZE(ctx->avif) - 3);
sii8620_write(ctx, REG_PKT_FILTER_0,
BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
BIT_PKT_FILTER_0_DROP_MPEG_PKT |
return;
}
- ret = hdmi_avi_infoframe_init(&frm.avi);
- frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
- frm.avi.active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
- frm.avi.picture_aspect = HDMI_PICTURE_ASPECT_16_9;
- frm.avi.colorimetry = HDMI_COLORIMETRY_ITU_709;
- frm.avi.video_code = ctx->video_code;
- if (!ret)
- ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
- if (ret > 0)
- sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
sii8620_write(ctx, REG_PKT_FILTER_0,
BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
BIT_PKT_FILTER_0_DROP_MPEG_PKT |
static void sii8620_start_video(struct sii8620 *ctx)
{
+ struct drm_display_mode *mode =
+ &ctx->bridge.encoder->crtc->state->adjusted_mode;
+
if (!sii8620_is_mhl3(ctx))
sii8620_stop_video(ctx);
sii8620_set_format(ctx);
if (!sii8620_is_mhl3(ctx)) {
- sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
- MHL_DST_LM_CLK_MODE_NORMAL | MHL_DST_LM_PATH_ENABLED);
+ u8 link_mode = MHL_DST_LM_PATH_ENABLED;
+
+ if (ctx->use_packed_pixel)
+ link_mode |= MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+ else
+ link_mode |= MHL_DST_LM_CLK_MODE_NORMAL;
+
+ sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), link_mode);
sii8620_set_auto_zone(ctx);
} else {
static const struct {
MHL_XDS_LINK_RATE_6_0_GBPS, 0x40 },
};
u8 p0_ctrl = BIT_M3_P0CTRL_MHL3_P0_PORT_EN;
- int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3);
+ int clk = mode->clock * (ctx->use_packed_pixel ? 2 : 3);
int i;
- for (i = 0; i < ARRAY_SIZE(clk_spec); ++i)
+ for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i)
if (clk < clk_spec[i].max_clk)
break;
clk_spec[i].link_rate);
}
- sii8620_set_infoframes(ctx);
+ sii8620_set_infoframes(ctx, mode);
}
static void sii8620_disable_hpd(struct sii8620 *ctx)
);
}
+static void sii8620_hpd_unplugged(struct sii8620 *ctx)
+{
+ sii8620_disable_hpd(ctx);
+ ctx->sink_type = SINK_NONE;
+ ctx->sink_detected = false;
+ ctx->feature_complete = false;
+ kfree(ctx->edid);
+ ctx->edid = NULL;
+}
+
static void sii8620_disconnect(struct sii8620 *ctx)
{
sii8620_disable_gen2_write_burst(ctx);
REG_MHL_DP_CTL6, 0x2A,
REG_MHL_DP_CTL7, 0x03
);
- sii8620_disable_hpd(ctx);
+ sii8620_hpd_unplugged(ctx);
sii8620_write_seq_static(ctx,
REG_M3_CTRL, VAL_M3_CTRL_MHL3_VALUE,
REG_MHL_COC_CTL1, 0x07,
memset(ctx->xstat, 0, sizeof(ctx->xstat));
memset(ctx->devcap, 0, sizeof(ctx->devcap));
memset(ctx->xdevcap, 0, sizeof(ctx->xdevcap));
+ ctx->devcap_read = false;
ctx->cbus_status = 0;
- ctx->sink_type = SINK_NONE;
- kfree(ctx->edid);
- ctx->edid = NULL;
sii8620_mt_cleanup(ctx);
}
static void sii8620_status_changed_path(struct sii8620 *ctx)
{
- if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) {
- sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
- MHL_DST_LM_CLK_MODE_NORMAL
- | MHL_DST_LM_PATH_ENABLED);
- if (!sii8620_is_mhl3(ctx))
- sii8620_mt_read_devcap(ctx, false);
- sii8620_mt_set_cont(ctx, sii8620_sink_detected);
- } else {
- sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
- MHL_DST_LM_CLK_MODE_NORMAL);
- }
+ u8 link_mode;
+
+ if (ctx->use_packed_pixel)
+ link_mode = MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+ else
+ link_mode = MHL_DST_LM_CLK_MODE_NORMAL;
+
+ if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED)
+ link_mode |= MHL_DST_LM_PATH_ENABLED;
+
+ sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
+ link_mode);
}
static void sii8620_msc_mr_write_stat(struct sii8620 *ctx)
sii8620_update_array(ctx->stat, st, MHL_DST_SIZE);
sii8620_update_array(ctx->xstat, xst, MHL_XDS_SIZE);
- if (ctx->stat[MHL_DST_CONNECTED_RDY] & MHL_DST_CONN_DCAP_RDY)
+ if (ctx->stat[MHL_DST_CONNECTED_RDY] & st[MHL_DST_CONNECTED_RDY] &
+ MHL_DST_CONN_DCAP_RDY) {
sii8620_status_dcap_ready(ctx);
+ if (!sii8620_is_mhl3(ctx))
+ sii8620_mt_read_devcap(ctx, false);
+ }
+
if (st[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED)
sii8620_status_changed_path(ctx);
}
}
if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_REQ)
sii8620_send_features(ctx);
- if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE)
- sii8620_edid_read(ctx, 0);
+ if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE) {
+ ctx->feature_complete = true;
+ if (ctx->edid)
+ sii8620_enable_hpd(ctx);
+ }
}
static struct sii8620_mt_msg *sii8620_msc_msg_first(struct sii8620 *ctx)
if (stat & BIT_CBUS_MSC_MR_WRITE_STAT)
sii8620_msc_mr_write_stat(ctx);
+ if (stat & BIT_CBUS_HPD_CHG) {
+ if (ctx->cbus_status & BIT_CBUS_STATUS_CBUS_HPD) {
+ ctx->sink_detected = true;
+ sii8620_identify_sink(ctx);
+ } else {
+ sii8620_hpd_unplugged(ctx);
+ }
+ }
+
if (stat & BIT_CBUS_MSC_MR_SET_INT)
sii8620_msc_mr_set_int(ctx);
ctx->mt_state = MT_STATE_DONE;
}
-static void sii8620_scdt_high(struct sii8620 *ctx)
-{
- sii8620_write_seq_static(ctx,
- REG_INTR8_MASK, BIT_CEA_NEW_AVI | BIT_CEA_NEW_VSI,
- REG_TPI_SC, BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI,
- );
-}
-
static void sii8620_irq_scdt(struct sii8620 *ctx)
{
u8 stat = sii8620_readb(ctx, REG_INTR5);
if (stat & BIT_INTR_SCDT_CHANGE) {
u8 cstat = sii8620_readb(ctx, REG_TMDS_CSTAT_P3);
- if (cstat & BIT_TMDS_CSTAT_P3_SCDT) {
- if (ctx->sink_type == SINK_HDMI)
- /* enable infoframe interrupt */
- sii8620_scdt_high(ctx);
- else
- sii8620_start_video(ctx);
- }
+ if (cstat & BIT_TMDS_CSTAT_P3_SCDT)
+ sii8620_start_video(ctx);
}
sii8620_write(ctx, REG_INTR5, stat);
}
-static void sii8620_new_vsi(struct sii8620 *ctx)
-{
- u8 vsif[11];
-
- sii8620_write(ctx, REG_RX_HDMI_CTRL2,
- VAL_RX_HDMI_CTRL2_DEFVAL |
- BIT_RX_HDMI_CTRL2_VSI_MON_SEL_VSI);
- sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, vsif,
- ARRAY_SIZE(vsif));
-}
-
-static void sii8620_new_avi(struct sii8620 *ctx)
-{
- sii8620_write(ctx, REG_RX_HDMI_CTRL2, VAL_RX_HDMI_CTRL2_DEFVAL);
- sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, ctx->avif,
- ARRAY_SIZE(ctx->avif));
-}
-
-static void sii8620_irq_infr(struct sii8620 *ctx)
-{
- u8 stat = sii8620_readb(ctx, REG_INTR8)
- & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI);
-
- sii8620_write(ctx, REG_INTR8, stat);
-
- if (stat & BIT_CEA_NEW_VSI)
- sii8620_new_vsi(ctx);
-
- if (stat & BIT_CEA_NEW_AVI)
- sii8620_new_avi(ctx);
-
- if (stat & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI))
- sii8620_start_video(ctx);
-}
-
static void sii8620_got_xdevcap(struct sii8620 *ctx, int ret)
{
if (ret < 0)
if (stat & BIT_DDC_CMD_DONE) {
sii8620_write(ctx, REG_INTR3_MASK, 0);
- if (sii8620_is_mhl3(ctx))
+ if (sii8620_is_mhl3(ctx) && !ctx->feature_complete)
sii8620_mt_set_int(ctx, MHL_INT_REG(RCHANGE),
MHL_INT_RC_FEAT_REQ);
else
- sii8620_edid_read(ctx, 0);
+ sii8620_enable_hpd(ctx);
}
sii8620_write(ctx, REG_INTR3, stat);
}
{ BIT_FAST_INTR_STAT_EDID, sii8620_irq_edid },
{ BIT_FAST_INTR_STAT_DDC, sii8620_irq_ddc },
{ BIT_FAST_INTR_STAT_SCDT, sii8620_irq_scdt },
- { BIT_FAST_INTR_STAT_INFR, sii8620_irq_infr },
};
struct sii8620 *ctx = data;
u8 stats[LEN_FAST_INTR_STAT];
dev_err(dev, "Error powering on, %d.\n", ret);
return;
}
- sii8620_hw_reset(ctx);
sii8620_read_buf(ctx, REG_VND_IDL, ver, ARRAY_SIZE(ver));
ret = sii8620_clear_error(ctx);
rc_unregister_device(ctx->rc_dev);
}
+static int sii8620_is_packing_required(struct sii8620 *ctx,
+ const struct drm_display_mode *mode)
+{
+ int max_pclk, max_pclk_pp_mode;
+
+ if (sii8620_is_mhl3(ctx)) {
+ max_pclk = MHL3_MAX_PCLK;
+ max_pclk_pp_mode = MHL3_MAX_PCLK_PP_MODE;
+ } else {
+ max_pclk = MHL1_MAX_PCLK;
+ max_pclk_pp_mode = MHL1_MAX_PCLK_PP_MODE;
+ }
+
+ if (mode->clock < max_pclk)
+ return 0;
+ else if (mode->clock < max_pclk_pp_mode)
+ return 1;
+ else
+ return -1;
+}
+
static enum drm_mode_status sii8620_mode_valid(struct drm_bridge *bridge,
const struct drm_display_mode *mode)
{
struct sii8620 *ctx = bridge_to_sii8620(bridge);
+ int pack_required = sii8620_is_packing_required(ctx, mode);
bool can_pack = ctx->devcap[MHL_DCAP_VID_LINK_MODE] &
MHL_DCAP_VID_LINK_PPIXEL;
- unsigned int max_pclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK :
- MHL1_MAX_LCLK;
- max_pclk /= can_pack ? 2 : 3;
- return (mode->clock > max_pclk) ? MODE_CLOCK_HIGH : MODE_OK;
+ switch (pack_required) {
+ case 0:
+ return MODE_OK;
+ case 1:
+ return (can_pack) ? MODE_OK : MODE_CLOCK_HIGH;
+ default:
+ return MODE_CLOCK_HIGH;
+ }
}
static bool sii8620_mode_fixup(struct drm_bridge *bridge,
struct drm_display_mode *adjusted_mode)
{
struct sii8620 *ctx = bridge_to_sii8620(bridge);
- int max_lclk;
- bool ret = true;
mutex_lock(&ctx->lock);
- max_lclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK : MHL1_MAX_LCLK;
- if (max_lclk > 3 * adjusted_mode->clock) {
- ctx->use_packed_pixel = 0;
- goto end;
- }
- if ((ctx->devcap[MHL_DCAP_VID_LINK_MODE] & MHL_DCAP_VID_LINK_PPIXEL) &&
- max_lclk > 2 * adjusted_mode->clock) {
- ctx->use_packed_pixel = 1;
- goto end;
- }
- ret = false;
-end:
- if (ret) {
- u8 vic = drm_match_cea_mode(adjusted_mode);
-
- if (!vic) {
- union hdmi_infoframe frm;
- u8 mhl_vic[] = { 0, 95, 94, 93, 98 };
-
- /* FIXME: We need the connector here */
- drm_hdmi_vendor_infoframe_from_display_mode(
- &frm.vendor.hdmi, NULL, adjusted_mode);
- vic = frm.vendor.hdmi.vic;
- if (vic >= ARRAY_SIZE(mhl_vic))
- vic = 0;
- vic = mhl_vic[vic];
- }
- ctx->video_code = vic;
- ctx->pixel_clock = adjusted_mode->clock;
- }
+ ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode);
+
mutex_unlock(&ctx->lock);
- return ret;
+
+ return true;
}
static const struct drm_bridge_funcs sii8620_bridge_funcs = {
{
struct drm_crtc *crtc;
struct drm_crtc_state *crtc_state;
- struct drm_plane *plane;
- struct drm_plane_state *old_plane_state, *new_plane_state;
+ struct drm_plane *plane = NULL;
+ struct drm_plane_state *old_plane_state = NULL;
+ struct drm_plane_state *new_plane_state = NULL;
const struct drm_plane_helper_funcs *funcs;
int i, n_planes = 0;
if (n_planes != 1)
return -EINVAL;
- if (!new_plane_state->crtc)
+ if (!new_plane_state->crtc ||
+ old_plane_state->crtc != new_plane_state->crtc)
return -EINVAL;
funcs = plane->helper_private;
ctx->handle = drm_legacy_ctxbitmap_next(dev);
}
DRM_DEBUG("%d\n", ctx->handle);
- if (ctx->handle == -1) {
+ if (ctx->handle < 0) {
DRM_DEBUG("Not enough free contexts.\n");
/* Should this return -EBUSY instead? */
return -ENOMEM;
*/
void drm_dev_unplug(struct drm_device *dev)
{
- drm_dev_unregister(dev);
-
- mutex_lock(&drm_global_mutex);
- if (dev->open_count == 0)
- drm_dev_put(dev);
- mutex_unlock(&drm_global_mutex);
-
/*
* After synchronizing any critical read section is guaranteed to see
* the new value of ->unplugged, and any critical section which might
*/
dev->unplugged = true;
synchronize_srcu(&drm_unplug_srcu);
+
+ drm_dev_unregister(dev);
+
+ mutex_lock(&drm_global_mutex);
+ if (dev->open_count == 0)
+ drm_dev_put(dev);
+ mutex_unlock(&drm_global_mutex);
}
EXPORT_SYMBOL(drm_dev_unplug);
/* Clone the lessor file to create a new file for us */
DRM_DEBUG_LEASE("Allocating lease file\n");
- path_get(&lessor_file->f_path);
- lessee_file = alloc_file(&lessor_file->f_path,
- lessor_file->f_mode,
- fops_get(lessor_file->f_inode->i_fop));
-
+ lessee_file = file_clone_open(lessor_file);
if (IS_ERR(lessee_file)) {
ret = PTR_ERR(lessee_file);
goto out_lessee;
}
- /* Initialize the new file for DRM */
- DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open);
- ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file);
- if (ret)
- goto out_lessee_file;
-
lessee_priv = lessee_file->private_data;
-
/* Change the file to a master one */
drm_master_put(&lessee_priv->master);
lessee_priv->master = lessee;
DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
return 0;
-out_lessee_file:
- fput(lessee_file);
-
out_lessee:
drm_master_put(&lessee);
drm_mode_object_unregister(blob->dev, &blob->base);
- kfree(blob);
+ kvfree(blob);
}
/**
if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob))
return ERR_PTR(-EINVAL);
- blob = kzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
+ blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
if (!blob)
return ERR_PTR(-ENOMEM);
ret = __drm_mode_object_add(dev, &blob->base, DRM_MODE_OBJECT_BLOB,
true, drm_property_free_blob);
if (ret) {
- kfree(blob);
+ kvfree(blob);
return ERR_PTR(-EINVAL);
}
},
};
+static struct platform_device *etnaviv_drm;
+
static int __init etnaviv_init(void)
{
+ struct platform_device *pdev;
int ret;
struct device_node *np;
ret = platform_driver_register(&etnaviv_platform_driver);
if (ret != 0)
- platform_driver_unregister(&etnaviv_gpu_driver);
+ goto unregister_gpu_driver;
/*
* If the DT contains at least one available GPU device, instantiate
for_each_compatible_node(np, NULL, "vivante,gc") {
if (!of_device_is_available(np))
continue;
-
- platform_device_register_simple("etnaviv", -1, NULL, 0);
+ pdev = platform_device_register_simple("etnaviv", -1,
+ NULL, 0);
+ if (IS_ERR(pdev)) {
+ ret = PTR_ERR(pdev);
+ of_node_put(np);
+ goto unregister_platform_driver;
+ }
+ etnaviv_drm = pdev;
of_node_put(np);
break;
}
+ return 0;
+
+unregister_platform_driver:
+ platform_driver_unregister(&etnaviv_platform_driver);
+unregister_gpu_driver:
+ platform_driver_unregister(&etnaviv_gpu_driver);
return ret;
}
module_init(etnaviv_init);
static void __exit etnaviv_exit(void)
{
- platform_driver_unregister(&etnaviv_gpu_driver);
+ platform_device_unregister(etnaviv_drm);
platform_driver_unregister(&etnaviv_platform_driver);
+ platform_driver_unregister(&etnaviv_gpu_driver);
}
module_exit(etnaviv_exit);
struct work_struct sync_point_work;
int sync_point_event;
+ /* hang detection */
+ u32 hangcheck_dma_addr;
+
void __iomem *mmio;
int irq;
#include "etnaviv_gem.h"
#include "etnaviv_gpu.h"
#include "etnaviv_sched.h"
+#include "state.xml.h"
static int etnaviv_job_hang_limit = 0;
module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444);
{
struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
struct etnaviv_gpu *gpu = submit->gpu;
+ u32 dma_addr;
+ int change;
+
+ /*
+ * If the GPU managed to complete this jobs fence, the timout is
+ * spurious. Bail out.
+ */
+ if (fence_completed(gpu, submit->out_fence->seqno))
+ return;
+
+ /*
+ * If the GPU is still making forward progress on the front-end (which
+ * should never loop) we shift out the timeout to give it a chance to
+ * finish the job.
+ */
+ dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);
+ change = dma_addr - gpu->hangcheck_dma_addr;
+ if (change < 0 || change > 16) {
+ gpu->hangcheck_dma_addr = dma_addr;
+ schedule_delayed_work(&sched_job->work_tdr,
+ sched_job->sched->timeout);
+ return;
+ }
/* block scheduler */
kthread_park(gpu->sched.thread);
unsigned long val;
val = readl(ctx->addr + DECON_WINCONx(win));
- val &= ~WINCONx_BPPMODE_MASK;
+ val &= WINCONx_ENWIN_F;
switch (fb->format->format) {
case DRM_FORMAT_XRGB1555:
writel(val, ctx->addr + DECON_VIDOSDxB(win));
}
- val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
- VIDOSD_Wx_ALPHA_B_F(0x0);
+ val = VIDOSD_Wx_ALPHA_R_F(0xff) | VIDOSD_Wx_ALPHA_G_F(0xff) |
+ VIDOSD_Wx_ALPHA_B_F(0xff);
writel(val, ctx->addr + DECON_VIDOSDxC(win));
val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
err_free_private:
kfree(private);
err_free_drm:
- drm_dev_unref(drm);
+ drm_dev_put(drm);
return ret;
}
drm->dev_private = NULL;
dev_set_drvdata(dev, NULL);
- drm_dev_unref(drm);
+ drm_dev_put(drm);
}
static const struct component_master_ops exynos_drm_ops = {
err:
while (i--)
- drm_gem_object_unreference_unlocked(&exynos_gem[i]->base);
+ drm_gem_object_put_unlocked(&exynos_gem[i]->base);
return ERR_PTR(ret);
}
static void fimc_set_window(struct fimc_context *ctx,
struct exynos_drm_ipp_buffer *buf)
{
+ unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
u32 cfg, h1, h2, v1, v2;
/* cropped image */
h1 = buf->rect.x;
- h2 = buf->buf.width - buf->rect.w - buf->rect.x;
+ h2 = real_width - buf->rect.w - buf->rect.x;
v1 = buf->rect.y;
v2 = buf->buf.height - buf->rect.h - buf->rect.y;
DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]hsize[%d]vsize[%d]\n",
buf->rect.x, buf->rect.y, buf->rect.w, buf->rect.h,
- buf->buf.width, buf->buf.height);
+ real_width, buf->buf.height);
DRM_DEBUG_KMS("h1[%d]h2[%d]v1[%d]v2[%d]\n", h1, h2, v1, v2);
/*
static void fimc_src_set_size(struct fimc_context *ctx,
struct exynos_drm_ipp_buffer *buf)
{
+ unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
u32 cfg;
- DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+ DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
/* original size */
- cfg = (EXYNOS_ORGISIZE_HORIZONTAL(buf->buf.width) |
+ cfg = (EXYNOS_ORGISIZE_HORIZONTAL(real_width) |
EXYNOS_ORGISIZE_VERTICAL(buf->buf.height));
fimc_write(ctx, cfg, EXYNOS_ORGISIZE);
* for now, we support only ITU601 8 bit mode
*/
cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
- EXYNOS_CISRCFMT_SOURCEHSIZE(buf->buf.width) |
+ EXYNOS_CISRCFMT_SOURCEHSIZE(real_width) |
EXYNOS_CISRCFMT_SOURCEVSIZE(buf->buf.height));
fimc_write(ctx, cfg, EXYNOS_CISRCFMT);
static void fimc_dst_set_size(struct fimc_context *ctx,
struct exynos_drm_ipp_buffer *buf)
{
+ unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
u32 cfg, cfg_ext;
- DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+ DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
/* original size */
- cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(buf->buf.width) |
+ cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(real_width) |
EXYNOS_ORGOSIZE_VERTICAL(buf->buf.height));
fimc_write(ctx, cfg, EXYNOS_ORGOSIZE);
DRM_DEBUG_KMS("gem handle = 0x%x\n", *handle);
/* drop reference from allocate - handle holds it now. */
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_put_unlocked(obj);
return 0;
}
exynos_gem = to_exynos_gem(obj);
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_put_unlocked(obj);
return exynos_gem->size;
}
return;
}
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_put_unlocked(obj);
/*
* decrease obj->refcount one more time because we has already
* increased it at exynos_drm_gem_get_dma_addr().
*/
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_put_unlocked(obj);
}
static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
args->flags = exynos_gem->flags;
args->size = exynos_gem->size;
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_put_unlocked(obj);
return 0;
}
GSC_IN_CHROMA_ORDER_CRCB);
break;
case DRM_FORMAT_NV21:
+ cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_2P);
+ break;
case DRM_FORMAT_NV61:
- cfg |= (GSC_IN_CHROMA_ORDER_CRCB |
- GSC_IN_YUV420_2P);
+ cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV422_2P);
break;
case DRM_FORMAT_YUV422:
cfg |= GSC_IN_YUV422_3P;
break;
case DRM_FORMAT_YUV420:
+ cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_3P);
+ break;
case DRM_FORMAT_YVU420:
- cfg |= GSC_IN_YUV420_3P;
+ cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_3P);
break;
case DRM_FORMAT_NV12:
+ cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_2P);
+ break;
case DRM_FORMAT_NV16:
- cfg |= (GSC_IN_CHROMA_ORDER_CBCR |
- GSC_IN_YUV420_2P);
+ cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV422_2P);
break;
}
switch (degree) {
case DRM_MODE_ROTATE_0:
- if (rotation & DRM_MODE_REFLECT_Y)
- cfg |= GSC_IN_ROT_XFLIP;
if (rotation & DRM_MODE_REFLECT_X)
+ cfg |= GSC_IN_ROT_XFLIP;
+ if (rotation & DRM_MODE_REFLECT_Y)
cfg |= GSC_IN_ROT_YFLIP;
break;
case DRM_MODE_ROTATE_90:
cfg |= GSC_IN_ROT_90;
- if (rotation & DRM_MODE_REFLECT_Y)
- cfg |= GSC_IN_ROT_XFLIP;
if (rotation & DRM_MODE_REFLECT_X)
+ cfg |= GSC_IN_ROT_XFLIP;
+ if (rotation & DRM_MODE_REFLECT_Y)
cfg |= GSC_IN_ROT_YFLIP;
break;
case DRM_MODE_ROTATE_180:
cfg |= GSC_IN_ROT_180;
- if (rotation & DRM_MODE_REFLECT_Y)
- cfg &= ~GSC_IN_ROT_XFLIP;
if (rotation & DRM_MODE_REFLECT_X)
+ cfg &= ~GSC_IN_ROT_XFLIP;
+ if (rotation & DRM_MODE_REFLECT_Y)
cfg &= ~GSC_IN_ROT_YFLIP;
break;
case DRM_MODE_ROTATE_270:
cfg |= GSC_IN_ROT_270;
- if (rotation & DRM_MODE_REFLECT_Y)
- cfg &= ~GSC_IN_ROT_XFLIP;
if (rotation & DRM_MODE_REFLECT_X)
+ cfg &= ~GSC_IN_ROT_XFLIP;
+ if (rotation & DRM_MODE_REFLECT_Y)
cfg &= ~GSC_IN_ROT_YFLIP;
break;
}
cfg &= ~(GSC_SRCIMG_HEIGHT_MASK |
GSC_SRCIMG_WIDTH_MASK);
- cfg |= (GSC_SRCIMG_WIDTH(buf->buf.width) |
+ cfg |= (GSC_SRCIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
GSC_SRCIMG_HEIGHT(buf->buf.height));
gsc_write(cfg, GSC_SRCIMG_SIZE);
GSC_OUT_CHROMA_ORDER_CRCB);
break;
case DRM_FORMAT_NV21:
- case DRM_FORMAT_NV61:
cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_2P);
break;
+ case DRM_FORMAT_NV61:
+ cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV422_2P);
+ break;
case DRM_FORMAT_YUV422:
+ cfg |= GSC_OUT_YUV422_3P;
+ break;
case DRM_FORMAT_YUV420:
+ cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_3P);
+ break;
case DRM_FORMAT_YVU420:
- cfg |= GSC_OUT_YUV420_3P;
+ cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_3P);
break;
case DRM_FORMAT_NV12:
+ cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_2P);
+ break;
case DRM_FORMAT_NV16:
- cfg |= (GSC_OUT_CHROMA_ORDER_CBCR |
- GSC_OUT_YUV420_2P);
+ cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV422_2P);
break;
}
/* original size */
cfg = gsc_read(GSC_DSTIMG_SIZE);
cfg &= ~(GSC_DSTIMG_HEIGHT_MASK | GSC_DSTIMG_WIDTH_MASK);
- cfg |= GSC_DSTIMG_WIDTH(buf->buf.width) |
+ cfg |= GSC_DSTIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
GSC_DSTIMG_HEIGHT(buf->buf.height);
gsc_write(cfg, GSC_DSTIMG_SIZE);
};
static const struct drm_exynos_ipp_limit gsc_5433_limits[] = {
- { IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 2 }, .v = { 16, 8191, 2 }) },
+ { IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 16 }, .v = { 16, 8191, 2 }) },
{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 1 }, .v = { 8, 3344, 1 }) },
{ IPP_SIZE_LIMIT(ROTATED, .h = { 32, 2047 }, .v = { 8, 8191 }) },
{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
int ret = 0;
int i;
- /* basic checks */
- if (buf->buf.width == 0 || buf->buf.height == 0)
- return -EINVAL;
- buf->format = drm_format_info(buf->buf.fourcc);
- for (i = 0; i < buf->format->num_planes; i++) {
- unsigned int width = (i == 0) ? buf->buf.width :
- DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
-
- if (buf->buf.pitch[i] == 0)
- buf->buf.pitch[i] = width * buf->format->cpp[i];
- if (buf->buf.pitch[i] < width * buf->format->cpp[i])
- return -EINVAL;
- if (!buf->buf.gem_id[i])
- return -ENOENT;
- }
-
- /* pitch for additional planes must match */
- if (buf->format->num_planes > 2 &&
- buf->buf.pitch[1] != buf->buf.pitch[2])
- return -EINVAL;
-
/* get GEM buffers and check their size */
for (i = 0; i < buf->format->num_planes; i++) {
unsigned int height = (i == 0) ? buf->buf.height :
IPP_LIMIT_BUFFER, IPP_LIMIT_AREA, IPP_LIMIT_ROTATED, IPP_LIMIT_MAX
};
-static const enum drm_ipp_size_id limit_id_fallback[IPP_LIMIT_MAX][4] = {
+static const enum drm_exynos_ipp_limit_type limit_id_fallback[IPP_LIMIT_MAX][4] = {
[IPP_LIMIT_BUFFER] = { DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
[IPP_LIMIT_AREA] = { DRM_EXYNOS_IPP_LIMIT_SIZE_AREA,
DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
enum drm_ipp_size_id id = rotate ? IPP_LIMIT_ROTATED : IPP_LIMIT_AREA;
struct drm_ipp_limit l;
struct drm_exynos_ipp_limit_val *lh = &l.h, *lv = &l.v;
+ int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
if (!limits)
return 0;
__get_size_limit(limits, num_limits, IPP_LIMIT_BUFFER, &l);
- if (!__size_limit_check(buf->buf.width, &l.h) ||
+ if (!__size_limit_check(real_width, &l.h) ||
!__size_limit_check(buf->buf.height, &l.v))
return -EINVAL;
return 0;
}
+static int exynos_drm_ipp_check_format(struct exynos_drm_ipp_task *task,
+ struct exynos_drm_ipp_buffer *buf,
+ struct exynos_drm_ipp_buffer *src,
+ struct exynos_drm_ipp_buffer *dst,
+ bool rotate, bool swap)
+{
+ const struct exynos_drm_ipp_formats *fmt;
+ int ret, i;
+
+ fmt = __ipp_format_get(task->ipp, buf->buf.fourcc, buf->buf.modifier,
+ buf == src ? DRM_EXYNOS_IPP_FORMAT_SOURCE :
+ DRM_EXYNOS_IPP_FORMAT_DESTINATION);
+ if (!fmt) {
+ DRM_DEBUG_DRIVER("Task %pK: %s format not supported\n", task,
+ buf == src ? "src" : "dst");
+ return -EINVAL;
+ }
+
+ /* basic checks */
+ if (buf->buf.width == 0 || buf->buf.height == 0)
+ return -EINVAL;
+
+ buf->format = drm_format_info(buf->buf.fourcc);
+ for (i = 0; i < buf->format->num_planes; i++) {
+ unsigned int width = (i == 0) ? buf->buf.width :
+ DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
+
+ if (buf->buf.pitch[i] == 0)
+ buf->buf.pitch[i] = width * buf->format->cpp[i];
+ if (buf->buf.pitch[i] < width * buf->format->cpp[i])
+ return -EINVAL;
+ if (!buf->buf.gem_id[i])
+ return -ENOENT;
+ }
+
+ /* pitch for additional planes must match */
+ if (buf->format->num_planes > 2 &&
+ buf->buf.pitch[1] != buf->buf.pitch[2])
+ return -EINVAL;
+
+ /* check driver limits */
+ ret = exynos_drm_ipp_check_size_limits(buf, fmt->limits,
+ fmt->num_limits,
+ rotate,
+ buf == dst ? swap : false);
+ if (ret)
+ return ret;
+ ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
+ fmt->limits,
+ fmt->num_limits, swap);
+ return ret;
+}
+
static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
{
struct exynos_drm_ipp *ipp = task->ipp;
- const struct exynos_drm_ipp_formats *src_fmt, *dst_fmt;
struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
unsigned int rotation = task->transform.rotation;
int ret = 0;
return -EINVAL;
}
- src_fmt = __ipp_format_get(ipp, src->buf.fourcc, src->buf.modifier,
- DRM_EXYNOS_IPP_FORMAT_SOURCE);
- if (!src_fmt) {
- DRM_DEBUG_DRIVER("Task %pK: src format not supported\n", task);
- return -EINVAL;
- }
- ret = exynos_drm_ipp_check_size_limits(src, src_fmt->limits,
- src_fmt->num_limits,
- rotate, false);
- if (ret)
- return ret;
- ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
- src_fmt->limits,
- src_fmt->num_limits, swap);
+ ret = exynos_drm_ipp_check_format(task, src, src, dst, rotate, swap);
if (ret)
return ret;
- dst_fmt = __ipp_format_get(ipp, dst->buf.fourcc, dst->buf.modifier,
- DRM_EXYNOS_IPP_FORMAT_DESTINATION);
- if (!dst_fmt) {
- DRM_DEBUG_DRIVER("Task %pK: dst format not supported\n", task);
- return -EINVAL;
- }
- ret = exynos_drm_ipp_check_size_limits(dst, dst_fmt->limits,
- dst_fmt->num_limits,
- false, swap);
- if (ret)
- return ret;
- ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
- dst_fmt->limits,
- dst_fmt->num_limits, swap);
+ ret = exynos_drm_ipp_check_format(task, dst, src, dst, false, swap);
if (ret)
return ret;
if (plane->state) {
exynos_state = to_exynos_plane_state(plane->state);
if (exynos_state->base.fb)
- drm_framebuffer_unreference(exynos_state->base.fb);
+ drm_framebuffer_put(exynos_state->base.fb);
kfree(exynos_state);
plane->state = NULL;
}
val &= ~ROT_CONTROL_FLIP_MASK;
if (rotation & DRM_MODE_REFLECT_X)
- val |= ROT_CONTROL_FLIP_HORIZONTAL;
- if (rotation & DRM_MODE_REFLECT_Y)
val |= ROT_CONTROL_FLIP_VERTICAL;
+ if (rotation & DRM_MODE_REFLECT_Y)
+ val |= ROT_CONTROL_FLIP_HORIZONTAL;
val &= ~ROT_CONTROL_ROT_MASK;
#define scaler_write(cfg, offset) writel(cfg, scaler->regs + (offset))
#define SCALER_MAX_CLK 4
#define SCALER_AUTOSUSPEND_DELAY 2000
+#define SCALER_RESET_WAIT_RETRIES 100
struct scaler_data {
const char *clk_name[SCALER_MAX_CLK];
static u32 scaler_get_format(u32 drm_fmt)
{
switch (drm_fmt) {
- case DRM_FORMAT_NV21:
- return SCALER_YUV420_2P_UV;
case DRM_FORMAT_NV12:
+ return SCALER_YUV420_2P_UV;
+ case DRM_FORMAT_NV21:
return SCALER_YUV420_2P_VU;
case DRM_FORMAT_YUV420:
return SCALER_YUV420_3P;
return SCALER_YUV422_1P_UYVY;
case DRM_FORMAT_YVYU:
return SCALER_YUV422_1P_YVYU;
- case DRM_FORMAT_NV61:
- return SCALER_YUV422_2P_UV;
case DRM_FORMAT_NV16:
+ return SCALER_YUV422_2P_UV;
+ case DRM_FORMAT_NV61:
return SCALER_YUV422_2P_VU;
case DRM_FORMAT_YUV422:
return SCALER_YUV422_3P;
- case DRM_FORMAT_NV42:
- return SCALER_YUV444_2P_UV;
case DRM_FORMAT_NV24:
+ return SCALER_YUV444_2P_UV;
+ case DRM_FORMAT_NV42:
return SCALER_YUV444_2P_VU;
case DRM_FORMAT_YUV444:
return SCALER_YUV444_3P;
return 0;
}
+static inline int scaler_reset(struct scaler_context *scaler)
+{
+ int retry = SCALER_RESET_WAIT_RETRIES;
+
+ scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG);
+ do {
+ cpu_relax();
+ } while (retry > 1 &&
+ scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET);
+ do {
+ cpu_relax();
+ scaler_write(1, SCALER_INT_EN);
+ } while (retry > 0 && scaler_read(SCALER_INT_EN) != 1);
+
+ return retry ? 0 : -EIO;
+}
+
static inline void scaler_enable_int(struct scaler_context *scaler)
{
u32 val;
u32 dst_fmt = scaler_get_format(task->dst.buf.fourcc);
struct drm_exynos_ipp_task_rect *dst_pos = &task->dst.rect;
- scaler->task = task;
-
pm_runtime_get_sync(scaler->dev);
+ if (scaler_reset(scaler)) {
+ pm_runtime_put(scaler->dev);
+ return -EIO;
+ }
+
+ scaler->task = task;
scaler_set_src_fmt(scaler, src_fmt);
scaler_set_src_base(scaler, &task->src);
static inline u32 scaler_get_int_status(struct scaler_context *scaler)
{
- return scaler_read(SCALER_INT_STATUS);
+ u32 val = scaler_read(SCALER_INT_STATUS);
+
+ scaler_write(val, SCALER_INT_STATUS);
+
+ return val;
}
static inline int scaler_task_done(u32 val)
#define GSC_OUT_YUV420_3P (3 << 4)
#define GSC_OUT_YUV422_1P (4 << 4)
#define GSC_OUT_YUV422_2P (5 << 4)
+#define GSC_OUT_YUV422_3P (6 << 4)
#define GSC_OUT_YUV444 (7 << 4)
#define GSC_OUT_TILE_TYPE_MASK (1 << 2)
#define GSC_OUT_TILE_C_16x8 (0 << 2)
{
struct intel_vgpu *vgpu = s->vgpu;
struct intel_gvt *gvt = vgpu->gvt;
+ u32 ctx_sr_ctl;
if (offset + 4 > gvt->device_info.mmio_size) {
gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE);
}
+ /* TODO
+ * Right now only scan LRI command on KBL and in inhibit context.
+ * It's good enough to support initializing mmio by lri command in
+ * vgpu inhibit context on KBL.
+ */
+ if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) &&
+ intel_gvt_mmio_is_in_ctx(gvt, offset) &&
+ !strncmp(cmd, "lri", 3)) {
+ intel_gvt_hypervisor_read_gpa(s->vgpu,
+ s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4);
+ /* check inhibit context */
+ if (ctx_sr_ctl & 1) {
+ u32 data = cmd_val(s, index + 1);
+
+ if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset))
+ intel_vgpu_mask_mmio_write(vgpu,
+ offset, &data, 4);
+ else
+ vgpu_vreg(vgpu, offset) = data;
+ }
+ }
+
/* TODO: Update the global mask if this MMIO is a masked-MMIO */
intel_gvt_mmio_set_cmd_accessed(gvt, offset);
return 0;
~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
TRANS_DDI_PORT_MASK);
vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
- (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+ (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
(PORT_B << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
if (IS_BROADWELL(dev_priv)) {
~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
TRANS_DDI_PORT_MASK);
vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
- (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+ (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
(PORT_C << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
if (IS_BROADWELL(dev_priv)) {
~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
TRANS_DDI_PORT_MASK);
vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
- (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+ (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
(PORT_D << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
if (IS_BROADWELL(dev_priv)) {
vgpu_free_mm(mm);
return ERR_PTR(-ENOMEM);
}
+ mm->ggtt_mm.last_partial_off = -1UL;
return mm;
}
invalidate_ppgtt_mm(mm);
} else {
vfree(mm->ggtt_mm.virtual_ggtt);
+ mm->ggtt_mm.last_partial_off = -1UL;
}
vgpu_free_mm(mm);
memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
bytes);
+ /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes
+ * write, we assume the two 4 bytes writes are consecutive.
+ * Otherwise, we abort and report error
+ */
+ if (bytes < info->gtt_entry_size) {
+ if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) {
+ /* the first partial part*/
+ ggtt_mm->ggtt_mm.last_partial_off = off;
+ ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+ return 0;
+ } else if ((g_gtt_index ==
+ (ggtt_mm->ggtt_mm.last_partial_off >>
+ info->gtt_entry_size_shift)) &&
+ (off != ggtt_mm->ggtt_mm.last_partial_off)) {
+ /* the second partial part */
+
+ int last_off = ggtt_mm->ggtt_mm.last_partial_off &
+ (info->gtt_entry_size - 1);
+
+ memcpy((void *)&e.val64 + last_off,
+ (void *)&ggtt_mm->ggtt_mm.last_partial_data +
+ last_off, bytes);
+
+ ggtt_mm->ggtt_mm.last_partial_off = -1UL;
+ } else {
+ int last_offset;
+
+ gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n",
+ ggtt_mm->ggtt_mm.last_partial_off, off,
+ bytes, info->gtt_entry_size);
+
+ /* set host ggtt entry to scratch page and clear
+ * virtual ggtt entry as not present for last
+ * partially write offset
+ */
+ last_offset = ggtt_mm->ggtt_mm.last_partial_off &
+ (~(info->gtt_entry_size - 1));
+
+ ggtt_get_host_entry(ggtt_mm, &m, last_offset);
+ ggtt_invalidate_pte(vgpu, &m);
+ ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+ ops->clear_present(&m);
+ ggtt_set_host_entry(ggtt_mm, &m, last_offset);
+ ggtt_invalidate(gvt->dev_priv);
+
+ ggtt_get_guest_entry(ggtt_mm, &e, last_offset);
+ ops->clear_present(&e);
+ ggtt_set_guest_entry(ggtt_mm, &e, last_offset);
+
+ ggtt_mm->ggtt_mm.last_partial_off = off;
+ ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+
+ return 0;
+ }
+ }
+
if (ops->test_present(&e)) {
gfn = ops->get_pfn(&e);
m = e;
} ppgtt_mm;
struct {
void *virtual_ggtt;
+ unsigned long last_partial_off;
+ u64 last_partial_data;
} ggtt_mm;
};
};
#define F_CMD_ACCESSED (1 << 5)
/* This reg could be accessed by unaligned address */
#define F_UNALIGN (1 << 6)
+/* This reg is saved/restored in context */
+#define F_IN_CTX (1 << 7)
struct gvt_mmio_block *mmio_block;
unsigned int num_mmio_block;
return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK;
}
+/**
+ * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if a MMIO has a in-context mask, false if it isn't.
+ *
+ */
+static inline bool intel_gvt_mmio_is_in_ctx(
+ struct intel_gvt *gvt, unsigned int offset)
+{
+ return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX;
+}
+
+/**
+ * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ */
+static inline void intel_gvt_mmio_set_in_ctx(
+ struct intel_gvt *gvt, unsigned int offset)
+{
+ gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX;
+}
+
int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu);
void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);
int intel_gvt_debugfs_init(struct intel_gvt *gvt);
return 0;
}
+/**
+ * intel_vgpu_mask_mmio_write - write mask register
+ * @vgpu: a vGPU
+ * @offset: access offset
+ * @p_data: write data buffer
+ * @bytes: access data length
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ */
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+ void *p_data, unsigned int bytes)
+{
+ u32 mask, old_vreg;
+
+ old_vreg = vgpu_vreg(vgpu, offset);
+ write_vreg(vgpu, offset, p_data, bytes);
+ mask = vgpu_vreg(vgpu, offset) >> 16;
+ vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) |
+ (vgpu_vreg(vgpu, offset) & mask);
+
+ return 0;
+}
+
/**
* intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
* force-nopriv register
int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
void *pdata, unsigned int bytes, bool is_read);
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+ void *p_data, unsigned int bytes);
#endif
for (mmio = gvt->engine_mmio_list.mmio;
i915_mmio_reg_valid(mmio->reg); mmio++) {
- if (mmio->in_context)
+ if (mmio->in_context) {
gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++;
+ intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg);
+ }
}
}
unsigned int bsd_engine;
-/* Client can have a maximum of 3 contexts banned before
- * it is denied of creating new contexts. As one context
- * ban needs 4 consecutive hangs, and more if there is
- * progress in between, this is a last resort stop gap measure
- * to limit the badly behaving clients access to gpu.
+/*
+ * Every context ban increments per client ban score. Also
+ * hangs in short succession increments ban score. If ban threshold
+ * is reached, client is considered banned and submitting more work
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
*/
-#define I915_MAX_CLIENT_CONTEXT_BANS 3
- atomic_t context_bans;
+#define I915_CLIENT_SCORE_HANG_FAST 1
+#define I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN 3
+#define I915_CLIENT_SCORE_BANNED 9
+ /** ban_score: Accumulated score of all ctx bans and fast hangs. */
+ atomic_t ban_score;
+ unsigned long hang_timestamp;
};
/* Interface history:
#define QUIRK_BACKLIGHT_PRESENT (1<<3)
#define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
#define QUIRK_INCREASE_T12_DELAY (1<<6)
+#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
struct intel_fbdev;
struct intel_fbc_work;
**/
static inline struct scatterlist *__sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
return sg_is_last(sg) ? NULL : ____sg_next(sg);
}
bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
struct i915_vma *vma;
pgoff_t page_offset;
- unsigned int flags;
int ret;
/* We don't use vmf->pgoff since that has the fake offset */
goto err_unlock;
}
- /* If the object is smaller than a couple of partial vma, it is
- * not worth only creating a single partial vma - we may as well
- * clear enough space for the full object.
- */
- flags = PIN_MAPPABLE;
- if (obj->base.size > 2 * MIN_CHUNK_PAGES << PAGE_SHIFT)
- flags |= PIN_NONBLOCK | PIN_NONFAULT;
/* Now pin it into the GTT as needed */
- vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, flags);
+ vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+ PIN_MAPPABLE |
+ PIN_NONBLOCK |
+ PIN_NONFAULT);
if (IS_ERR(vma)) {
/* Use a partial view if it is bigger than available space */
struct i915_ggtt_view view =
compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
+ unsigned int flags;
- /* Userspace is now writing through an untracked VMA, abandon
+ flags = PIN_MAPPABLE;
+ if (view.type == I915_GGTT_VIEW_NORMAL)
+ flags |= PIN_NONBLOCK; /* avoid warnings for pinned */
+
+ /*
+ * Userspace is now writing through an untracked VMA, abandon
* all hope that the hardware is able to track future writes.
*/
obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
- vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+ vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+ if (IS_ERR(vma) && !view.type) {
+ flags = PIN_MAPPABLE;
+ view.type = I915_GGTT_VIEW_PARTIAL;
+ vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+ }
}
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
return 0;
}
+static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
+ const struct i915_gem_context *ctx)
+{
+ unsigned int score;
+ unsigned long prev_hang;
+
+ if (i915_gem_context_is_banned(ctx))
+ score = I915_CLIENT_SCORE_CONTEXT_BAN;
+ else
+ score = 0;
+
+ prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
+ if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
+ score += I915_CLIENT_SCORE_HANG_FAST;
+
+ if (score) {
+ atomic_add(score, &file_priv->ban_score);
+
+ DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
+ ctx->name, score,
+ atomic_read(&file_priv->ban_score));
+ }
+}
+
static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
{
- bool banned;
+ unsigned int score;
+ bool banned, bannable;
atomic_inc(&ctx->guilty_count);
- banned = false;
- if (i915_gem_context_is_bannable(ctx)) {
- unsigned int score;
+ bannable = i915_gem_context_is_bannable(ctx);
+ score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
+ banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
- score = atomic_add_return(CONTEXT_SCORE_GUILTY,
- &ctx->ban_score);
- banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+ DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
+ ctx->name, atomic_read(&ctx->guilty_count),
+ score, yesno(banned && bannable));
- DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
- ctx->name, score, yesno(banned));
- }
- if (!banned)
+ /* Cool contexts don't accumulate client ban score */
+ if (!bannable)
return;
- i915_gem_context_set_banned(ctx);
- if (!IS_ERR_OR_NULL(ctx->file_priv)) {
- atomic_inc(&ctx->file_priv->context_bans);
- DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
- ctx->name, atomic_read(&ctx->file_priv->context_bans));
- }
+ if (banned)
+ i915_gem_context_set_banned(ctx);
+
+ if (!IS_ERR_OR_NULL(ctx->file_priv))
+ i915_gem_client_mark_guilty(ctx->file_priv, ctx);
}
static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
INIT_LIST_HEAD(&file_priv->mm.request_list);
file_priv->bsd_engine = -1;
+ file_priv->hang_timestamp = jiffies;
ret = i915_gem_context_open(i915, file);
if (ret)
static bool client_is_banned(struct drm_i915_file_private *file_priv)
{
- return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS;
+ return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
}
int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
}
static int
-eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
+eb_add_vma(struct i915_execbuffer *eb,
+ unsigned int i, unsigned batch_idx,
+ struct i915_vma *vma)
{
struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
int err;
eb->flags[i] = entry->flags;
vma->exec_flags = &eb->flags[i];
+ /*
+ * SNA is doing fancy tricks with compressing batch buffers, which leads
+ * to negative relocation deltas. Usually that works out ok since the
+ * relocate address is still positive, except when the batch is placed
+ * very low in the GTT. Ensure this doesn't happen.
+ *
+ * Note that actual hangs have only been observed on gen7, but for
+ * paranoia do it everywhere.
+ */
+ if (i == batch_idx) {
+ if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+ eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
+ if (eb->reloc_cache.has_fence)
+ eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
+
+ eb->batch = vma;
+ }
+
err = 0;
if (eb_pin_vma(eb, entry, vma)) {
if (entry->offset != vma->node.start) {
{
struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
struct drm_i915_gem_object *obj;
- unsigned int i;
+ unsigned int i, batch;
int err;
if (unlikely(i915_gem_context_is_closed(eb->ctx)))
INIT_LIST_HEAD(&eb->relocs);
INIT_LIST_HEAD(&eb->unbound);
+ batch = eb_batch_index(eb);
+
for (i = 0; i < eb->buffer_count; i++) {
u32 handle = eb->exec[i].handle;
struct i915_lut_handle *lut;
lut->handle = handle;
add_vma:
- err = eb_add_vma(eb, i, vma);
+ err = eb_add_vma(eb, i, batch, vma);
if (unlikely(err))
goto err_vma;
GEM_BUG_ON(vma != eb->vma[i]);
GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
+ GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
+ eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i]));
}
- /* take note of the batch buffer before we might reorder the lists */
- i = eb_batch_index(eb);
- eb->batch = eb->vma[i];
- GEM_BUG_ON(eb->batch->exec_flags != &eb->flags[i]);
-
- /*
- * SNA is doing fancy tricks with compressing batch buffers, which leads
- * to negative relocation deltas. Usually that works out ok since the
- * relocate address is still positive, except when the batch is placed
- * very low in the GTT. Ensure this doesn't happen.
- *
- * Note that actual hangs have only been observed on gen7, but for
- * paranoia do it everywhere.
- */
- if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
- eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
- if (eb->reloc_cache.has_fence)
- eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
-
eb->args->flags |= __EXEC_VALIDATED;
return eb_reserve(eb);
/*
* Clear the PIPE*STAT regs before the IIR
+ *
+ * Toggle the enable bits to make sure we get an
+ * edge in the ISR pipe event bit if we don't clear
+ * all the enabled status bits. Otherwise the edge
+ * triggered IIR on i965/g4x wouldn't notice that
+ * an interrupt is still pending.
*/
- if (pipe_stats[pipe])
- I915_WRITE(reg, enable_mask | pipe_stats[pipe]);
+ if (pipe_stats[pipe]) {
+ I915_WRITE(reg, pipe_stats[pipe]);
+ I915_WRITE(reg, enable_mask);
+ }
}
spin_unlock(&dev_priv->irq_lock);
}
static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
{
- u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+ u32 hotplug_status = 0, hotplug_status_mask;
+ int i;
- if (hotplug_status)
+ if (IS_G4X(dev_priv) ||
+ IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+ hotplug_status_mask = HOTPLUG_INT_STATUS_G4X |
+ DP_AUX_CHANNEL_MASK_INT_STATUS_G4X;
+ else
+ hotplug_status_mask = HOTPLUG_INT_STATUS_I915;
+
+ /*
+ * We absolutely have to clear all the pending interrupt
+ * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port
+ * interrupt bit won't have an edge, and the i965/g4x
+ * edge triggered IIR will not notice that an interrupt
+ * is still pending. We can't use PORT_HOTPLUG_EN to
+ * guarantee the edge as the act of toggling the enable
+ * bits can itself generate a new hotplug interrupt :(
+ */
+ for (i = 0; i < 10; i++) {
+ u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask;
+
+ if (tmp == 0)
+ return hotplug_status;
+
+ hotplug_status |= tmp;
I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+ }
+
+ WARN_ONCE(1,
+ "PORT_HOTPLUG_STAT did not clear (0x%08x)\n",
+ I915_READ(PORT_HOTPLUG_STAT));
return hotplug_status;
}
#define _3D_CHICKEN _MMIO(0x2084)
#define _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB (1 << 10)
#define _3D_CHICKEN2 _MMIO(0x208c)
+
+#define FF_SLICE_CHICKEN _MMIO(0x2088)
+#define FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX (1 << 1)
+
/* Disables pipelining of read flushes past the SF-WIZ interface.
* Required on all Ironlake steppings according to the B-Spec, but the
* particular danger of not doing so is not specified.
*/
# define _3D_CHICKEN2_WM_READ_PIPELINED (1 << 14)
#define _3D_CHICKEN3 _MMIO(0x2090)
+#define _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX (1 << 12)
#define _3D_CHICKEN_SF_DISABLE_OBJEND_CULL (1 << 10)
#define _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE (1 << 5)
#define _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL (1 << 5)
obj->base.size >> PAGE_SHIFT));
vma->size = view->partial.size;
vma->size <<= PAGE_SHIFT;
- GEM_BUG_ON(vma->size >= obj->base.size);
+ GEM_BUG_ON(vma->size > obj->base.size);
} else if (view->type == I915_GGTT_VIEW_ROTATED) {
vma->size = intel_rotation_info_size(&view->rotated);
vma->size <<= PAGE_SHIFT;
int max_dotclk = dev_priv->max_dotclk_freq;
int max_clock;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (mode->clock < 25000)
return MODE_CLOCK_LOW;
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
return true;
}
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_pch_encoder = true;
return true;
struct drm_connector_state *conn_state)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
pipe_config->has_pch_encoder = true;
I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
}
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
- enum transcoder cpu_transcoder)
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
uint32_t val = I915_READ(reg);
val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
val |= TRANS_DDI_PORT_NONE;
I915_WRITE(reg, val);
+
+ if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
+ intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+ DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n");
+ /* Quirk time at 100ms for reliable operation */
+ msleep(100);
+ }
}
int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
intel_ddi_set_vc_payload_alloc(intel_crtc->config, false);
if (!transcoder_is_dsi(cpu_transcoder))
- intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
+ intel_ddi_disable_transcoder_func(old_crtc_state);
if (INTEL_GEN(dev_priv) >= 9)
skylake_scaler_disable(intel_crtc);
intel_mode_valid(struct drm_device *dev,
const struct drm_display_mode *mode)
{
+ /*
+ * Can't reject DBLSCAN here because Xorg ddxen can add piles
+ * of DBLSCAN modes to the output's mode list when they detect
+ * the scaling mode property on the connector. And they don't
+ * ask the kernel to validate those modes in any way until
+ * modeset time at which point the client gets a protocol error.
+ * So in order to not upset those clients we silently ignore the
+ * DBLSCAN flag on such connectors. For other connectors we will
+ * reject modes with the DBLSCAN flag in encoder->compute_config().
+ * And we always reject DBLSCAN modes in connector->mode_valid()
+ * as we never want such modes on the connector's mode list.
+ */
+
if (mode->vscan > 1)
return MODE_NO_VSCAN;
- if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
- return MODE_NO_DBLESCAN;
-
if (mode->flags & DRM_MODE_FLAG_HSKEW)
return MODE_H_ILLEGAL;
DRM_INFO("Applying T12 delay quirk\n");
}
+/*
+ * GeminiLake NUC HDMI outputs require additional off time
+ * this allows the onboard retimer to correctly sync to signal
+ */
+static void quirk_increase_ddi_disabled_time(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+
+ dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME;
+ DRM_INFO("Applying Increase DDI Disabled quirk\n");
+}
+
struct intel_quirk {
int device;
int subsystem_vendor;
/* Toshiba Satellite P50-C-18C */
{ 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay },
+
+ /* GeminiLake NUC */
+ { 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+ { 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+ /* ASRock ITX*/
+ { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+ { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
};
static void intel_init_quirks(struct drm_device *dev)
int max_rate, mode_rate, max_lanes, max_link_clock;
int max_dotclk;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
max_dotclk = intel_dp_downstream_max_dotclock(intel_dp);
if (intel_dp_is_edp(intel_dp) && fixed_mode) {
conn_state->scaling_mode);
}
- if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
+ if (HAS_GMCH_DISPLAY(dev_priv) &&
adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
return false;
static void g4x_disable_dp(struct intel_encoder *encoder,
const struct intel_crtc_state *old_crtc_state,
const struct drm_connector_state *old_conn_state)
-{
- intel_disable_dp(encoder, old_crtc_state, old_conn_state);
-
- /* disable the port before the pipe on g4x */
- intel_dp_link_down(encoder, old_crtc_state);
-}
-
-static void ilk_disable_dp(struct intel_encoder *encoder,
- const struct intel_crtc_state *old_crtc_state,
- const struct drm_connector_state *old_conn_state)
{
intel_disable_dp(encoder, old_crtc_state, old_conn_state);
}
intel_disable_dp(encoder, old_crtc_state, old_conn_state);
}
-static void ilk_post_disable_dp(struct intel_encoder *encoder,
+static void g4x_post_disable_dp(struct intel_encoder *encoder,
const struct intel_crtc_state *old_crtc_state,
const struct drm_connector_state *old_conn_state)
{
struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
enum port port = encoder->port;
+ /*
+ * Bspec does not list a specific disable sequence for g4x DP.
+ * Follow the ilk+ sequence (disable pipe before the port) for
+ * g4x DP as it does not suffer from underruns like the normal
+ * g4x modeset sequence (disable pipe after the port).
+ */
intel_dp_link_down(encoder, old_crtc_state);
/* Only ilk+ has port A */
drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
- if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+ if (!HAS_GMCH_DISPLAY(dev_priv))
connector->interlace_allowed = true;
connector->doublescan_allowed = 0;
intel_encoder->enable = vlv_enable_dp;
intel_encoder->disable = vlv_disable_dp;
intel_encoder->post_disable = vlv_post_disable_dp;
- } else if (INTEL_GEN(dev_priv) >= 5) {
- intel_encoder->pre_enable = g4x_pre_enable_dp;
- intel_encoder->enable = g4x_enable_dp;
- intel_encoder->disable = ilk_disable_dp;
- intel_encoder->post_disable = ilk_post_disable_dp;
} else {
intel_encoder->pre_enable = g4x_pre_enable_dp;
intel_encoder->enable = g4x_enable_dp;
intel_encoder->disable = g4x_disable_dp;
+ intel_encoder->post_disable = g4x_post_disable_dp;
}
intel_dig_port->dp.output_reg = output_reg;
bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
DP_DPCD_QUIRK_LIMITED_M_N);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_pch_encoder = false;
bpp = 24;
if (intel_dp->compliance.test_data.bpc) {
if (!intel_dp)
return MODE_ERROR;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
max_link_clock = intel_dp_max_link_rate(intel_dp);
max_lanes = intel_dp_max_lane_count(intel_dp);
void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state);
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
- enum transcoder cpu_transcoder);
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state);
struct intel_encoder *
conn_state->scaling_mode);
}
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
/* DSI uses short packets for sync events, so clear mode flags for DSI */
adjusted_mode->flags = 0;
DRM_DEBUG_KMS("\n");
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (fixed_mode) {
if (mode->hdisplay > fixed_mode->hdisplay)
return MODE_PANEL;
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
int target_clock = mode->clock;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
/* XXX: Validate clock range */
if (fixed_mode) {
if (fixed_mode)
intel_fixed_panel_mode(fixed_mode, adjusted_mode);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
return true;
}
bool force_dvi =
READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
clock = mode->clock;
if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
int desired_bpp;
bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink;
if (pipe_config->has_hdmi_sink)
/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
batch = gen8_emit_flush_coherentl3_wa(engine, batch);
+ *batch++ = MI_LOAD_REGISTER_IMM(3);
+
/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
- *batch++ = MI_LOAD_REGISTER_IMM(1);
*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
*batch++ = _MASKED_BIT_DISABLE(
GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+
+ /* BSpec: 11391 */
+ *batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
+ *batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+
+ /* BSpec: 11299 */
+ *batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
+ *batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+
*batch++ = MI_NOOP;
/* WaClearSlmSpaceAtContextSwitch:kbl */
context_size += LRC_HEADER_PAGES * PAGE_SIZE;
ctx_obj = i915_gem_object_create(ctx->i915, context_size);
- if (IS_ERR(ctx_obj)) {
- ret = PTR_ERR(ctx_obj);
- goto error_deref_obj;
- }
+ if (IS_ERR(ctx_obj))
+ return PTR_ERR(ctx_obj);
vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
if (IS_ERR(vma)) {
struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
int max_pixclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
if (mode->hdisplay > fixed_mode->hdisplay)
return MODE_PANEL;
if (mode->vdisplay > fixed_mode->vdisplay)
intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
adjusted_mode);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
if (HAS_PCH_SPLIT(dev_priv)) {
pipe_config->has_pch_encoder = true;
adjusted_mode);
}
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
/*
* Make the CRTC code factor in the SDVO pixel multiplier. The
* SDVO device will factor out the multiplier during mode_set.
struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (intel_sdvo->pixel_clock_min > mode->clock)
return MODE_CLOCK_LOW;
const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (mode->clock > max_dotclk)
return MODE_CLOCK_HIGH;
struct drm_connector_state *conn_state)
{
const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
if (!tv_mode)
return false;
- pipe_config->base.adjusted_mode.crtc_clock = tv_mode->clock;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
+ adjusted_mode->crtc_clock = tv_mode->clock;
DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
pipe_config->pipe_bpp = 8*3;
/* TV has it's own notion of sync and other mode flags, so clear them. */
- pipe_config->base.adjusted_mode.flags = 0;
+ adjusted_mode->flags = 0;
/*
* FIXME: We don't check whether the input mode is actually what we want
return PTR_ERR(imx_ldb->regmap);
}
+ /* disable LDB by resetting the control register to POR default */
+ regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0);
+
imx_ldb->dev = dev;
if (of_id)
if (ret || i < 0 || i > 1)
return -EINVAL;
+ if (!of_device_is_available(child))
+ continue;
+
if (dual && i > 0) {
dev_warn(dev, "dual-channel mode, ignoring second output\n");
continue;
}
- if (!of_device_is_available(child))
- continue;
-
channel = &imx_ldb->channel[i];
channel->ldb = imx_ldb;
channel->chno = i;
priv->io_base = regs;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hhi");
- if (!res)
- return -EINVAL;
+ if (!res) {
+ ret = -EINVAL;
+ goto free_drm;
+ }
/* Simply ioremap since it may be a shared register zone */
regs = devm_ioremap(dev, res->start, resource_size(res));
if (!regs) {
}
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dmc");
- if (!res)
- return -EINVAL;
+ if (!res) {
+ ret = -EINVAL;
+ goto free_drm;
+ }
/* Simply ioremap since it may be a shared register zone */
regs = devm_ioremap(dev, res->start, resource_size(res));
if (!regs) {
nouveau_display(dev)->init = nv04_display_init;
nouveau_display(dev)->fini = nv04_display_fini;
+ /* Pre-nv50 doesn't support atomic, so don't expose the ioctls */
+ dev->driver->driver_features &= ~DRIVER_ATOMIC;
+
nouveau_hw_save_vga_fonts(dev, 1);
nv04_crtc_create(dev, 0);
nvif_object_map(&wndw->wimm.base.user, NULL, 0);
wndw->immd = func;
- wndw->ctxdma.parent = &disp->core->chan.base.user;
+ wndw->ctxdma.parent = NULL;
return 0;
}
*****************************************************************************/
static void
-nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
+nv50_disp_atomic_commit_core(struct drm_atomic_state *state, u32 *interlock)
{
+ struct nouveau_drm *drm = nouveau_drm(state->dev);
struct nv50_disp *disp = nv50_disp(drm->dev);
struct nv50_core *core = disp->core;
struct nv50_mstm *mstm;
}
}
+static void
+nv50_disp_atomic_commit_wndw(struct drm_atomic_state *state, u32 *interlock)
+{
+ struct drm_plane_state *new_plane_state;
+ struct drm_plane *plane;
+ int i;
+
+ for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+ struct nv50_wndw *wndw = nv50_wndw(plane);
+ if (interlock[wndw->interlock.type] & wndw->interlock.data) {
+ if (wndw->func->update)
+ wndw->func->update(wndw, interlock);
+ }
+ }
+}
+
static void
nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
{
help->disable(encoder);
interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
if (outp->flush_disable) {
- nv50_disp_atomic_commit_core(drm, interlock);
+ nv50_disp_atomic_commit_wndw(state, interlock);
+ nv50_disp_atomic_commit_core(state, interlock);
memset(interlock, 0x00, sizeof(interlock));
}
}
/* Flush disable. */
if (interlock[NV50_DISP_INTERLOCK_CORE]) {
if (atom->flush_disable) {
- for_each_new_plane_in_state(state, plane, new_plane_state, i) {
- struct nv50_wndw *wndw = nv50_wndw(plane);
- if (interlock[wndw->interlock.type] & wndw->interlock.data) {
- if (wndw->func->update)
- wndw->func->update(wndw, interlock);
- }
- }
-
- nv50_disp_atomic_commit_core(drm, interlock);
+ nv50_disp_atomic_commit_wndw(state, interlock);
+ nv50_disp_atomic_commit_core(state, interlock);
memset(interlock, 0x00, sizeof(interlock));
}
}
}
/* Flush update. */
- for_each_new_plane_in_state(state, plane, new_plane_state, i) {
- struct nv50_wndw *wndw = nv50_wndw(plane);
- if (interlock[wndw->interlock.type] & wndw->interlock.data) {
- if (wndw->func->update)
- wndw->func->update(wndw, interlock);
- }
- }
+ nv50_disp_atomic_commit_wndw(state, interlock);
if (interlock[NV50_DISP_INTERLOCK_CORE]) {
if (interlock[NV50_DISP_INTERLOCK_BASE] ||
+ interlock[NV50_DISP_INTERLOCK_OVLY] ||
+ interlock[NV50_DISP_INTERLOCK_WNDW] ||
!atom->state.legacy_cursor_update)
- nv50_disp_atomic_commit_core(drm, interlock);
+ nv50_disp_atomic_commit_core(state, interlock);
else
disp->core->func->update(disp->core, interlock, false);
}
nv50_disp_atomic_commit_tail(state);
drm_for_each_crtc(crtc, dev) {
- if (crtc->state->enable) {
+ if (crtc->state->active) {
if (!drm->have_disp_power_ref) {
drm->have_disp_power_ref = true;
return 0;
kfree(disp);
}
-MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
-static int nouveau_atomic = 0;
-module_param_named(atomic, nouveau_atomic, int, 0400);
-
int
nv50_display_create(struct drm_device *dev)
{
disp->disp = &nouveau_display(dev)->disp;
dev->mode_config.funcs = &nv50_disp_func;
dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
- if (nouveau_atomic)
- dev->driver->driver_features |= DRIVER_ATOMIC;
/* small shared memory area we use for notifiers and semaphores */
ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
if (ret)
return ret;
- ctxdma = nv50_wndw_ctxdma_new(wndw, fb);
- if (IS_ERR(ctxdma)) {
- nouveau_bo_unpin(fb->nvbo);
- return PTR_ERR(ctxdma);
+ if (wndw->ctxdma.parent) {
+ ctxdma = nv50_wndw_ctxdma_new(wndw, fb);
+ if (IS_ERR(ctxdma)) {
+ nouveau_bo_unpin(fb->nvbo);
+ return PTR_ERR(ctxdma);
+ }
+
+ asyw->image.handle[0] = ctxdma->object.handle;
}
asyw->state.fence = reservation_object_get_excl_rcu(fb->nvbo->bo.resv);
- asyw->image.handle[0] = ctxdma->object.handle;
asyw->image.offset[0] = fb->nvbo->bo.offset;
if (wndw->func->prepare) {
struct nouveau_drm *drm = nouveau_drm(dev);
struct nvif_device *device = &drm->client.device;
struct drm_connector *connector;
+ struct drm_connector_list_iter conn_iter;
INIT_LIST_HEAD(&drm->bl_connectors);
return 0;
}
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ drm_for_each_connector_iter(connector, &conn_iter) {
if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS &&
connector->connector_type != DRM_MODE_CONNECTOR_eDP)
continue;
break;
}
}
-
+ drm_connector_list_iter_end(&conn_iter);
return 0;
}
struct nouveau_display *disp = nouveau_display(dev);
struct nouveau_connector *nv_connector = NULL;
struct drm_connector *connector;
+ struct drm_connector_list_iter conn_iter;
int type, ret = 0;
bool dummy;
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
nv_connector = nouveau_connector(connector);
- if (nv_connector->index == index)
+ if (nv_connector->index == index) {
+ drm_connector_list_iter_end(&conn_iter);
return connector;
+ }
}
+ drm_connector_list_iter_end(&conn_iter);
nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL);
if (!nv_connector)
#include <drm/drm_encoder.h>
#include <drm/drm_dp_helper.h>
#include "nouveau_crtc.h"
+#include "nouveau_encoder.h"
struct nvkm_i2c_port;
return container_of(con, struct nouveau_connector, base);
}
+static inline bool
+nouveau_connector_is_mst(struct drm_connector *connector)
+{
+ const struct nouveau_encoder *nv_encoder;
+ const struct drm_encoder *encoder;
+
+ if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
+ return false;
+
+ nv_encoder = find_encoder(connector, DCB_OUTPUT_ANY);
+ if (!nv_encoder)
+ return false;
+
+ encoder = &nv_encoder->base.base;
+ return encoder->encoder_type == DRM_MODE_ENCODER_DPMST;
+}
+
+#define nouveau_for_each_non_mst_connector_iter(connector, iter) \
+ drm_for_each_connector_iter(connector, iter) \
+ for_each_if(!nouveau_connector_is_mst(connector))
+
static inline struct nouveau_connector *
nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc)
{
struct drm_device *dev = nv_crtc->base.dev;
struct drm_connector *connector;
+ struct drm_connector_list_iter conn_iter;
+ struct nouveau_connector *nv_connector = NULL;
struct drm_crtc *crtc = to_drm_crtc(nv_crtc);
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
- if (connector->encoder && connector->encoder->crtc == crtc)
- return nouveau_connector(connector);
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
+ if (connector->encoder && connector->encoder->crtc == crtc) {
+ nv_connector = nouveau_connector(connector);
+ break;
+ }
}
+ drm_connector_list_iter_end(&conn_iter);
- return NULL;
+ return nv_connector;
}
struct drm_connector *
struct nouveau_display *disp = nouveau_display(dev);
struct nouveau_drm *drm = nouveau_drm(dev);
struct drm_connector *connector;
+ struct drm_connector_list_iter conn_iter;
int ret;
ret = disp->init(dev);
return ret;
/* enable hotplug interrupts */
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
struct nouveau_connector *conn = nouveau_connector(connector);
nvif_notify_get(&conn->hpd);
}
+ drm_connector_list_iter_end(&conn_iter);
/* enable flip completion events */
nvif_notify_get(&drm->flip);
struct nouveau_display *disp = nouveau_display(dev);
struct nouveau_drm *drm = nouveau_drm(dev);
struct drm_connector *connector;
+ struct drm_connector_list_iter conn_iter;
if (!suspend) {
if (drm_drv_uses_atomic_modeset(dev))
nvif_notify_put(&drm->flip);
/* disable hotplug interrupts */
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
struct nouveau_connector *conn = nouveau_connector(connector);
nvif_notify_put(&conn->hpd);
}
+ drm_connector_list_iter_end(&conn_iter);
drm_kms_helper_poll_disable(dev);
disp->fini(dev);
int nouveau_modeset = -1;
module_param_named(modeset, nouveau_modeset, int, 0400);
+MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
+static int nouveau_atomic = 0;
+module_param_named(atomic, nouveau_atomic, int, 0400);
+
MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
static int nouveau_runtime_pm = -1;
module_param_named(runpm, nouveau_runtime_pm, int, 0400);
pci_set_master(pdev);
+ if (nouveau_atomic)
+ driver_pci.driver_features |= DRIVER_ATOMIC;
+
ret = drm_get_pci_dev(pdev, pent, &driver_pci);
if (ret) {
nvkm_device_del(&device);
static int
nouveau_pmops_runtime_idle(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct drm_device *drm_dev = pci_get_drvdata(pdev);
- struct nouveau_drm *drm = nouveau_drm(drm_dev);
- struct drm_crtc *crtc;
-
if (!nouveau_pmops_runtime()) {
pm_runtime_forbid(dev);
return -EBUSY;
}
- list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) {
- if (crtc->enabled) {
- DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
- return -EBUSY;
- }
- }
pm_runtime_mark_last_busy(dev);
pm_runtime_autosuspend(dev);
/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
struct nouveau_bo *nvbo;
uint32_t data;
- if (unlikely(r->bo_index > req->nr_buffers)) {
+ if (unlikely(r->bo_index >= req->nr_buffers)) {
NV_PRINTK(err, cli, "reloc bo index invalid\n");
ret = -EINVAL;
break;
if (b->presumed.valid)
continue;
- if (unlikely(r->reloc_bo_index > req->nr_buffers)) {
+ if (unlikely(r->reloc_bo_index >= req->nr_buffers)) {
NV_PRINTK(err, cli, "reloc container bo index invalid\n");
ret = -EINVAL;
break;
if (fb->func->init)
fb->func->init(fb);
+ if (fb->func->init_remapper)
+ fb->func->init_remapper(fb);
+
if (fb->func->init_page) {
ret = fb->func->init_page(fb);
if (WARN_ON(ret))
nvkm_wr32(device, 0x1faccc, nvkm_rd32(device, 0x100ccc));
}
+void
+gp100_fb_init_remapper(struct nvkm_fb *fb)
+{
+ struct nvkm_device *device = fb->subdev.device;
+ /* Disable address remapper. */
+ nvkm_mask(device, 0x100c14, 0x00040000, 0x00000000);
+}
+
void
gp100_fb_init(struct nvkm_fb *base)
{
.dtor = gf100_fb_dtor,
.oneinit = gf100_fb_oneinit,
.init = gp100_fb_init,
+ .init_remapper = gp100_fb_init_remapper,
.init_page = gm200_fb_init_page,
.init_unkn = gp100_fb_init_unkn,
.ram_new = gp100_ram_new,
.dtor = gf100_fb_dtor,
.oneinit = gf100_fb_oneinit,
.init = gp100_fb_init,
+ .init_remapper = gp100_fb_init_remapper,
.init_page = gm200_fb_init_page,
.ram_new = gp100_ram_new,
};
u32 (*tags)(struct nvkm_fb *);
int (*oneinit)(struct nvkm_fb *);
void (*init)(struct nvkm_fb *);
+ void (*init_remapper)(struct nvkm_fb *);
int (*init_page)(struct nvkm_fb *);
void (*init_unkn)(struct nvkm_fb *);
void (*intr)(struct nvkm_fb *);
int gm200_fb_init_page(struct nvkm_fb *);
+void gp100_fb_init_remapper(struct nvkm_fb *);
void gp100_fb_init_unkn(struct nvkm_fb *);
#endif
struct qxl_cursor_cmd *cmd;
struct qxl_cursor *cursor;
struct drm_gem_object *obj;
- struct qxl_bo *cursor_bo = NULL, *user_bo = NULL;
+ struct qxl_bo *cursor_bo = NULL, *user_bo = NULL, *old_cursor_bo = NULL;
int ret;
void *user_ptr;
int size = 64*64*4;
cursor_bo, 0);
cmd->type = QXL_CURSOR_SET;
- qxl_bo_unref(&qcrtc->cursor_bo);
+ old_cursor_bo = qcrtc->cursor_bo;
qcrtc->cursor_bo = cursor_bo;
cursor_bo = NULL;
} else {
qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
qxl_release_fence_buffer_objects(release);
+ if (old_cursor_bo)
+ qxl_bo_unref(&old_cursor_bo);
+
qxl_bo_unref(&cursor_bo);
return;
struct dma_fence * fence = entity->dependency;
struct drm_sched_fence *s_fence;
- if (fence->context == entity->fence_context) {
- /* We can ignore fences from ourself */
+ if (fence->context == entity->fence_context ||
+ fence->context == entity->fence_context + 1) {
+ /*
+ * Fence is a scheduled/finished fence from a job
+ * which belongs to the same entity, we can ignore
+ * fences from ourself
+ */
dma_fence_put(entity->dependency);
return false;
}
tristate "DRM Support for SH Mobile"
depends on DRM && ARM
depends on ARCH_SHMOBILE || COMPILE_TEST
- depends on FB_SH_MOBILE_MERAM || !FB_SH_MOBILE_MERAM
select BACKLIGHT_CLASS_DEVICE
select BACKLIGHT_LCD_SUPPORT
select DRM_KMS_HELPER
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_plane_helper.h>
-#include <video/sh_mobile_meram.h>
-
#include "shmob_drm_backlight.h"
#include "shmob_drm_crtc.h"
#include "shmob_drm_drv.h"
if (ret < 0)
return ret;
}
-#if 0
- if (sdev->meram_dev && sdev->meram_dev->pdev)
- pm_runtime_get_sync(&sdev->meram_dev->pdev->dev);
-#endif
return 0;
}
static void shmob_drm_clk_off(struct shmob_drm_device *sdev)
{
-#if 0
- if (sdev->meram_dev && sdev->meram_dev->pdev)
- pm_runtime_put_sync(&sdev->meram_dev->pdev->dev);
-#endif
if (sdev->clock)
clk_disable_unprepare(sdev->clock);
}
if (!scrtc->started)
return;
- /* Disable the MERAM cache. */
- if (scrtc->cache) {
- sh_mobile_meram_cache_free(sdev->meram, scrtc->cache);
- scrtc->cache = NULL;
- }
-
/* Stop the LCDC. */
shmob_drm_crtc_start_stop(scrtc, false);
{
struct drm_crtc *crtc = &scrtc->crtc;
struct drm_framebuffer *fb = crtc->primary->fb;
- struct shmob_drm_device *sdev = crtc->dev->dev_private;
struct drm_gem_cma_object *gem;
unsigned int bpp;
+ y / (bpp == 4 ? 2 : 1) * fb->pitches[1]
+ x * (bpp == 16 ? 2 : 1);
}
-
- if (scrtc->cache)
- sh_mobile_meram_cache_update(sdev->meram, scrtc->cache,
- scrtc->dma[0], scrtc->dma[1],
- &scrtc->dma[0], &scrtc->dma[1]);
}
static void shmob_drm_crtc_update_base(struct shmob_drm_crtc *scrtc)
{
struct shmob_drm_crtc *scrtc = to_shmob_crtc(crtc);
struct shmob_drm_device *sdev = crtc->dev->dev_private;
- const struct sh_mobile_meram_cfg *mdata = sdev->pdata->meram;
const struct shmob_drm_format_info *format;
- void *cache;
format = shmob_drm_format_info(crtc->primary->fb->format->format);
if (format == NULL) {
scrtc->format = format;
scrtc->line_size = crtc->primary->fb->pitches[0];
- if (sdev->meram) {
- /* Enable MERAM cache if configured. We need to de-init
- * configured ICBs before we can re-initialize them.
- */
- if (scrtc->cache) {
- sh_mobile_meram_cache_free(sdev->meram, scrtc->cache);
- scrtc->cache = NULL;
- }
-
- cache = sh_mobile_meram_cache_alloc(sdev->meram, mdata,
- crtc->primary->fb->pitches[0],
- adjusted_mode->vdisplay,
- format->meram,
- &scrtc->line_size);
- if (!IS_ERR(cache))
- scrtc->cache = cache;
- }
-
shmob_drm_crtc_compute_base(scrtc, x, y);
return 0;
int dpms;
const struct shmob_drm_format_info *format;
- void *cache;
unsigned long dma[2];
unsigned int line_size;
bool started;
struct clk;
struct device;
struct drm_device;
-struct sh_mobile_meram_info;
struct shmob_drm_device {
struct device *dev;
void __iomem *mmio;
struct clk *clock;
- struct sh_mobile_meram_info *meram;
u32 lddckr;
u32 ldmt1r;
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_gem_framebuffer_helper.h>
-#include <video/sh_mobile_meram.h>
-
#include "shmob_drm_crtc.h"
#include "shmob_drm_drv.h"
#include "shmob_drm_kms.h"
.bpp = 16,
.yuv = false,
.lddfr = LDDFR_PKF_RGB16,
- .meram = SH_MOBILE_MERAM_PF_RGB,
}, {
.fourcc = DRM_FORMAT_RGB888,
.bpp = 24,
.yuv = false,
.lddfr = LDDFR_PKF_RGB24,
- .meram = SH_MOBILE_MERAM_PF_RGB,
}, {
.fourcc = DRM_FORMAT_ARGB8888,
.bpp = 32,
.yuv = false,
.lddfr = LDDFR_PKF_ARGB32,
- .meram = SH_MOBILE_MERAM_PF_RGB,
}, {
.fourcc = DRM_FORMAT_NV12,
.bpp = 12,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_420,
- .meram = SH_MOBILE_MERAM_PF_NV,
}, {
.fourcc = DRM_FORMAT_NV21,
.bpp = 12,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_420,
- .meram = SH_MOBILE_MERAM_PF_NV,
}, {
.fourcc = DRM_FORMAT_NV16,
.bpp = 16,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_422,
- .meram = SH_MOBILE_MERAM_PF_NV,
}, {
.fourcc = DRM_FORMAT_NV61,
.bpp = 16,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_422,
- .meram = SH_MOBILE_MERAM_PF_NV,
}, {
.fourcc = DRM_FORMAT_NV24,
.bpp = 24,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_444,
- .meram = SH_MOBILE_MERAM_PF_NV24,
}, {
.fourcc = DRM_FORMAT_NV42,
.bpp = 24,
.yuv = true,
.lddfr = LDDFR_CC | LDDFR_YF_444,
- .meram = SH_MOBILE_MERAM_PF_NV24,
},
};
unsigned int bpp;
bool yuv;
u32 lddfr;
- unsigned int meram;
};
const struct shmob_drm_format_info *shmob_drm_format_info(u32 fourcc);
#include <drm/drm_fb_cma_helper.h>
#include <drm/drm_gem_cma_helper.h>
-#include <video/sh_mobile_meram.h>
-
#include "shmob_drm_drv.h"
#include "shmob_drm_kms.h"
#include "shmob_drm_plane.h"
obj-$(CONFIG_DRM_SUN4I) += sun4i_tv.o
obj-$(CONFIG_DRM_SUN4I) += sun6i_drc.o
-obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o sun4i-frontend.o
+obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o
+ifdef CONFIG_DRM_SUN4I_BACKEND
+obj-$(CONFIG_DRM_SUN4I) += sun4i-frontend.o
+endif
obj-$(CONFIG_DRM_SUN4I_HDMI) += sun4i-drm-hdmi.o
obj-$(CONFIG_DRM_SUN6I_DSI) += sun6i-dsi.o
obj-$(CONFIG_DRM_SUN8I_DW_HDMI) += sun8i-drm-hdmi.o
#include <drm/drm_encoder.h>
#include <drm/drm_modes.h>
#include <drm/drm_of.h>
-#include <drm/drm_panel.h>
#include <uapi/drm/drm_mode.h>
static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
const struct drm_display_mode *mode)
{
- struct drm_panel *panel = tcon->panel;
- struct drm_connector *connector = panel->connector;
- struct drm_display_info display_info = connector->display_info;
unsigned int bp, hsync, vsync;
u8 clk_delay;
u32 val = 0;
if (mode->flags & DRM_MODE_FLAG_PVSYNC)
val |= SUN4I_TCON0_IO_POL_VSYNC_POSITIVE;
- /*
- * On A20 and similar SoCs, the only way to achieve Positive Edge
- * (Rising Edge), is setting dclk clock phase to 2/3(240°).
- * By default TCON works in Negative Edge(Falling Edge),
- * this is why phase is set to 0 in that case.
- * Unfortunately there's no way to logically invert dclk through
- * IO_POL register.
- * The only acceptable way to work, triple checked with scope,
- * is using clock phase set to 0° for Negative Edge and set to 240°
- * for Positive Edge.
- * On A33 and similar SoCs there would be a 90° phase option,
- * but it divides also dclk by 2.
- * Following code is a way to avoid quirks all around TCON
- * and DOTCLOCK drivers.
- */
- if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
- clk_set_phase(tcon->dclk, 240);
-
- if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
- clk_set_phase(tcon->dclk, 0);
-
regmap_update_bits(tcon->regs, SUN4I_TCON0_IO_POL_REG,
SUN4I_TCON0_IO_POL_HSYNC_POSITIVE | SUN4I_TCON0_IO_POL_VSYNC_POSITIVE,
val);
* unaligned offset is malformed and cause commands stream
* corruption on the buffer address relocation.
*/
- if (offset & 3 || offset >= obj->gem.size) {
+ if (offset & 3 || offset > obj->gem.size) {
err = -EINVAL;
goto fail;
}
if (cmd > (char *) urb->transfer_buffer) {
/* Send partial buffer remaining before exiting */
- int len = cmd - (char *) urb->transfer_buffer;
+ int len;
+ if (cmd < (char *) urb->transfer_buffer + urb->transfer_buffer_length)
+ *cmd++ = 0xAF;
+ len = cmd - (char *) urb->transfer_buffer;
ret = udl_submit_urb(dev, urb, len);
bytes_sent += len;
} else
raw_pixels_count_byte = cmd++; /* we'll know this later */
raw_pixel_start = pixel;
- cmd_pixel_end = pixel + (min(MAX_CMD_PIXELS + 1,
- min((int)(pixel_end - pixel) / bpp,
- (int)(cmd_buffer_end - cmd) / 2))) * bpp;
+ cmd_pixel_end = pixel + min3(MAX_CMD_PIXELS + 1UL,
+ (unsigned long)(pixel_end - pixel) / bpp,
+ (unsigned long)(cmd_buffer_end - 1 - cmd) / 2) * bpp;
- prefetch_range((void *) pixel, (cmd_pixel_end - pixel) * bpp);
+ prefetch_range((void *) pixel, cmd_pixel_end - pixel);
pixel_val16 = get_pixel_val16(pixel, bpp);
while (pixel < cmd_pixel_end) {
if (pixel > raw_pixel_start) {
/* finalize last RAW span */
*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
+ } else {
+ /* undo unused byte */
+ cmd--;
}
*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
vc4_state->x_scaling[0] = VC4_SCALING_TPZ;
if (vc4_state->y_scaling[0] == VC4_SCALING_NONE)
vc4_state->y_scaling[0] = VC4_SCALING_TPZ;
+ } else {
+ vc4_state->x_scaling[1] = VC4_SCALING_NONE;
+ vc4_state->y_scaling[1] = VC4_SCALING_NONE;
}
vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE &&
return err;
}
+ if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+ goto skip_iommu;
+
host->group = iommu_group_get(&pdev->dev);
if (host->group) {
struct iommu_domain_geometry *geometry;
for (i = 0; i < job->num_unpins; i++) {
struct host1x_job_unpin_data *unpin = &job->unpins[i];
- if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) {
+ if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) &&
+ unpin->size && host->domain) {
iommu_unmap(host->domain, job->addr_phys[i],
unpin->size);
free_iova(&host->iova,
break;
case V4L2_MBUS_BT656:
csicfg->ext_vsync = 0;
- if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field))
+ if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) ||
+ mbus_fmt->field == V4L2_FIELD_ALTERNATE)
csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED;
else
csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE;
Some "legacy" VGA devices implemented on PCI typically have the same
hard-decoded addresses as they did on ISA. When multiple PCI devices
are accessed at same time they need some kind of coordination. Please
- see Documentation/vgaarbiter.txt for more details. Select this to
+ see Documentation/gpu/vgaarbiter.rst for more details. Select this to
enable VGA arbiter.
config VGA_ARB_MAX_GPUS
/*
* vgaarb.c: Implements the VGA arbitration. For details refer to
- * Documentation/vgaarbiter.txt
+ * Documentation/gpu/vgaarbiter.rst
*
*
* (C) Copyright 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>
}
hdev->io_started = false;
+ clear_bit(ffs(HID_STAT_REPROBED), &hdev->status);
+
if (!hdev->driver) {
id = hid_match_device(hdev, hdrv);
if (id == NULL) {
struct hid_device *hdev = to_hid_device(dev);
if (hdev->driver == hdrv &&
- !hdrv->match(hdev, hid_ignore_special_drivers))
+ !hdrv->match(hdev, hid_ignore_special_drivers) &&
+ !test_and_set_bit(ffs(HID_STAT_REPROBED), &hdev->status))
return device_reprobe(dev);
return 0;
goto out;
if (list->tail > list->head) {
len = list->tail - list->head;
+ if (len > count)
+ len = count;
if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) {
ret = -EFAULT;
list->head += len;
} else {
len = HID_DEBUG_BUFSIZE - list->head;
+ if (len > count)
+ len = count;
if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) {
ret = -EFAULT;
}
list->head = 0;
ret += len;
- goto copy_rest;
+ count -= len;
+ if (count > 0)
+ goto copy_rest;
}
}
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) },
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WHISKERS) },
{ }
};
MODULE_DEVICE_TABLE(hid, hammer_devices);
#define USB_DEVICE_ID_GOOGLE_TOUCH_ROSE 0x5028
#define USB_DEVICE_ID_GOOGLE_STAFF 0x502b
#define USB_DEVICE_ID_GOOGLE_WAND 0x502d
+#define USB_DEVICE_ID_GOOGLE_WHISKERS 0x5030
#define USB_VENDOR_ID_GOTOP 0x08f2
#define USB_DEVICE_ID_SUPER_Q2 0x007f
static int steam_client_ll_parse(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
return hid_parse_report(hdev, steam->hdev->dev_rdesc,
steam->hdev->dev_rsize);
static int steam_client_ll_open(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
int ret;
ret = hid_hw_open(steam->hdev);
static void steam_client_ll_close(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
mutex_lock(&steam->mutex);
steam->client_opened = false;
size_t count, unsigned char report_type,
int reqtype)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
return hid_hw_raw_request(steam->hdev, reportnum, buf, count,
report_type, reqtype);
ret = PTR_ERR(steam->client_hdev);
goto client_hdev_fail;
}
- hid_set_drvdata(steam->client_hdev, steam);
+ steam->client_hdev->driver_data = steam;
/*
* With the real steam controller interface, do not connect hidraw.
return;
}
- if ((ret_size > size) || (ret_size <= 2)) {
+ if ((ret_size > size) || (ret_size < 2)) {
dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
__func__, size, ret_size);
return;
kfree(ishtp_dev);
}
-#ifdef CONFIG_PM
-static struct device *ish_resume_device;
+static struct device __maybe_unused *ish_resume_device;
/* 50ms to get resume response */
#define WAIT_FOR_RESUME_ACK_MS 50
* in that case a simple resume message is enough, others we need
* a reset sequence.
*/
-static void ish_resume_handler(struct work_struct *work)
+static void __maybe_unused ish_resume_handler(struct work_struct *work)
{
struct pci_dev *pdev = to_pci_dev(ish_resume_device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
*
* Return: 0 to the pm core
*/
-static int ish_suspend(struct device *device)
+static int __maybe_unused ish_suspend(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
return 0;
}
-static DECLARE_WORK(resume_work, ish_resume_handler);
+static __maybe_unused DECLARE_WORK(resume_work, ish_resume_handler);
/**
* ish_resume() - ISH resume callback
* @device: device pointer
*
* Return: 0 to the pm core
*/
-static int ish_resume(struct device *device)
+static int __maybe_unused ish_resume(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
return 0;
}
-static const struct dev_pm_ops ish_pm_ops = {
- .suspend = ish_suspend,
- .resume = ish_resume,
-};
-#define ISHTP_ISH_PM_OPS (&ish_pm_ops)
-#else
-#define ISHTP_ISH_PM_OPS NULL
-#endif /* CONFIG_PM */
+static SIMPLE_DEV_PM_OPS(ish_pm_ops, ish_suspend, ish_resume);
static struct pci_driver ish_driver = {
.name = KBUILD_MODNAME,
.id_table = ish_pci_tbl,
.probe = ish_probe,
.remove = ish_remove,
- .driver.pm = ISHTP_ISH_PM_OPS,
+ .driver.pm = &ish_pm_ops,
};
module_pci_driver(ish_driver);
You can't use this driver and the HIDBP (Boot Protocol) keyboard
and mouse drivers at the same time. More information is available:
- <file:Documentation/input/input.txt>.
+ <file:Documentation/input/input.rst>.
If unsure, say Y.
#include <linux/hiddev.h>
#include <linux/compat.h>
#include <linux/vmalloc.h>
+#include <linux/nospec.h>
#include "usbhid.h"
#ifdef CONFIG_USB_DYNAMIC_MINORS
if (uref->field_index >= report->maxfield)
goto inval;
+ uref->field_index = array_index_nospec(uref->field_index,
+ report->maxfield);
field = report->field[uref->field_index];
if (uref->usage_index >= field->maxusage)
goto inval;
+ uref->usage_index = array_index_nospec(uref->usage_index,
+ field->maxusage);
uref->usage_code = field->usage[uref->usage_index].hid;
if (uref->field_index >= report->maxfield)
goto inval;
+ uref->field_index = array_index_nospec(uref->field_index,
+ report->maxfield);
field = report->field[uref->field_index];
if (finfo.field_index >= report->maxfield)
break;
+ finfo.field_index = array_index_nospec(finfo.field_index,
+ report->maxfield);
field = report->field[finfo.field_index];
memset(&finfo, 0, sizeof(finfo));
if (cinfo.index >= hid->maxcollection)
break;
+ cinfo.index = array_index_nospec(cinfo.index,
+ hid->maxcollection);
cinfo.type = hid->collection[cinfo.index].type;
cinfo.usage = hid->collection[cinfo.index].usage;
}
}
+ /* 2nd-generation Intuos Pro Large has incorrect Y maximum */
+ if (hdev->vendor == USB_VENDOR_ID_WACOM &&
+ hdev->product == 0x0358 &&
+ WACOM_PEN_FIELD(field) &&
+ wacom_equivalent_usage(usage->hid) == HID_GD_Y) {
+ field->logical_maximum = 43200;
+ }
+
switch (usage->hid) {
case HID_GD_X:
features->x_max = field->logical_maximum;
if (features->type >= INTUOSHT && features->type <= BAMBOO_PT)
features->device_type |= WACOM_DEVICETYPE_PAD;
- features->x_max = 4096;
- features->y_max = 4096;
+ if (features->type == INTUOSHT2) {
+ features->x_max = features->x_max / 10;
+ features->y_max = features->y_max / 10;
+ }
+ else {
+ features->x_max = 4096;
+ features->y_max = 4096;
+ }
}
else if (features->pktlen == WACOM_PKGLEN_BBTOUCH) {
features->device_type |= WACOM_DEVICETYPE_PAD;
This driver can also be built as a module. If so, the module
will be called mcp3021.
+config SENSORS_MLXREG_FAN
+ tristate "Mellanox Mellanox FAN driver"
+ depends on MELLANOX_PLATFORM
+ imply THERMAL
+ select REGMAP
+ help
+ This option enables support for the FAN control on the Mellanox
+ Ethernet and InfiniBand switches. The driver can be activated by the
+ platform device add call. Say Y to enable these. To compile this
+ driver as a module, choose 'M' here: the module will be called
+ mlxreg-fan.
+
config SENSORS_TC654
tristate "Microchip TC654/TC655 and compatibles"
depends on I2C
This driver can also be built as a module. If so, the module
will be called nct7904.
+config SENSORS_NPCM7XX
+ tristate "Nuvoton NPCM750 and compatible PWM and Fan controllers"
+ imply THERMAL
+ help
+ This driver provides support for Nuvoton NPCM750/730/715/705 PWM
+ and Fan controllers.
+
+ This driver can also be built as a module. If so, the module
+ will be called npcm750-pwm-fan.
+
config SENSORS_NSA320
tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
depends on GPIOLIB && OF
obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
obj-$(CONFIG_SENSORS_MCP3021) += mcp3021.o
obj-$(CONFIG_SENSORS_TC654) += tc654.o
+obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o
obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
obj-$(CONFIG_SENSORS_NCT6683) += nct6683.o
obj-$(CONFIG_SENSORS_NCT6775) += nct6775.o
obj-$(CONFIG_SENSORS_NCT7802) += nct7802.o
obj-$(CONFIG_SENSORS_NCT7904) += nct7904.o
+obj-$(CONFIG_SENSORS_NPCM7XX) += npcm750-pwm-fan.o
obj-$(CONFIG_SENSORS_NSA320) += nsa320-hwmon.o
obj-$(CONFIG_SENSORS_NTC_THERMISTOR) += ntc_thermistor.o
obj-$(CONFIG_SENSORS_PC87360) += pc87360.o
struct mutex lock;
unsigned long measure_updated;
- unsigned long limits_updated;
- char valid;
+ bool valid;
u8 config4;
u8 config5;
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
unsigned short val;
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
switch (sattr->nr) {
case ALARM:
return sprintf(buf, "%d\n",
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
int out;
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
switch (sattr->nr) {
case HYSTERSIS:
mutex_lock(&data->lock);
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
int out, val;
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
mutex_lock(&data->lock);
out = (data->range[sattr->index] >> 4) & 0x0F;
val = reg2temp(data, data->temp[AUTOMIN][sattr->index]);
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
int out;
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
if (sattr->nr == ALARM)
out = (data->alarms >> (sattr->index + 10)) & 1;
else
struct adt7475_data *data = adt7475_update_device(dev);
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
return sprintf(buf, "%d\n", data->pwm[sattr->nr][sattr->index]);
}
struct adt7475_data *data = adt7475_update_device(dev);
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
return sprintf(buf, "%d\n", data->pwmchan[sattr->index]);
}
struct adt7475_data *data = adt7475_update_device(dev);
struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
return sprintf(buf, "%d\n", data->pwmctl[sattr->index]);
}
int i = clamp_val(data->range[sattr->index] & 0xf, 0,
ARRAY_SIZE(pwmfreq_table) - 1);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
return sprintf(buf, "%d\n", pwmfreq_table[i]);
}
struct device_attribute *devattr, char *buf)
{
struct adt7475_data *data = adt7475_update_device(dev);
+
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
}
+static int adt7475_update_limits(struct i2c_client *client)
+{
+ struct adt7475_data *data = i2c_get_clientdata(client);
+ int i;
+ int ret;
+
+ ret = adt7475_read(REG_CONFIG4);
+ if (ret < 0)
+ return ret;
+ data->config4 = ret;
+
+ ret = adt7475_read(REG_CONFIG5);
+ if (ret < 0)
+ return ret;
+ data->config5 = ret;
+
+ for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+ if (!(data->has_voltage & (1 << i)))
+ continue;
+ /* Adjust values so they match the input precision */
+ ret = adt7475_read(VOLTAGE_MIN_REG(i));
+ if (ret < 0)
+ return ret;
+ data->voltage[MIN][i] = ret << 2;
+
+ ret = adt7475_read(VOLTAGE_MAX_REG(i));
+ if (ret < 0)
+ return ret;
+ data->voltage[MAX][i] = ret << 2;
+ }
+
+ if (data->has_voltage & (1 << 5)) {
+ ret = adt7475_read(REG_VTT_MIN);
+ if (ret < 0)
+ return ret;
+ data->voltage[MIN][5] = ret << 2;
+
+ ret = adt7475_read(REG_VTT_MAX);
+ if (ret < 0)
+ return ret;
+ data->voltage[MAX][5] = ret << 2;
+ }
+
+ for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+ /* Adjust values so they match the input precision */
+ ret = adt7475_read(TEMP_MIN_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[MIN][i] = ret << 2;
+
+ ret = adt7475_read(TEMP_MAX_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[MAX][i] = ret << 2;
+
+ ret = adt7475_read(TEMP_TMIN_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[AUTOMIN][i] = ret << 2;
+
+ ret = adt7475_read(TEMP_THERM_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[THERM][i] = ret << 2;
+
+ ret = adt7475_read(TEMP_OFFSET_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[OFFSET][i] = ret;
+ }
+ adt7475_read_hystersis(client);
+
+ for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+ if (i == 3 && !data->has_fan4)
+ continue;
+ ret = adt7475_read_word(client, TACH_MIN_REG(i));
+ if (ret < 0)
+ return ret;
+ data->tach[MIN][i] = ret;
+ }
+
+ for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+ if (i == 1 && !data->has_pwm2)
+ continue;
+ ret = adt7475_read(PWM_MAX_REG(i));
+ if (ret < 0)
+ return ret;
+ data->pwm[MAX][i] = ret;
+
+ ret = adt7475_read(PWM_MIN_REG(i));
+ if (ret < 0)
+ return ret;
+ data->pwm[MIN][i] = ret;
+ /* Set the channel and control information */
+ adt7475_read_pwm(client, i);
+ }
+
+ ret = adt7475_read(TEMP_TRANGE_REG(0));
+ if (ret < 0)
+ return ret;
+ data->range[0] = ret;
+
+ ret = adt7475_read(TEMP_TRANGE_REG(1));
+ if (ret < 0)
+ return ret;
+ data->range[1] = ret;
+
+ ret = adt7475_read(TEMP_TRANGE_REG(2));
+ if (ret < 0)
+ return ret;
+ data->range[2] = ret;
+
+ return 0;
+}
+
static int adt7475_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
(data->bypass_attn & (1 << 3)) ? " in3" : "",
(data->bypass_attn & (1 << 4)) ? " in4" : "");
+ /* Limits and settings, should never change update more than once */
+ ret = adt7475_update_limits(client);
+ if (ret)
+ goto eremove;
+
return 0;
eremove:
}
}
-static struct adt7475_data *adt7475_update_device(struct device *dev)
+static int adt7475_update_measure(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
struct adt7475_data *data = i2c_get_clientdata(client);
u16 ext;
int i;
+ int ret;
- mutex_lock(&data->lock);
+ ret = adt7475_read(REG_STATUS2);
+ if (ret < 0)
+ return ret;
+ data->alarms = ret << 8;
- /* Measurement values update every 2 seconds */
- if (time_after(jiffies, data->measure_updated + HZ * 2) ||
- !data->valid) {
- data->alarms = adt7475_read(REG_STATUS2) << 8;
- data->alarms |= adt7475_read(REG_STATUS1);
-
- ext = (adt7475_read(REG_EXTEND2) << 8) |
- adt7475_read(REG_EXTEND1);
- for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
- if (!(data->has_voltage & (1 << i)))
- continue;
- data->voltage[INPUT][i] =
- (adt7475_read(VOLTAGE_REG(i)) << 2) |
- ((ext >> (i * 2)) & 3);
- }
+ ret = adt7475_read(REG_STATUS1);
+ if (ret < 0)
+ return ret;
+ data->alarms |= ret;
- for (i = 0; i < ADT7475_TEMP_COUNT; i++)
- data->temp[INPUT][i] =
- (adt7475_read(TEMP_REG(i)) << 2) |
- ((ext >> ((i + 5) * 2)) & 3);
+ ret = adt7475_read(REG_EXTEND2);
+ if (ret < 0)
+ return ret;
- if (data->has_voltage & (1 << 5)) {
- data->alarms |= adt7475_read(REG_STATUS4) << 24;
- ext = adt7475_read(REG_EXTEND3);
- data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
- ((ext >> 4) & 3);
- }
+ ext = (ret << 8);
- for (i = 0; i < ADT7475_TACH_COUNT; i++) {
- if (i == 3 && !data->has_fan4)
- continue;
- data->tach[INPUT][i] =
- adt7475_read_word(client, TACH_REG(i));
- }
+ ret = adt7475_read(REG_EXTEND1);
+ if (ret < 0)
+ return ret;
- /* Updated by hw when in auto mode */
- for (i = 0; i < ADT7475_PWM_COUNT; i++) {
- if (i == 1 && !data->has_pwm2)
- continue;
- data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
- }
+ ext |= ret;
+
+ for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+ if (!(data->has_voltage & (1 << i)))
+ continue;
+ ret = adt7475_read(VOLTAGE_REG(i));
+ if (ret < 0)
+ return ret;
+ data->voltage[INPUT][i] =
+ (ret << 2) |
+ ((ext >> (i * 2)) & 3);
+ }
- if (data->has_vid)
- data->vid = adt7475_read(REG_VID) & 0x3f;
+ for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+ ret = adt7475_read(TEMP_REG(i));
+ if (ret < 0)
+ return ret;
+ data->temp[INPUT][i] =
+ (ret << 2) |
+ ((ext >> ((i + 5) * 2)) & 3);
+ }
- data->measure_updated = jiffies;
+ if (data->has_voltage & (1 << 5)) {
+ ret = adt7475_read(REG_STATUS4);
+ if (ret < 0)
+ return ret;
+ data->alarms |= ret << 24;
+
+ ret = adt7475_read(REG_EXTEND3);
+ if (ret < 0)
+ return ret;
+ ext = ret;
+
+ ret = adt7475_read(REG_VTT);
+ if (ret < 0)
+ return ret;
+ data->voltage[INPUT][5] = ret << 2 |
+ ((ext >> 4) & 3);
}
- /* Limits and settings, should never change update every 60 seconds */
- if (time_after(jiffies, data->limits_updated + HZ * 60) ||
- !data->valid) {
- data->config4 = adt7475_read(REG_CONFIG4);
- data->config5 = adt7475_read(REG_CONFIG5);
-
- for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
- if (!(data->has_voltage & (1 << i)))
- continue;
- /* Adjust values so they match the input precision */
- data->voltage[MIN][i] =
- adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
- data->voltage[MAX][i] =
- adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
- }
+ for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+ if (i == 3 && !data->has_fan4)
+ continue;
+ ret = adt7475_read_word(client, TACH_REG(i));
+ if (ret < 0)
+ return ret;
+ data->tach[INPUT][i] = ret;
+ }
- if (data->has_voltage & (1 << 5)) {
- data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
- data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
- }
+ /* Updated by hw when in auto mode */
+ for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+ if (i == 1 && !data->has_pwm2)
+ continue;
+ ret = adt7475_read(PWM_REG(i));
+ if (ret < 0)
+ return ret;
+ data->pwm[INPUT][i] = ret;
+ }
- for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
- /* Adjust values so they match the input precision */
- data->temp[MIN][i] =
- adt7475_read(TEMP_MIN_REG(i)) << 2;
- data->temp[MAX][i] =
- adt7475_read(TEMP_MAX_REG(i)) << 2;
- data->temp[AUTOMIN][i] =
- adt7475_read(TEMP_TMIN_REG(i)) << 2;
- data->temp[THERM][i] =
- adt7475_read(TEMP_THERM_REG(i)) << 2;
- data->temp[OFFSET][i] =
- adt7475_read(TEMP_OFFSET_REG(i));
- }
- adt7475_read_hystersis(client);
+ if (data->has_vid) {
+ ret = adt7475_read(REG_VID);
+ if (ret < 0)
+ return ret;
+ data->vid = ret & 0x3f;
+ }
- for (i = 0; i < ADT7475_TACH_COUNT; i++) {
- if (i == 3 && !data->has_fan4)
- continue;
- data->tach[MIN][i] =
- adt7475_read_word(client, TACH_MIN_REG(i));
- }
+ return 0;
+}
- for (i = 0; i < ADT7475_PWM_COUNT; i++) {
- if (i == 1 && !data->has_pwm2)
- continue;
- data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
- data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
- /* Set the channel and control information */
- adt7475_read_pwm(client, i);
- }
+static struct adt7475_data *adt7475_update_device(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct adt7475_data *data = i2c_get_clientdata(client);
+ int ret;
- data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
- data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
- data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+ mutex_lock(&data->lock);
- data->limits_updated = jiffies;
- data->valid = 1;
+ /* Measurement values update every 2 seconds */
+ if (time_after(jiffies, data->measure_updated + HZ * 2) ||
+ !data->valid) {
+ ret = adt7475_update_measure(dev);
+ if (ret) {
+ data->valid = false;
+ mutex_unlock(&data->lock);
+ return ERR_PTR(ret);
+ }
+ data->measure_updated = jiffies;
+ data->valid = true;
}
mutex_unlock(&data->lock);
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Vostro 3360"),
},
},
+ {
+ .ident = "Dell XPS13 9333",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS13 9333"),
+ },
+ },
{ }
};
switch (id->driver_data) {
case emc1404:
data->groups[2] = &emc1404_group;
+ /* fall through */
case emc1403:
data->groups[1] = &emc1403_group;
+ /* fall through */
case emc1402:
data->groups[0] = &emc1402_group;
}
* struct iio_hwmon_state - device instance state
* @channels: filled with array of channels from iio
* @num_channels: number of channels in channels (saves counting twice)
- * @hwmon_dev: associated hwmon device
* @attr_group: the group of attributes
* @groups: null terminated array of attribute groups
* @attrs: null terminated array of attribute pointers.
struct iio_hwmon_state {
struct iio_channel *channels;
int num_channels;
- struct device *hwmon_dev;
struct attribute_group attr_group;
const struct attribute_group *groups[2];
struct attribute **attrs;
enum iio_chan_type type;
struct iio_channel *channels;
const char *name = "iio_hwmon";
+ struct device *hwmon_dev;
char *sname;
if (dev->of_node && dev->of_node->name)
name = dev->of_node->name;
- channels = iio_channel_get_all(dev);
+ channels = devm_iio_channel_get_all(dev);
if (IS_ERR(channels)) {
if (PTR_ERR(channels) == -ENODEV)
return -EPROBE_DEFER;
}
st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
- if (st == NULL) {
- ret = -ENOMEM;
- goto error_release_channels;
- }
+ if (st == NULL)
+ return -ENOMEM;
st->channels = channels;
st->attrs = devm_kcalloc(dev,
st->num_channels + 1, sizeof(*st->attrs),
GFP_KERNEL);
- if (st->attrs == NULL) {
- ret = -ENOMEM;
- goto error_release_channels;
- }
+ if (st->attrs == NULL)
+ return -ENOMEM;
for (i = 0; i < st->num_channels; i++) {
a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
- if (a == NULL) {
- ret = -ENOMEM;
- goto error_release_channels;
- }
+ if (a == NULL)
+ return -ENOMEM;
sysfs_attr_init(&a->dev_attr.attr);
ret = iio_get_channel_type(&st->channels[i], &type);
if (ret < 0)
- goto error_release_channels;
+ return ret;
switch (type) {
case IIO_VOLTAGE:
humidity_i++);
break;
default:
- ret = -EINVAL;
- goto error_release_channels;
- }
- if (a->dev_attr.attr.name == NULL) {
- ret = -ENOMEM;
- goto error_release_channels;
+ return -EINVAL;
}
+ if (a->dev_attr.attr.name == NULL)
+ return -ENOMEM;
+
a->dev_attr.show = iio_hwmon_read_val;
a->dev_attr.attr.mode = S_IRUGO;
a->index = i;
st->groups[0] = &st->attr_group;
sname = devm_kstrdup(dev, name, GFP_KERNEL);
- if (!sname) {
- ret = -ENOMEM;
- goto error_release_channels;
- }
+ if (!sname)
+ return -ENOMEM;
strreplace(sname, '-', '_');
- st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
- st->groups);
- if (IS_ERR(st->hwmon_dev)) {
- ret = PTR_ERR(st->hwmon_dev);
- goto error_release_channels;
- }
- platform_set_drvdata(pdev, st);
- return 0;
-
-error_release_channels:
- iio_channel_release_all(channels);
- return ret;
-}
-
-static int iio_hwmon_remove(struct platform_device *pdev)
-{
- struct iio_hwmon_state *st = platform_get_drvdata(pdev);
-
- hwmon_device_unregister(st->hwmon_dev);
- iio_channel_release_all(st->channels);
-
- return 0;
+ hwmon_dev = devm_hwmon_device_register_with_groups(dev, sname, st,
+ st->groups);
+ return PTR_ERR_OR_ZERO(hwmon_dev);
}
static const struct of_device_id iio_hwmon_of_match[] = {
.of_match_table = iio_hwmon_of_match,
},
.probe = iio_hwmon_probe,
- .remove = iio_hwmon_remove,
};
module_platform_driver(iio_hwmon_driver);
{ 0x17, "AMD Ryzen 7 1700X", 20000 },
{ 0x17, "AMD Ryzen 7 1800X", 20000 },
{ 0x17, "AMD Ryzen 7 2700X", 10000 },
- { 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
- { 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
- { 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
- { 0x17, "AMD Ryzen Threadripper 1950", 10000 },
- { 0x17, "AMD Ryzen Threadripper 1920", 10000 },
- { 0x17, "AMD Ryzen Threadripper 1910", 10000 },
+ { 0x17, "AMD Ryzen Threadripper 19", 27000 }, /* 19{00,20,50}X */
+ { 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
};
static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+//
+// Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+// Copyright (c) 2018 Vadim Pasternak <vadimp@mellanox.com>
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define MLXREG_FAN_MAX_TACHO 12
+#define MLXREG_FAN_MAX_STATE 10
+#define MLXREG_FAN_MIN_DUTY 51 /* 20% */
+#define MLXREG_FAN_MAX_DUTY 255 /* 100% */
+/*
+ * Minimum and maximum FAN allowed speed in percent: from 20% to 100%. Values
+ * MLXREG_FAN_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting FAN speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXREG_FAN_SPEED_MIN (MLXREG_FAN_MAX_STATE + 2)
+#define MLXREG_FAN_SPEED_MAX (MLXREG_FAN_MAX_STATE * 2)
+#define MLXREG_FAN_SPEED_MIN_LEVEL 2 /* 20 percent */
+#define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF 44
+#define MLXREG_FAN_TACHO_DIVIDER_DEF 1132
+/*
+ * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
+ * The logic in a programmable device measures the time t-high by sampling the
+ * tachometer every t-sample (with the default value 11.32 uS) and increment
+ * a counter (N) as long as the pulse has not change:
+ * RPM = 15 / (t-sample * (K + Regval)), where:
+ * Regval: is the value read from the programmable device register;
+ * - 0xff - represents tachometer fault;
+ * - 0xfe - represents tachometer minimum value , which is 4444 RPM;
+ * - 0x00 - represents tachometer maximum value , which is 300000 RPM;
+ * K: is 44 and it represents the minimum allowed samples per pulse;
+ * N: is equal K + Regval;
+ * In order to calculate RPM from the register value the following formula is
+ * used: RPM = 15 / ((Regval + K) * 11.32) * 10^(-6)), which in the
+ * default case is modified to:
+ * RPM = 15000000 * 100 / ((Regval + 44) * 1132);
+ * - for Regval 0x00, RPM will be 15000000 * 100 / (44 * 1132) = 30115;
+ * - for Regval 0xfe, RPM will be 15000000 * 100 / ((254 + 44) * 1132) = 4446;
+ * In common case the formula is modified to:
+ * RPM = 15000000 * 100 / ((Regval + samples) * divider).
+ */
+#define MLXREG_FAN_GET_RPM(rval, d, s) (DIV_ROUND_CLOSEST(15000000 * 100, \
+ ((rval) + (s)) * (d)))
+#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask)))
+#define MLXREG_FAN_PWM_DUTY2STATE(duty) (DIV_ROUND_CLOSEST((duty) * \
+ MLXREG_FAN_MAX_STATE, \
+ MLXREG_FAN_MAX_DUTY))
+#define MLXREG_FAN_PWM_STATE2DUTY(stat) (DIV_ROUND_CLOSEST((stat) * \
+ MLXREG_FAN_MAX_DUTY, \
+ MLXREG_FAN_MAX_STATE))
+
+/*
+ * struct mlxreg_fan_tacho - tachometer data (internal use):
+ *
+ * @connected: indicates if tachometer is connected;
+ * @reg: register offset;
+ * @mask: fault mask;
+ */
+struct mlxreg_fan_tacho {
+ bool connected;
+ u32 reg;
+ u32 mask;
+};
+
+/*
+ * struct mlxreg_fan_pwm - PWM data (internal use):
+ *
+ * @connected: indicates if PWM is connected;
+ * @reg: register offset;
+ */
+struct mlxreg_fan_pwm {
+ bool connected;
+ u32 reg;
+};
+
+/*
+ * struct mlxreg_fan - private data (internal use):
+ *
+ * @dev: basic device;
+ * @regmap: register map of parent device;
+ * @tacho: tachometer data;
+ * @pwm: PWM data;
+ * @samples: minimum allowed samples per pulse;
+ * @divider: divider value for tachometer RPM calculation;
+ * @cooling: cooling device levels;
+ * @cdev: cooling device;
+ */
+struct mlxreg_fan {
+ struct device *dev;
+ void *regmap;
+ struct mlxreg_core_platform_data *pdata;
+ struct mlxreg_fan_tacho tacho[MLXREG_FAN_MAX_TACHO];
+ struct mlxreg_fan_pwm pwm;
+ int samples;
+ int divider;
+ u8 cooling_levels[MLXREG_FAN_MAX_STATE + 1];
+ struct thermal_cooling_device *cdev;
+};
+
+static int
+mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+ int channel, long *val)
+{
+ struct mlxreg_fan *fan = dev_get_drvdata(dev);
+ struct mlxreg_fan_tacho *tacho;
+ u32 regval;
+ int err;
+
+ switch (type) {
+ case hwmon_fan:
+ tacho = &fan->tacho[channel];
+ switch (attr) {
+ case hwmon_fan_input:
+ err = regmap_read(fan->regmap, tacho->reg, ®val);
+ if (err)
+ return err;
+
+ *val = MLXREG_FAN_GET_RPM(regval, fan->divider,
+ fan->samples);
+ break;
+
+ case hwmon_fan_fault:
+ err = regmap_read(fan->regmap, tacho->reg, ®val);
+ if (err)
+ return err;
+
+ *val = MLXREG_FAN_GET_FAULT(regval, tacho->mask);
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+ break;
+
+ case hwmon_pwm:
+ switch (attr) {
+ case hwmon_pwm_input:
+ err = regmap_read(fan->regmap, fan->pwm.reg, ®val);
+ if (err)
+ return err;
+
+ *val = regval;
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int
+mlxreg_fan_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+ int channel, long val)
+{
+ struct mlxreg_fan *fan = dev_get_drvdata(dev);
+
+ switch (type) {
+ case hwmon_pwm:
+ switch (attr) {
+ case hwmon_pwm_input:
+ if (val < MLXREG_FAN_MIN_DUTY ||
+ val > MLXREG_FAN_MAX_DUTY)
+ return -EINVAL;
+ return regmap_write(fan->regmap, fan->pwm.reg, val);
+ default:
+ return -EOPNOTSUPP;
+ }
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static umode_t
+mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+ int channel)
+{
+ switch (type) {
+ case hwmon_fan:
+ if (!(((struct mlxreg_fan *)data)->tacho[channel].connected))
+ return 0;
+
+ switch (attr) {
+ case hwmon_fan_input:
+ case hwmon_fan_fault:
+ return 0444;
+ default:
+ break;
+ }
+ break;
+
+ case hwmon_pwm:
+ if (!(((struct mlxreg_fan *)data)->pwm.connected))
+ return 0;
+
+ switch (attr) {
+ case hwmon_pwm_input:
+ return 0644;
+ default:
+ break;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static const u32 mlxreg_fan_hwmon_fan_config[] = {
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ HWMON_F_INPUT | HWMON_F_FAULT,
+ 0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
+ .type = hwmon_fan,
+ .config = mlxreg_fan_hwmon_fan_config,
+};
+
+static const u32 mlxreg_fan_hwmon_pwm_config[] = {
+ HWMON_PWM_INPUT,
+ 0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
+ .type = hwmon_pwm,
+ .config = mlxreg_fan_hwmon_pwm_config,
+};
+
+static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
+ &mlxreg_fan_hwmon_fan,
+ &mlxreg_fan_hwmon_pwm,
+ NULL
+};
+
+static const struct hwmon_ops mlxreg_fan_hwmon_hwmon_ops = {
+ .is_visible = mlxreg_fan_is_visible,
+ .read = mlxreg_fan_read,
+ .write = mlxreg_fan_write,
+};
+
+static const struct hwmon_chip_info mlxreg_fan_hwmon_chip_info = {
+ .ops = &mlxreg_fan_hwmon_hwmon_ops,
+ .info = mlxreg_fan_hwmon_info,
+};
+
+static int mlxreg_fan_get_max_state(struct thermal_cooling_device *cdev,
+ unsigned long *state)
+{
+ *state = MLXREG_FAN_MAX_STATE;
+ return 0;
+}
+
+static int mlxreg_fan_get_cur_state(struct thermal_cooling_device *cdev,
+ unsigned long *state)
+
+{
+ struct mlxreg_fan *fan = cdev->devdata;
+ u32 regval;
+ int err;
+
+ err = regmap_read(fan->regmap, fan->pwm.reg, ®val);
+ if (err) {
+ dev_err(fan->dev, "Failed to query PWM duty\n");
+ return err;
+ }
+
+ *state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+
+ return 0;
+}
+
+static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
+ unsigned long state)
+
+{
+ struct mlxreg_fan *fan = cdev->devdata;
+ unsigned long cur_state;
+ u32 regval;
+ int i;
+ int err;
+
+ /*
+ * Verify if this request is for changing allowed FAN dynamical
+ * minimum. If it is - update cooling levels accordingly and update
+ * state, if current state is below the newly requested minimum state.
+ * For example, if current state is 5, and minimal state is to be
+ * changed from 4 to 6, fan->cooling_levels[0 to 5] will be changed all
+ * from 4 to 6. And state 5 (fan->cooling_levels[4]) should be
+ * overwritten.
+ */
+ if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+ state -= MLXREG_FAN_MAX_STATE;
+ for (i = 0; i < state; i++)
+ fan->cooling_levels[i] = state;
+ for (i = state; i <= MLXREG_FAN_MAX_STATE; i++)
+ fan->cooling_levels[i] = i;
+
+ err = regmap_read(fan->regmap, fan->pwm.reg, ®val);
+ if (err) {
+ dev_err(fan->dev, "Failed to query PWM duty\n");
+ return err;
+ }
+
+ cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+ if (state < cur_state)
+ return 0;
+
+ state = cur_state;
+ }
+
+ if (state > MLXREG_FAN_MAX_STATE)
+ return -EINVAL;
+
+ /* Normalize the state to the valid speed range. */
+ state = fan->cooling_levels[state];
+ err = regmap_write(fan->regmap, fan->pwm.reg,
+ MLXREG_FAN_PWM_STATE2DUTY(state));
+ if (err) {
+ dev_err(fan->dev, "Failed to write PWM duty\n");
+ return err;
+ }
+ return 0;
+}
+
+static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
+ .get_max_state = mlxreg_fan_get_max_state,
+ .get_cur_state = mlxreg_fan_get_cur_state,
+ .set_cur_state = mlxreg_fan_set_cur_state,
+};
+
+static int mlxreg_fan_config(struct mlxreg_fan *fan,
+ struct mlxreg_core_platform_data *pdata)
+{
+ struct mlxreg_core_data *data = pdata->data;
+ bool configured = false;
+ int tacho_num = 0, i;
+
+ fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
+ fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+ for (i = 0; i < pdata->counter; i++, data++) {
+ if (strnstr(data->label, "tacho", sizeof(data->label))) {
+ if (tacho_num == MLXREG_FAN_MAX_TACHO) {
+ dev_err(fan->dev, "too many tacho entries: %s\n",
+ data->label);
+ return -EINVAL;
+ }
+ fan->tacho[tacho_num].reg = data->reg;
+ fan->tacho[tacho_num].mask = data->mask;
+ fan->tacho[tacho_num++].connected = true;
+ } else if (strnstr(data->label, "pwm", sizeof(data->label))) {
+ if (fan->pwm.connected) {
+ dev_err(fan->dev, "duplicate pwm entry: %s\n",
+ data->label);
+ return -EINVAL;
+ }
+ fan->pwm.reg = data->reg;
+ fan->pwm.connected = true;
+ } else if (strnstr(data->label, "conf", sizeof(data->label))) {
+ if (configured) {
+ dev_err(fan->dev, "duplicate conf entry: %s\n",
+ data->label);
+ return -EINVAL;
+ }
+ /* Validate that conf parameters are not zeros. */
+ if (!data->mask || !data->bit) {
+ dev_err(fan->dev, "invalid conf entry params: %s\n",
+ data->label);
+ return -EINVAL;
+ }
+ fan->samples = data->mask;
+ fan->divider = data->bit;
+ configured = true;
+ } else {
+ dev_err(fan->dev, "invalid label: %s\n", data->label);
+ return -EINVAL;
+ }
+ }
+
+ /* Init cooling levels per PWM state. */
+ for (i = 0; i < MLXREG_FAN_SPEED_MIN_LEVEL; i++)
+ fan->cooling_levels[i] = MLXREG_FAN_SPEED_MIN_LEVEL;
+ for (i = MLXREG_FAN_SPEED_MIN_LEVEL; i <= MLXREG_FAN_MAX_STATE; i++)
+ fan->cooling_levels[i] = i;
+
+ return 0;
+}
+
+static int mlxreg_fan_probe(struct platform_device *pdev)
+{
+ struct mlxreg_core_platform_data *pdata;
+ struct mlxreg_fan *fan;
+ struct device *hwm;
+ int err;
+
+ pdata = dev_get_platdata(&pdev->dev);
+ if (!pdata) {
+ dev_err(&pdev->dev, "Failed to get platform data.\n");
+ return -EINVAL;
+ }
+
+ fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
+ if (!fan)
+ return -ENOMEM;
+
+ fan->dev = &pdev->dev;
+ fan->regmap = pdata->regmap;
+ platform_set_drvdata(pdev, fan);
+
+ err = mlxreg_fan_config(fan, pdata);
+ if (err)
+ return err;
+
+ hwm = devm_hwmon_device_register_with_info(&pdev->dev, "mlxreg_fan",
+ fan,
+ &mlxreg_fan_hwmon_chip_info,
+ NULL);
+ if (IS_ERR(hwm)) {
+ dev_err(&pdev->dev, "Failed to register hwmon device\n");
+ return PTR_ERR(hwm);
+ }
+
+ if (IS_REACHABLE(CONFIG_THERMAL)) {
+ fan->cdev = thermal_cooling_device_register("mlxreg_fan", fan,
+ &mlxreg_fan_cooling_ops);
+ if (IS_ERR(fan->cdev)) {
+ dev_err(&pdev->dev, "Failed to register cooling device\n");
+ return PTR_ERR(fan->cdev);
+ }
+ }
+
+ return 0;
+}
+
+static int mlxreg_fan_remove(struct platform_device *pdev)
+{
+ struct mlxreg_fan *fan = platform_get_drvdata(pdev);
+
+ if (IS_REACHABLE(CONFIG_THERMAL))
+ thermal_cooling_device_unregister(fan->cdev);
+
+ return 0;
+}
+
+static struct platform_driver mlxreg_fan_driver = {
+ .driver = {
+ .name = "mlxreg-fan",
+ },
+ .probe = mlxreg_fan_probe,
+ .remove = mlxreg_fan_remove,
+};
+
+module_platform_driver(mlxreg_fan_driver);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox FAN driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlxreg-fan");
u64 beeps;
u8 pwm_num; /* number of pwm */
- u8 pwm_mode[NUM_FAN]; /* 1->DC variable voltage,
- * 0->PWM variable duty cycle
+ u8 pwm_mode[NUM_FAN]; /* 0->DC variable voltage,
+ * 1->PWM variable duty cycle
*/
enum pwm_enable pwm_enable[NUM_FAN];
/* 0->off
case thermal_cruise:
nct6775_write_value(data, data->REG_TARGET[nr],
data->target_temp[nr]);
- /* intentional */
+ /* fall through */
default:
reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
reg = (reg & ~data->tolerance_mask) |
* The temperature is already monitored if the respective bit in <mask>
* is set.
*/
- for (i = 0; i < 32; i++) {
+ for (i = 0; i < 31; i++) {
if (!(data->temp_mask & BIT(i + 1)))
continue;
if (!reg_temp_alternate[i])
};
/* Access functions */
-static int nct7904_bank_lock(struct nct7904_data *data, unsigned bank)
+static int nct7904_bank_lock(struct nct7904_data *data, unsigned int bank)
{
int ret;
/* Read 1-byte register. Returns unsigned reg or -ERRNO on error. */
static int nct7904_read_reg(struct nct7904_data *data,
- unsigned bank, unsigned reg)
+ unsigned int bank, unsigned int reg)
{
struct i2c_client *client = data->client;
int ret;
* -ERRNO on error.
*/
static int nct7904_read_reg16(struct nct7904_data *data,
- unsigned bank, unsigned reg)
+ unsigned int bank, unsigned int reg)
{
struct i2c_client *client = data->client;
int ret, hi;
/* Write 1-byte register. Returns 0 or -ERRNO on error. */
static int nct7904_write_reg(struct nct7904_data *data,
- unsigned bank, unsigned reg, u8 val)
+ unsigned int bank, unsigned int reg, u8 val)
{
struct i2c_client *client = data->client;
int ret;
unsigned int cnt, rpm;
int ret;
- switch(attr) {
+ switch (attr) {
case hwmon_fan_input:
ret = nct7904_read_reg16(data, BANK_0,
FANIN1_HV_REG + channel * 2);
index = nct7904_chan_to_index[channel];
- switch(attr) {
+ switch (attr) {
case hwmon_in_input:
ret = nct7904_read_reg16(data, BANK_0,
VSEN1_HV_REG + index * 2);
struct nct7904_data *data = dev_get_drvdata(dev);
int ret, temp;
- switch(attr) {
+ switch (attr) {
case hwmon_temp_input:
if (channel == 0)
ret = nct7904_read_reg16(data, BANK_0, LTD_HV_REG);
struct nct7904_data *data = dev_get_drvdata(dev);
int ret;
- switch(attr) {
+ switch (attr) {
case hwmon_pwm_input:
ret = nct7904_read_reg(data, BANK_3, FANCTL1_OUT_REG + channel);
if (ret < 0)
struct nct7904_data *data = dev_get_drvdata(dev);
int ret;
- switch(attr) {
+ switch (attr) {
case hwmon_pwm_input:
if (val < 0 || val > 255)
return -EINVAL;
static umode_t nct7904_pwm_is_visible(const void *_data, u32 attr, int channel)
{
- switch(attr) {
+ switch (attr) {
case hwmon_pwm_input:
case hwmon_pwm_enable:
return S_IRUGO | S_IWUSR;
};
static const u32 nct7904_fan_config[] = {
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- HWMON_F_INPUT,
- 0
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ 0
};
static const struct hwmon_channel_info nct7904_fan = {
};
static const u32 nct7904_pwm_config[] = {
- HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
- HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
- HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
- HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
- 0
+ HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+ HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+ HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+ HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+ 0
};
static const struct hwmon_channel_info nct7904_pwm = {
};
static const u32 nct7904_temp_config[] = {
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- HWMON_T_INPUT,
- 0
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ HWMON_T_INPUT,
+ 0
};
static const struct hwmon_channel_info nct7904_temp = {
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014-2018 Nuvoton Technology corporation.
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+
+/* NPCM7XX PWM registers */
+#define NPCM7XX_PWM_REG_BASE(base, n) ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_PWM_REG_PR(base, n) (NPCM7XX_PWM_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_PWM_REG_CSR(base, n) (NPCM7XX_PWM_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_PWM_REG_CR(base, n) (NPCM7XX_PWM_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_PWM_REG_CNRx(base, n, ch) \
+ (NPCM7XX_PWM_REG_BASE(base, n) + 0x0C + (12 * (ch)))
+#define NPCM7XX_PWM_REG_CMRx(base, n, ch) \
+ (NPCM7XX_PWM_REG_BASE(base, n) + 0x10 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PDRx(base, n, ch) \
+ (NPCM7XX_PWM_REG_BASE(base, n) + 0x14 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PIER(base, n) (NPCM7XX_PWM_REG_BASE(base, n) + 0x3C)
+#define NPCM7XX_PWM_REG_PIIR(base, n) (NPCM7XX_PWM_REG_BASE(base, n) + 0x40)
+
+#define NPCM7XX_PWM_CTRL_CH0_MODE_BIT BIT(3)
+#define NPCM7XX_PWM_CTRL_CH1_MODE_BIT BIT(11)
+#define NPCM7XX_PWM_CTRL_CH2_MODE_BIT BIT(15)
+#define NPCM7XX_PWM_CTRL_CH3_MODE_BIT BIT(19)
+
+#define NPCM7XX_PWM_CTRL_CH0_INV_BIT BIT(2)
+#define NPCM7XX_PWM_CTRL_CH1_INV_BIT BIT(10)
+#define NPCM7XX_PWM_CTRL_CH2_INV_BIT BIT(14)
+#define NPCM7XX_PWM_CTRL_CH3_INV_BIT BIT(18)
+
+#define NPCM7XX_PWM_CTRL_CH0_EN_BIT BIT(0)
+#define NPCM7XX_PWM_CTRL_CH1_EN_BIT BIT(8)
+#define NPCM7XX_PWM_CTRL_CH2_EN_BIT BIT(12)
+#define NPCM7XX_PWM_CTRL_CH3_EN_BIT BIT(16)
+
+/* Define the maximum PWM channel number */
+#define NPCM7XX_PWM_MAX_CHN_NUM 8
+#define NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE 4
+#define NPCM7XX_PWM_MAX_MODULES 2
+
+/* Define the Counter Register, value = 100 for match 100% */
+#define NPCM7XX_PWM_COUNTER_DEFAULT_NUM 255
+#define NPCM7XX_PWM_CMR_DEFAULT_NUM 127
+#define NPCM7XX_PWM_CMR_MAX 255
+
+/* default all PWM channels PRESCALE2 = 1 */
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 0x4
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 0x40
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 0x400
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3 0x4000
+
+#define PWM_OUTPUT_FREQ_25KHZ 25000
+#define PWN_CNT_DEFAULT 256
+#define MIN_PRESCALE1 2
+#define NPCM7XX_PWM_PRESCALE_SHIFT_CH01 8
+
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT (NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 | \
+ NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 | \
+ NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 | \
+ NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3)
+
+#define NPCM7XX_PWM_CTRL_MODE_DEFAULT (NPCM7XX_PWM_CTRL_CH0_MODE_BIT | \
+ NPCM7XX_PWM_CTRL_CH1_MODE_BIT | \
+ NPCM7XX_PWM_CTRL_CH2_MODE_BIT | \
+ NPCM7XX_PWM_CTRL_CH3_MODE_BIT)
+
+/* NPCM7XX FAN Tacho registers */
+#define NPCM7XX_FAN_REG_BASE(base, n) ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_FAN_REG_TCNT1(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_FAN_REG_TCRA(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x02)
+#define NPCM7XX_FAN_REG_TCRB(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_FAN_REG_TCNT2(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x06)
+#define NPCM7XX_FAN_REG_TPRSC(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_FAN_REG_TCKC(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x0A)
+#define NPCM7XX_FAN_REG_TMCTRL(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x0C)
+#define NPCM7XX_FAN_REG_TICTRL(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x0E)
+#define NPCM7XX_FAN_REG_TICLR(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x10)
+#define NPCM7XX_FAN_REG_TIEN(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x12)
+#define NPCM7XX_FAN_REG_TCPA(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x14)
+#define NPCM7XX_FAN_REG_TCPB(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x16)
+#define NPCM7XX_FAN_REG_TCPCFG(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x18)
+#define NPCM7XX_FAN_REG_TINASEL(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x1A)
+#define NPCM7XX_FAN_REG_TINBSEL(base, n) (NPCM7XX_FAN_REG_BASE(base, n) + 0x1C)
+
+#define NPCM7XX_FAN_TCKC_CLKX_NONE 0
+#define NPCM7XX_FAN_TCKC_CLK1_APB BIT(0)
+#define NPCM7XX_FAN_TCKC_CLK2_APB BIT(3)
+
+#define NPCM7XX_FAN_TMCTRL_TBEN BIT(6)
+#define NPCM7XX_FAN_TMCTRL_TAEN BIT(5)
+#define NPCM7XX_FAN_TMCTRL_TBEDG BIT(4)
+#define NPCM7XX_FAN_TMCTRL_TAEDG BIT(3)
+#define NPCM7XX_FAN_TMCTRL_MODE_5 BIT(2)
+
+#define NPCM7XX_FAN_TICLR_CLEAR_ALL GENMASK(5, 0)
+#define NPCM7XX_FAN_TICLR_TFCLR BIT(5)
+#define NPCM7XX_FAN_TICLR_TECLR BIT(4)
+#define NPCM7XX_FAN_TICLR_TDCLR BIT(3)
+#define NPCM7XX_FAN_TICLR_TCCLR BIT(2)
+#define NPCM7XX_FAN_TICLR_TBCLR BIT(1)
+#define NPCM7XX_FAN_TICLR_TACLR BIT(0)
+
+#define NPCM7XX_FAN_TIEN_ENABLE_ALL GENMASK(5, 0)
+#define NPCM7XX_FAN_TIEN_TFIEN BIT(5)
+#define NPCM7XX_FAN_TIEN_TEIEN BIT(4)
+#define NPCM7XX_FAN_TIEN_TDIEN BIT(3)
+#define NPCM7XX_FAN_TIEN_TCIEN BIT(2)
+#define NPCM7XX_FAN_TIEN_TBIEN BIT(1)
+#define NPCM7XX_FAN_TIEN_TAIEN BIT(0)
+
+#define NPCM7XX_FAN_TICTRL_TFPND BIT(5)
+#define NPCM7XX_FAN_TICTRL_TEPND BIT(4)
+#define NPCM7XX_FAN_TICTRL_TDPND BIT(3)
+#define NPCM7XX_FAN_TICTRL_TCPND BIT(2)
+#define NPCM7XX_FAN_TICTRL_TBPND BIT(1)
+#define NPCM7XX_FAN_TICTRL_TAPND BIT(0)
+
+#define NPCM7XX_FAN_TCPCFG_HIBEN BIT(7)
+#define NPCM7XX_FAN_TCPCFG_EQBEN BIT(6)
+#define NPCM7XX_FAN_TCPCFG_LOBEN BIT(5)
+#define NPCM7XX_FAN_TCPCFG_CPBSEL BIT(4)
+#define NPCM7XX_FAN_TCPCFG_HIAEN BIT(3)
+#define NPCM7XX_FAN_TCPCFG_EQAEN BIT(2)
+#define NPCM7XX_FAN_TCPCFG_LOAEN BIT(1)
+#define NPCM7XX_FAN_TCPCFG_CPASEL BIT(0)
+
+/* FAN General Definition */
+/* Define the maximum FAN channel number */
+#define NPCM7XX_FAN_MAX_MODULE 8
+#define NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE 2
+#define NPCM7XX_FAN_MAX_CHN_NUM 16
+
+/*
+ * Get Fan Tach Timeout (base on clock 214843.75Hz, 1 cnt = 4.654us)
+ * Timeout 94ms ~= 0x5000
+ * (The minimum FAN speed could to support ~640RPM/pulse 1,
+ * 320RPM/pulse 2, ...-- 10.6Hz)
+ */
+#define NPCM7XX_FAN_TIMEOUT 0x5000
+#define NPCM7XX_FAN_TCNT 0xFFFF
+#define NPCM7XX_FAN_TCPA (NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+#define NPCM7XX_FAN_TCPB (NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+
+#define NPCM7XX_FAN_POLL_TIMER_200MS 200
+#define NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION 2
+#define NPCM7XX_FAN_TINASEL_FANIN_DEFAULT 0
+#define NPCM7XX_FAN_CLK_PRESCALE 255
+
+#define NPCM7XX_FAN_CMPA 0
+#define NPCM7XX_FAN_CMPB 1
+
+/* Obtain the fan number */
+#define NPCM7XX_FAN_INPUT(fan, cmp) (((fan) << 1) + (cmp))
+
+/* fan sample status */
+#define FAN_DISABLE 0xFF
+#define FAN_INIT 0x00
+#define FAN_PREPARE_TO_GET_FIRST_CAPTURE 0x01
+#define FAN_ENOUGH_SAMPLE 0x02
+
+struct npcm7xx_fan_dev {
+ u8 fan_st_flg;
+ u8 fan_pls_per_rev;
+ u16 fan_cnt;
+ u32 fan_cnt_tmp;
+};
+
+struct npcm7xx_cooling_device {
+ char name[THERMAL_NAME_LENGTH];
+ struct npcm7xx_pwm_fan_data *data;
+ struct thermal_cooling_device *tcdev;
+ int pwm_port;
+ u8 *cooling_levels;
+ u8 max_state;
+ u8 cur_state;
+};
+
+struct npcm7xx_pwm_fan_data {
+ void __iomem *pwm_base;
+ void __iomem *fan_base;
+ unsigned long pwm_clk_freq;
+ unsigned long fan_clk_freq;
+ struct clk *pwm_clk;
+ struct clk *fan_clk;
+ struct mutex pwm_lock[NPCM7XX_PWM_MAX_MODULES];
+ spinlock_t fan_lock[NPCM7XX_FAN_MAX_MODULE];
+ int fan_irq[NPCM7XX_FAN_MAX_MODULE];
+ bool pwm_present[NPCM7XX_PWM_MAX_CHN_NUM];
+ bool fan_present[NPCM7XX_FAN_MAX_CHN_NUM];
+ u32 input_clk_freq;
+ struct timer_list fan_timer;
+ struct npcm7xx_fan_dev fan_dev[NPCM7XX_FAN_MAX_CHN_NUM];
+ struct npcm7xx_cooling_device *cdev[NPCM7XX_PWM_MAX_CHN_NUM];
+ u8 fan_select;
+};
+
+static int npcm7xx_pwm_config_set(struct npcm7xx_pwm_fan_data *data,
+ int channel, u16 val)
+{
+ u32 pwm_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+ u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+ u32 tmp_buf, ctrl_en_bit, env_bit;
+
+ /*
+ * Config PWM Comparator register for setting duty cycle
+ */
+ mutex_lock(&data->pwm_lock[module]);
+
+ /* write new CMR value */
+ iowrite32(val, NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pwm_ch));
+ tmp_buf = ioread32(NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+
+ switch (pwm_ch) {
+ case 0:
+ ctrl_en_bit = NPCM7XX_PWM_CTRL_CH0_EN_BIT;
+ env_bit = NPCM7XX_PWM_CTRL_CH0_INV_BIT;
+ break;
+ case 1:
+ ctrl_en_bit = NPCM7XX_PWM_CTRL_CH1_EN_BIT;
+ env_bit = NPCM7XX_PWM_CTRL_CH1_INV_BIT;
+ break;
+ case 2:
+ ctrl_en_bit = NPCM7XX_PWM_CTRL_CH2_EN_BIT;
+ env_bit = NPCM7XX_PWM_CTRL_CH2_INV_BIT;
+ break;
+ case 3:
+ ctrl_en_bit = NPCM7XX_PWM_CTRL_CH3_EN_BIT;
+ env_bit = NPCM7XX_PWM_CTRL_CH3_INV_BIT;
+ break;
+ default:
+ mutex_unlock(&data->pwm_lock[module]);
+ return -ENODEV;
+ }
+
+ if (val == 0) {
+ /* Disable PWM */
+ tmp_buf &= ~ctrl_en_bit;
+ tmp_buf |= env_bit;
+ } else {
+ /* Enable PWM */
+ tmp_buf |= ctrl_en_bit;
+ tmp_buf &= ~env_bit;
+ }
+
+ iowrite32(tmp_buf, NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+ mutex_unlock(&data->pwm_lock[module]);
+
+ return 0;
+}
+
+static inline void npcm7xx_fan_start_capture(struct npcm7xx_pwm_fan_data *data,
+ u8 fan, u8 cmp)
+{
+ u8 fan_id;
+ u8 reg_mode;
+ u8 reg_int;
+ unsigned long flags;
+
+ fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+ /* to check whether any fan tach is enable */
+ if (data->fan_dev[fan_id].fan_st_flg != FAN_DISABLE) {
+ /* reset status */
+ spin_lock_irqsave(&data->fan_lock[fan], flags);
+
+ data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+ reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ /*
+ * the interrupt enable bits do not need to be cleared before
+ * it sets, the interrupt enable bits are cleared only on reset.
+ * the clock unit control register is behaving in the same
+ * manner that the interrupt enable register behave.
+ */
+ if (cmp == NPCM7XX_FAN_CMPA) {
+ /* enable interrupt */
+ iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TAIEN |
+ NPCM7XX_FAN_TIEN_TEIEN),
+ NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ reg_mode = NPCM7XX_FAN_TCKC_CLK1_APB
+ | ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+ fan));
+
+ /* start to Capture */
+ iowrite8(reg_mode, NPCM7XX_FAN_REG_TCKC(data->fan_base,
+ fan));
+ } else {
+ /* enable interrupt */
+ iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TBIEN |
+ NPCM7XX_FAN_TIEN_TFIEN),
+ NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ reg_mode =
+ NPCM7XX_FAN_TCKC_CLK2_APB
+ | ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+ fan));
+
+ /* start to Capture */
+ iowrite8(reg_mode,
+ NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+ }
+
+ spin_unlock_irqrestore(&data->fan_lock[fan], flags);
+ }
+}
+
+/*
+ * Enable a background timer to poll fan tach value, (200ms * 4)
+ * to polling all fan
+ */
+static void npcm7xx_fan_polling(struct timer_list *t)
+{
+ struct npcm7xx_pwm_fan_data *data;
+ int i;
+
+ data = from_timer(data, t, fan_timer);
+
+ /*
+ * Polling two module per one round,
+ * FAN01 & FAN89 / FAN23 & FAN1011 / FAN45 & FAN1213 / FAN67 & FAN1415
+ */
+ for (i = data->fan_select; i < NPCM7XX_FAN_MAX_MODULE;
+ i = i + 4) {
+ /* clear the flag and reset the counter (TCNT) */
+ iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+ NPCM7XX_FAN_REG_TICLR(data->fan_base, i));
+
+ if (data->fan_present[i * 2]) {
+ iowrite16(NPCM7XX_FAN_TCNT,
+ NPCM7XX_FAN_REG_TCNT1(data->fan_base, i));
+ npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPA);
+ }
+ if (data->fan_present[(i * 2) + 1]) {
+ iowrite16(NPCM7XX_FAN_TCNT,
+ NPCM7XX_FAN_REG_TCNT2(data->fan_base, i));
+ npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPB);
+ }
+ }
+
+ data->fan_select++;
+ data->fan_select &= 0x3;
+
+ /* reset the timer interval */
+ data->fan_timer.expires = jiffies +
+ msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+ add_timer(&data->fan_timer);
+}
+
+static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data,
+ u8 fan, u8 cmp, u8 fan_id, u8 flag_int,
+ u8 flag_mode, u8 flag_clear)
+{
+ u8 reg_int;
+ u8 reg_mode;
+ u16 fan_cap;
+
+ if (cmp == NPCM7XX_FAN_CMPA)
+ fan_cap = ioread16(NPCM7XX_FAN_REG_TCRA(data->fan_base, fan));
+ else
+ fan_cap = ioread16(NPCM7XX_FAN_REG_TCRB(data->fan_base, fan));
+
+ /* clear capature flag, H/W will auto reset the NPCM7XX_FAN_TCNTx */
+ iowrite8(flag_clear, NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+ if (data->fan_dev[fan_id].fan_st_flg == FAN_INIT) {
+ /* First capture, drop it */
+ data->fan_dev[fan_id].fan_st_flg =
+ FAN_PREPARE_TO_GET_FIRST_CAPTURE;
+
+ /* reset counter */
+ data->fan_dev[fan_id].fan_cnt_tmp = 0;
+ } else if (data->fan_dev[fan_id].fan_st_flg < FAN_ENOUGH_SAMPLE) {
+ /*
+ * collect the enough sample,
+ * (ex: 2 pulse fan need to get 2 sample)
+ */
+ data->fan_dev[fan_id].fan_cnt_tmp +=
+ (NPCM7XX_FAN_TCNT - fan_cap);
+
+ data->fan_dev[fan_id].fan_st_flg++;
+ } else {
+ /* get enough sample or fan disable */
+ if (data->fan_dev[fan_id].fan_st_flg == FAN_ENOUGH_SAMPLE) {
+ data->fan_dev[fan_id].fan_cnt_tmp +=
+ (NPCM7XX_FAN_TCNT - fan_cap);
+
+ /* compute finial average cnt per pulse */
+ data->fan_dev[fan_id].fan_cnt =
+ data->fan_dev[fan_id].fan_cnt_tmp /
+ FAN_ENOUGH_SAMPLE;
+
+ data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+ }
+
+ reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ /* disable interrupt */
+ iowrite8((reg_int & ~flag_int),
+ NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+ reg_mode = ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+ /* stop capturing */
+ iowrite8((reg_mode & ~flag_mode),
+ NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+ }
+}
+
+static inline void npcm7xx_check_cmp(struct npcm7xx_pwm_fan_data *data,
+ u8 fan, u8 cmp, u8 flag)
+{
+ u8 reg_int;
+ u8 reg_mode;
+ u8 flag_timeout;
+ u8 flag_cap;
+ u8 flag_clear;
+ u8 flag_int;
+ u8 flag_mode;
+ u8 fan_id;
+
+ fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+ if (cmp == NPCM7XX_FAN_CMPA) {
+ flag_cap = NPCM7XX_FAN_TICTRL_TAPND;
+ flag_timeout = NPCM7XX_FAN_TICTRL_TEPND;
+ flag_int = NPCM7XX_FAN_TIEN_TAIEN | NPCM7XX_FAN_TIEN_TEIEN;
+ flag_mode = NPCM7XX_FAN_TCKC_CLK1_APB;
+ flag_clear = NPCM7XX_FAN_TICLR_TACLR | NPCM7XX_FAN_TICLR_TECLR;
+ } else {
+ flag_cap = NPCM7XX_FAN_TICTRL_TBPND;
+ flag_timeout = NPCM7XX_FAN_TICTRL_TFPND;
+ flag_int = NPCM7XX_FAN_TIEN_TBIEN | NPCM7XX_FAN_TIEN_TFIEN;
+ flag_mode = NPCM7XX_FAN_TCKC_CLK2_APB;
+ flag_clear = NPCM7XX_FAN_TICLR_TBCLR | NPCM7XX_FAN_TICLR_TFCLR;
+ }
+
+ if (flag & flag_timeout) {
+ reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ /* disable interrupt */
+ iowrite8((reg_int & ~flag_int),
+ NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+ /* clear interrupt flag */
+ iowrite8(flag_clear,
+ NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+ reg_mode = ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+ /* stop capturing */
+ iowrite8((reg_mode & ~flag_mode),
+ NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+ /*
+ * If timeout occurs (NPCM7XX_FAN_TIMEOUT), the fan doesn't
+ * connect or speed is lower than 10.6Hz (320RPM/pulse2).
+ * In these situation, the RPM output should be zero.
+ */
+ data->fan_dev[fan_id].fan_cnt = 0;
+ } else {
+ /* input capture is occurred */
+ if (flag & flag_cap)
+ npcm7xx_fan_compute(data, fan, cmp, fan_id, flag_int,
+ flag_mode, flag_clear);
+ }
+}
+
+static irqreturn_t npcm7xx_fan_isr(int irq, void *dev_id)
+{
+ struct npcm7xx_pwm_fan_data *data = dev_id;
+ unsigned long flags;
+ int module;
+ u8 flag;
+
+ module = irq - data->fan_irq[0];
+ spin_lock_irqsave(&data->fan_lock[module], flags);
+
+ flag = ioread8(NPCM7XX_FAN_REG_TICTRL(data->fan_base, module));
+ if (flag > 0) {
+ npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPA, flag);
+ npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPB, flag);
+ spin_unlock_irqrestore(&data->fan_lock[module], flags);
+ return IRQ_HANDLED;
+ }
+
+ spin_unlock_irqrestore(&data->fan_lock[module], flags);
+
+ return IRQ_NONE;
+}
+
+static int npcm7xx_read_pwm(struct device *dev, u32 attr, int channel,
+ long *val)
+{
+ struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+ u32 pmw_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+ u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+
+ switch (attr) {
+ case hwmon_pwm_input:
+ *val = ioread32
+ (NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pmw_ch));
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int npcm7xx_write_pwm(struct device *dev, u32 attr, int channel,
+ long val)
+{
+ struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+ int err;
+
+ switch (attr) {
+ case hwmon_pwm_input:
+ if (val < 0 || val > NPCM7XX_PWM_CMR_MAX)
+ return -EINVAL;
+ err = npcm7xx_pwm_config_set(data, channel, (u16)val);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
+static umode_t npcm7xx_pwm_is_visible(const void *_data, u32 attr, int channel)
+{
+ const struct npcm7xx_pwm_fan_data *data = _data;
+
+ if (!data->pwm_present[channel])
+ return 0;
+
+ switch (attr) {
+ case hwmon_pwm_input:
+ return 0644;
+ default:
+ return 0;
+ }
+}
+
+static int npcm7xx_read_fan(struct device *dev, u32 attr, int channel,
+ long *val)
+{
+ struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+
+ switch (attr) {
+ case hwmon_fan_input:
+ *val = 0;
+ if (data->fan_dev[channel].fan_cnt <= 0)
+ return data->fan_dev[channel].fan_cnt;
+
+ /* Convert the raw reading to RPM */
+ if (data->fan_dev[channel].fan_cnt > 0 &&
+ data->fan_dev[channel].fan_pls_per_rev > 0)
+ *val = ((data->input_clk_freq * 60) /
+ (data->fan_dev[channel].fan_cnt *
+ data->fan_dev[channel].fan_pls_per_rev));
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static umode_t npcm7xx_fan_is_visible(const void *_data, u32 attr, int channel)
+{
+ const struct npcm7xx_pwm_fan_data *data = _data;
+
+ if (!data->fan_present[channel])
+ return 0;
+
+ switch (attr) {
+ case hwmon_fan_input:
+ return 0444;
+ default:
+ return 0;
+ }
+}
+
+static int npcm7xx_read(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long *val)
+{
+ switch (type) {
+ case hwmon_pwm:
+ return npcm7xx_read_pwm(dev, attr, channel, val);
+ case hwmon_fan:
+ return npcm7xx_read_fan(dev, attr, channel, val);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int npcm7xx_write(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long val)
+{
+ switch (type) {
+ case hwmon_pwm:
+ return npcm7xx_write_pwm(dev, attr, channel, val);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static umode_t npcm7xx_is_visible(const void *data,
+ enum hwmon_sensor_types type,
+ u32 attr, int channel)
+{
+ switch (type) {
+ case hwmon_pwm:
+ return npcm7xx_pwm_is_visible(data, attr, channel);
+ case hwmon_fan:
+ return npcm7xx_fan_is_visible(data, attr, channel);
+ default:
+ return 0;
+ }
+}
+
+static const u32 npcm7xx_pwm_config[] = {
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ HWMON_PWM_INPUT,
+ 0
+};
+
+static const struct hwmon_channel_info npcm7xx_pwm = {
+ .type = hwmon_pwm,
+ .config = npcm7xx_pwm_config,
+};
+
+static const u32 npcm7xx_fan_config[] = {
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ HWMON_F_INPUT,
+ 0
+};
+
+static const struct hwmon_channel_info npcm7xx_fan = {
+ .type = hwmon_fan,
+ .config = npcm7xx_fan_config,
+};
+
+static const struct hwmon_channel_info *npcm7xx_info[] = {
+ &npcm7xx_pwm,
+ &npcm7xx_fan,
+ NULL
+};
+
+static const struct hwmon_ops npcm7xx_hwmon_ops = {
+ .is_visible = npcm7xx_is_visible,
+ .read = npcm7xx_read,
+ .write = npcm7xx_write,
+};
+
+static const struct hwmon_chip_info npcm7xx_chip_info = {
+ .ops = &npcm7xx_hwmon_ops,
+ .info = npcm7xx_info,
+};
+
+static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
+{
+ int m, ch;
+ u32 prescale_val, output_freq;
+
+ data->pwm_clk_freq = clk_get_rate(data->pwm_clk);
+
+ /* Adjust NPCM7xx PWMs output frequency to ~25Khz */
+ output_freq = data->pwm_clk_freq / PWN_CNT_DEFAULT;
+ prescale_val = DIV_ROUND_CLOSEST(output_freq, PWM_OUTPUT_FREQ_25KHZ);
+
+ /* If prescale_val = 0, then the prescale output clock is stopped */
+ if (prescale_val < MIN_PRESCALE1)
+ prescale_val = MIN_PRESCALE1;
+ /*
+ * prescale_val need to decrement in one because in the PWM Prescale
+ * register the Prescale value increment by one
+ */
+ prescale_val--;
+
+ /* Setting PWM Prescale Register value register to both modules */
+ prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
+
+ for (m = 0; m < NPCM7XX_PWM_MAX_MODULES ; m++) {
+ iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
+ iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
+ NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
+ iowrite32(NPCM7XX_PWM_CTRL_MODE_DEFAULT,
+ NPCM7XX_PWM_REG_CR(data->pwm_base, m));
+
+ for (ch = 0; ch < NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; ch++) {
+ iowrite32(NPCM7XX_PWM_COUNTER_DEFAULT_NUM,
+ NPCM7XX_PWM_REG_CNRx(data->pwm_base, m, ch));
+ }
+ }
+
+ return output_freq / ((prescale_val & 0xf) + 1);
+}
+
+static void npcm7xx_fan_init(struct npcm7xx_pwm_fan_data *data)
+{
+ int md;
+ int ch;
+ int i;
+ u32 apb_clk_freq;
+
+ for (md = 0; md < NPCM7XX_FAN_MAX_MODULE; md++) {
+ /* stop FAN0~7 clock */
+ iowrite8(NPCM7XX_FAN_TCKC_CLKX_NONE,
+ NPCM7XX_FAN_REG_TCKC(data->fan_base, md));
+
+ /* disable all interrupt */
+ iowrite8(0x00, NPCM7XX_FAN_REG_TIEN(data->fan_base, md));
+
+ /* clear all interrupt */
+ iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+ NPCM7XX_FAN_REG_TICLR(data->fan_base, md));
+
+ /* set FAN0~7 clock prescaler */
+ iowrite8(NPCM7XX_FAN_CLK_PRESCALE,
+ NPCM7XX_FAN_REG_TPRSC(data->fan_base, md));
+
+ /* set FAN0~7 mode (high-to-low transition) */
+ iowrite8((NPCM7XX_FAN_TMCTRL_MODE_5 | NPCM7XX_FAN_TMCTRL_TBEN |
+ NPCM7XX_FAN_TMCTRL_TAEN),
+ NPCM7XX_FAN_REG_TMCTRL(data->fan_base, md));
+
+ /* set FAN0~7 Initial Count/Cap */
+ iowrite16(NPCM7XX_FAN_TCNT,
+ NPCM7XX_FAN_REG_TCNT1(data->fan_base, md));
+ iowrite16(NPCM7XX_FAN_TCNT,
+ NPCM7XX_FAN_REG_TCNT2(data->fan_base, md));
+
+ /* set FAN0~7 compare (equal to count) */
+ iowrite8((NPCM7XX_FAN_TCPCFG_EQAEN | NPCM7XX_FAN_TCPCFG_EQBEN),
+ NPCM7XX_FAN_REG_TCPCFG(data->fan_base, md));
+
+ /* set FAN0~7 compare value */
+ iowrite16(NPCM7XX_FAN_TCPA,
+ NPCM7XX_FAN_REG_TCPA(data->fan_base, md));
+ iowrite16(NPCM7XX_FAN_TCPB,
+ NPCM7XX_FAN_REG_TCPB(data->fan_base, md));
+
+ /* set FAN0~7 fan input FANIN 0~15 */
+ iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+ NPCM7XX_FAN_REG_TINASEL(data->fan_base, md));
+ iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+ NPCM7XX_FAN_REG_TINBSEL(data->fan_base, md));
+
+ for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE; i++) {
+ ch = md * NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE + i;
+ data->fan_dev[ch].fan_st_flg = FAN_DISABLE;
+ data->fan_dev[ch].fan_pls_per_rev =
+ NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION;
+ data->fan_dev[ch].fan_cnt = 0;
+ }
+ }
+
+ apb_clk_freq = clk_get_rate(data->fan_clk);
+
+ /* Fan tach input clock = APB clock / prescalar, default is 255. */
+ data->input_clk_freq = apb_clk_freq / (NPCM7XX_FAN_CLK_PRESCALE + 1);
+}
+
+static int
+npcm7xx_pwm_cz_get_max_state(struct thermal_cooling_device *tcdev,
+ unsigned long *state)
+{
+ struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+ *state = cdev->max_state;
+
+ return 0;
+}
+
+static int
+npcm7xx_pwm_cz_get_cur_state(struct thermal_cooling_device *tcdev,
+ unsigned long *state)
+{
+ struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+ *state = cdev->cur_state;
+
+ return 0;
+}
+
+static int
+npcm7xx_pwm_cz_set_cur_state(struct thermal_cooling_device *tcdev,
+ unsigned long state)
+{
+ struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+ int ret;
+
+ if (state > cdev->max_state)
+ return -EINVAL;
+
+ cdev->cur_state = state;
+ ret = npcm7xx_pwm_config_set(cdev->data, cdev->pwm_port,
+ cdev->cooling_levels[cdev->cur_state]);
+
+ return ret;
+}
+
+static const struct thermal_cooling_device_ops npcm7xx_pwm_cool_ops = {
+ .get_max_state = npcm7xx_pwm_cz_get_max_state,
+ .get_cur_state = npcm7xx_pwm_cz_get_cur_state,
+ .set_cur_state = npcm7xx_pwm_cz_set_cur_state,
+};
+
+static int npcm7xx_create_pwm_cooling(struct device *dev,
+ struct device_node *child,
+ struct npcm7xx_pwm_fan_data *data,
+ u32 pwm_port, u8 num_levels)
+{
+ int ret;
+ struct npcm7xx_cooling_device *cdev;
+
+ cdev = devm_kzalloc(dev, sizeof(*cdev), GFP_KERNEL);
+ if (!cdev)
+ return -ENOMEM;
+
+ cdev->cooling_levels = devm_kzalloc(dev, num_levels, GFP_KERNEL);
+ if (!cdev->cooling_levels)
+ return -ENOMEM;
+
+ cdev->max_state = num_levels - 1;
+ ret = of_property_read_u8_array(child, "cooling-levels",
+ cdev->cooling_levels,
+ num_levels);
+ if (ret) {
+ dev_err(dev, "Property 'cooling-levels' cannot be read.\n");
+ return ret;
+ }
+ snprintf(cdev->name, THERMAL_NAME_LENGTH, "%s%d", child->name,
+ pwm_port);
+
+ cdev->tcdev = thermal_of_cooling_device_register(child,
+ cdev->name,
+ cdev,
+ &npcm7xx_pwm_cool_ops);
+ if (IS_ERR(cdev->tcdev))
+ return PTR_ERR(cdev->tcdev);
+
+ cdev->data = data;
+ cdev->pwm_port = pwm_port;
+
+ data->cdev[pwm_port] = cdev;
+
+ return 0;
+}
+
+static int npcm7xx_en_pwm_fan(struct device *dev,
+ struct device_node *child,
+ struct npcm7xx_pwm_fan_data *data)
+{
+ u8 *fan_ch;
+ u32 pwm_port;
+ int ret, fan_cnt;
+ u8 index, ch;
+
+ ret = of_property_read_u32(child, "reg", &pwm_port);
+ if (ret)
+ return ret;
+
+ data->pwm_present[pwm_port] = true;
+ ret = npcm7xx_pwm_config_set(data, pwm_port,
+ NPCM7XX_PWM_CMR_DEFAULT_NUM);
+
+ ret = of_property_count_u8_elems(child, "cooling-levels");
+ if (ret > 0) {
+ ret = npcm7xx_create_pwm_cooling(dev, child, data, pwm_port,
+ ret);
+ if (ret)
+ return ret;
+ }
+
+ fan_cnt = of_property_count_u8_elems(child, "fan-tach-ch");
+ if (fan_cnt < 1)
+ return -EINVAL;
+
+ fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL);
+ if (!fan_ch)
+ return -ENOMEM;
+
+ ret = of_property_read_u8_array(child, "fan-tach-ch", fan_ch, fan_cnt);
+ if (ret)
+ return ret;
+
+ for (ch = 0; ch < fan_cnt; ch++) {
+ index = fan_ch[ch];
+ data->fan_present[index] = true;
+ data->fan_dev[index].fan_st_flg = FAN_INIT;
+ }
+
+ return 0;
+}
+
+static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np, *child;
+ struct npcm7xx_pwm_fan_data *data;
+ struct resource *res;
+ struct device *hwmon;
+ char name[20];
+ int ret, cnt;
+ u32 output_freq;
+ u32 i;
+
+ np = dev->of_node;
+
+ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
+ if (!res) {
+ dev_err(dev, "pwm resource not found\n");
+ return -ENODEV;
+ }
+
+ data->pwm_base = devm_ioremap_resource(dev, res);
+ dev_dbg(dev, "pwm base resource is %pR\n", res);
+ if (IS_ERR(data->pwm_base))
+ return PTR_ERR(data->pwm_base);
+
+ data->pwm_clk = devm_clk_get(dev, "pwm");
+ if (IS_ERR(data->pwm_clk)) {
+ dev_err(dev, "couldn't get pwm clock\n");
+ return PTR_ERR(data->pwm_clk);
+ }
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fan");
+ if (!res) {
+ dev_err(dev, "fan resource not found\n");
+ return -ENODEV;
+ }
+
+ data->fan_base = devm_ioremap_resource(dev, res);
+ dev_dbg(dev, "fan base resource is %pR\n", res);
+ if (IS_ERR(data->fan_base))
+ return PTR_ERR(data->fan_base);
+
+ data->fan_clk = devm_clk_get(dev, "fan");
+ if (IS_ERR(data->fan_clk)) {
+ dev_err(dev, "couldn't get fan clock\n");
+ return PTR_ERR(data->fan_clk);
+ }
+
+ output_freq = npcm7xx_pwm_init(data);
+ npcm7xx_fan_init(data);
+
+ for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES ; cnt++)
+ mutex_init(&data->pwm_lock[cnt]);
+
+ for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
+ spin_lock_init(&data->fan_lock[i]);
+
+ data->fan_irq[i] = platform_get_irq(pdev, i);
+ if (data->fan_irq[i] < 0) {
+ dev_err(dev, "get IRQ fan%d failed\n", i);
+ return data->fan_irq[i];
+ }
+
+ sprintf(name, "NPCM7XX-FAN-MD%d", i);
+ ret = devm_request_irq(dev, data->fan_irq[i], npcm7xx_fan_isr,
+ 0, name, (void *)data);
+ if (ret) {
+ dev_err(dev, "register IRQ fan%d failed\n", i);
+ return ret;
+ }
+ }
+
+ for_each_child_of_node(np, child) {
+ ret = npcm7xx_en_pwm_fan(dev, child, data);
+ if (ret) {
+ dev_err(dev, "enable pwm and fan failed\n");
+ of_node_put(child);
+ return ret;
+ }
+ }
+
+ hwmon = devm_hwmon_device_register_with_info(dev, "npcm7xx_pwm_fan",
+ data, &npcm7xx_chip_info,
+ NULL);
+ if (IS_ERR(hwmon)) {
+ dev_err(dev, "unable to register hwmon device\n");
+ return PTR_ERR(hwmon);
+ }
+
+ for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM; i++) {
+ if (data->fan_present[i]) {
+ /* fan timer initialization */
+ data->fan_timer.expires = jiffies +
+ msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+ timer_setup(&data->fan_timer,
+ npcm7xx_fan_polling, 0);
+ add_timer(&data->fan_timer);
+ break;
+ }
+ }
+
+ pr_info("NPCM7XX PWM-FAN Driver probed, output Freq %dHz[PWM], input Freq %dHz[FAN]\n",
+ output_freq, data->input_clk_freq);
+
+ return 0;
+}
+
+static const struct of_device_id of_pwm_fan_match_table[] = {
+ { .compatible = "nuvoton,npcm750-pwm-fan", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match_table);
+
+static struct platform_driver npcm7xx_pwm_fan_driver = {
+ .probe = npcm7xx_pwm_fan_probe,
+ .driver = {
+ .name = "npcm7xx_pwm_fan",
+ .of_match_table = of_pwm_fan_match_table,
+ },
+};
+
+module_platform_driver(npcm7xx_pwm_fan_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM7XX PWM and Fan Tacho driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
default n
help
If you say yes here you get hardware monitoring support for Maxim
- MAX34440, MAX34441, MAX34446, MAX34460, and MAX34461.
+ MAX34440, MAX34441, MAX34446, MAX34451, MAX34460, and MAX34461.
This driver can also be built as a module. If so, the module will
be called max34440.
#include <linux/i2c.h>
#include "pmbus.h"
-enum chips { max34440, max34441, max34446, max34460, max34461 };
+enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
#define MAX34440_MFR_VOUT_PEAK 0xd4
#define MAX34440_MFR_IOUT_PEAK 0xd5
#define MAX34440_STATUS_OT_FAULT BIT(5)
#define MAX34440_STATUS_OT_WARN BIT(6)
+#define MAX34451_MFR_CHANNEL_CONFIG 0xe4
+#define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK 0x3f
+
struct max34440_data {
int id;
struct pmbus_driver_info info;
MAX34440_MFR_VOUT_PEAK);
break;
case PMBUS_VIRT_READ_IOUT_AVG:
- if (data->id != max34446)
+ if (data->id != max34446 && data->id != max34451)
return -ENXIO;
ret = pmbus_read_word_data(client, page,
MAX34446_MFR_IOUT_AVG);
case PMBUS_VIRT_RESET_IOUT_HISTORY:
ret = pmbus_write_word_data(client, page,
MAX34440_MFR_IOUT_PEAK, 0);
- if (!ret && data->id == max34446)
+ if (!ret && (data->id == max34446 || data->id == max34451))
ret = pmbus_write_word_data(client, page,
MAX34446_MFR_IOUT_AVG, 0);
return ret;
}
+static int max34451_set_supported_funcs(struct i2c_client *client,
+ struct max34440_data *data)
+{
+ /*
+ * Each of the channel 0-15 can be configured to monitor the following
+ * functions based on MFR_CHANNEL_CONFIG[5:0]
+ * 0x10: Sequencing + voltage monitoring (only valid for PAGES 0–11)
+ * 0x20: Voltage monitoring (no sequencing)
+ * 0x21: Voltage read only
+ * 0x22: Current monitoring
+ * 0x23: Current read only
+ * 0x30: General-purpose input active low
+ * 0x34: General-purpose input active high
+ * 0x00: Disabled
+ */
+
+ int page, rv;
+
+ for (page = 0; page < 16; page++) {
+ rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+ if (rv < 0)
+ return rv;
+
+ rv = i2c_smbus_read_word_data(client,
+ MAX34451_MFR_CHANNEL_CONFIG);
+ if (rv < 0)
+ return rv;
+
+ switch (rv & MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK) {
+ case 0x10:
+ case 0x20:
+ data->info.func[page] = PMBUS_HAVE_VOUT |
+ PMBUS_HAVE_STATUS_VOUT;
+ break;
+ case 0x21:
+ data->info.func[page] = PMBUS_HAVE_VOUT;
+ break;
+ case 0x22:
+ data->info.func[page] = PMBUS_HAVE_IOUT |
+ PMBUS_HAVE_STATUS_IOUT;
+ break;
+ case 0x23:
+ data->info.func[page] = PMBUS_HAVE_IOUT;
+ break;
+ default:
+ break;
+ }
+ }
+
+ return 0;
+}
+
static struct pmbus_driver_info max34440_info[] = {
[max34440] = {
.pages = 14,
.read_word_data = max34440_read_word_data,
.write_word_data = max34440_write_word_data,
},
+ [max34451] = {
+ .pages = 21,
+ .format[PSC_VOLTAGE_OUT] = direct,
+ .format[PSC_TEMPERATURE] = direct,
+ .format[PSC_CURRENT_OUT] = direct,
+ .m[PSC_VOLTAGE_OUT] = 1,
+ .b[PSC_VOLTAGE_OUT] = 0,
+ .R[PSC_VOLTAGE_OUT] = 3,
+ .m[PSC_CURRENT_OUT] = 1,
+ .b[PSC_CURRENT_OUT] = 0,
+ .R[PSC_CURRENT_OUT] = 2,
+ .m[PSC_TEMPERATURE] = 1,
+ .b[PSC_TEMPERATURE] = 0,
+ .R[PSC_TEMPERATURE] = 2,
+ /* func 0-15 is set dynamically before probing */
+ .func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+ .func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+ .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+ .func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+ .func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+ .read_byte_data = max34440_read_byte_data,
+ .read_word_data = max34440_read_word_data,
+ .write_word_data = max34440_write_word_data,
+ },
[max34460] = {
.pages = 18,
.format[PSC_VOLTAGE_OUT] = direct,
const struct i2c_device_id *id)
{
struct max34440_data *data;
+ int rv;
data = devm_kzalloc(&client->dev, sizeof(struct max34440_data),
GFP_KERNEL);
data->id = id->driver_data;
data->info = max34440_info[id->driver_data];
+ if (data->id == max34451) {
+ rv = max34451_set_supported_funcs(client, data);
+ if (rv)
+ return rv;
+ }
+
return pmbus_do_probe(client, id, &data->info);
}
{"max34440", max34440},
{"max34441", max34441},
{"max34446", max34446},
+ {"max34451", max34451},
{"max34460", max34460},
{"max34461", max34461},
{}
if (bit_adap->getscl == NULL)
adap->quirks = &i2c_bit_quirk_no_clk_stretch;
- /* Bring bus to a known state. Looks like STOP if bus is not free yet */
- setscl(bit_adap, 1);
- udelay(bit_adap->udelay);
- setsda(bit_adap, 1);
+ /*
+ * We tried forcing SCL/SDA to an initial state here. But that caused a
+ * regression, sadly. Check Bugzilla #200045 for details.
+ */
ret = add_adapter(adap);
if (ret < 0)
.name = "cht_wc_ext_chrg_irq_chip",
};
-static const char * const bq24190_suppliers[] = { "fusb302-typec-source" };
+static const char * const bq24190_suppliers[] = {
+ "tcpm-source-psy-i2c-fusb302" };
static const struct property_entry bq24190_props[] = {
PROPERTY_ENTRY_STRING_ARRAY("supplied-from", bq24190_suppliers),
/*
* It's not always possible to have 1 to 2 ratio when d=7, so fall back
* to minimal possible clkh in this case.
+ *
+ * Note:
+ * CLKH is not allowed to be 0, in this case I2C clock is not generated
+ * at all
*/
- if (clk >= clkl + d) {
+ if (clk > clkl + d) {
clkh = clk - clkl - d;
clkl -= d;
} else {
- clkh = 0;
+ clkh = 1;
clkl = clk - (d << 1);
}
* required for an I2C bus.
*/
if (pdata->scl_is_open_drain)
- gflags = GPIOD_OUT_LOW;
+ gflags = GPIOD_OUT_HIGH;
else
- gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
+ gflags = GPIOD_OUT_HIGH_OPEN_DRAIN;
priv->scl = i2c_gpio_get_desc(dev, "scl", 1, gflags);
if (IS_ERR(priv->scl))
return PTR_ERR(priv->scl);
goto err_desc;
}
+ reinit_completion(&dma->cmd_complete);
txdesc->callback = i2c_imx_dma_callback;
txdesc->callback_param = i2c_imx;
if (dma_submit_error(dmaengine_submit(txdesc))) {
* The first byte must be transmitted by the CPU.
*/
imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR);
- reinit_completion(&i2c_imx->dma->cmd_complete);
time_left = wait_for_completion_timeout(
&i2c_imx->dma->cmd_complete,
msecs_to_jiffies(DMA_TIMEOUT));
if (result)
return result;
- reinit_completion(&i2c_imx->dma->cmd_complete);
time_left = wait_for_completion_timeout(
&i2c_imx->dma->cmd_complete,
msecs_to_jiffies(DMA_TIMEOUT));
i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl,
"gpio");
rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
- rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH);
+ rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER ||
PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) {
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
+#include <linux/reset.h>
#include <linux/slab.h>
/* register offsets */
#define ID_ARBLOST (1 << 3)
#define ID_NACK (1 << 4)
/* persistent flags */
+#define ID_P_NO_RXDMA (1 << 30) /* HW forbids RXDMA sometimes */
#define ID_P_PM_BLOCKED (1 << 31)
-#define ID_P_MASK ID_P_PM_BLOCKED
+#define ID_P_MASK (ID_P_PM_BLOCKED | ID_P_NO_RXDMA)
enum rcar_i2c_type {
I2C_RCAR_GEN1,
struct dma_chan *dma_rx;
struct scatterlist sg;
enum dma_data_direction dma_direction;
+
+ struct reset_control *rstc;
};
#define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent)
dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg),
sg_dma_len(&priv->sg), priv->dma_direction);
+ /* Gen3 can only do one RXDMA per transfer and we just completed it */
+ if (priv->devtype == I2C_RCAR_GEN3 &&
+ priv->dma_direction == DMA_FROM_DEVICE)
+ priv->flags |= ID_P_NO_RXDMA;
+
priv->dma_direction = DMA_NONE;
}
unsigned char *buf;
int len;
- /* Do not use DMA if it's not available or for messages < 8 bytes */
- if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE))
+ /* Do various checks to see if DMA is feasible at all */
+ if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) ||
+ (read && priv->flags & ID_P_NO_RXDMA))
return;
if (read) {
}
}
+/* I2C is a special case, we need to poll the status of a reset */
+static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv)
+{
+ int i, ret;
+
+ ret = reset_control_reset(priv->rstc);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < LOOP_TIMEOUT; i++) {
+ ret = reset_control_status(priv->rstc);
+ if (ret == 0)
+ return 0;
+ udelay(1);
+ }
+
+ return -ETIMEDOUT;
+}
+
static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
struct i2c_msg *msgs,
int num)
pm_runtime_get_sync(dev);
+ /* Gen3 needs a reset before allowing RXDMA once */
+ if (priv->devtype == I2C_RCAR_GEN3) {
+ priv->flags |= ID_P_NO_RXDMA;
+ if (!IS_ERR(priv->rstc)) {
+ ret = rcar_i2c_do_reset(priv);
+ if (ret == 0)
+ priv->flags &= ~ID_P_NO_RXDMA;
+ }
+ }
+
rcar_i2c_init(priv);
ret = rcar_i2c_bus_barrier(priv);
if (ret < 0)
goto out_pm_put;
+ if (priv->devtype == I2C_RCAR_GEN3) {
+ priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+ if (!IS_ERR(priv->rstc)) {
+ ret = reset_control_status(priv->rstc);
+ if (ret < 0)
+ priv->rstc = ERR_PTR(-ENOTSUPP);
+ }
+ }
+
/* Stay always active when multi-master to keep arbitration working */
if (of_property_read_bool(dev->of_node, "multi-master"))
priv->flags |= ID_P_PM_BLOCKED;
/*
* The number of address send athemps tried before giving up.
- * If the first one failes it seems like 5 to 8 attempts are required.
+ * If the first one fails it seems like 5 to 8 attempts are required.
*/
#define NUM_ADDR_RESEND_ATTEMPTS 12
{
u32 cnfg;
+ /*
+ * NACK interrupt is generated before the I2C controller generates
+ * the STOP condition on the bus. So wait for 2 clock periods
+ * before disabling the controller so that the STOP condition has
+ * been delivered properly.
+ */
+ udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
+
cnfg = i2c_readl(i2c_dev, I2C_CNFG);
if (cnfg & I2C_CNFG_PACKET_MODE_EN)
i2c_writel(i2c_dev, cnfg & ~I2C_CNFG_PACKET_MODE_EN, I2C_CNFG);
if (likely(i2c_dev->msg_err == I2C_ERR_NONE))
return 0;
- /*
- * NACK interrupt is generated before the I2C controller generates
- * the STOP condition on the bus. So wait for 2 clock periods
- * before resetting the controller so that the STOP condition has
- * been delivered properly.
- */
- if (i2c_dev->msg_err == I2C_ERR_NO_ACK)
- udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
-
tegra_i2c_init(i2c_dev);
if (i2c_dev->msg_err == I2C_ERR_NO_ACK) {
if (msg->flags & I2C_M_IGNORE_NAK)
if (priv->len_recv) {
/* read length byte */
rlen = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+ /*
+ * We expect at least 2 interrupts for I2C_M_RECV_LEN
+ * transactions. The length is updated during the first
+ * interrupt, and the buffer contents are only copied
+ * during subsequent interrupts. If in case the interrupts
+ * get merged we would complete the transaction without
+ * copying out the bytes from RX fifo. To avoid this now we
+ * drain the fifo as and when data is available.
+ * We drained the rlen byte already, decrement total length
+ * by one.
+ */
+
+ len--;
if (rlen > I2C_SMBUS_BLOCK_MAX || rlen == 0) {
rlen = 0; /*abort transfer */
priv->msg_buf_remaining = 0;
priv->msg_len = 0;
- } else {
- *buf++ = rlen;
- if (priv->client_pec)
- ++rlen; /* account for error check byte */
- /* update remaining bytes and message length */
- priv->msg_buf_remaining = rlen;
- priv->msg_len = rlen + 1;
+ xlp9xx_i2c_update_rlen(priv);
+ return;
}
+
+ *buf++ = rlen;
+ if (priv->client_pec)
+ ++rlen; /* account for error check byte */
+ /* update remaining bytes and message length */
+ priv->msg_buf_remaining = rlen;
+ priv->msg_len = rlen + 1;
xlp9xx_i2c_update_rlen(priv);
priv->len_recv = false;
- } else {
- len = min(priv->msg_buf_remaining, len);
- for (i = 0; i < len; i++, buf++)
- *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
-
- priv->msg_buf_remaining -= len;
}
+ len = min(priv->msg_buf_remaining, len);
+ for (i = 0; i < len; i++, buf++)
+ *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+ priv->msg_buf_remaining -= len;
priv->msg_buf = buf;
if (priv->msg_buf_remaining)
val = !val;
bri->set_scl(adap, val);
- ndelay(RECOVERY_NDELAY);
+
+ /*
+ * If we can set SDA, we will always create STOP here to ensure
+ * the additional pulses will do no harm. This is achieved by
+ * letting SDA follow SCL half a cycle later.
+ */
+ ndelay(RECOVERY_NDELAY / 2);
+ if (bri->set_sda)
+ bri->set_sda(adap, val);
+ ndelay(RECOVERY_NDELAY / 2);
}
/* check if recovery actually succeeded */
static void i2c_adapter_lock_bus(struct i2c_adapter *adapter,
unsigned int flags)
{
- rt_mutex_lock(&adapter->bus_lock);
+ rt_mutex_lock_nested(&adapter->bus_lock, i2c_adapter_depth(adapter));
}
/**
status = i2c_transfer(adapter, msg, num);
if (status < 0)
- return status;
- if (status != num)
- return -EIO;
+ goto cleanup;
+ if (status != num) {
+ status = -EIO;
+ goto cleanup;
+ }
+ status = 0;
/* Check PEC if last message is a read */
if (i && (msg[num-1].flags & I2C_M_RD)) {
status = i2c_smbus_check_pec(partial_pec, &msg[num-1]);
if (status < 0)
- return status;
+ goto cleanup;
}
if (read_write == I2C_SMBUS_READ)
break;
}
+cleanup:
if (msg[0].flags & I2C_M_DMA_SAFE)
kfree(msg[0].buf);
if (msg[1].flags & I2C_M_DMA_SAFE)
kfree(msg[1].buf);
- return 0;
+ return status;
}
/**
struct i2c_mux_priv *priv = adapter->algo_data;
struct i2c_adapter *parent = priv->muxc->parent;
- rt_mutex_lock(&parent->mux_lock);
+ rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter));
if (!(flags & I2C_LOCK_ROOT_ADAPTER))
return;
i2c_lock_bus(parent, flags);
struct i2c_mux_priv *priv = adapter->algo_data;
struct i2c_adapter *parent = priv->muxc->parent;
- rt_mutex_lock(&parent->mux_lock);
+ rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter));
i2c_lock_bus(parent, flags);
}
if (src < 0)
return IRQ_NONE;
- if (!(src & data->chip_info->enabled_events))
+ if (!(src & (data->chip_info->enabled_events | MMA8452_INT_DRDY)))
return IRQ_NONE;
if (src & MMA8452_INT_DRDY) {
}
irq_type = irqd_get_trigger_type(desc);
+ if (!irq_type)
+ irq_type = IRQF_TRIGGER_RISING;
if (irq_type == IRQF_TRIGGER_RISING)
st->irq_mask = INV_MPU6050_ACTIVE_HIGH;
else if (irq_type == IRQF_TRIGGER_FALLING)
"%s: failed to get lux\n", __func__);
return lux_val;
}
+ if (lux_val == 0)
+ return -ERANGE;
ret = (chip->settings.als_cal_target * chip->settings.als_gain_trim) /
lux_val;
}
comp_humidity = bmp280_compensate_humidity(data, adc_humidity);
- *val = comp_humidity;
- *val2 = 1024;
+ *val = comp_humidity * 1000 / 1024;
- return IIO_VAL_FRACTIONAL;
+ return IIO_VAL_INT;
}
static int bmp280_read_raw(struct iio_dev *indio_dev,
* this lock.
*/
if (!exclusive)
- return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+ return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
-EBUSY : 0;
/* lock is either WRITE or DESTROY - should be exclusive */
goto release_qp;
}
- if ((cmd->base.attr_mask & IB_QP_AV) &&
- !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
- ret = -EINVAL;
- goto release_qp;
+ if ((cmd->base.attr_mask & IB_QP_AV)) {
+ if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
+ ret = -EINVAL;
+ goto release_qp;
+ }
+
+ if (cmd->base.attr_mask & IB_QP_STATE &&
+ cmd->base.qp_state == IB_QPS_RTR) {
+ /* We are in INIT->RTR TRANSITION (if we are not,
+ * this transition will be rejected in subsequent checks).
+ * In the INIT->RTR transition, we cannot have IB_QP_PORT set,
+ * but the IB_QP_STATE flag is required.
+ *
+ * Since kernel 3.14 (commit dbf727de7440), the uverbs driver,
+ * when IB_QP_AV is set, has required inclusion of a valid
+ * port number in the primary AV. (AVs are created and handled
+ * differently for infiniband and ethernet (RoCE) ports).
+ *
+ * Check the port number included in the primary AV against
+ * the port number in the qp struct, which was set (and saved)
+ * in the RST->INIT transition.
+ */
+ if (cmd->base.dest.port_num != qp->real_qp->port) {
+ ret = -EINVAL;
+ goto release_qp;
+ }
+ } else {
+ /* We are in SQD->SQD. (If we are not, this transition will
+ * be rejected later in the verbs layer checks).
+ * Check for both IB_QP_PORT and IB_QP_AV, these can be set
+ * together in the SQD->SQD transition.
+ *
+ * If only IP_QP_AV was set, add in IB_QP_PORT as well (the
+ * verbs layer driver does not track primary port changes
+ * resulting from path migration. Thus, in SQD, if the primary
+ * AV is modified, the primary port should also be modified).
+ *
+ * Note that in this transition, the IB_QP_STATE flag
+ * is not allowed.
+ */
+ if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+ == (IB_QP_AV | IB_QP_PORT)) &&
+ cmd->base.port_num != cmd->base.dest.port_num) {
+ ret = -EINVAL;
+ goto release_qp;
+ }
+ if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+ == IB_QP_AV) {
+ cmd->base.attr_mask |= IB_QP_PORT;
+ cmd->base.port_num = cmd->base.dest.port_num;
+ }
+ }
}
if ((cmd->base.attr_mask & IB_QP_ALT_PATH) &&
(!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) ||
- !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) {
+ !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) ||
+ cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) {
ret = -EINVAL;
goto release_qp;
}
struct ib_flow_attr *flow_attr;
struct ib_qp *qp;
struct ib_uflow_resources *uflow_res;
+ struct ib_uverbs_flow_spec_hdr *kern_spec;
int err = 0;
- void *kern_spec;
void *ib_spec;
int i;
if (!kern_flow_attr)
return -ENOMEM;
- memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
- err = ib_copy_from_udata(kern_flow_attr + 1, ucore,
+ *kern_flow_attr = cmd.flow_attr;
+ err = ib_copy_from_udata(&kern_flow_attr->flow_specs, ucore,
cmd.flow_attr.size);
if (err)
goto err_free_attr;
goto err_uobj;
}
+ if (qp->qp_type != IB_QPT_UD && qp->qp_type != IB_QPT_RAW_PACKET) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
flow_attr = kzalloc(struct_size(flow_attr, flows,
cmd.flow_attr.num_of_specs), GFP_KERNEL);
if (!flow_attr) {
flow_attr->flags = kern_flow_attr->flags;
flow_attr->size = sizeof(*flow_attr);
- kern_spec = kern_flow_attr + 1;
+ kern_spec = kern_flow_attr->flow_specs;
ib_spec = flow_attr + 1;
for (i = 0; i < flow_attr->num_of_specs &&
- cmd.flow_attr.size > offsetof(struct ib_uverbs_flow_spec, reserved) &&
- cmd.flow_attr.size >=
- ((struct ib_uverbs_flow_spec *)kern_spec)->size; i++) {
- err = kern_spec_to_ib_spec(file->ucontext, kern_spec, ib_spec,
- uflow_res);
+ cmd.flow_attr.size >= sizeof(*kern_spec) &&
+ cmd.flow_attr.size >= kern_spec->size;
+ i++) {
+ err = kern_spec_to_ib_spec(
+ file->ucontext, (struct ib_uverbs_flow_spec *)kern_spec,
+ ib_spec, uflow_res);
if (err)
goto err_free;
flow_attr->size +=
((union ib_flow_spec *) ib_spec)->size;
- cmd.flow_attr.size -= ((struct ib_uverbs_flow_spec *)kern_spec)->size;
- kern_spec += ((struct ib_uverbs_flow_spec *) kern_spec)->size;
+ cmd.flow_attr.size -= kern_spec->size;
+ kern_spec = ((void *)kern_spec) + kern_spec->size;
ib_spec += ((union ib_flow_spec *) ib_spec)->size;
}
if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
if (ret)
return ret;
- if (!file->ucontext &&
- (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended))
- return -EINVAL;
-
if (extended) {
if (count < (sizeof(hdr) + sizeof(ex_hdr)))
return -EINVAL;
goto out;
}
+ /*
+ * Must be after the ib_dev check, as once the RCU clears ib_dev ==
+ * NULL means ucontext == NULL
+ */
+ if (!file->ucontext &&
+ (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (!verify_command_mask(ib_dev, command, extended)) {
ret = -EOPNOTSUPP;
goto out;
/* Completion queues */
-struct ib_cq *ib_create_cq(struct ib_device *device,
- ib_comp_handler comp_handler,
- void (*event_handler)(struct ib_event *, void *),
- void *cq_context,
- const struct ib_cq_init_attr *cq_attr)
+struct ib_cq *__ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context,
+ const struct ib_cq_init_attr *cq_attr,
+ const char *caller)
{
struct ib_cq *cq;
cq->cq_context = cq_context;
atomic_set(&cq->usecnt, 0);
cq->res.type = RDMA_RESTRACK_CQ;
+ cq->res.kern_name = caller;
rdma_restrack_add(&cq->res);
}
return cq;
}
-EXPORT_SYMBOL(ib_create_cq);
+EXPORT_SYMBOL(__ib_create_cq);
int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
{
struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
- if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+ if (unlikely(mhp->mpl_len == mhp->attr.pbl_size))
return -ENOMEM;
mhp->mpl[mhp->mpl_len++] = addr;
lockdep_assert_held(&qp->s_lock);
ps->s_txreq = get_txreq(ps->dev, qp);
- if (IS_ERR(ps->s_txreq))
+ if (!ps->s_txreq)
goto bail_no_tx;
if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
/*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
int middle = 0;
ps->s_txreq = get_txreq(ps->dev, qp);
- if (IS_ERR(ps->s_txreq))
+ if (!ps->s_txreq)
goto bail_no_tx;
if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
/*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
u32 lid;
ps->s_txreq = get_txreq(ps->dev, qp);
- if (IS_ERR(ps->s_txreq))
+ if (!ps->s_txreq)
goto bail_no_tx;
if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
/*
- * Copyright(c) 2016 - 2017 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
struct rvt_qp *qp)
__must_hold(&qp->s_lock)
{
- struct verbs_txreq *tx = ERR_PTR(-EBUSY);
+ struct verbs_txreq *tx = NULL;
write_seqlock(&dev->txwait_lock);
if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
/*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
if (unlikely(!tx)) {
/* call slow path to get the lock */
tx = __get_txreq(dev, qp);
- if (IS_ERR(tx))
+ if (!tx)
return tx;
}
tx->qp = qp;
}
if (flags & IB_MR_REREG_ACCESS) {
- if (ib_access_writable(mr_access_flags) && !mmr->umem->writable)
- return -EPERM;
+ if (ib_access_writable(mr_access_flags) &&
+ !mmr->umem->writable) {
+ err = -EPERM;
+ goto release_mpt_entry;
+ }
err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry,
convert_access(mr_access_flags));
if (!mcounters->hw_cntrs_hndl) {
mcounters->hw_cntrs_hndl = mlx5_fc_create(
to_mdev(ibcounters->device)->mdev, false);
- if (!mcounters->hw_cntrs_hndl) {
- ret = -ENOMEM;
+ if (IS_ERR(mcounters->hw_cntrs_hndl)) {
+ ret = PTR_ERR(mcounters->hw_cntrs_hndl);
goto free;
}
hw_hndl = true;
return ERR_PTR(-ENOMEM);
err = ib_copy_from_udata(ucmd, udata, required_ucmd_sz);
- if (err) {
- kfree(ucmd);
- return ERR_PTR(err);
- }
+ if (err)
+ goto free_ucmd;
}
- if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
- return ERR_PTR(-ENOMEM);
+ if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO) {
+ err = -ENOMEM;
+ goto free_ucmd;
+ }
if (domain != IB_FLOW_DOMAIN_USER ||
flow_attr->port > dev->num_ports ||
(flow_attr->flags & ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP |
- IB_FLOW_ATTR_FLAGS_EGRESS)))
- return ERR_PTR(-EINVAL);
+ IB_FLOW_ATTR_FLAGS_EGRESS))) {
+ err = -EINVAL;
+ goto free_ucmd;
+ }
if (is_egress &&
(flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
- flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT))
- return ERR_PTR(-EINVAL);
+ flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
+ err = -EINVAL;
+ goto free_ucmd;
+ }
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
- if (!dst)
- return ERR_PTR(-ENOMEM);
+ if (!dst) {
+ err = -ENOMEM;
+ goto free_ucmd;
+ }
mutex_lock(&dev->flow_db->lock);
unlock:
mutex_unlock(&dev->flow_db->lock);
kfree(dst);
+free_ucmd:
kfree(ucmd);
- kfree(handler);
return ERR_PTR(err);
}
dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
MLX5_CAP_GEN(mdev, num_vhca_ports));
- if (MLX5_VPORT_MANAGER(mdev) &&
+ if (MLX5_ESWITCH_MANAGER(mdev) &&
mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
desc_size = sizeof(struct mlx5_wqe_srq_next_seg) +
srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg);
- if (desc_size == 0 || srq->msrq.max_gs > desc_size)
- return ERR_PTR(-EINVAL);
+ if (desc_size == 0 || srq->msrq.max_gs > desc_size) {
+ err = -EINVAL;
+ goto err_srq;
+ }
desc_size = roundup_pow_of_two(desc_size);
desc_size = max_t(size_t, 32, desc_size);
- if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg))
- return ERR_PTR(-EINVAL);
+ if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) {
+ err = -EINVAL;
+ goto err_srq;
+ }
srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) /
sizeof(struct mlx5_wqe_data_seg);
srq->msrq.wqe_shift = ilog2(desc_size);
buf_size = srq->msrq.max * desc_size;
- if (buf_size < desc_size)
- return ERR_PTR(-EINVAL);
+ if (buf_size < desc_size) {
+ err = -EINVAL;
+ goto err_srq;
+ }
in.type = init_attr->srq_type;
if (pd->uobject)
}
if (attr_mask & (IB_QP_AV | IB_QP_PATH_MTU)) {
+ if (rdma_protocol_iwarp(&dev->ibdev, 1))
+ return -EINVAL;
+
if (attr_mask & IB_QP_PATH_MTU) {
if (attr->path_mtu < IB_MTU_256 ||
attr->path_mtu > IB_MTU_4096) {
} else {
goto exit;
}
+ if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
+ qp->sq_sig_type == IB_SIGNAL_ALL_WR)
+ rxe_run_task(&qp->comp.task, 1);
qp->req.wqe_index = next_index(qp->sq.queue,
qp->req.wqe_index);
goto next_wqe;
if (fill_packet(qp, wqe, &pkt, skb, payload)) {
pr_debug("qp#%d Error during fill packet\n", qp_num(qp));
+ kfree_skb(skb);
goto err;
}
goto next_wqe;
err:
- kfree_skb(skb);
wqe->status = IB_WC_LOC_PROT_ERR;
wqe->state = wqe_state_error;
__rxe_do_task(&qp->comp.task);
Say N here if you have a headless (no monitor, no keyboard) system.
- More information is available: <file:Documentation/input/input.txt>
+ More information is available: <file:Documentation/input/input.rst>
If unsure, say Y.
If unsure, say Y.
- More information is available: <file:Documentation/input/joystick.txt>
+ More information is available: <file:Documentation/input/joydev/joystick.rst>
To compile this driver as a module, choose M here: the
module will be called joydev.
* inactive, or if the tool type is changed, a new tracking id is
* assigned to the slot. The tool type is only reported if the
* corresponding absbit field is set.
+ *
+ * Returns true if contact is active.
*/
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
unsigned int tool_type, bool active)
{
struct input_mt *mt = dev->mt;
int id;
if (!mt)
- return;
+ return false;
slot = &mt->slots[mt->slot];
slot->frame = mt->frame;
if (!active) {
input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, -1);
- return;
+ return false;
}
id = input_mt_get_value(slot, ABS_MT_TRACKING_ID);
- if (id < 0 || input_mt_get_value(slot, ABS_MT_TOOL_TYPE) != tool_type)
+ if (id < 0)
id = input_mt_new_trkid(mt);
input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, id);
input_event(dev, EV_ABS, ABS_MT_TOOL_TYPE, tool_type);
+
+ return true;
}
EXPORT_SYMBOL(input_mt_report_slot_state);
and the list of supported devices will be displayed. This option
doesn't affect the kernel.
- Please read the file <file:Documentation/input/joystick.txt> which
+ Please read the file <file:Documentation/input/joydev/joystick.rst> which
contains more information.
if INPUT_JOYSTICK
Flightstick Pro, ThrustMaster FCS, 6 and 8 button gamepads, or
Saitek Cyborg joysticks.
- Please read the file <file:Documentation/input/joystick.txt> which
+ Please read the file <file:Documentation/input/joydev/joystick.rst> which
contains more information.
To compile this driver as a module, choose M here: the
gamepad, Sega Saturn gamepad, or a Multisystem -- Atari, Amiga,
Commodore, Amstrad CPC joystick connected to your parallel port.
For more information on how to use the driver please read
- <file:Documentation/input/joystick-parport.txt>.
+ <file:Documentation/input/devices/joystick-parport.rst>.
To compile this driver as a module, choose M here: the
module will be called db9.
Sony PlayStation gamepad or a Multisystem -- Atari, Amiga,
Commodore, Amstrad CPC joystick connected to your parallel port.
For more information on how to use the driver please read
- <file:Documentation/input/joystick-parport.txt>.
+ <file:Documentation/input/devices/joystick-parport.rst>.
To compile this driver as a module, choose M here: the
module will be called gamecon.
Say Y here if you have the TurboGraFX interface by Steffen Schwenke,
and want to use it with Multisystem -- Atari, Amiga, Commodore,
Amstrad CPC joystick. For more information on how to use the driver
- please read <file:Documentation/input/joystick-parport.txt>.
+ please read <file:Documentation/input/devices/joystick-parport.rst>.
To compile this driver as a module, choose M here: the
module will be called turbografx.
and/or "Event interface support" (CONFIG_INPUT_EVDEV) as well.
For information about how to connect the X-Box pad to USB, see
- <file:Documentation/input/xpad.txt>.
+ <file:Documentation/input/devices/xpad.rst>.
To compile this driver as a module, choose M here: the
module will be called xpad.
Say Y or M here if you have a Walkera WK-0701 transmitter which is
supplied with a ready to fly Walkera helicopters such as HM36,
HM37, HM60 and want to use it via parport as a joystick. More
- information is available: <file:Documentation/input/walkera0701.txt>
+ information is available: <file:Documentation/input/devices/walkera0701.rst>
To compile this driver as a module, choose M here: the
module will be called walkera0701.
connected to your serial (COM) port.
You will need an additional utility called inputattach, see
- <file:Documentation/input/joystick.txt>
- and <file:Documentation/input/ff.txt>.
+ <file:Documentation/input/joydev/joystick.rst>
+ and <file:Documentation/input/ff.rst>.
*
* Copyright (c) 2008 Peter Popovec
*
- * More about driver: <file:Documentation/input/walkera0701.txt>
+ * More about driver: <file:Documentation/input/devices/walkera0701.rst>
*/
/*
u8 mapping;
u8 xtype;
} xpad_device[] = {
- { 0x0079, 0x18d4, "GPD Win 2 Controller", 0, XTYPE_XBOX360 },
+ { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 },
{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
static irqreturn_t events_interrupt(int irq, void *dev_id)
{
struct event_dev *edev = dev_id;
- unsigned type, code, value;
+ unsigned int type, code, value;
type = __raw_readl(edev->addr + REG_READ);
code = __raw_readl(edev->addr + REG_READ);
}
static void events_import_bits(struct event_dev *edev,
- unsigned long bits[], unsigned type, size_t count)
+ unsigned long bits[], unsigned int type, size_t count)
{
void __iomem *addr = edev->addr;
int i, j;
for (j = 0; j < ARRAY_SIZE(val); j++) {
int offset = (i * ARRAY_SIZE(val) + j) * sizeof(u32);
+
val[j] = __raw_readl(edev->addr + REG_DATA + offset);
}
struct input_dev *input_dev;
struct event_dev *edev;
struct resource *res;
- unsigned keymapnamelen;
+ unsigned int keymapnamelen;
void __iomem *addr;
int irq;
int i;
for (i = 0; i < keymapnamelen; i++)
edev->name[i] = __raw_readb(edev->addr + REG_DATA + i);
- pr_debug("events_probe() keymap=%s\n", edev->name);
+ pr_debug("%s: keymap=%s\n", __func__, edev->name);
input_dev->name = edev->name;
input_dev->id.bustype = BUS_HOST;
#define HIL_DATA 0x1
#define HIL_CMD 0x3
#define HIL_IRQ 2
- #define hil_readb(p) readb(p)
- #define hil_writeb(v,p) writeb((v),(p))
+ #define hil_readb(p) readb((const volatile void __iomem *)(p))
+ #define hil_writeb(v, p) writeb((v), (volatile void __iomem *)(p))
#else
#error "HIL is not supported on this platform"
usb sound driver, so you might want to enable that as well.
For information about how to use these additional functions, see
- <file:Documentation/input/yealink.txt>.
+ <file:Documentation/input/devices/yealink.rst>.
To compile this driver as a module, choose M here: the module will be
called yealink.
depends on GPIOLIB || COMPILE_TEST
help
Say Y here to add support for rotary encoders connected to GPIO lines.
- Check file:Documentation/input/rotary-encoder.txt for more
+ Check file:Documentation/input/devices/rotary-encoder.rst for more
information.
To compile this driver as a module, choose M here: the
To compile this driver as a module, choose M here: the
module will be called rave-sp-pwrbutton.
+config INPUT_SC27XX_VIBRA
+ tristate "Spreadtrum sc27xx vibrator support"
+ depends on MFD_SC27XX_PMIC || COMPILE_TEST
+ select INPUT_FF_MEMLESS
+ help
+ This option enables support for Spreadtrum sc27xx vibrator driver.
+
+ To compile this driver as a module, choose M here. The module will
+ be called sc27xx_vibra.
+
endif
obj-$(CONFIG_INPUT_AXP20X_PEK) += axp20x-pek.o
obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER) += rotary_encoder.o
obj-$(CONFIG_INPUT_RK805_PWRKEY) += rk805-pwrkey.o
+obj-$(CONFIG_INPUT_SC27XX_VIBRA) += sc27xx-vibra.o
obj-$(CONFIG_INPUT_SGI_BTNS) += sgi_btns.o
obj-$(CONFIG_INPUT_SIRFSOC_ONKEY) += sirfsoc-onkey.o
obj-$(CONFIG_INPUT_SOC_BUTTON_ARRAY) += soc_button_array.o
* state machine code inspired by code from Tim Ruetz
*
* A generic driver for rotary encoders connected to GPIO lines.
- * See file:Documentation/input/rotary-encoder.txt for more information
+ * See file:Documentation/input/devices/rotary-encoder.rst for more information
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Spreadtrum Communications Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/input.h>
+#include <linux/workqueue.h>
+
+#define CUR_DRV_CAL_SEL GENMASK(13, 12)
+#define SLP_LDOVIBR_PD_EN BIT(9)
+#define LDO_VIBR_PD BIT(8)
+
+struct vibra_info {
+ struct input_dev *input_dev;
+ struct work_struct play_work;
+ struct regmap *regmap;
+ u32 base;
+ u32 strength;
+ bool enabled;
+};
+
+static void sc27xx_vibra_set(struct vibra_info *info, bool on)
+{
+ if (on) {
+ regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD, 0);
+ regmap_update_bits(info->regmap, info->base,
+ SLP_LDOVIBR_PD_EN, 0);
+ info->enabled = true;
+ } else {
+ regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD,
+ LDO_VIBR_PD);
+ regmap_update_bits(info->regmap, info->base,
+ SLP_LDOVIBR_PD_EN, SLP_LDOVIBR_PD_EN);
+ info->enabled = false;
+ }
+}
+
+static int sc27xx_vibra_hw_init(struct vibra_info *info)
+{
+ return regmap_update_bits(info->regmap, info->base, CUR_DRV_CAL_SEL, 0);
+}
+
+static void sc27xx_vibra_play_work(struct work_struct *work)
+{
+ struct vibra_info *info = container_of(work, struct vibra_info,
+ play_work);
+
+ if (info->strength && !info->enabled)
+ sc27xx_vibra_set(info, true);
+ else if (info->strength == 0 && info->enabled)
+ sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_play(struct input_dev *input, void *data,
+ struct ff_effect *effect)
+{
+ struct vibra_info *info = input_get_drvdata(input);
+
+ info->strength = effect->u.rumble.weak_magnitude;
+ schedule_work(&info->play_work);
+
+ return 0;
+}
+
+static void sc27xx_vibra_close(struct input_dev *input)
+{
+ struct vibra_info *info = input_get_drvdata(input);
+
+ cancel_work_sync(&info->play_work);
+ if (info->enabled)
+ sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_probe(struct platform_device *pdev)
+{
+ struct vibra_info *info;
+ int error;
+
+ info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ info->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+ if (!info->regmap) {
+ dev_err(&pdev->dev, "failed to get vibrator regmap.\n");
+ return -ENODEV;
+ }
+
+ error = device_property_read_u32(&pdev->dev, "reg", &info->base);
+ if (error) {
+ dev_err(&pdev->dev, "failed to get vibrator base address.\n");
+ return error;
+ }
+
+ info->input_dev = devm_input_allocate_device(&pdev->dev);
+ if (!info->input_dev) {
+ dev_err(&pdev->dev, "failed to allocate input device.\n");
+ return -ENOMEM;
+ }
+
+ info->input_dev->name = "sc27xx:vibrator";
+ info->input_dev->id.version = 0;
+ info->input_dev->close = sc27xx_vibra_close;
+
+ input_set_drvdata(info->input_dev, info);
+ input_set_capability(info->input_dev, EV_FF, FF_RUMBLE);
+ INIT_WORK(&info->play_work, sc27xx_vibra_play_work);
+ info->enabled = false;
+
+ error = sc27xx_vibra_hw_init(info);
+ if (error) {
+ dev_err(&pdev->dev, "failed to initialize the vibrator.\n");
+ return error;
+ }
+
+ error = input_ff_create_memless(info->input_dev, NULL,
+ sc27xx_vibra_play);
+ if (error) {
+ dev_err(&pdev->dev, "failed to register vibrator to FF.\n");
+ return error;
+ }
+
+ error = input_register_device(info->input_dev);
+ if (error) {
+ dev_err(&pdev->dev, "failed to register input device.\n");
+ return error;
+ }
+
+ return 0;
+}
+
+static const struct of_device_id sc27xx_vibra_of_match[] = {
+ { .compatible = "sprd,sc2731-vibrator", },
+ {}
+};
+MODULE_DEVICE_TABLE(of, sc27xx_vibra_of_match);
+
+static struct platform_driver sc27xx_vibra_driver = {
+ .driver = {
+ .name = "sc27xx-vibrator",
+ .of_match_table = sc27xx_vibra_of_match,
+ },
+ .probe = sc27xx_vibra_probe,
+};
+
+module_platform_driver(sc27xx_vibra_driver);
+
+MODULE_DESCRIPTION("Spreadtrum SC27xx Vibrator Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Xiaotong Lu <xiaotong.lu@spreadtrum.com>");
This driver exposes some configuration registers via sysfs
entries. For further information,
- see <file:Documentation/input/elantech.txt>.
+ see <file:Documentation/input/devices/elantech.rst>.
If unsure, say N.
scrolling in X11.
For further information, see
- <file:Documentation/input/appletouch.txt>.
+ <file:Documentation/input/devices/appletouch.rst>.
To compile this driver as a module, choose M here: the
module will be called appletouch.
The interface is currently identical to the appletouch interface,
for further information, see
- <file:Documentation/input/appletouch.txt>.
+ <file:Documentation/input/devices/appletouch.rst>.
To compile this driver as a module, choose M here: the
module will be called bcm5974.
static void alps_set_abs_params_ss4_v2(struct alps_data *priv,
struct input_dev *dev1);
-/* Packet formats are described in Documentation/input/alps.txt */
+/* Packet formats are described in Documentation/input/devices/alps.rst */
static bool alps_is_valid_first_byte(struct alps_data *priv,
unsigned char data)
#define ETP_DISABLE_POWER 0x0001
#define ETP_PRESSURE_OFFSET 25
+#define ETP_CALIBRATE_MAX_LEN 3
+
/* IAP Firmware handling */
#define ETP_PRODUCT_ID_FORMAT_STRING "%d.0"
#define ETP_FW_NAME "elan_i2c_" ETP_PRODUCT_ID_FORMAT_STRING ".bin"
int tries = 20;
int retval;
int error;
- u8 val[3];
+ u8 val[ETP_CALIBRATE_MAX_LEN];
retval = mutex_lock_interruptible(&data->sysfs_mutex);
if (retval)
{ "ELAN060C", 0 },
{ "ELAN0611", 0 },
{ "ELAN0612", 0 },
+ { "ELAN0618", 0 },
+ { "ELAN061D", 0 },
+ { "ELAN0622", 0 },
{ "ELAN1000", 0 },
{ }
};
static int elan_smbus_initialize(struct i2c_client *client)
{
u8 check[ETP_SMBUS_HELLOPACKET_LEN] = { 0x55, 0x55, 0x55, 0x55, 0x55 };
- u8 values[ETP_SMBUS_HELLOPACKET_LEN] = { 0, 0, 0, 0, 0 };
+ u8 values[I2C_SMBUS_BLOCK_MAX] = {0};
int len, error;
/* Get hello packet */
static int elan_smbus_calibrate_result(struct i2c_client *client, u8 *val)
{
int error;
+ u8 buf[I2C_SMBUS_BLOCK_MAX] = {0};
+
+ BUILD_BUG_ON(ETP_CALIBRATE_MAX_LEN > sizeof(buf));
error = i2c_smbus_read_block_data(client,
- ETP_SMBUS_CALIBRATE_QUERY, val);
+ ETP_SMBUS_CALIBRATE_QUERY, buf);
if (error < 0)
return error;
+ memcpy(val, buf, ETP_CALIBRATE_MAX_LEN);
return 0;
}
{
int len;
+ BUILD_BUG_ON(I2C_SMBUS_BLOCK_MAX > ETP_SMBUS_REPORT_LEN);
+
len = i2c_smbus_read_block_data(client,
ETP_SMBUS_PACKET_QUERY,
&report[ETP_SMBUS_REPORT_OFFSET]);
else if (ic_version == 7 && etd->info.samples[1] == 0x2A)
sanity_check = ((packet[3] & 0x1c) == 0x10);
else
- sanity_check = ((packet[0] & 0x0c) == 0x04 &&
+ sanity_check = ((packet[0] & 0x08) == 0x00 &&
(packet[3] & 0x1c) == 0x10);
if (!sanity_check)
{ }
};
+static const char * const middle_button_pnp_ids[] = {
+ "LEN2131", /* ThinkPad P52 w/ NFC */
+ "LEN2132", /* ThinkPad P52 */
+ NULL
+};
+
/*
* Set the appropriate event bits for the input subsystem
*/
__clear_bit(EV_REL, dev->evbit);
__set_bit(BTN_LEFT, dev->keybit);
- if (dmi_check_system(elantech_dmi_has_middle_button))
+ if (dmi_check_system(elantech_dmi_has_middle_button) ||
+ psmouse_matches_pnp_id(psmouse, middle_button_pnp_ids))
__set_bit(BTN_MIDDLE, dev->keybit);
__set_bit(BTN_RIGHT, dev->keybit);
else
input_report_rel(dev, REL_WHEEL, -wheel);
- input_report_key(dev, BTN_SIDE, BIT(4));
- input_report_key(dev, BTN_EXTRA, BIT(5));
+ input_report_key(dev, BTN_SIDE, packet[3] & BIT(4));
+ input_report_key(dev, BTN_EXTRA, packet[3] & BIT(5));
break;
}
break;
input_report_rel(dev, REL_WHEEL, -(s8) packet[3]);
/* Extra buttons on Genius NewNet 3D */
- input_report_key(dev, BTN_SIDE, BIT(6));
- input_report_key(dev, BTN_EXTRA, BIT(7));
+ input_report_key(dev, BTN_SIDE, packet[0] & BIT(6));
+ input_report_key(dev, BTN_EXTRA, packet[0] & BIT(7));
break;
case PSMOUSE_THINKPS:
/* Extra button on ThinkingMouse */
- input_report_key(dev, BTN_EXTRA, BIT(3));
+ input_report_key(dev, BTN_EXTRA, packet[0] & BIT(3));
/*
* Without this bit of weirdness moving up gives wildly
* Cortron PS2 Trackball reports SIDE button in the
* 4th bit of the first byte.
*/
- input_report_key(dev, BTN_SIDE, BIT(3));
+ input_report_key(dev, BTN_SIDE, packet[0] & BIT(3));
packet[0] |= BIT(3);
break;
#
config RMI4_CORE
tristate "Synaptics RMI4 bus support"
+ select IRQ_DOMAIN
help
Say Y here if you want to support the Synaptics RMI4 bus. This is
required for all RMI4 device support.
if (obj->type == RMI_2D_OBJECT_NONE)
return;
- if (axis_align->swap_axes)
- swap(obj->x, obj->y);
-
if (axis_align->flip_x)
obj->x = sensor->max_x - obj->x;
if (axis_align->flip_y)
obj->y = sensor->max_y - obj->y;
+ if (axis_align->swap_axes)
+ swap(obj->x, obj->y);
+
/*
* Here checking if X offset or y offset are specified is
* redundant. We just add the offsets or clip the values.
x = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)x));
y = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)y));
- if (axis_align->swap_axes)
- swap(x, y);
-
if (axis_align->flip_x)
x = min(RMI_2D_REL_POS_MAX, -x);
if (axis_align->flip_y)
y = min(RMI_2D_REL_POS_MAX, -y);
+ if (axis_align->swap_axes)
+ swap(x, y);
+
if (x || y) {
input_report_rel(sensor->input, REL_X, x);
input_report_rel(sensor->input, REL_Y, y);
struct input_dev *input = sensor->input;
int res_x;
int res_y;
+ int max_x, max_y;
int input_flags = 0;
if (sensor->report_abs) {
- if (sensor->axis_align.swap_axes) {
- swap(sensor->max_x, sensor->max_y);
- swap(sensor->axis_align.clip_x_low,
- sensor->axis_align.clip_y_low);
- swap(sensor->axis_align.clip_x_high,
- sensor->axis_align.clip_y_high);
- }
-
sensor->min_x = sensor->axis_align.clip_x_low;
if (sensor->axis_align.clip_x_high)
sensor->max_x = min(sensor->max_x,
sensor->axis_align.clip_y_high);
set_bit(EV_ABS, input->evbit);
- input_set_abs_params(input, ABS_MT_POSITION_X, 0, sensor->max_x,
- 0, 0);
- input_set_abs_params(input, ABS_MT_POSITION_Y, 0, sensor->max_y,
- 0, 0);
+
+ max_x = sensor->max_x;
+ max_y = sensor->max_y;
+ if (sensor->axis_align.swap_axes)
+ swap(max_x, max_y);
+ input_set_abs_params(input, ABS_MT_POSITION_X, 0, max_x, 0, 0);
+ input_set_abs_params(input, ABS_MT_POSITION_Y, 0, max_y, 0, 0);
if (sensor->x_mm && sensor->y_mm) {
res_x = (sensor->max_x - sensor->min_x) / sensor->x_mm;
res_y = (sensor->max_y - sensor->min_y) / sensor->y_mm;
+ if (sensor->axis_align.swap_axes)
+ swap(res_x, res_y);
input_abs_set_res(input, ABS_X, res_x);
input_abs_set_res(input, ABS_Y, res_y);
#include <linux/kernel.h>
#include <linux/device.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
#include <linux/list.h>
#include <linux/pm.h>
#include <linux/rmi.h>
{}
#endif
+static struct irq_chip rmi_irq_chip = {
+ .name = "rmi4",
+};
+
+static int rmi_create_function_irq(struct rmi_function *fn,
+ struct rmi_function_handler *handler)
+{
+ struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
+ int i, error;
+
+ for (i = 0; i < fn->num_of_irqs; i++) {
+ set_bit(fn->irq_pos + i, fn->irq_mask);
+
+ fn->irq[i] = irq_create_mapping(drvdata->irqdomain,
+ fn->irq_pos + i);
+
+ irq_set_chip_data(fn->irq[i], fn);
+ irq_set_chip_and_handler(fn->irq[i], &rmi_irq_chip,
+ handle_simple_irq);
+ irq_set_nested_thread(fn->irq[i], 1);
+
+ error = devm_request_threaded_irq(&fn->dev, fn->irq[i], NULL,
+ handler->attention, IRQF_ONESHOT,
+ dev_name(&fn->dev), fn);
+ if (error) {
+ dev_err(&fn->dev, "Error %d registering IRQ\n", error);
+ return error;
+ }
+ }
+
+ return 0;
+}
+
static int rmi_function_probe(struct device *dev)
{
struct rmi_function *fn = to_rmi_function(dev);
if (handler->probe) {
error = handler->probe(fn);
- return error;
+ if (error)
+ return error;
+ }
+
+ if (fn->num_of_irqs && handler->attention) {
+ error = rmi_create_function_irq(fn, handler);
+ if (error)
+ return error;
}
return 0;
void rmi_unregister_function(struct rmi_function *fn)
{
+ int i;
+
rmi_dbg(RMI_DEBUG_CORE, &fn->dev, "Unregistering F%02X.\n",
fn->fd.function_number);
device_del(&fn->dev);
of_node_put(fn->dev.of_node);
put_device(&fn->dev);
+
+ for (i = 0; i < fn->num_of_irqs; i++)
+ irq_dispose_mapping(fn->irq[i]);
+
}
/**
struct rmi_device;
+/*
+ * The interrupt source count in the function descriptor can represent up to
+ * 6 interrupt sources in the normal manner.
+ */
+#define RMI_FN_MAX_IRQS 6
+
/**
* struct rmi_function - represents the implementation of an RMI4
* function for a particular device (basically, a driver for that RMI4 function)
* @irq_pos: The position in the irq bitfield this function holds
* @irq_mask: For convenience, can be used to mask IRQ bits off during ATTN
* interrupt handling.
+ * @irqs: assigned virq numbers (up to num_of_irqs)
*
* @node: entry in device's list of functions
*/
struct list_head node;
unsigned int num_of_irqs;
+ int irq[RMI_FN_MAX_IRQS];
unsigned int irq_pos;
unsigned long irq_mask[];
};
void (*remove)(struct rmi_function *fn);
int (*config)(struct rmi_function *fn);
int (*reset)(struct rmi_function *fn);
- int (*attention)(struct rmi_function *fn, unsigned long *irq_bits);
+ irqreturn_t (*attention)(int irq, void *ctx);
int (*suspend)(struct rmi_function *fn);
int (*resume)(struct rmi_function *fn);
};
#include <linux/pm.h>
#include <linux/slab.h>
#include <linux/of.h>
+#include <linux/irqdomain.h>
#include <uapi/linux/input.h>
#include <linux/rmi.h>
#include "rmi_bus.h"
return 0;
}
-static void process_one_interrupt(struct rmi_driver_data *data,
- struct rmi_function *fn)
-{
- struct rmi_function_handler *fh;
-
- if (!fn || !fn->dev.driver)
- return;
-
- fh = to_rmi_function_handler(fn->dev.driver);
- if (fh->attention) {
- bitmap_and(data->fn_irq_bits, data->irq_status, fn->irq_mask,
- data->irq_count);
- if (!bitmap_empty(data->fn_irq_bits, data->irq_count))
- fh->attention(fn, data->fn_irq_bits);
- }
-}
-
static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
{
struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
struct device *dev = &rmi_dev->dev;
- struct rmi_function *entry;
+ int i;
int error;
if (!data)
*/
mutex_unlock(&data->irq_mutex);
- /*
- * It would be nice to be able to use irq_chip to handle these
- * nested IRQs. Unfortunately, most of the current customers for
- * this driver are using older kernels (3.0.x) that don't support
- * the features required for that. Once they've shifted to more
- * recent kernels (say, 3.3 and higher), this should be switched to
- * use irq_chip.
- */
- list_for_each_entry(entry, &data->function_list, node)
- process_one_interrupt(data, entry);
+ for_each_set_bit(i, data->irq_status, data->irq_count)
+ handle_nested_irq(irq_find_mapping(data->irqdomain, i));
if (data->input)
input_sync(data->input);
static int rmi_driver_remove(struct device *dev)
{
struct rmi_device *rmi_dev = to_rmi_device(dev);
+ struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
rmi_disable_irq(rmi_dev, false);
+ irq_domain_remove(data->irqdomain);
+ data->irqdomain = NULL;
+
rmi_f34_remove_sysfs(rmi_dev);
rmi_free_function_list(rmi_dev);
{
struct rmi_device *rmi_dev = data->rmi_dev;
struct device *dev = &rmi_dev->dev;
- int irq_count;
+ struct fwnode_handle *fwnode = rmi_dev->xport->dev->fwnode;
+ int irq_count = 0;
size_t size;
int retval;
* being accessed.
*/
rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Counting IRQs.\n", __func__);
- irq_count = 0;
data->bootloader_mode = false;
retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_count_irqs);
if (data->bootloader_mode)
dev_warn(dev, "Device in bootloader mode.\n");
+ /* Allocate and register a linear revmap irq_domain */
+ data->irqdomain = irq_domain_create_linear(fwnode, irq_count,
+ &irq_domain_simple_ops,
+ data);
+ if (!data->irqdomain) {
+ dev_err(&rmi_dev->dev, "Failed to create IRQ domain\n");
+ return -ENOMEM;
+ }
+
data->irq_count = irq_count;
data->num_of_irq_regs = (data->irq_count + 7) / 8;
{
struct rmi_device *rmi_dev = data->rmi_dev;
struct device *dev = &rmi_dev->dev;
- int irq_count;
+ int irq_count = 0;
int retval;
- irq_count = 0;
rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Creating functions.\n", __func__);
retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_create_function);
if (retval < 0) {
return 0;
}
-static int rmi_f01_attention(struct rmi_function *fn,
- unsigned long *irq_bits)
+static irqreturn_t rmi_f01_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
int error;
u8 device_status;
if (error) {
dev_err(&fn->dev,
"Failed to read device status: %d.\n", error);
- return error;
+ return IRQ_RETVAL(error);
}
if (RMI_F01_STATUS_BOOTLOADER(device_status))
error = rmi_dev->driver->reset_handler(rmi_dev);
if (error) {
dev_err(&fn->dev, "Device reset failed: %d\n", error);
- return error;
+ return IRQ_RETVAL(error);
}
}
- return 0;
+ return IRQ_HANDLED;
}
struct rmi_function_handler rmi_f01_handler = {
return 0;
}
-static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f03_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f03_data *f03 = dev_get_drvdata(&fn->dev);
/* First grab the data passed by the transport device */
if (drvdata->attn_data.size < ob_len) {
dev_warn(&fn->dev, "F03 interrupted, but data is missing!\n");
- return 0;
+ return IRQ_HANDLED;
}
memcpy(obs, drvdata->attn_data.data, ob_len);
"%s: Failed to read F03 output buffers: %d\n",
__func__, error);
serio_interrupt(f03->serio, 0, SERIO_TIMEOUT);
- return error;
+ return IRQ_RETVAL(error);
}
}
serio_interrupt(f03->serio, ob_data, serio_flags);
}
- return 0;
+ return IRQ_HANDLED;
}
static void rmi_f03_remove(struct rmi_function *fn)
}
static void rmi_f11_finger_handler(struct f11_data *f11,
- struct rmi_2d_sensor *sensor,
- unsigned long *irq_bits, int num_irq_regs,
- int size)
+ struct rmi_2d_sensor *sensor, int size)
{
const u8 *f_state = f11->data.f_state;
u8 finger_state;
int rel_fingers;
int abs_size = sensor->nbr_fingers * RMI_F11_ABS_BYTES;
- int abs_bits = bitmap_and(f11->result_bits, irq_bits, f11->abs_mask,
- num_irq_regs * 8);
- int rel_bits = bitmap_and(f11->result_bits, irq_bits, f11->rel_mask,
- num_irq_regs * 8);
-
- if (abs_bits) {
+ if (sensor->report_abs) {
if (abs_size > size)
abs_fingers = size / RMI_F11_ABS_BYTES;
else
rmi_f11_abs_pos_process(f11, sensor, &sensor->objs[i],
finger_state, i);
}
- }
- if (rel_bits) {
- if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
- rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
- else
- rel_fingers = sensor->nbr_fingers;
-
- for (i = 0; i < rel_fingers; i++)
- rmi_f11_rel_pos_report(f11, i);
- }
-
- if (abs_bits) {
/*
* the absolute part is made in 2 parts to allow the kernel
* tracking to take place.
}
input_mt_sync_frame(sensor->input);
+ } else if (sensor->report_rel) {
+ if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
+ rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
+ else
+ rel_fingers = sensor->nbr_fingers;
+
+ for (i = 0; i < rel_fingers; i++)
+ rmi_f11_rel_pos_report(f11, i);
}
+
}
static int f11_2d_construct_data(struct f11_data *f11)
return 0;
}
-static int rmi_f11_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f11_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f11_data *f11 = dev_get_drvdata(&fn->dev);
data_base_addr, f11->sensor.data_pkt,
f11->sensor.pkt_size);
if (error < 0)
- return error;
+ return IRQ_RETVAL(error);
}
- rmi_f11_finger_handler(f11, &f11->sensor, irq_bits,
- drvdata->num_of_irq_regs, valid_bytes);
+ rmi_f11_finger_handler(f11, &f11->sensor, valid_bytes);
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f11_resume(struct rmi_function *fn)
rmi_2d_sensor_abs_report(sensor, &sensor->objs[i], i);
}
-static int rmi_f12_attention(struct rmi_function *fn,
- unsigned long *irq_nr_regs)
+static irqreturn_t rmi_f12_attention(int irq, void *ctx)
{
int retval;
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f12_data *f12 = dev_get_drvdata(&fn->dev);
if (retval < 0) {
dev_err(&fn->dev, "Failed to read object data. Code: %d.\n",
retval);
- return retval;
+ return IRQ_RETVAL(retval);
}
}
input_mt_sync_frame(sensor->input);
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f12_write_control_regs(struct rmi_function *fn)
}
}
-static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f30_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct f30_data *f30 = dev_get_drvdata(&fn->dev);
struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
int error;
if (drvdata->attn_data.size < f30->register_count) {
dev_warn(&fn->dev,
"F30 interrupted, but data is missing\n");
- return 0;
+ return IRQ_HANDLED;
}
memcpy(f30->data_regs, drvdata->attn_data.data,
f30->register_count);
dev_err(&fn->dev,
"%s: Failed to read F30 data registers: %d\n",
__func__, error);
- return error;
+ return IRQ_RETVAL(error);
}
}
rmi_f03_commit_buttons(f30->f03);
}
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f30_config(struct rmi_function *fn)
return 0;
}
-static int rmi_f34_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f34_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct f34_data *f34 = dev_get_drvdata(&fn->dev);
int ret;
u8 status;
complete(&f34->v7.cmd_done);
}
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f34_write_blocks(struct f34_data *f34, const void *data,
mutex_unlock(&f54->data_mutex);
}
-static int rmi_f54_attention(struct rmi_function *fn, unsigned long *irqbits)
-{
- return 0;
-}
-
static int rmi_f54_config(struct rmi_function *fn)
{
struct rmi_driver *drv = fn->rmi_dev->driver;
.func = 0x54,
.probe = rmi_f54_probe,
.config = rmi_f54_config,
- .attention = rmi_f54_attention,
.remove = rmi_f54_remove,
};
Say Y here if you plan to use an input device (mouse, joystick,
tablet, 6dof) that communicates over the RS232 serial (COM) port.
- More information is available: <file:Documentation/input/input.txt>
+ More information is available: <file:Documentation/input/input.rst>
If unsure, say Y.
Say Y here if you built a simple parallel port adapter to attach
an additional AT keyboard, XT keyboard or PS/2 mouse.
- More information is available: <file:Documentation/input/input.txt>
+ More information is available: <file:Documentation/input/input.rst>
If unsure, say N.
DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
},
},
+ {
+ /* Lenovo LaVie Z */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
+ },
+ },
{ }
};
{ "GSL3692", 0 },
{ "MSSL1680", 0 },
{ "MSSL0001", 0 },
+ { "MSSL0002", 0 },
{ }
};
MODULE_DEVICE_TABLE(acpi, silead_ts_acpi_match);
* The default values correspond to Mainstone II in QVGA mode
*
* Please read
- * Documentation/input/input-programming.txt for more details.
+ * Documentation/input/input-programming.rst for more details.
*/
static int abs_x[3] = {150, 4000, 5};
config INTEL_IOMMU
bool "Support for Intel IOMMU using DMA Remapping Devices"
depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
- select DMA_DIRECT_OPS
select IOMMU_API
select IOMMU_IOVA
select NEED_DMA_MAP_STATE
#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/dma-mapping.h>
-#include <linux/dma-direct.h>
#include <linux/mempool.h>
#include <linux/memory.h>
#include <linux/cpu.h>
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
static int intel_iommu_ecs = 1;
+static int intel_iommu_pasid28;
static int iommu_identity_mapping;
#define IDENTMAP_ALL 1
#define IDENTMAP_GFX 2
#define IDENTMAP_AZALIA 4
-#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap))
-#define pasid_enabled(iommu) (ecs_enabled(iommu) && ecap_pasid(iommu->ecap))
+/* Broadwell and Skylake have broken ECS support — normal so-called "second
+ * level" translation of DMA requests-without-PASID doesn't actually happen
+ * unless you also set the NESTE bit in an extended context-entry. Which of
+ * course means that SVM doesn't work because it's trying to do nested
+ * translation of the physical addresses it finds in the process page tables,
+ * through the IOVA->phys mapping found in the "second level" page tables.
+ *
+ * The VT-d specification was retroactively changed to change the definition
+ * of the capability bits and pretend that Broadwell/Skylake never happened...
+ * but unfortunately the wrong bit was changed. It's ECS which is broken, but
+ * for some reason it was the PASID capability bit which was redefined (from
+ * bit 28 on BDW/SKL to bit 40 in future).
+ *
+ * So our test for ECS needs to eschew those implementations which set the old
+ * PASID capabiity bit 28, since those are the ones on which ECS is broken.
+ * Unless we are working around the 'pasid28' limitations, that is, by putting
+ * the device into passthrough mode for normal DMA and thus masking the bug.
+ */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+ (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
+/* PASID support is thus enabled if ECS is enabled and *either* of the old
+ * or new capability bits are set. */
+#define pasid_enabled(iommu) (ecs_enabled(iommu) && \
+ (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))
int intel_iommu_gfx_mapped;
EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
printk(KERN_INFO
"Intel-IOMMU: disable extended context table support\n");
intel_iommu_ecs = 0;
+ } else if (!strncmp(str, "pasid28", 7)) {
+ printk(KERN_INFO
+ "Intel-IOMMU: enable pre-production PASID support\n");
+ intel_iommu_pasid28 = 1;
+ iommu_identity_mapping |= IDENTMAP_GFX;
} else if (!strncmp(str, "tboot_noforce", 13)) {
printk(KERN_INFO
"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
dma_addr_t *dma_handle, gfp_t flags,
unsigned long attrs)
{
- void *vaddr;
+ struct page *page = NULL;
+ int order;
- vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
- if (iommu_no_mapping(dev) || !vaddr)
- return vaddr;
+ size = PAGE_ALIGN(size);
+ order = get_order(size);
- *dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
- PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
- dev->coherent_dma_mask);
- if (!*dma_handle)
- goto out_free_pages;
- return vaddr;
+ if (!iommu_no_mapping(dev))
+ flags &= ~(GFP_DMA | GFP_DMA32);
+ else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+ if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+ flags |= GFP_DMA;
+ else
+ flags |= GFP_DMA32;
+ }
+
+ if (gfpflags_allow_blocking(flags)) {
+ unsigned int count = size >> PAGE_SHIFT;
+
+ page = dma_alloc_from_contiguous(dev, count, order, flags);
+ if (page && iommu_no_mapping(dev) &&
+ page_to_phys(page) + size > dev->coherent_dma_mask) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
+
+ if (!page)
+ page = alloc_pages(flags, order);
+ if (!page)
+ return NULL;
+ memset(page_address(page), 0, size);
+
+ *dma_handle = __intel_map_single(dev, page_to_phys(page), size,
+ DMA_BIDIRECTIONAL,
+ dev->coherent_dma_mask);
+ if (*dma_handle)
+ return page_address(page);
+ if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+ __free_pages(page, order);
-out_free_pages:
- dma_direct_free(dev, size, vaddr, *dma_handle, attrs);
return NULL;
}
static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
- if (!iommu_no_mapping(dev))
- intel_unmap(dev, dma_handle, PAGE_ALIGN(size));
- dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+ int order;
+ struct page *page = virt_to_page(vaddr);
+
+ size = PAGE_ALIGN(size);
+ order = get_order(size);
+
+ intel_unmap(dev, dma_handle, size);
+ if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+ __free_pages(page, order);
}
static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
bool
select IRQ_DOMAIN
select IRQ_DOMAIN_HIERARCHY
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config ARM_GIC_PM
config ARM_GIC_V3
bool
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select IRQ_DOMAIN_HIERARCHY
select PARTITION_PERCPU
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config ARM_VIC
bool
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
config ARM_VIC_NR
int
bool
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config ATMEL_AIC5_IRQ
bool
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config I8259
config FARADAY_FTINTC010
bool
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config HISILICON_IRQ_MBIGEN
bool
depends on ARCH_CLPS711X
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
default y
config ORION_IRQCHIP
bool
select IRQ_DOMAIN
- select MULTI_IRQ_HANDLER
+ select GENERIC_IRQ_MULTI_HANDLER
config PIC32_EVIC
bool
fail:
irq_domain_free_irqs_parent(domain, virq, nr_irqs);
- gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs));
+ gicv2m_unalloc_msi(v2m, hwirq, nr_irqs);
return err;
}
*/
info->scratchpad[0].ul = mc_bus_dev->icid;
msi_info = msi_get_domain_info(msi_domain->parent);
+
+ /* Allocate at least 32 MSIs, and always as a power of 2 */
+ nvec = max_t(int, 32, roundup_pow_of_two(nvec));
return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
}
{
struct pci_dev *pdev, *alias_dev;
struct msi_domain_info *msi_info;
- int alias_count = 0;
+ int alias_count = 0, minnvec = 1;
if (!dev_is_pci(dev))
return -EINVAL;
/* ITS specific DeviceID, as the core ITS ignores dev. */
info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
- return msi_info->ops->msi_prepare(domain->parent,
- dev, max(nvec, alias_count), info);
+ /*
+ * Always allocate a power of 2, and special case device 0 for
+ * broken systems where the DevID is not wired (and all devices
+ * appear as DevID 0). For that reason, we generously allocate a
+ * minimum of 32 MSIs for DevID 0. If you want more because all
+ * your devices are aliasing to DevID 0, consider fixing your HW.
+ */
+ nvec = max(nvec, alias_count);
+ if (!info->scratchpad[0].ul)
+ minnvec = 32;
+ nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+ return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
}
static struct msi_domain_ops its_pci_msi_ops = {
/* ITS specific DeviceID, as the core ITS ignores dev. */
info->scratchpad[0].ul = dev_id;
+ /* Allocate at least 32 MSIs, and always as a power of 2 */
+ nvec = max_t(int, 32, roundup_pow_of_two(nvec));
return msi_info->ops->msi_prepare(domain->parent,
dev, nvec, info);
}
#include <linux/dma-iommu.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/msi.h>
} vpe_proxy;
static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
static struct rdists *gic_rdists;
static struct irq_domain *its_parent;
return its->collections + its_dev->event_map.col_map[event];
}
+static struct its_collection *valid_col(struct its_collection *col)
+{
+ if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(0, 15)))
+ return NULL;
+
+ return col;
+}
+
+static struct its_vpe *valid_vpe(struct its_node *its, struct its_vpe *vpe)
+{
+ if (valid_col(its->collections + vpe->col_idx))
+ return vpe;
+
+ return NULL;
+}
+
/*
* ITS command descriptors - parameters to be encoded in a command
* block.
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_movi_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_discard_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_inv_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_int_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_clear_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_invall_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vinvall_cmd.vpe;
+ return valid_vpe(its, desc->its_vinvall_cmd.vpe);
}
static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmapp_cmd.vpe;
+ return valid_vpe(its, desc->its_vmapp_cmd.vpe);
}
static struct its_vpe *its_build_vmapti_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmapti_cmd.vpe;
+ return valid_vpe(its, desc->its_vmapti_cmd.vpe);
}
static struct its_vpe *its_build_vmovi_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmovi_cmd.vpe;
+ return valid_vpe(its, desc->its_vmovi_cmd.vpe);
}
static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmovp_cmd.vpe;
+ return valid_vpe(its, desc->its_vmovp_cmd.vpe);
}
static u64 its_cmd_ptr_to_offset(struct its_node *its,
.irq_set_vcpu_affinity = its_irq_set_vcpu_affinity,
};
+
/*
* How we allocate LPIs:
*
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
*
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
+ *
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
*/
-#define IRQS_PER_CHUNK_SHIFT 5
-#define IRQS_PER_CHUNK (1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
+
+struct lpi_range {
+ struct list_head entry;
+ u32 base_id;
+ u32 span;
+};
+
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
+{
+ struct lpi_range *range;
+
+ range = kzalloc(sizeof(*range), GFP_KERNEL);
+ if (range) {
+ INIT_LIST_HEAD(&range->entry);
+ range->base_id = base;
+ range->span = span;
+ }
-static int its_lpi_to_chunk(int lpi)
+ return range;
+}
+
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
{
- return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+ struct lpi_range *ra, *rb;
+
+ ra = container_of(a, struct lpi_range, entry);
+ rb = container_of(b, struct lpi_range, entry);
+
+ return rb->base_id - ra->base_id;
}
-static int its_chunk_to_lpi(int chunk)
+static void merge_lpi_ranges(void)
{
- return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+ struct lpi_range *range, *tmp;
+
+ list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+ if (!list_is_last(&range->entry, &lpi_range_list) &&
+ (tmp->base_id == (range->base_id + range->span))) {
+ tmp->base_id = range->base_id;
+ tmp->span += range->span;
+ list_del(&range->entry);
+ kfree(range);
+ }
+ }
}
-static int __init its_lpi_init(u32 id_bits)
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
{
- lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+ struct lpi_range *range, *tmp;
+ int err = -ENOSPC;
- lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
- GFP_KERNEL);
- if (!lpi_bitmap) {
- lpi_chunks = 0;
- return -ENOMEM;
+ mutex_lock(&lpi_range_lock);
+
+ list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+ if (range->span >= nr_lpis) {
+ *base = range->base_id;
+ range->base_id += nr_lpis;
+ range->span -= nr_lpis;
+
+ if (range->span == 0) {
+ list_del(&range->entry);
+ kfree(range);
+ }
+
+ err = 0;
+ break;
+ }
}
- pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
- return 0;
+ mutex_unlock(&lpi_range_lock);
+
+ pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+ return err;
}
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
{
- unsigned long *bitmap = NULL;
- int chunk_id;
- int nr_chunks;
- int i;
+ struct lpi_range *new;
+ int err = 0;
- nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+ mutex_lock(&lpi_range_lock);
- spin_lock(&lpi_lock);
+ new = mk_lpi_range(base, nr_lpis);
+ if (!new) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ list_add(&new->entry, &lpi_range_list);
+ list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+ merge_lpi_ranges();
+out:
+ mutex_unlock(&lpi_range_lock);
+ return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+ u32 lpis = (1UL << id_bits) - 8192;
+ u32 numlpis;
+ int err;
+
+ numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+ if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+ lpis = numlpis;
+ pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+ lpis);
+ }
+
+ /*
+ * Initializing the allocator is just the same as freeing the
+ * full range of LPIs.
+ */
+ err = free_lpi_range(8192, lpis);
+ pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+ return err;
+}
+
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
+{
+ unsigned long *bitmap = NULL;
+ int err = 0;
do {
- chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
- 0, nr_chunks, 0);
- if (chunk_id < lpi_chunks)
+ err = alloc_lpi_range(nr_irqs, base);
+ if (!err)
break;
- nr_chunks--;
- } while (nr_chunks > 0);
+ nr_irqs /= 2;
+ } while (nr_irqs > 0);
- if (!nr_chunks)
+ if (err)
goto out;
- bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
- sizeof(long),
- GFP_ATOMIC);
+ bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
if (!bitmap)
goto out;
- for (i = 0; i < nr_chunks; i++)
- set_bit(chunk_id + i, lpi_bitmap);
-
- *base = its_chunk_to_lpi(chunk_id);
- *nr_ids = nr_chunks * IRQS_PER_CHUNK;
+ *nr_ids = nr_irqs;
out:
- spin_unlock(&lpi_lock);
-
if (!bitmap)
*base = *nr_ids = 0;
return bitmap;
}
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
{
- int lpi;
-
- spin_lock(&lpi_lock);
-
- for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
- int chunk = its_lpi_to_chunk(lpi);
-
- BUG_ON(chunk > lpi_chunks);
- if (test_bit(chunk, lpi_bitmap)) {
- clear_bit(chunk, lpi_bitmap);
- } else {
- pr_err("Bad LPI chunk %d\n", chunk);
- }
- }
-
- spin_unlock(&lpi_lock);
-
+ WARN_ON(free_lpi_range(base, nr_ids));
kfree(bitmap);
}
{
phys_addr_t paddr;
- lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+ lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
if (!gic_rdists->prop_page) {
pr_err("Failed to allocate PROPBASE\n");
static int its_alloc_collections(struct its_node *its)
{
+ int i;
+
its->collections = kcalloc(nr_cpu_ids, sizeof(*its->collections),
GFP_KERNEL);
if (!its->collections)
return -ENOMEM;
+ for (i = 0; i < nr_cpu_ids; i++)
+ its->collections[i].target_address = ~0ULL;
+
return 0;
}
{
struct its_node *its;
- spin_lock(&its_lock);
+ raw_spin_lock(&its_lock);
list_for_each_entry(its, &its_nodes, entry)
its_cpu_init_collection(its);
- spin_unlock(&its_lock);
+ raw_spin_unlock(&its_lock);
}
static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
if (!its_alloc_device_table(its, dev_id))
return NULL;
+ if (WARN_ON(!is_power_of_2(nvecs)))
+ nvecs = roundup_pow_of_two(nvecs);
+
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
/*
- * We allocate at least one chunk worth of LPIs bet device,
- * and thus that many ITEs. The device may require less though.
+ * Even if the device wants a single LPI, the ITT must be
+ * sized as a power of two (and you need at least one bit...).
*/
- nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+ nr_ites = max(2, nvecs);
sz = nr_ites * its->ite_size;
sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
itt = kzalloc(sz, GFP_KERNEL);
if (alloc_lpis) {
- lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+ lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
if (lpi_map)
col_map = kcalloc(nr_lpis, sizeof(*col_map),
GFP_KERNEL);
cpu_mask = cpumask_of_node(its_dev->its->numa_node);
/* Bind the LPI to the first possible CPU */
- cpu = cpumask_first(cpu_mask);
+ cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
+ if (cpu >= nr_cpu_ids) {
+ if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
+ return -EINVAL;
+
+ cpu = cpumask_first(cpu_online_mask);
+ }
+
its_dev->event_map.col_map[event] = cpu;
irq_data_update_effective_affinity(d, cpumask_of(cpu));
/* If all interrupts have been freed, start mopping the floor */
if (bitmap_empty(its_dev->event_map.lpi_map,
its_dev->event_map.nr_lpis)) {
- its_lpi_free_chunks(its_dev->event_map.lpi_map,
- its_dev->event_map.lpi_base,
- its_dev->event_map.nr_lpis);
+ its_lpi_free(its_dev->event_map.lpi_map,
+ its_dev->event_map.lpi_base,
+ its_dev->event_map.nr_lpis);
kfree(its_dev->event_map.col_map);
/* Unmap device/itt */
}
if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
- its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+ its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
its_free_prop_table(vm->vprop_page);
}
}
BUG_ON(!vm);
- bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+ bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
if (!bitmap)
return -ENOMEM;
if (nr_ids < nr_irqs) {
- its_lpi_free_chunks(bitmap, base, nr_ids);
+ its_lpi_free(bitmap, base, nr_ids);
return -ENOMEM;
}
vprop_page = its_allocate_prop_table(GFP_KERNEL);
if (!vprop_page) {
- its_lpi_free_chunks(bitmap, base, nr_ids);
+ its_lpi_free(bitmap, base, nr_ids);
return -ENOMEM;
}
if (i > 0)
its_vpe_irq_domain_free(domain, virq, i - 1);
- its_lpi_free_chunks(bitmap, base, nr_ids);
+ its_lpi_free(bitmap, base, nr_ids);
its_free_prop_table(vprop_page);
}
struct its_node *its;
int err = 0;
- spin_lock(&its_lock);
+ raw_spin_lock(&its_lock);
list_for_each_entry(its, &its_nodes, entry) {
void __iomem *base;
writel_relaxed(its->ctlr_save, base + GITS_CTLR);
}
}
- spin_unlock(&its_lock);
+ raw_spin_unlock(&its_lock);
return err;
}
struct its_node *its;
int ret;
- spin_lock(&its_lock);
+ raw_spin_lock(&its_lock);
list_for_each_entry(its, &its_nodes, entry) {
void __iomem *base;
int i;
GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
its_cpu_init_collection(its);
}
- spin_unlock(&its_lock);
+ raw_spin_unlock(&its_lock);
}
static struct syscore_ops its_syscore_ops = {
if (err)
goto out_free_tables;
- spin_lock(&its_lock);
+ raw_spin_lock(&its_lock);
list_add(&its->entry, &its_nodes);
- spin_unlock(&its_lock);
+ raw_spin_unlock(&its_lock);
return 0;
u64 timeout = USEC_PER_SEC;
u64 val;
+ /*
+ * If coming via a CPU hotplug event, we don't need to disable
+ * LPIs before trying to re-enable them. They are already
+ * configured and all is well in the world. Detect this case
+ * by checking the allocation of the pending table for the
+ * current CPU.
+ */
+ if (gic_data_rdist()->pend_page)
+ return 0;
+
if (!gic_rdists_supports_plpis()) {
pr_info("CPU%d: LPIs not supported\n", smp_processor_id());
return -ENXIO;
.flags = IRQCHIP_SET_TYPE_MASKED,
};
-#define GIC_ID_NR (1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
* The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
*/
typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
- gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+ gic_data.rdists.gicd_typer = typer;
gic_irqs = GICD_TYPER_IRQS(typer);
if (gic_irqs > 1020)
gic_irqs = 1020;
return ingenic_intc_of_init(node, 1);
}
IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
static int __init intc_2chip_of_init(struct device_node *node,
struct device_node *parent)
msg->address_lo = lower_32_bits(msi_data->msiir_addr);
msg->data = data->hwirq;
- if (msi_affinity_flag)
- msg->data |= cpumask_first(data->common->affinity);
+ if (msi_affinity_flag) {
+ const struct cpumask *mask;
+
+ mask = irq_data_get_effective_affinity_mask(data);
+ msg->data |= cpumask_first(mask);
+ }
iommu_dma_map_msi_msg(data->irq, msg);
}
return -EINVAL;
}
- cpumask_copy(irq_data->common->affinity, mask);
+ irq_data_update_effective_affinity(irq_data, cpumask_of(cpu));
return IRQ_SET_MASK_OK;
}
};
static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+ { .exti = 0, .irq_parent = 6 },
{ .exti = 1, .irq_parent = 7 },
{ .exti = 2, .irq_parent = 8 },
{ .exti = 3, .irq_parent = 9 },
.getname = data_sock_getname,
.sendmsg = mISDN_sock_sendmsg,
.recvmsg = mISDN_sock_recvmsg,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = data_sock_setsockopt,
menuconfig NVM
bool "Open-Channel SSD target support"
- depends on BLOCK && HAS_DMA && PCI
+ depends on BLOCK && PCI
select BLK_DEV_NVME
help
Say Y here to get to enable Open-channel SSDs.
/*
* Initialize ring buffer. The data and metadata buffers must be previously
* allocated and their size must be a power of two
- * (Documentation/circular-buffers.txt)
+ * (Documentation/core-api/circular-buffers.rst)
*/
int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
unsigned int power_size, unsigned int power_seg_sz)
Allows a block device to be used as cache for other devices; uses
a btree for indexing and the layout is optimized for SSDs.
- See Documentation/bcache.txt for details.
+ See Documentation/admin-guide/bcache.rst for details.
config BCACHE_DEBUG
bool "Bcache debugging"
* as keys are inserted we only sort the pages that have not yet been written.
* When garbage collection is run, we resort the entire node.
*
- * All configuration is done via sysfs; see Documentation/bcache.txt.
+ * All configuration is done via sysfs; see Documentation/admin-guide/bcache.rst.
*/
#include "bcache.h"
* as keys are inserted we only sort the pages that have not yet been written.
* When garbage collection is run, we resort the entire node.
*
- * All configuration is done via sysfs; see Documentation/bcache.txt.
+ * All configuration is done via sysfs; see Documentation/admin-guide/bcache.rst.
*/
#include "bcache.h"
}
/* Return md raid10 algorithm for @name */
-static const int raid10_name_to_format(const char *name)
+static int raid10_name_to_format(const char *name)
{
if (!strcasecmp(name, "near"))
return ALGORITHM_RAID10_NEAR;
static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return q && blk_queue_dax(q);
+ return bdev_dax_supported(dev->bdev, PAGE_SIZE);
}
static bool dm_table_supports_dax(struct dm_table *t)
if (dm_table_supports_dax(t))
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ else
+ blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+
if (dm_table_supports_dax_write_cache(t))
dax_write_cache(t->md->dax_dev, true);
static int __commit_transaction(struct dm_pool_metadata *pmd)
{
int r;
- size_t metadata_len, data_len;
struct thin_disk_superblock *disk_super;
struct dm_block *sblock;
if (r < 0)
return r;
- r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
- if (r < 0)
- return r;
-
- r = dm_sm_root_size(pmd->data_sm, &data_len);
- if (r < 0)
- return r;
-
r = save_sm_roots(pmd);
if (r < 0)
return r;
static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+static void requeue_bios(struct pool *pool);
+
static void check_for_space(struct pool *pool)
{
int r;
if (r)
return;
- if (nr_free)
+ if (nr_free) {
set_pool_mode(pool, PM_WRITE);
+ requeue_bios(pool);
+ }
}
/*
r = dm_pool_alloc_data_block(pool->pmd, result);
if (r) {
- metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
+ if (r == -ENOSPC)
+ set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
+ else
+ metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
return r;
}
struct dm_target *ti;
struct dm_dev *dev;
struct dm_dev *ssd_dev;
+ sector_t start_sector;
void *memory_map;
uint64_t memory_map_size;
size_t metadata_sectors;
if (da != p) {
long i;
wc->memory_map = NULL;
- pages = kvmalloc(p * sizeof(struct page *), GFP_KERNEL);
+ pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
if (!pages) {
r = -ENOMEM;
goto err2;
}
dax_read_unlock(id);
+
+ wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT;
+ wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT;
+
return 0;
err3:
kvfree(pages);
static void persistent_memory_release(struct dm_writecache *wc)
{
if (wc->memory_vmapped)
- vunmap(wc->memory_map);
+ vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT));
}
static struct page *persistent_memory_page(void *addr)
static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e)
{
- return wc->metadata_sectors +
+ return wc->start_sector + wc->metadata_sectors +
((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT));
}
if (unlikely(region.sector + region.count > wc->metadata_sectors))
region.count = wc->metadata_sectors - region.sector;
+ region.sector += wc->start_sector;
atomic_inc(&endio.count);
req.bi_op = REQ_OP_WRITE;
req.bi_op_flags = REQ_SYNC;
if (wc->entries)
return 0;
- wc->entries = vmalloc(sizeof(struct wc_entry) * wc->n_blocks);
+ wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
if (!wc->entries)
return -ENOMEM;
for (b = 0; b < wc->n_blocks; b++) {
wb->bio.bi_iter.bi_sector = read_original_sector(wc, e);
wb->page_offset = PAGE_SIZE;
if (max_pages <= WB_LIST_INLINE ||
- unlikely(!(wb->wc_list = kmalloc(max_pages * sizeof(struct wc_entry *),
- GFP_NOIO | __GFP_NORETRY |
- __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
+ unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *),
+ GFP_NOIO | __GFP_NORETRY |
+ __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
wb->wc_list = wb->wc_list_inline;
max_pages = WB_LIST_INLINE;
}
}
wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode);
- if (WC_MODE_PMEM(wc)) {
- r = persistent_memory_claim(wc);
- if (r) {
- ti->error = "Unable to map persistent memory for cache";
- goto bad;
- }
- }
-
/*
* Parse the cache block size
*/
while (opt_params) {
string = dm_shift_arg(&as), opt_params--;
- if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
+ if (!strcasecmp(string, "start_sector") && opt_params >= 1) {
+ unsigned long long start_sector;
+ string = dm_shift_arg(&as), opt_params--;
+ if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1)
+ goto invalid_optional;
+ wc->start_sector = start_sector;
+ if (wc->start_sector != start_sector ||
+ wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT)
+ goto invalid_optional;
+ } else if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
string = dm_shift_arg(&as), opt_params--;
if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1)
goto invalid_optional;
goto bad;
}
- if (!WC_MODE_PMEM(wc)) {
+ if (WC_MODE_PMEM(wc)) {
+ r = persistent_memory_claim(wc);
+ if (r) {
+ ti->error = "Unable to map persistent memory for cache";
+ goto bad;
+ }
+ } else {
struct dm_io_region region;
struct dm_io_request req;
size_t n_blocks, n_metadata_blocks;
uint64_t n_bitmap_bits;
+ wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT;
+
bio_list_init(&wc->flush_list);
wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush");
if (IS_ERR(wc->flush_thread)) {
}
region.bdev = wc->ssd_dev->bdev;
- region.sector = 0;
+ region.sector = wc->start_sector;
region.count = wc->metadata_sectors;
req.bi_op = REQ_OP_READ;
req.bi_op_flags = REQ_SYNC;
static struct target_type writecache_target = {
.name = "writecache",
- .version = {1, 0, 0},
+ .version = {1, 1, 0},
.module = THIS_MODULE,
.ctr = writecache_ctr,
.dtr = writecache_dtr,
/* Chunk BIO work */
mutex_init(&dmz->chunk_lock);
- INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_KERNEL);
+ INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
0, dev->name);
if (!dmz->chunk_wq) {
if (len < 1)
goto out;
nr_pages = min(len, nr_pages);
- if (ti->type->direct_access)
- ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+ ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
out:
dm_put_live_table(md, srcu_idx);
* the usage of io->orig_bio in dm_remap_zone_report()
* won't be affected by this reassignment.
*/
- struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
- &md->queue->bio_split);
+ struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
+ GFP_NOIO, &md->queue->bio_split);
ci.io->orig_bio = b;
- bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
bio_chain(b, bio);
ret = generic_make_request(bio);
break;
else
pr_warn("md: personality for level %s is not loaded!\n",
mddev->clevel);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
spin_unlock(&pers_lock);
if (mddev->level != pers->level) {
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
module_put(pers->owner);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
if (pers->sync_request) {
mddev->private = NULL;
module_put(pers->owner);
bitmap_destroy(mddev);
- return err;
+ goto abort;
}
if (mddev->queue) {
bool nonrot = true;
disk->rdev->saved_raid_disk < 0)
conf->fullsync = 1;
}
+
+ if (disk->replacement &&
+ !test_bit(In_sync, &disk->replacement->flags) &&
+ disk->replacement->saved_raid_disk < 0) {
+ conf->fullsync = 1;
+ }
+
disk->recovery_disabled = mddev->recovery_disabled - 1;
}
* this pairs with smp_store_release() in dvb_ringbuffer_write(),
* dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset()
*
- * for memory barriers also see Documentation/circular-buffers.txt
+ * for memory barriers also see Documentation/core-api/circular-buffers.rst
*/
return (rbuf->pread == smp_load_acquire(&rbuf->pwrite));
}
A DVB-T tuner module. Say Y when you want to support this frontend.
This driver needs external firmware. Please use the command
- "<kerneldir>/Documentation/dvb/get_dvb_firmware sp8870" to
+ "<kerneldir>/scripts/get_dvb_firmware sp8870" to
download/extract it, and then copy it to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
A DVB-T tuner module. Say Y when you want to support this frontend.
This driver needs external firmware. Please use the command
- "<kerneldir>/Documentation/dvb/get_dvb_firmware sp887x" to
+ "<kerneldir>/scripts/get_dvb_firmware sp887x" to
download/extract it, and then copy it to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
A DVB-T tuner module. Say Y when you want to support this frontend.
This driver needs external firmware. Please use the commands
- "<kerneldir>/Documentation/dvb/get_dvb_firmware tda10045",
- "<kerneldir>/Documentation/dvb/get_dvb_firmware tda10046" to
+ "<kerneldir>/scripts/get_dvb_firmware tda10045",
+ "<kerneldir>/scripts/get_dvb_firmware tda10046" to
download/extract them, and then copy them to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
to support this frontend.
This driver needs external firmware. Please use the commands
- "<kerneldir>/Documentation/dvb/get_dvb_firmware nxt2002" and
- "<kerneldir>/Documentation/dvb/get_dvb_firmware nxt2004" to
+ "<kerneldir>/scripts/get_dvb_firmware nxt2002" and
+ "<kerneldir>/scripts/get_dvb_firmware nxt2004" to
download/extract them, and then copy them to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
An ATSC 8VSB tuner module. Say Y when you want to support this frontend.
This driver needs external firmware. Please use the command
- "<kerneldir>/Documentation/dvb/get_dvb_firmware or51211" to
+ "<kerneldir>/scripts/get_dvb_firmware or51211" to
download it, and then copy it to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
to support this frontend.
This driver needs external firmware. Please use the commands
- "<kerneldir>/Documentation/dvb/get_dvb_firmware or51132_vsb" and/or
- "<kerneldir>/Documentation/dvb/get_dvb_firmware or51132_qam" to
+ "<kerneldir>/scripts/get_dvb_firmware or51132_vsb" and/or
+ "<kerneldir>/scripts/get_dvb_firmware or51132_qam" to
download firmwares for 8VSB and QAM64/256, respectively. Copy them to
/usr/lib/hotplug/firmware or /lib/firmware (depending on
configuration of firmware hotplug).
* Amaury Demol from DiBcom for providing specs and driver
* sources, on which this driver (and the dvb-dibusb) are based.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*
*/
* Amaury Demol from DiBcom for providing specs and driver
* sources, on which this driver (and the dvb-dibusb) are based.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*
*/
* under the terms of the GNU General Public License as published by the
* Free Software Foundation, version 2.
*
-* see Documentation/dvb/README.dvb-usb for more information
+* see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef EDS1547
* ATI HDTV Wonder (NXT2004)
*
* This driver needs external firmware. Please use the command
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware nxt2002" or
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware nxt2004" to
+ * "<kerneldir>/scripts/get_dvb_firmware nxt2002" or
+ * "<kerneldir>/scripts/get_dvb_firmware nxt2004" to
* download/extract the appropriate firmware, and then copy it to
* /usr/lib/hotplug/firmware/ or /lib/firmware/
* (depending on configuration of firmware hotplug).
/*
* This driver needs external firmware. Please use the command
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware or51211" to
+ * "<kerneldir>/scripts/get_dvb_firmware or51211" to
* download/extract it, and then copy it to /usr/lib/hotplug/firmware
* or /lib/firmware (depending on configuration of firmware hotplug).
*/
*/
/*
* This driver needs external firmware. Please use the command
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware alps_tdlb7" to
+ * "<kerneldir>/scripts/get_dvb_firmware alps_tdlb7" to
* download/extract it, and then copy it to /usr/lib/hotplug/firmware
* or /lib/firmware (depending on configuration of firmware hotplug).
*/
/*
* This driver needs external firmware. Please use the command
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware sp887x" to
+ * "<kerneldir>/scripts/get_dvb_firmware sp887x" to
* download/extract it, and then copy it to /usr/lib/hotplug/firmware
* or /lib/firmware (depending on configuration of firmware hotplug).
*/
*/
/*
* This driver needs external firmware. Please use the commands
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware tda10045",
- * "<kerneldir>/Documentation/dvb/get_dvb_firmware tda10046" to
+ * "<kerneldir>/scripts/get_dvb_firmware tda10045",
+ * "<kerneldir>/scripts/get_dvb_firmware tda10046" to
* download/extract them, and then copy them to /usr/lib/hotplug/firmware
* or /lib/firmware (depending on configuration of firmware hotplug).
*/
ret = request_firmware(&fw, fw_file, &client->dev);
if (ret) {
dev_err(&client->dev,
- "did not find the firmware file. (%s) Please see linux/Documentation/dvb/ for more details on firmware-problems. (%d)\n",
+ "did not find the firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware\n",
fw_file, ret);
goto error;
}
* under the terms of the GNU General Public License as published by the
* Free Software Foundation, version 2.
*
-* see Documentation/dvb/README.dvb-usb for more information
+* see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef Z0194A
/*
* I2S output enable/disable configuration. This is a private control.
- * Refer to Documentation/media/v4l-drivers/max2175 for more details.
+ * Refer to Documentation/media/v4l-drivers/max2175.rst for more details.
*/
static const struct v4l2_ctrl_config max2175_i2s_en = {
.ops = &max2175_ctrl_ops,
/*
* HSLS value control LO freq adjacent location configuration.
- * Refer to Documentation/media/v4l-drivers/max2175 for more details.
+ * Refer to Documentation/media/v4l-drivers/max2175.rst for more details.
*/
static const struct v4l2_ctrl_config max2175_hsls = {
.ops = &max2175_ctrl_ops,
/*
* Rx modes below are a set of preset configurations that decides the tuner's
* sck and sample rate of transmission. They are separate for EU & NA regions.
- * Refer to Documentation/media/v4l-drivers/max2175 for more details.
+ * Refer to Documentation/media/v4l-drivers/max2175.rst for more details.
*/
static const char * const max2175_ctrl_eu_rx_modes[] = {
[MAX2175_EU_FM_1_2] = "EU FM 1.2",
---help---
Support for BT848 based frame grabber/overlay boards. This includes
the Miro, Hauppauge and STB boards. Please read the material in
- <file:Documentation/video4linux/bttv/> for more information.
+ <file:Documentation/media/v4l-drivers/bttv.rst> for more information.
To compile this driver as a module, choose M here: the
module will be called bttv.
if (ret) {
CX18_ERR("The MPC718 board variant with the MT352 DVB-T demodulator will not work without it\n");
- CX18_ERR("Run 'linux/Documentation/dvb/get_dvb_firmware mpc718' if you need the firmware\n");
+ CX18_ERR("Run 'linux/scripts/get_dvb_firmware mpc718' if you need the firmware\n");
}
return ret;
}
/*
* Audio related reset according to
- * Documentation/video4linux/cx2341x/fw-encoder-api.txt
+ * Documentation/media/v4l-drivers/cx2341x.rst
*/
if (atomic_read(&cx->ana_capturing) == 0)
cx18_vapi(cx, CX18_CPU_SET_MISC_PARAMETERS, 2,
/*
* Number of lines for Field 1 & Field 2 according to
- * Documentation/video4linux/cx2341x/fw-encoder-api.txt
+ * Documentation/media/v4l-drivers/cx2341x.rst
* Field 1 is 312 for 625 line systems in BT.656
* Field 2 is 313 for 625 line systems in BT.656
*/
ret = request_firmware(&fw, filename, &dev->pci->dev);
if (ret != 0)
- pr_err("did not find the firmware file. (%s) Please see linux/Documentation/dvb/ for more details on firmware-problems.",
+ pr_err("did not find the firmware file '%s'. You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware.",
filename);
else
altera_init(&netup_config, fw);
---help---
This is the video4linux driver for the Motion Eye camera found
in the Vaio Picturebook laptops. Please read the material in
- <file:Documentation/video4linux/meye.txt> for more information.
+ <file:Documentation/media/v4l-drivers/meye.rst> for more information.
If you say Y or M here, you need to say Y or M to "Sony Laptop
Extras" in the misc device section.
onboard MPEG2 decoder.
This driver needs an external firmware. Please use the script
- "<kerneldir>/Documentation/dvb/get_dvb_firmware av7110" to
+ "<kerneldir>/scripts/get_dvb_firmware av7110" to
download/extract it, and then copy it to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
* - a videobuffer is queued on the pcdev->capture list
*
* Please check the "DMA hot chaining timeslice issue" in
- * Documentation/video4linux/pxa_camera.txt
+ * Documentation/media/v4l-drivers/pxa_camera.rst
*
* Context: should only be called within the dma irq handler
*/
/*
* Please check the DMA prepared buffer structure in :
- * Documentation/video4linux/pxa_camera.txt
+ * Documentation/media/v4l-drivers/pxa_camera.rst
* Please check also in pxa_camera_check_link_miss() to understand why DMA chain
* modification while DMA chain is running will work anyway.
*/
/*
* CEU can scale and crop, but we don't want to waste bandwidth and kill the
* framerate by always requesting the maximum image from the client. See
- * Documentation/video4linux/sh_mobile_ceu_camera.txt for a description of
+ * Documentation/media/v4l-drivers/sh_mobile_ceu_camera.rst for a description of
* scaling and cropping algorithms and for the meaning of referenced here steps.
*/
static int sh_mobile_ceu_set_selection(struct soc_camera_device *icd,
#include <linux/via-core.h>
#include <linux/via-gpio.h>
#include <linux/via_i2c.h>
+
+#ifdef CONFIG_X86
#include <asm/olpc.h>
+#else
+#define machine_is_olpc(x) 0
+#endif
#include "via-camera.h"
*/
void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index)
{
- struct vsp1_device *vsp1 = dev_get_drvdata(dev);
-
- mutex_lock(&vsp1->drm->lock);
}
EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin);
drm_pipe->crc = cfg->crc;
+ mutex_lock(&vsp1->drm->lock);
vsp1_du_pipeline_setup_inputs(vsp1, pipe);
vsp1_du_pipeline_configure(pipe);
mutex_unlock(&vsp1->drm->lock);
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux 2 API. Information on
this API and pointers to "v4l2" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-si476x.
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux API. Information on
this API and pointers to "v4l" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-maxiradio.
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux API. Information on
this API and pointers to "v4l" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-shark.
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux API. Information on
this API and pointers to "v4l" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-shark2.
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux 2 API. Information on
this API and pointers to "v4l2" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-wl1273.
been reported to be used by these cards.
More information is contained in the file
- <file:Documentation/video4linux/radiotrack.txt>.
+ <file:Documentation/media/v4l-drivers/radiotrack.rst>.
To compile this driver as a module, choose M here: the
module will be called radio-aimslab.
Please have a look at the documentation, especially on how
to redirect the audio stream from the radio to your sound device:
- Documentation/video4linux/si470x.txt
+ Documentation/media/v4l-drivers/si470x.rst
Say Y here if you want to connect this type of radio to your
computer's USB port.
In order to control your radio card, you will need to use programs
that are compatible with the Video For Linux 2 API. Information on
this API and pointers to "v4l2" programs may be found at
- <file:Documentation/video4linux/API.html>.
+ <file:Documentation/media/media_uapi.rst>.
endmenu
rcu_assign_pointer(raw->progs, new_array);
bpf_prog_array_free(old_array);
+ bpf_prog_put(prog);
unlock:
mutex_unlock(&ir_raw_handler_lock);
return ret;
bpf_prog_array_free(rcdev->raw->progs);
}
-int lirc_prog_attach(const union bpf_attr *attr)
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
- struct bpf_prog *prog;
struct rc_dev *rcdev;
int ret;
if (attr->attach_flags)
return -EINVAL;
- prog = bpf_prog_get_type(attr->attach_bpf_fd,
- BPF_PROG_TYPE_LIRC_MODE2);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
-
rcdev = rc_dev_get_from_fd(attr->target_fd);
- if (IS_ERR(rcdev)) {
- bpf_prog_put(prog);
+ if (IS_ERR(rcdev))
return PTR_ERR(rcdev);
- }
ret = lirc_bpf_attach(rcdev, prog);
- if (ret)
- bpf_prog_put(prog);
put_device(&rcdev->dev);
while (kfifo_out(&raw->kfifo, &ev, 1)) {
if (is_timing_event(ev)) {
if (ev.duration == 0)
- dev_err(&dev->dev, "nonsensical timing event of duration 0");
+ dev_warn_once(&dev->dev, "nonsensical timing event of duration 0");
if (is_timing_event(raw->prev_ev) &&
!is_transition(&ev, &raw->prev_ev))
- dev_err(&dev->dev, "two consecutive events of type %s",
- TO_STR(ev.pulse));
+ dev_warn_once(&dev->dev, "two consecutive events of type %s",
+ TO_STR(ev.pulse));
if (raw->prev_ev.reset && ev.pulse == 0)
- dev_err(&dev->dev, "timing event after reset should be pulse");
+ dev_warn_once(&dev->dev, "timing event after reset should be pulse");
}
list_for_each_entry(handler, &ir_raw_handler_list, list)
if (dev->enabled_protocols &
spin_unlock_irqrestore(&dev->keylock, flags);
}
+static unsigned int repeat_period(int protocol)
+{
+ if (protocol >= ARRAY_SIZE(protocols))
+ return 100;
+
+ return protocols[protocol].repeat_period;
+}
+
/**
* rc_repeat() - signals that a key is still pressed
* @dev: the struct rc_dev descriptor of the device
{
unsigned long flags;
unsigned int timeout = nsecs_to_jiffies(dev->timeout) +
- msecs_to_jiffies(protocols[dev->last_protocol].repeat_period);
+ msecs_to_jiffies(repeat_period(dev->last_protocol));
struct lirc_scancode sc = {
.scancode = dev->last_scancode, .rc_proto = dev->last_protocol,
.keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED,
if (dev->keypressed) {
dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) +
- msecs_to_jiffies(protocols[protocol].repeat_period);
+ msecs_to_jiffies(repeat_period(protocol));
mod_timer(&dev->timer_keyup, dev->keyup_jiffies);
}
spin_unlock_irqrestore(&dev->keylock, flags);
USB1.1 and USB2.0 DVB devices.
Almost every USB device needs a firmware, please look into
- <file:Documentation/dvb/README.dvb-usb>.
+ <file:Documentation/media/dvb-drivers/dvb-usb.rst>.
For a complete list of supported USB devices see the LinuxTV DVB Wiki:
<https://linuxtv.org/wiki/index.php/DVB_USB>
ret = request_firmware(&fw, name, &d->udev->dev);
if (ret < 0) {
dev_err(&d->udev->dev,
- "%s: Did not find the firmware file '%s'. Please see linux/Documentation/dvb/ for more details on firmware-problems. Status %d\n",
+ "%s: Did not find the firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware\n",
KBUILD_MODNAME, name, ret);
goto err;
}
* under the terms of the GNU General Public License as published by the
* Free Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "gl861.h"
*
* LME2510C + M88RS2000
*
- * For firmware see Documentation/dvb/lmedm04.txt
+ * For firmware see Documentation/media/dvb-drivers/lmedm04.rst
*
* I2C addresses:
* 0xd0 - STV0288 - Demodulator
* GNU General Public License for more details.
*
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*
* Known Issues :
* LME2510: Non Intel USB chipsets fail to maintain High Speed on
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
* *
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_LME2510_H_
#define _DVB_USB_LME2510_H_
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include <linux/vmalloc.h>
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_MXL111SF_H_
USB1.1 and USB2.0 DVB devices.
Almost every USB device needs a firmware, please look into
- <file:Documentation/dvb/README.dvb-usb>.
+ <file:Documentation/media/dvb-drivers/dvb-usb.rst>.
For a complete list of supported USB devices see the LinuxTV DVB Wiki:
<https://linuxtv.org/wiki/index.php/DVB_USB>
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "af9005.h"
#include "af9005-script.h"
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "af9005.h"
/* debug */
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "af9005.h"
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_AF9005_H_
#define _DVB_USB_AF9005_H_
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "az6027.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include <media/tuner.h>
#include <linux/vmalloc.h>
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_DIBUSB_H_
#define _DVB_USB_DIBUSB_H_
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "digitv.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dtt200u.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dtt200u.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_DTT200U_H_
#define _DVB_USB_DTT200U_H_
const struct firmware *fw = NULL;
if ((ret = request_firmware(&fw, props->firmware, &udev->dev)) != 0) {
- err("did not find the firmware file. (%s) Please see linux/Documentation/dvb/ for more details on firmware-problems. (%d)",
+ err("did not find the firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware",
props->firmware,ret);
return ret;
}
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dvb-usb-common.h"
* under the terms of the GNU General Public License as published by the
* Free Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include <media/dvb-usb-ids.h>
#include "dw2102.h"
#define P1100_FIRMWARE "dvb-usb-p1100.fw"
#define P7500_FIRMWARE "dvb-usb-p7500.fw"
-#define err_str "did not find the firmware file. (%s) " \
- "Please see linux/Documentation/dvb/ for more details " \
- "on firmware-problems."
+#define err_str "did not find the firmware file '%s'. You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware"
struct dw2102_state {
u8 initialized;
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include <linux/init.h>
#include <linux/string.h>
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "friio.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_FRIIO_H_
#define _DVB_USB_FRIIO_H_
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "gp8psk.h"
#include "gp8psk-fe.h"
u8 *buf;
if ((ret = request_firmware(&fw, bcm4500_firmware,
&d->udev->dev)) != 0) {
- err("did not find the bcm4500 firmware file. (%s) Please see linux/Documentation/dvb/ for more details on firmware-problems. (%d)",
+ err("did not find the bcm4500 firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware",
bcm4500_firmware,ret);
return ret;
}
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_GP8PSK_H_
#define _DVB_USB_GP8PSK_H_
* under the terms of the GNU General Public License as published by the
* Free Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "m920x.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
-* see Documentation/dvb/README.dvb-usb for more information
+* see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#define DVB_USB_LOG_PREFIX "opera"
info("start downloading fpga firmware %s",filename);
if ((ret = request_firmware(&fw, filename, &dev->dev)) != 0) {
- err("did not find the firmware file. (%s) Please see linux/Documentation/dvb/ for more details on firmware-problems.",
+ err("did not find the firmware file '%s'. You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware",
filename);
return ret;
} else {
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#define DVB_USB_LOG_PREFIX "ttusb2"
#include "dvb-usb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_TTUSB2_H_
#define _DVB_USB_TTUSB2_H_
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "dibusb.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*
*/
#include "vp702x.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "vp702x.h"
#include <linux/mutex.h>
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*
*/
#include "vp7045.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#include "vp7045.h"
* under the terms of the GNU General Public License as published by the Free
* Software Foundation, version 2.
*
- * see Documentation/dvb/README.dvb-usb for more information
+ * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
*/
#ifndef _DVB_USB_VP7045_H_
#define _DVB_USB_VP7045_H_
Say Y here if you want support for cameras based on the
ALi m5602 connected to various image sensors.
- See <file:Documentation/video4linux/m5602.txt> for more info.
-
To compile this driver as a module, choose M here: the
module will be called gspca_m5602.
an external software decoder to watch TV on your computer.
This driver needs external firmware. Please use the commands
- "<kerneldir>/Documentation/dvb/get_dvb_firmware dec2000t",
- "<kerneldir>/Documentation/dvb/get_dvb_firmware dec2540t",
- "<kerneldir>/Documentation/dvb/get_dvb_firmware dec3000s",
+ "<kerneldir>/scripts/get_dvb_firmware dec2000t",
+ "<kerneldir>/scripts/get_dvb_firmware dec2540t",
+ "<kerneldir>/scripts/get_dvb_firmware dec3000s",
download/extract them, and then copy them to /usr/lib/hotplug/firmware
or /lib/firmware (depending on configuration of firmware hotplug).
---help---
Say Y here if you want to connect this type of camera to your
computer's USB port.
- See <file:Documentation/video4linux/zr364xx.txt> for more info
+ See <file:Documentation/media/v4l-drivers/zr364xx.rst> for more info
and list of supported cameras.
To compile this driver as a module, choose M here: the
const struct file_operations *fops,
void *priv, int flags)
{
- struct qstr this;
- struct path path;
struct file *file;
- struct inode *inode = NULL;
+ struct inode *inode;
int rc;
/* strongly inspired by anon_inode_getfile() */
goto err_fs;
}
- file = ERR_PTR(-ENOMEM);
- this.name = name;
- this.len = strlen(name);
- this.hash = 0;
- path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
- if (!path.dentry)
+ file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+ flags & (O_ACCMODE | O_NONBLOCK), fops);
+ if (IS_ERR(file))
goto err_inode;
- path.mnt = mntget(cxl_vfs_mount);
- d_instantiate(path.dentry, inode);
-
- file = alloc_file(&path, OPEN_FMODE(flags), fops);
- if (IS_ERR(file))
- goto err_dput;
- file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
file->private_data = priv;
return file;
-err_dput:
- path_put(&path);
err_inode:
iput(inode);
err_fs:
static ssize_t remote_settings_file_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
{
void __iomem *address = (void __iomem *)file->private_data;
- unsigned char *page;
- int retval;
int len = 0;
unsigned int value;
-
- if (*offset < 0)
- return -EINVAL;
- if (count == 0 || count > 1024)
- return 0;
- if (*offset != 0)
- return 0;
-
- page = (unsigned char *)__get_free_page(GFP_KERNEL);
- if (!page)
- return -ENOMEM;
+ char lbuf[20];
value = readl(address);
- len = sprintf(page, "%d\n", value);
-
- if (copy_to_user(buf, page, len)) {
- retval = -EFAULT;
- goto exit;
- }
- *offset += len;
- retval = len;
+ len = snprintf(lbuf, sizeof(lbuf), "%d\n", value);
-exit:
- free_page((unsigned long)page);
- return retval;
+ return simple_read_from_buffer(buf, count, offset, lbuf, len);
}
static ssize_t remote_settings_file_write(struct file *file, const char __user *ubuff, size_t count, loff_t *offset)
if (&cl->link == &dev->file_list) {
/* A message for not connected fixed address clients
* should be silently discarded
+ * On power down client may be force cleaned,
+ * silently discard such messages
*/
- if (hdr_is_fixed(mei_hdr)) {
+ if (hdr_is_fixed(mei_hdr) ||
+ dev->dev_state == MEI_DEV_POWER_DOWN) {
mei_irq_discard_msg(dev, mei_hdr);
ret = 0;
goto reset_slots;
unsigned int num_pages, bool is_2m_pages, unsigned int *target)
{
unsigned long status;
- unsigned long pfn = page_to_pfn(b->page);
+ unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
STATS_INC(b->stats.lock[is_2m_pages]);
unsigned int num_pages, bool is_2m_pages, unsigned int *target)
{
unsigned long status;
- unsigned long pfn = page_to_pfn(b->page);
+ unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
STATS_INC(b->stats.unlock[is_2m_pages]);
bool override_cd_active_level;
irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id);
char *ro_label;
- char cd_label[0];
u32 cd_debounce_delay_ms;
+ char cd_label[];
};
static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
* It's used when HS400 mode is enabled.
*/
if (data->flags & MMC_DATA_WRITE &&
- !(host->timing != MMC_TIMING_MMC_HS400))
- return;
+ host->timing != MMC_TIMING_MMC_HS400)
+ goto disable;
if (data->flags & MMC_DATA_WRITE)
enable = SDMMC_CARD_WR_THR_EN;
enable = SDMMC_CARD_RD_THR_EN;
if (host->timing != MMC_TIMING_MMC_HS200 &&
- host->timing != MMC_TIMING_UHS_SDR104)
+ host->timing != MMC_TIMING_UHS_SDR104 &&
+ host->timing != MMC_TIMING_MMC_HS400)
goto disable;
blksz_depth = blksz / (1 << host->data_shift);
int i;
for_each_sg(data->sg, sg, data->sg_len, i) {
- void *buf = kmap_atomic(sg_page(sg) + sg->offset;
+ void *buf = kmap_atomic(sg_page(sg) + sg->offset);
buffer_swap32(buf, sg->length);
kunmap_atomic(buf);
+ }
}
#else
static inline void mxcmci_swap_buffers(struct mmc_data *data) {}
renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
RST_RESERVED_BITS | val);
- if (host->data && host->data->flags & MMC_DATA_READ)
- clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+ clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
renesas_sdhi_internal_dmac_enable_dma(host, true);
}
goto force_pio;
/* This DMAC cannot handle if buffer is not 8-bytes alignment */
- if (!IS_ALIGNED(sg_dma_address(sg), 8)) {
- dma_unmap_sg(&host->pdev->dev, sg, host->sg_len,
- mmc_get_dma_dir(data));
- goto force_pio;
- }
+ if (!IS_ALIGNED(sg_dma_address(sg), 8))
+ goto force_pio_with_unmap;
if (data->flags & MMC_DATA_READ) {
dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
- goto force_pio;
+ goto force_pio_with_unmap;
} else {
dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
}
return;
+force_pio_with_unmap:
+ dma_unmap_sg(&host->pdev->dev, sg, host->sg_len, mmc_get_dma_dir(data));
+
force_pio:
host->force_pio = true;
renesas_sdhi_internal_dmac_enable_dma(host, false);
if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
val |= SDHCI_SUPPORT_HS400;
+
+ /*
+ * Do not advertise faster UHS modes if there are no
+ * pinctrl states for 100MHz/200MHz.
+ */
+ if (IS_ERR_OR_NULL(imx_data->pins_100mhz) ||
+ IS_ERR_OR_NULL(imx_data->pins_200mhz))
+ val &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50
+ | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_HS400);
}
}
ESDHC_PINCTRL_STATE_100MHZ);
imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
ESDHC_PINCTRL_STATE_200MHZ);
- if (IS_ERR(imx_data->pins_100mhz) ||
- IS_ERR(imx_data->pins_200mhz)) {
- dev_warn(mmc_dev(host->mmc),
- "could not get ultra high speed state, work on normal mode\n");
- /*
- * fall back to not supporting uhs by specifying no
- * 1.8v quirk
- */
- host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
- }
- } else {
- host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
}
/* call to generic mmc_of_parse to support additional capabilities */
sunxi_mmc_init_host(host);
sunxi_mmc_set_bus_width(host, mmc->ios.bus_width);
sunxi_mmc_set_clk(host, &mmc->ios);
+ enable_irq(host->irq);
return 0;
}
struct mmc_host *mmc = dev_get_drvdata(dev);
struct sunxi_mmc_host *host = mmc_priv(mmc);
+ /*
+ * When clocks are off, it's possible receiving
+ * fake interrupts, which will stall the system.
+ * Disabling the irq will prevent this.
+ */
+ disable_irq(host->irq);
sunxi_mmc_reset_host(host);
sunxi_mmc_disable(host);
struct ppb_lock {
struct flchip *chip;
- loff_t offset;
+ unsigned long adr;
int locked;
};
unsigned long timeo;
int ret;
+ adr += chip->start;
mutex_lock(&chip->mutex);
- ret = get_chip(map, chip, adr + chip->start, FL_LOCKING);
+ ret = get_chip(map, chip, adr, FL_LOCKING);
if (ret) {
mutex_unlock(&chip->mutex);
return ret;
if (thunk == DO_XXLOCK_ONEBLOCK_LOCK) {
chip->state = FL_LOCKING;
- map_write(map, CMD(0xA0), chip->start + adr);
- map_write(map, CMD(0x00), chip->start + adr);
+ map_write(map, CMD(0xA0), adr);
+ map_write(map, CMD(0x00), adr);
} else if (thunk == DO_XXLOCK_ONEBLOCK_UNLOCK) {
/*
* Unlocking of one specific sector is not supported, so we
map_write(map, CMD(0x00), chip->start);
chip->state = FL_READY;
- put_chip(map, chip, adr + chip->start);
+ put_chip(map, chip, adr);
mutex_unlock(&chip->mutex);
return ret;
* sectors shall be unlocked, so lets keep their locking
* status at "unlocked" (locked=0) for the final re-locking.
*/
- if ((adr < ofs) || (adr >= (ofs + len))) {
+ if ((offset < ofs) || (offset >= (ofs + len))) {
sect[sectors].chip = &cfi->chips[chipnum];
- sect[sectors].offset = offset;
+ sect[sectors].adr = adr;
sect[sectors].locked = do_ppb_xxlock(
map, &cfi->chips[chipnum], adr, 0,
DO_XXLOCK_ONEBLOCK_GETLOCK);
i++;
if (adr >> cfi->chipshift) {
+ if (offset >= (ofs + len))
+ break;
adr = 0;
chipnum++;
*/
for (i = 0; i < sectors; i++) {
if (sect[i].locked)
- do_ppb_xxlock(map, sect[i].chip, sect[i].offset, 0,
+ do_ppb_xxlock(map, sect[i].chip, sect[i].adr, 0,
DO_XXLOCK_ONEBLOCK_LOCK);
}
{ "AT45DB642x", 0x1f2800, 8192, 1056, 11, SUP_POW2PS},
{ "at45db642d", 0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS},
- { "AT45DB641E", 0x1f28000100, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
- { "at45db641e", 0x1f28000100, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
+ { "AT45DB641E", 0x1f28000100ULL, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
+ { "at45db641e", 0x1f28000100ULL, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
};
static struct flash_info *jedec_lookup(struct spi_device *spi,
if (ret)
return ret;
- denali->clk_x_rate = clk_get_rate(dt->clk);
+ /*
+ * Hardcode the clock rate for the backward compatibility.
+ * This works for both SOCFPGA and UniPhier.
+ */
+ denali->clk_x_rate = 200000000;
ret = denali_init(denali);
if (ret)
#define NFC_V1_V2_CONFIG (host->regs + 0x0a)
#define NFC_V1_V2_ECC_STATUS_RESULT (host->regs + 0x0c)
#define NFC_V1_V2_RSLTMAIN_AREA (host->regs + 0x0e)
-#define NFC_V1_V2_RSLTSPARE_AREA (host->regs + 0x10)
+#define NFC_V21_RSLTSPARE_AREA (host->regs + 0x10)
#define NFC_V1_V2_WRPROT (host->regs + 0x12)
#define NFC_V1_UNLOCKSTART_BLKADDR (host->regs + 0x14)
#define NFC_V1_UNLOCKEND_BLKADDR (host->regs + 0x16)
writew(config1, NFC_V1_V2_CONFIG1);
/* preset operation */
+ /* spare area size in 16-bit half-words */
+ writew(mtd->oobsize / 2, NFC_V21_RSLTSPARE_AREA);
+
/* Unlock the internal RAM Buffer */
writew(0x2, NFC_V1_V2_CONFIG);
for (; page < page_end; page++) {
res = chip->ecc.read_oob(mtd, chip, page);
- if (res)
+ if (res < 0)
return res;
bad = chip->oob_poi[chip->badblockpos];
#include <linux/mtd/rawnand.h>
+/*
+ * Macronix AC series does not support using SET/GET_FEATURES to change
+ * the timings unlike what is declared in the parameter page. Unflag
+ * this feature to avoid unnecessary downturns.
+ */
+static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip)
+{
+ unsigned int i;
+ static const char * const broken_get_timings[] = {
+ "MX30LF1G18AC",
+ "MX30LF1G28AC",
+ "MX30LF2G18AC",
+ "MX30LF2G28AC",
+ "MX30LF4G18AC",
+ "MX30LF4G28AC",
+ "MX60LF8G18AC",
+ };
+
+ if (!chip->parameters.supports_set_get_features)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(broken_get_timings); i++) {
+ if (!strcmp(broken_get_timings[i], chip->parameters.model))
+ break;
+ }
+
+ if (i == ARRAY_SIZE(broken_get_timings))
+ return;
+
+ bitmap_clear(chip->parameters.get_feature_list,
+ ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+ bitmap_clear(chip->parameters.set_feature_list,
+ ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+}
+
static int macronix_nand_init(struct nand_chip *chip)
{
if (nand_is_slc(chip))
chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
- /*
- * MX30LF2G18AC chip does not support using SET/GET_FEATURES to change
- * the timings unlike what is declared in the parameter page. Unflag
- * this feature to avoid unnecessary downturns.
- */
- if (chip->parameters.supports_set_get_features &&
- !strcmp("MX30LF2G18AC", chip->parameters.model)) {
- bitmap_clear(chip->parameters.get_feature_list,
- ONFI_FEATURE_ADDR_TIMING_MODE, 1);
- bitmap_clear(chip->parameters.set_feature_list,
- ONFI_FEATURE_ADDR_TIMING_MODE, 1);
- }
+ macronix_nand_fix_broken_get_timings(chip);
return 0;
}
if (p->supports_set_get_features) {
set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->set_feature_list);
+ set_bit(ONFI_FEATURE_ON_DIE_ECC, p->set_feature_list);
set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->get_feature_list);
+ set_bit(ONFI_FEATURE_ON_DIE_ECC, p->get_feature_list);
}
return 0;
if (ret)
return ret;
- if (f_pdata->use_direct_mode)
+ if (f_pdata->use_direct_mode) {
memcpy_toio(cqspi->ahb_base + to, buf, len);
- else
+ ret = cqspi_wait_idle(cqspi);
+ } else {
ret = cqspi_indirect_write_execute(nor, to, buf, len);
+ }
if (ret)
return ret;
goto err_upper_unlink;
}
+ bond->nest_level = dev_get_nest_level(bond_dev) + 1;
+
/* If the mode uses primary, then the following is handled by
* bond_change_active_slave().
*/
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
- bond->nest_level = dev_get_nest_level(bond_dev);
netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
slave_dev->name,
}
}
+static int bond_get_nest_level(struct net_device *bond_dev)
+{
+ struct bonding *bond = netdev_priv(bond_dev);
+
+ return bond->nest_level;
+}
+
static void bond_get_stats(struct net_device *bond_dev,
struct rtnl_link_stats64 *stats)
{
struct list_head *iter;
struct slave *slave;
- spin_lock(&bond->stats_lock);
+ spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
memcpy(stats, &bond->bond_stats, sizeof(*stats));
rcu_read_lock();
.ndo_neigh_setup = bond_neigh_setup,
.ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid,
+ .ndo_get_lock_subclass = bond_get_nest_level,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_netpoll_setup = bond_netpoll_setup,
.ndo_netpoll_cleanup = bond_netpoll_cleanup,
if (!bond->wq)
return -ENOMEM;
+ bond->nest_level = SINGLE_DEPTH_NESTING;
netdev_lockdep_set_classes(bond_dev);
list_add_tail(&bond->bond_list, &bn->dev_list);
static int bond_option_mode_set(struct bonding *bond,
const struct bond_opt_value *newval)
{
- if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
- netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
- newval->string);
- /* disable arp monitoring */
- bond->params.arp_interval = 0;
- /* set miimon to default value */
- bond->params.miimon = BOND_DEFAULT_MIIMON;
- netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
- bond->params.miimon);
+ if (!bond_mode_uses_arp(newval->value)) {
+ if (bond->params.arp_interval) {
+ netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
+ newval->string);
+ /* disable arp monitoring */
+ bond->params.arp_interval = 0;
+ }
+
+ if (!bond->params.miimon) {
+ /* set miimon to default value */
+ bond->params.miimon = BOND_DEFAULT_MIIMON;
+ netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
+ bond->params.miimon);
+ }
}
if (newval->value == BOND_MODE_ALB)
int err;
err = pm_runtime_get_sync(priv->device);
- if (err)
+ if (err < 0) {
pm_runtime_put_noidle(priv->device);
+ return err;
+ }
- return err;
+ return 0;
}
static void m_can_clk_stop(struct m_can_priv *priv)
} else {
/* Version 3.1.x or 3.2.x */
- cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE);
+ cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE |
+ CCCR_NISO);
/* Only 3.2.x has NISO Bit implemented */
if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
priv->can.clock.freq = clk_get_rate(cclk);
priv->mram_base = mram_addr;
- m_can_of_parse_mram(priv, mram_config_vals);
-
platform_set_drvdata(pdev, dev);
SET_NETDEV_DEV(dev, &pdev->dev);
goto clk_disable;
}
+ m_can_of_parse_mram(priv, mram_config_vals);
+
devm_can_led_init(dev);
of_can_transceiver(dev);
return ret;
}
-/* TODO: runtime PM with power down or sleep mode */
-
static __maybe_unused int m_can_suspend(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
pinctrl_pm_select_default_state(dev);
- m_can_init_ram(priv);
-
priv->can.state = CAN_STATE_ERROR_ACTIVE;
if (netif_running(ndev)) {
if (ret)
return ret;
+ m_can_init_ram(priv);
m_can_start(ndev);
netif_device_attach(ndev);
netif_start_queue(ndev);
return 0;
}
cdm = of_iomap(np_cdm, 0);
+ if (!cdm) {
+ of_node_put(np_cdm);
+ dev_err(&ofdev->dev, "can't map clock node!\n");
+ return 0;
+ }
if (in_8(&cdm->ipb_clk_sel) & 0x1)
freq *= 2;
#define PCIEFD_REG_SYS_VER1 0x0040 /* version reg #1 */
#define PCIEFD_REG_SYS_VER2 0x0044 /* version reg #2 */
+#define PCIEFD_FW_VERSION(x, y, z) (((u32)(x) << 24) | \
+ ((u32)(y) << 16) | \
+ ((u32)(z) << 8))
+
/* System Control Registers Bits */
#define PCIEFD_SYS_CTL_TS_RST 0x00000001 /* timestamp clock */
#define PCIEFD_SYS_CTL_CLK_EN 0x00000002 /* system clock */
"%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count,
hw_ver_major, hw_ver_minor, hw_ver_sub);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ /* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and
+ * 64-bit logical addresses: this workaround forces usage of 32-bit
+ * DMA addresses only when such a fw is detected.
+ */
+ if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) <
+ PCIEFD_FW_VERSION(3, 3, 0)) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err)
+ dev_warn(&pdev->dev,
+ "warning: can't set DMA mask %llxh (err %d)\n",
+ DMA_BIT_MASK(32), err);
+ }
+#endif
+
/* stop system clock */
pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
PCIEFD_REG_SYS_CTL_CLR);
usb_free_urb(dev->intr_urb);
kfree(dev->intr_in_buffer);
+ kfree(dev->tx_msg_buffer);
}
}
*
* Copyright (C) 2012 - 2014 Xilinx, Inc.
* Copyright (C) 2009 PetaLogix. All rights reserved.
+ * Copyright (C) 2017 Sandvik Mining and Construction Oy
*
* Description:
* This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/skbuff.h>
+#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/can/dev.h>
#define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
- XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+ XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
/* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
#define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */
/**
* struct xcan_priv - This definition define CAN driver instance
* @can: CAN private data structure.
+ * @tx_lock: Lock for synchronizing TX interrupt handling
* @tx_head: Tx CAN packets ready to send on the queue
* @tx_tail: Tx CAN packets successfully sended on the queue
* @tx_max: Maximum number packets the driver can send
*/
struct xcan_priv {
struct can_priv can;
+ spinlock_t tx_lock;
unsigned int tx_head;
unsigned int tx_tail;
unsigned int tx_max;
.brp_inc = 1,
};
+#define XCAN_CAP_WATERMARK 0x0001
+struct xcan_devtype_data {
+ unsigned int caps;
+};
+
/**
* xcan_write_reg_le - Write a value to the device register little endian
* @priv: Driver private data structure
usleep_range(500, 10000);
}
+ /* reset clears FIFOs */
+ priv->tx_head = 0;
+ priv->tx_tail = 0;
+
return 0;
}
struct net_device_stats *stats = &ndev->stats;
struct can_frame *cf = (struct can_frame *)skb->data;
u32 id, dlc, data[2] = {0, 0};
+ unsigned long flags;
if (can_dropped_invalid_skb(ndev, skb))
return NETDEV_TX_OK;
data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+
+ spin_lock_irqsave(&priv->tx_lock, flags);
+
priv->tx_head++;
/* Write the Frame to Xilinx CAN TX FIFO */
stats->tx_bytes += cf->can_dlc;
}
+ /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
+ if (priv->tx_max > 1)
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK);
+
/* Check if the TX buffer is full */
if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
netif_stop_queue(ndev);
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+
return NETDEV_TX_OK;
}
return 1;
}
+/**
+ * xcan_current_error_state - Get current error state from HW
+ * @ndev: Pointer to net_device structure
+ *
+ * Checks the current CAN error state from the HW. Note that this
+ * only checks for ERROR_PASSIVE and ERROR_WARNING.
+ *
+ * Return:
+ * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE
+ * otherwise.
+ */
+static enum can_state xcan_current_error_state(struct net_device *ndev)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ u32 status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+ if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK)
+ return CAN_STATE_ERROR_PASSIVE;
+ else if (status & XCAN_SR_ERRWRN_MASK)
+ return CAN_STATE_ERROR_WARNING;
+ else
+ return CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_set_error_state - Set new CAN error state
+ * @ndev: Pointer to net_device structure
+ * @new_state: The new CAN state to be set
+ * @cf: Error frame to be populated or NULL
+ *
+ * Set new CAN error state for the device, updating statistics and
+ * populating the error frame if given.
+ */
+static void xcan_set_error_state(struct net_device *ndev,
+ enum can_state new_state,
+ struct can_frame *cf)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
+ u32 txerr = ecr & XCAN_ECR_TEC_MASK;
+ u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+
+ priv->can.state = new_state;
+
+ if (cf) {
+ cf->can_id |= CAN_ERR_CRTL;
+ cf->data[6] = txerr;
+ cf->data[7] = rxerr;
+ }
+
+ switch (new_state) {
+ case CAN_STATE_ERROR_PASSIVE:
+ priv->can.can_stats.error_passive++;
+ if (cf)
+ cf->data[1] = (rxerr > 127) ?
+ CAN_ERR_CRTL_RX_PASSIVE :
+ CAN_ERR_CRTL_TX_PASSIVE;
+ break;
+ case CAN_STATE_ERROR_WARNING:
+ priv->can.can_stats.error_warning++;
+ if (cf)
+ cf->data[1] |= (txerr > rxerr) ?
+ CAN_ERR_CRTL_TX_WARNING :
+ CAN_ERR_CRTL_RX_WARNING;
+ break;
+ case CAN_STATE_ERROR_ACTIVE:
+ if (cf)
+ cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
+ break;
+ default:
+ /* non-ERROR states are handled elsewhere */
+ WARN_ON(1);
+ break;
+ }
+}
+
+/**
+ * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX
+ * @ndev: Pointer to net_device structure
+ *
+ * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if
+ * the performed RX/TX has caused it to drop to a lesser state and set
+ * the interface state accordingly.
+ */
+static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ enum can_state old_state = priv->can.state;
+ enum can_state new_state;
+
+ /* changing error state due to successful frame RX/TX can only
+ * occur from these states
+ */
+ if (old_state != CAN_STATE_ERROR_WARNING &&
+ old_state != CAN_STATE_ERROR_PASSIVE)
+ return;
+
+ new_state = xcan_current_error_state(ndev);
+
+ if (new_state != old_state) {
+ struct sk_buff *skb;
+ struct can_frame *cf;
+
+ skb = alloc_can_err_skb(ndev, &cf);
+
+ xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+
+ if (skb) {
+ struct net_device_stats *stats = &ndev->stats;
+
+ stats->rx_packets++;
+ stats->rx_bytes += cf->can_dlc;
+ netif_rx(skb);
+ }
+ }
+}
+
/**
* xcan_err_interrupt - error frame Isr
* @ndev: net_device pointer
struct net_device_stats *stats = &ndev->stats;
struct can_frame *cf;
struct sk_buff *skb;
- u32 err_status, status, txerr = 0, rxerr = 0;
+ u32 err_status;
skb = alloc_can_err_skb(ndev, &cf);
err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
- txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
- rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
- XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
- status = priv->read_reg(priv, XCAN_SR_OFFSET);
if (isr & XCAN_IXR_BSOFF_MASK) {
priv->can.state = CAN_STATE_BUS_OFF;
can_bus_off(ndev);
if (skb)
cf->can_id |= CAN_ERR_BUSOFF;
- } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
- priv->can.state = CAN_STATE_ERROR_PASSIVE;
- priv->can.can_stats.error_passive++;
- if (skb) {
- cf->can_id |= CAN_ERR_CRTL;
- cf->data[1] = (rxerr > 127) ?
- CAN_ERR_CRTL_RX_PASSIVE :
- CAN_ERR_CRTL_TX_PASSIVE;
- cf->data[6] = txerr;
- cf->data[7] = rxerr;
- }
- } else if (status & XCAN_SR_ERRWRN_MASK) {
- priv->can.state = CAN_STATE_ERROR_WARNING;
- priv->can.can_stats.error_warning++;
- if (skb) {
- cf->can_id |= CAN_ERR_CRTL;
- cf->data[1] |= (txerr > rxerr) ?
- CAN_ERR_CRTL_TX_WARNING :
- CAN_ERR_CRTL_RX_WARNING;
- cf->data[6] = txerr;
- cf->data[7] = rxerr;
- }
+ } else {
+ enum can_state new_state = xcan_current_error_state(ndev);
+
+ xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
}
/* Check for Arbitration lost interrupt */
if (isr & XCAN_IXR_RXOFLW_MASK) {
stats->rx_over_errors++;
stats->rx_errors++;
- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
if (skb) {
cf->can_id |= CAN_ERR_CRTL;
cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
- if (isr & XCAN_IXR_RXOK_MASK) {
- priv->write_reg(priv, XCAN_ICR_OFFSET,
- XCAN_IXR_RXOK_MASK);
- work_done += xcan_rx(ndev);
- } else {
- priv->write_reg(priv, XCAN_ICR_OFFSET,
- XCAN_IXR_RXNEMP_MASK);
- break;
- }
+ work_done += xcan_rx(ndev);
priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
}
- if (work_done)
+ if (work_done) {
can_led_event(ndev, CAN_LED_EVENT_RX);
+ xcan_update_error_state_after_rxtx(ndev);
+ }
if (work_done < quota) {
napi_complete_done(napi, work_done);
ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+ ier |= XCAN_IXR_RXNEMP_MASK;
priv->write_reg(priv, XCAN_IER_OFFSET, ier);
}
return work_done;
{
struct xcan_priv *priv = netdev_priv(ndev);
struct net_device_stats *stats = &ndev->stats;
+ unsigned int frames_in_fifo;
+ int frames_sent = 1; /* TXOK => at least 1 frame was sent */
+ unsigned long flags;
+ int retries = 0;
+
+ /* Synchronize with xmit as we need to know the exact number
+ * of frames in the FIFO to stay in sync due to the TXFEMP
+ * handling.
+ * This also prevents a race between netif_wake_queue() and
+ * netif_stop_queue().
+ */
+ spin_lock_irqsave(&priv->tx_lock, flags);
+
+ frames_in_fifo = priv->tx_head - priv->tx_tail;
+
+ if (WARN_ON_ONCE(frames_in_fifo == 0)) {
+ /* clear TXOK anyway to avoid getting back here */
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+ return;
+ }
+
+ /* Check if 2 frames were sent (TXOK only means that at least 1
+ * frame was sent).
+ */
+ if (frames_in_fifo > 1) {
+ WARN_ON(frames_in_fifo > priv->tx_max);
+
+ /* Synchronize TXOK and isr so that after the loop:
+ * (1) isr variable is up-to-date at least up to TXOK clear
+ * time. This avoids us clearing a TXOK of a second frame
+ * but not noticing that the FIFO is now empty and thus
+ * marking only a single frame as sent.
+ * (2) No TXOK is left. Having one could mean leaving a
+ * stray TXOK as we might process the associated frame
+ * via TXFEMP handling as we read TXFEMP *after* TXOK
+ * clear to satisfy (1).
+ */
+ while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) {
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+ }
- while ((priv->tx_head - priv->tx_tail > 0) &&
- (isr & XCAN_IXR_TXOK_MASK)) {
+ if (isr & XCAN_IXR_TXFEMP_MASK) {
+ /* nothing in FIFO anymore */
+ frames_sent = frames_in_fifo;
+ }
+ } else {
+ /* single frame in fifo, just clear TXOK */
priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ }
+
+ while (frames_sent--) {
can_get_echo_skb(ndev, priv->tx_tail %
priv->tx_max);
priv->tx_tail++;
stats->tx_packets++;
- isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
}
- can_led_event(ndev, CAN_LED_EVENT_TX);
+
netif_wake_queue(ndev);
+
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+ can_led_event(ndev, CAN_LED_EVENT_TX);
+ xcan_update_error_state_after_rxtx(ndev);
}
/**
struct net_device *ndev = (struct net_device *)dev_id;
struct xcan_priv *priv = netdev_priv(ndev);
u32 isr, ier;
+ u32 isr_errors;
/* Get the interrupt status from Xilinx CAN */
isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
xcan_tx_interrupt(ndev, isr);
/* Check for the type of error interrupt and Processing it */
- if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
- XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
- priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
- XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
- XCAN_IXR_ARBLST_MASK));
+ isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+ XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+ if (isr_errors) {
+ priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
xcan_err_interrupt(ndev, isr);
}
/* Check for the type of receive interrupt and Processing it */
- if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+ if (isr & XCAN_IXR_RXNEMP_MASK) {
ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+ ier &= ~XCAN_IXR_RXNEMP_MASK;
priv->write_reg(priv, XCAN_IER_OFFSET, ier);
napi_schedule(&priv->napi);
}
static void xcan_chip_stop(struct net_device *ndev)
{
struct xcan_priv *priv = netdev_priv(ndev);
- u32 ier;
/* Disable interrupts and leave the can in configuration mode */
- ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier &= ~XCAN_INTR_ALL;
- priv->write_reg(priv, XCAN_IER_OFFSET, ier);
- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+ set_reset_mode(ndev);
priv->can.state = CAN_STATE_STOPPED;
}
*/
static int __maybe_unused xcan_suspend(struct device *dev)
{
- if (!device_may_wakeup(dev))
- return pm_runtime_force_suspend(dev);
+ struct net_device *ndev = dev_get_drvdata(dev);
- return 0;
+ if (netif_running(ndev)) {
+ netif_stop_queue(ndev);
+ netif_device_detach(ndev);
+ xcan_chip_stop(ndev);
+ }
+
+ return pm_runtime_force_suspend(dev);
}
/**
*/
static int __maybe_unused xcan_resume(struct device *dev)
{
- if (!device_may_wakeup(dev))
- return pm_runtime_force_resume(dev);
+ struct net_device *ndev = dev_get_drvdata(dev);
+ int ret;
- return 0;
+ ret = pm_runtime_force_resume(dev);
+ if (ret) {
+ dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+ return ret;
+ }
+
+ if (netif_running(ndev)) {
+ ret = xcan_chip_start(ndev);
+ if (ret) {
+ dev_err(dev, "xcan_chip_start failed on resume\n");
+ return ret;
+ }
+
+ netif_device_attach(ndev);
+ netif_start_queue(ndev);
+ }
+ return 0;
}
/**
struct net_device *ndev = dev_get_drvdata(dev);
struct xcan_priv *priv = netdev_priv(ndev);
- if (netif_running(ndev)) {
- netif_stop_queue(ndev);
- netif_device_detach(ndev);
- }
-
- priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
- priv->can.state = CAN_STATE_SLEEPING;
-
clk_disable_unprepare(priv->bus_clk);
clk_disable_unprepare(priv->can_clk);
struct net_device *ndev = dev_get_drvdata(dev);
struct xcan_priv *priv = netdev_priv(ndev);
int ret;
- u32 isr, status;
ret = clk_prepare_enable(priv->bus_clk);
if (ret) {
return ret;
}
- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
- isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
- status = priv->read_reg(priv, XCAN_SR_OFFSET);
-
- if (netif_running(ndev)) {
- if (isr & XCAN_IXR_BSOFF_MASK) {
- priv->can.state = CAN_STATE_BUS_OFF;
- priv->write_reg(priv, XCAN_SRR_OFFSET,
- XCAN_SRR_RESET_MASK);
- } else if ((status & XCAN_SR_ESTAT_MASK) ==
- XCAN_SR_ESTAT_MASK) {
- priv->can.state = CAN_STATE_ERROR_PASSIVE;
- } else if (status & XCAN_SR_ERRWRN_MASK) {
- priv->can.state = CAN_STATE_ERROR_WARNING;
- } else {
- priv->can.state = CAN_STATE_ERROR_ACTIVE;
- }
- netif_device_attach(ndev);
- netif_start_queue(ndev);
- }
-
return 0;
}
SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL)
};
+static const struct xcan_devtype_data xcan_zynq_data = {
+ .caps = XCAN_CAP_WATERMARK,
+};
+
+/* Match table for OF platform binding */
+static const struct of_device_id xcan_of_match[] = {
+ { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
+ { .compatible = "xlnx,axi-can-1.00.a", },
+ { /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
/**
* xcan_probe - Platform registration call
* @pdev: Handle to the platform device structure
struct resource *res; /* IO mem resources */
struct net_device *ndev;
struct xcan_priv *priv;
+ const struct of_device_id *of_id;
+ int caps = 0;
void __iomem *addr;
- int ret, rx_max, tx_max;
+ int ret, rx_max, tx_max, tx_fifo_depth;
/* Get the virtual base address for the device */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
goto err;
}
- ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+ ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+ &tx_fifo_depth);
if (ret < 0)
goto err;
if (ret < 0)
goto err;
+ of_id = of_match_device(xcan_of_match, &pdev->dev);
+ if (of_id) {
+ const struct xcan_devtype_data *devtype_data = of_id->data;
+
+ if (devtype_data)
+ caps = devtype_data->caps;
+ }
+
+ /* There is no way to directly figure out how many frames have been
+ * sent when the TXOK interrupt is processed. If watermark programming
+ * is supported, we can have 2 frames in the FIFO and use TXFEMP
+ * to determine if 1 or 2 frames have been sent.
+ * Theoretically we should be able to use TXFWMEMP to determine up
+ * to 3 frames, but it seems that after putting a second frame in the
+ * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less
+ * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
+ * sent), which is not a sensible state - possibly TXFWMEMP is not
+ * completely synchronized with the rest of the bits?
+ */
+ if (caps & XCAN_CAP_WATERMARK)
+ tx_max = min(tx_fifo_depth, 2);
+ else
+ tx_max = 1;
+
/* Create a CAN device instance */
ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
if (!ndev)
CAN_CTRLMODE_BERR_REPORTING;
priv->reg_base = addr;
priv->tx_max = tx_max;
+ spin_lock_init(&priv->tx_lock);
/* Get IRQ for the device */
ndev->irq = platform_get_irq(pdev, 0);
pm_runtime_put(&pdev->dev);
- netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+ netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
priv->reg_base, ndev->irq, priv->can.clock.freq,
- priv->tx_max);
+ tx_fifo_depth, priv->tx_max);
return 0;
return 0;
}
-/* Match table for OF platform binding */
-static const struct of_device_id xcan_of_match[] = {
- { .compatible = "xlnx,zynq-can-1.0", },
- { .compatible = "xlnx,axi-can-1.00.a", },
- { /* end of list */ },
-};
-MODULE_DEVICE_TABLE(of, xcan_of_match);
-
static struct platform_driver xcan_driver = {
.probe = xcan_probe,
.remove = xcan_remove,
.xlate = irq_domain_xlate_twocell,
};
+/* To be called with reg_lock held */
static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
{
int irq, virq;
static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
{
- mv88e6xxx_g1_irq_free_common(chip);
-
+ /*
+ * free_irq must be called without reg_lock taken because the irq
+ * handler takes this lock, too.
+ */
free_irq(chip->irq, chip);
+
+ mutex_lock(&chip->reg_lock);
+ mv88e6xxx_g1_irq_free_common(chip);
+ mutex_unlock(&chip->reg_lock);
}
static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
{
- mv88e6xxx_g1_irq_free_common(chip);
-
kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
kthread_destroy_worker(chip->kworker);
+
+ mutex_lock(&chip->reg_lock);
+ mv88e6xxx_g1_irq_free_common(chip);
+ mutex_unlock(&chip->reg_lock);
}
int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
.rmu_disable = mv88e6085_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .serdes_power = mv88e6341_serdes_power,
};
static const struct mv88e6xxx_ops mv88e6095_ops = {
.reset = mv88e6352_g1_reset,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+ .serdes_power = mv88e6341_serdes_power,
.gpio_ops = &mv88e6352_gpio_ops,
};
.reset = mv88e6352_g1_reset,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .serdes_power = mv88e6341_serdes_power,
};
static const struct mv88e6xxx_ops mv88e6176_ops = {
.reset = mv88e6352_g1_reset,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+ .serdes_power = mv88e6341_serdes_power,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
};
if (chip->info->g2_irqs > 0)
mv88e6xxx_g2_irq_free(chip);
out_g1_irq:
- mutex_lock(&chip->reg_lock);
if (chip->irq > 0)
mv88e6xxx_g1_irq_free(chip);
else
mv88e6xxx_irq_poll_free(chip);
- mutex_unlock(&chip->reg_lock);
out:
if (pdata)
dev_put(pdata->netdev);
if (chip->info->g2_irqs > 0)
mv88e6xxx_g2_irq_free(chip);
- mutex_lock(&chip->reg_lock);
if (chip->irq > 0)
mv88e6xxx_g1_irq_free(chip);
else
mv88e6xxx_irq_poll_free(chip);
- mutex_unlock(&chip->reg_lock);
}
static const struct of_device_id mv88e6xxx_of_match[] = {
config 3C515
tristate "3c515 ISA \"Fast EtherLink\""
- depends on ISA && ISA_DMA_API
+ depends on ISA && ISA_DMA_API && !PPC32
---help---
If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
network card, say Y here.
static void dayna_block_output(struct net_device *dev, int count,
const unsigned char *buf, int start_page);
-#define memcpy_fromio(a, b, c) memcpy((a), (void *)(b), (c))
-#define memcpy_toio(a, b, c) memcpy((void *)(a), (b), (c))
-
#define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c))
/* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
unsigned long outdata = 0xA5A0B5B0;
unsigned long indata = 0x00000000;
/* Try writing 32 bits */
- memcpy_toio(membase, &outdata, 4);
+ memcpy_toio((void __iomem *)membase, &outdata, 4);
/* Now compare them */
if (memcmp_withio(&outdata, membase, 4) == 0)
return ACCESS_32;
struct e8390_pkt_hdr *hdr, int ring_page)
{
unsigned long hdr_start = (ring_page - WD_START_PG)<<8;
- memcpy_fromio(hdr, dev->mem_start + hdr_start, 4);
+ memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4);
/* Fix endianness */
hdr->count = swab16(hdr->count);
}
if (xfer_start + count > ei_status.rmem_end) {
/* We must wrap the input move. */
int semi_count = ei_status.rmem_end - xfer_start;
- memcpy_fromio(skb->data, dev->mem_start + xfer_base,
+ memcpy_fromio(skb->data,
+ (void __iomem *)dev->mem_start + xfer_base,
semi_count);
count -= semi_count;
- memcpy_fromio(skb->data + semi_count, ei_status.rmem_start,
- count);
+ memcpy_fromio(skb->data + semi_count,
+ (void __iomem *)ei_status.rmem_start, count);
} else {
- memcpy_fromio(skb->data, dev->mem_start + xfer_base, count);
+ memcpy_fromio(skb->data,
+ (void __iomem *)dev->mem_start + xfer_base,
+ count);
}
}
{
long shmem = (start_page - WD_START_PG)<<8;
- memcpy_toio(dev->mem_start + shmem, buf, count);
+ memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count);
}
/* dayna block input/output */
memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
+ io_sq->dma_addr_bits = ena_dev->dma_addr_bits;
io_sq->desc_entry_size =
(io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ?
sizeof(struct ena_eth_io_tx_desc) :
config LANCE
tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
- depends on ISA && ISA_DMA_API && !ARM
+ depends on ISA && ISA_DMA_API && !ARM && !PPC32
---help---
If you have a network (Ethernet) card of this type, say Y here.
Some LinkSys cards are of this type.
config NI65
tristate "NI6510 support"
- depends on ISA && ISA_DMA_API && !ARM
+ depends on ISA && ISA_DMA_API && !ARM && !PPC32
---help---
If you have a network (Ethernet) card of this type, say Y here.
config AMD_XGBE
tristate "AMD 10GbE Ethernet driver"
- depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM && HAS_DMA
+ depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM
depends on X86 || ARM64 || COMPILE_TEST
select BITREVERSE
select CRC32
if (pdata->tx_pause != pdata->phy.tx_pause) {
new_state = 1;
- pdata->hw_if.config_tx_flow_control(pdata);
pdata->tx_pause = pdata->phy.tx_pause;
+ pdata->hw_if.config_tx_flow_control(pdata);
}
if (pdata->rx_pause != pdata->phy.rx_pause) {
new_state = 1;
- pdata->hw_if.config_rx_flow_control(pdata);
pdata->rx_pause = pdata->phy.rx_pause;
+ pdata->hw_if.config_rx_flow_control(pdata);
}
/* Speed support */
config NET_XGENE_V2
tristate "APM X-Gene SoC Ethernet-v2 Driver"
- depends on HAS_DMA
depends on ARCH_XGENE || COMPILE_TEST
help
This is the Ethernet driver for the on-chip ethernet interface
config NET_XGENE
tristate "APM X-Gene SoC Ethernet Driver"
- depends on HAS_DMA
depends on ARCH_XGENE || COMPILE_TEST
select PHYLIB
select MDIO_XGENE
#define AQ_CFG_NAPI_WEIGHT 64U
-#define AQ_CFG_MULTICAST_ADDRESS_MAX 32U
-
/*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/
#define AQ_NIC_FC_OFF 0U
#define AQ_HW_MEDIA_TYPE_TP 1U
#define AQ_HW_MEDIA_TYPE_FIBRE 2U
+#define AQ_HW_MULTICAST_ADDRESS_MAX 32U
+
struct aq_hw_s {
atomic_t flags;
u8 rbl_enabled:1;
unsigned int packet_filter);
int (*hw_multicast_list_set)(struct aq_hw_s *self,
- u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX]
+ u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
[ETH_ALEN],
u32 count);
static void aq_ndev_set_multicast_settings(struct net_device *ndev)
{
struct aq_nic_s *aq_nic = netdev_priv(ndev);
- int err = 0;
- err = aq_nic_set_packet_filter(aq_nic, ndev->flags);
- if (err < 0)
- return;
+ aq_nic_set_packet_filter(aq_nic, ndev->flags);
- if (netdev_mc_count(ndev)) {
- err = aq_nic_set_multicast_list(aq_nic, ndev);
- if (err < 0)
- return;
- }
+ aq_nic_set_multicast_list(aq_nic, ndev);
}
static const struct net_device_ops aq_ndev_ops = {
int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
{
+ unsigned int packet_filter = self->packet_filter;
struct netdev_hw_addr *ha = NULL;
unsigned int i = 0U;
- self->mc_list.count = 0U;
-
- netdev_for_each_mc_addr(ha, ndev) {
- ether_addr_copy(self->mc_list.ar[i++], ha->addr);
- ++self->mc_list.count;
+ self->mc_list.count = 0;
+ if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+ packet_filter |= IFF_PROMISC;
+ } else {
+ netdev_for_each_uc_addr(ha, ndev) {
+ ether_addr_copy(self->mc_list.ar[i++], ha->addr);
- if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX)
- break;
+ if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+ break;
+ }
}
- if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) {
- /* Number of filters is too big: atlantic does not support this.
- * Force all multi filter to support this.
- * With this we disable all UC filters and setup "all pass"
- * multicast mask
- */
- self->packet_filter |= IFF_ALLMULTI;
- self->aq_nic_cfg.mc_list_count = 0;
- return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw,
- self->packet_filter);
+ if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+ packet_filter |= IFF_ALLMULTI;
} else {
- return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
- self->mc_list.ar,
- self->mc_list.count);
+ netdev_for_each_mc_addr(ha, ndev) {
+ ether_addr_copy(self->mc_list.ar[i++], ha->addr);
+
+ if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+ break;
+ }
+ }
+
+ if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) {
+ packet_filter |= IFF_MULTICAST;
+ self->mc_list.count = i;
+ self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
+ self->mc_list.ar,
+ self->mc_list.count);
}
+ return aq_nic_set_packet_filter(self, packet_filter);
}
int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
struct aq_hw_link_status_s link_status;
struct {
u32 count;
- u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN];
+ u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
} mc_list;
struct pci_dev *pdev;
static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
u8 ar_mac
- [AQ_CFG_MULTICAST_ADDRESS_MAX]
+ [AQ_HW_MULTICAST_ADDRESS_MAX]
[ETH_ALEN],
u32 count)
{
hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
hw_atl_rpfl2multicast_flr_en_set(self,
- IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+ IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
hw_atl_rpfl2_accept_all_mc_packets_set(self,
IS_FILTER_ENABLED(IFF_ALLMULTI));
static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
u8 ar_mac
- [AQ_CFG_MULTICAST_ADDRESS_MAX]
+ [AQ_HW_MULTICAST_ADDRESS_MAX]
[ETH_ALEN],
u32 count)
{
hw_atl_rpfl2_uc_flr_en_set(self,
(self->aq_nic_cfg->is_mc_list_enabled),
- HW_ATL_B0_MAC_MIN + i);
+ HW_ATL_B0_MAC_MIN + i);
}
err = aq_hw_err_from_flags(self);
config ARC_EMAC
tristate "ARC EMAC support"
select ARC_EMAC_CORE
- depends on OF_IRQ && OF_NET && HAS_DMA && (ARC || COMPILE_TEST)
+ depends on OF_IRQ && OF_NET
+ depends on ARC || COMPILE_TEST
---help---
On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x
non-standard on-chip ethernet device ARC EMAC 10/100 is used.
config EMAC_ROCKCHIP
tristate "Rockchip EMAC support"
select ARC_EMAC_CORE
- depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA && (ARCH_ROCKCHIP || COMPILE_TEST)
+ depends on OF_IRQ && OF_NET && REGULATOR
+ depends on ARCH_ROCKCHIP || COMPILE_TEST
---help---
Support for Rockchip RK3036/RK3066/RK3188 EMAC ethernet controllers.
This selects Rockchip SoC glue layer support for the
struct pci_dev *pdev = to_pci_dev(dev);
struct alx_priv *alx = pci_get_drvdata(pdev);
struct alx_hw *hw = &alx->hw;
+ int err;
alx_reset_phy(hw);
if (!netif_running(alx->dev))
return 0;
netif_device_attach(alx->dev);
- return __alx_open(alx, true);
+
+ rtnl_lock();
+ err = __alx_open(alx, true);
+ rtnl_unlock();
+
+ return err;
}
static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
skb = build_skb(page_address(page) + adapter->rx_page_offset,
adapter->rx_frag_size);
if (likely(skb)) {
+ skb_reserve(skb, NET_SKB_PAD);
adapter->rx_page_offset += adapter->rx_frag_size;
if (adapter->rx_page_offset >= PAGE_SIZE)
adapter->rx_page = NULL;
config BGMAC_BCMA
tristate "Broadcom iProc GBit BCMA support"
depends on BCMA && BCMA_HOST_SOC
- depends on HAS_DMA
depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST
select BGMAC
select PHYLIB
config BGMAC_PLATFORM
tristate "Broadcom iProc GBit platform support"
- depends on HAS_DMA
depends on ARCH_BCM_IPROC || COMPILE_TEST
depends on OF
select BGMAC
if (!priv->is_lite)
priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
else
- priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) &
- GIB_FCS_STRIP);
+ priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) &
+ GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT);
phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
0, priv->phy_interface);
#define GIB_GTX_CLK_EXT_CLK (0 << GIB_GTX_CLK_SEL_SHIFT)
#define GIB_GTX_CLK_125MHZ (1 << GIB_GTX_CLK_SEL_SHIFT)
#define GIB_GTX_CLK_250MHZ (2 << GIB_GTX_CLK_SEL_SHIFT)
-#define GIB_FCS_STRIP (1 << 6)
+#define GIB_FCS_STRIP_SHIFT 6
+#define GIB_FCS_STRIP (1 << GIB_FCS_STRIP_SHIFT)
#define GIB_LCL_LOOP_EN (1 << 7)
#define GIB_LCL_LOOP_TXEN (1 << 8)
#define GIB_RMT_LOOP_EN (1 << 9)
struct link_vars link_vars;
u32 link_cnt;
struct bnx2x_link_report_data last_reported_link;
+ bool force_link_down;
struct mdio_if_info mdio;
{
struct bnx2x_link_report_data cur_data;
+ if (bp->force_link_down) {
+ bp->link_vars.link_up = 0;
+ return;
+ }
+
/* reread mf_cfg */
if (IS_PF(bp) && !CHIP_IS_E1(bp))
bnx2x_read_mf_cfg(bp);
bp->pending_max = 0;
}
+ bp->force_link_down = false;
if (bp->port.pmf) {
rc = bnx2x_initial_phy_init(bp, load_mode);
if (rc)
DP(BNX2X_MSG_ETHTOOL,
"rss re-configured, UDP 4-tupple %s\n",
udp_rss_requested ? "enabled" : "disabled");
- return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+ if (bp->state == BNX2X_STATE_OPEN)
+ return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+ true);
} else if ((info->flow_type == UDP_V6_FLOW) &&
(bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
DP(BNX2X_MSG_ETHTOOL,
"rss re-configured, UDP 4-tupple %s\n",
udp_rss_requested ? "enabled" : "disabled");
- return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+ if (bp->state == BNX2X_STATE_OPEN)
+ return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+ true);
}
return 0;
bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
}
- return bnx2x_config_rss_eth(bp, false);
+ if (bp->state == BNX2X_STATE_OPEN)
+ return bnx2x_config_rss_eth(bp, false);
+
+ return 0;
}
/**
bp->sp_rtnl_state = 0;
smp_mb();
+ /* Immediately indicate link as down */
+ bp->link_vars.link_up = 0;
+ bp->force_link_down = true;
+ netif_carrier_off(bp->dev);
+ BNX2X_ERR("Indicating link is down due to Tx-timeout\n");
+
bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
/* When ret value shows failure of allocation failure,
* the nic is rebooted again. If open still fails, a error
}
vnic->uc_filter_count = 1;
- vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
+ vnic->rx_mask = 0;
+ if (bp->dev->flags & IFF_BROADCAST)
+ vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
}
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
+static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
{
bp->hw_resc.max_irqs = max_irqs;
}
rc = bnxt_request_irq(bp);
if (rc) {
netdev_err(bp->dev, "bnxt_request_irq err: %x\n", rc);
- goto open_err;
+ goto open_err_irq;
}
}
open_err:
bnxt_debug_dev_exit(bp);
bnxt_disable_napi(bp);
+
+open_err_irq:
bnxt_del_napi(bp);
open_err_free_mem:
mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS |
CFA_L2_SET_RX_MASK_REQ_MASK_MCAST |
- CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST);
+ CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST |
+ CFA_L2_SET_RX_MASK_REQ_MASK_BCAST);
if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
uc_update = bnxt_uc_list_updated(bp);
+ if (dev->flags & IFF_BROADCAST)
+ mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
if (dev->flags & IFF_ALLMULTI) {
mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
vnic->mc_list_count = 0;
int rx, tx, cp;
_bnxt_get_max_rings(bp, &rx, &tx, &cp);
+ *max_rx = rx;
+ *max_tx = tx;
if (!rx || !tx || !cp)
return -ENOMEM;
- *max_rx = rx;
- *max_tx = tx;
return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared);
}
/* Not enough rings, try disabling agg rings. */
bp->flags &= ~BNXT_FLAG_AGG_RINGS;
rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
- if (rc)
+ if (rc) {
+ /* set BNXT_FLAG_AGG_RINGS back for consistency */
+ bp->flags |= BNXT_FLAG_AGG_RINGS;
return rc;
+ }
bp->flags |= BNXT_FLAG_NO_AGG_RINGS;
bp->dev->hw_features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
bp->dev->features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
unsigned int bnxt_get_max_func_irqs(struct bnxt *bp);
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
int bnxt_get_avail_msix(struct bnxt *bp, int num);
int bnxt_reserve_rings(struct bnxt *bp);
void bnxt_tx_disable(struct bnxt *bp);
#define BNXT_FID_INVALID 0xffff
#define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT))
+#define is_vlan_pcp_wildcarded(vlan_tci_mask) \
+ ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vlan_pcp_exactmatch(vlan_tci_mask) \
+ ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == VLAN_PRIO_MASK)
+#define is_vlan_pcp_zero(vlan_tci) \
+ ((ntohs(vlan_tci) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vid_exactmatch(vlan_tci_mask) \
+ ((ntohs(vlan_tci_mask) & VLAN_VID_MASK) == VLAN_VID_MASK)
+
/* Return the dst fid of the func for flow forwarding
* For PFs: src_fid is the fid of the PF
* For VF-reps: src_fid the fid of the VF
return true;
}
+static bool is_vlan_tci_allowed(__be16 vlan_tci_mask,
+ __be16 vlan_tci)
+{
+ /* VLAN priority must be either exactly zero or fully wildcarded and
+ * VLAN id must be exact match.
+ */
+ if (is_vid_exactmatch(vlan_tci_mask) &&
+ ((is_vlan_pcp_exactmatch(vlan_tci_mask) &&
+ is_vlan_pcp_zero(vlan_tci)) ||
+ is_vlan_pcp_wildcarded(vlan_tci_mask)))
+ return true;
+
+ return false;
+}
+
static bool bits_set(void *key, int len)
{
const u8 *p = key;
/* Currently VLAN fields cannot be partial wildcard */
if (bits_set(&flow->l2_key.inner_vlan_tci,
sizeof(flow->l2_key.inner_vlan_tci)) &&
- !is_exactmatch(&flow->l2_mask.inner_vlan_tci,
- sizeof(flow->l2_mask.inner_vlan_tci))) {
- netdev_info(bp->dev, "Wildcard match unsupported for VLAN TCI\n");
+ !is_vlan_tci_allowed(flow->l2_mask.inner_vlan_tci,
+ flow->l2_key.inner_vlan_tci)) {
+ netdev_info(bp->dev, "Unsupported VLAN TCI\n");
return false;
}
if (bits_set(&flow->l2_key.inner_vlan_tpid,
edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
}
bnxt_fill_msix_vecs(bp, ent);
- bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) - avail_msix);
bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
return avail_msix;
msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
edev->ulp_tbl[ulp_id].msix_requested = 0;
- bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) + msix_requested);
edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
if (netif_running(dev)) {
bnxt_close_nic(bp, true, false);
id_tbl->max = size;
id_tbl->next = next;
spin_lock_init(&id_tbl->lock);
- id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+ id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
if (!id_tbl->table)
return -ENOMEM;
* Copyright (C) 2004 Sun Microsystems Inc.
* Copyright (C) 2005-2016 Broadcom Corporation.
* Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
*
* Firmware is:
* Derived from proprietary unpublished source code,
* Copyright (C) 2000-2016 Broadcom Corporation.
* Copyright (C) 2016-2017 Broadcom Ltd.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
*
* Permission is hereby granted for the distribution of this firmware
* data in hexadecimal or equivalent format, provided this copyright
tg3_restore_clk(tp);
+ /* Increase the core clock speed to fix tx timeout issue for 5762
+ * with 100Mbps link speed.
+ */
+ if (tg3_asic_rev(tp) == ASIC_REV_5762) {
+ val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE);
+ tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val |
+ TG3_CPMU_MAC_ORIDE_ENABLE);
+ }
+
/* Reprobe ASF enable state. */
tg3_flag_clear(tp, ENABLE_ASF);
tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK |
* Copyright (C) 2004 Sun Microsystems Inc.
* Copyright (C) 2007-2016 Broadcom Corporation.
* Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
*/
#ifndef _T3_H
#define GEM_DCFG6 0x0294 /* Design Config 6 */
#define GEM_DCFG7 0x0298 /* Design Config 7 */
#define GEM_DCFG8 0x029C /* Design Config 8 */
+#define GEM_DCFG10 0x02A4 /* Design Config 10 */
#define GEM_TXBDCTRL 0x04cc /* TX Buffer Descriptor control register */
#define GEM_RXBDCTRL 0x04d0 /* RX Buffer Descriptor control register */
#define GEM_SCR2CMP_OFFSET 0
#define GEM_SCR2CMP_SIZE 8
+/* Bitfields in DCFG10 */
+#define GEM_TXBD_RDBUFF_OFFSET 12
+#define GEM_TXBD_RDBUFF_SIZE 4
+#define GEM_RXBD_RDBUFF_OFFSET 8
+#define GEM_RXBD_RDBUFF_SIZE 4
+
/* Bitfields in TISUBN */
#define GEM_SUBNSINCR_OFFSET 0
#define GEM_SUBNSINCR_SIZE 16
#define MACB_CAPS_USRIO_DISABLED 0x00000010
#define MACB_CAPS_JUMBO 0x00000020
#define MACB_CAPS_GEM_HAS_PTP 0x00000040
+#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
unsigned int max_tuples;
struct tasklet_struct hresp_err_tasklet;
+
+ int rx_bd_rd_prefetch;
+ int tx_bd_rd_prefetch;
};
#ifdef CONFIG_MACB_USE_HWSTAMP
{
struct macb_queue *queue;
unsigned int q;
+ int size;
- queue = &bp->queues[0];
bp->macbgem_ops.mog_free_rx_buffers(bp);
- if (queue->rx_ring) {
- dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp),
- queue->rx_ring, queue->rx_ring_dma);
- queue->rx_ring = NULL;
- }
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
kfree(queue->tx_skb);
queue->tx_skb = NULL;
if (queue->tx_ring) {
- dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp),
+ size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
+ dma_free_coherent(&bp->pdev->dev, size,
queue->tx_ring, queue->tx_ring_dma);
queue->tx_ring = NULL;
}
+ if (queue->rx_ring) {
+ size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
+ dma_free_coherent(&bp->pdev->dev, size,
+ queue->rx_ring, queue->rx_ring_dma);
+ queue->rx_ring = NULL;
+ }
}
}
int size;
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
- size = TX_RING_BYTES(bp);
+ size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
&queue->tx_ring_dma,
GFP_KERNEL);
if (!queue->tx_skb)
goto out_err;
- size = RX_RING_BYTES(bp);
+ size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
&queue->rx_ring_dma, GFP_KERNEL);
if (!queue->rx_ring)
int err;
u32 reg;
+ bp->queues[0].bp = bp;
+
dev->netdev_ops = &at91ether_netdev_ops;
dev->ethtool_ops = &macb_ethtool_ops;
static const struct macb_config zynqmp_config = {
.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
MACB_CAPS_JUMBO |
- MACB_CAPS_GEM_HAS_PTP,
+ MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
.init = macb_init,
void __iomem *mem;
const char *mac;
struct macb *bp;
- int err;
+ int err, val;
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mem = devm_ioremap_resource(&pdev->dev, regs);
else
dev->max_mtu = ETH_DATA_LEN;
+ if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
+ val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
+ if (val)
+ bp->rx_bd_rd_prefetch = (2 << (val - 1)) *
+ macb_dma_desc_get_size(bp);
+
+ val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10));
+ if (val)
+ bp->tx_bd_rd_prefetch = (2 << (val - 1)) *
+ macb_dma_desc_get_size(bp);
+ }
+
mac = of_get_mac_address(np);
if (mac) {
ether_addr_copy(bp->dev->dev_addr, mac);
if (delta > TSU_NSEC_MAX_VAL) {
gem_tsu_get_time(&bp->ptp_clock_info, &now);
- if (sign)
- now = timespec64_sub(now, then);
- else
- now = timespec64_add(now, then);
+ now = timespec64_add(now, then);
gem_tsu_set_time(&bp->ptp_clock_info,
(const struct timespec64 *)&now);
config NET_CALXEDA_XGMAC
tristate "Calxeda 1G/10G XGMAC Ethernet driver"
- depends on HAS_IOMEM && HAS_DMA
+ depends on HAS_IOMEM
depends on ARCH_HIGHBANK || COMPILE_TEST
select CRC32
help
config THUNDER_NIC_PF
tristate "Thunder Physical function driver"
- depends on 64BIT
+ depends on 64BIT && PCI
select THUNDER_NIC_BGX
---help---
This driver supports Thunder's NIC physical function.
config THUNDER_NIC_VF
tristate "Thunder Virtual function driver"
imply CAVIUM_PTP
- depends on 64BIT
+ depends on 64BIT && PCI
---help---
This driver supports Thunder's NIC virtual function
config THUNDER_NIC_BGX
tristate "Thunder MAC interface driver (BGX)"
- depends on 64BIT
+ depends on 64BIT && PCI
select PHYLIB
select MDIO_THUNDER
select THUNDER_NIC_RGX
config THUNDER_NIC_RGX
tristate "Thunder MAC interface driver (RGX)"
- depends on 64BIT
+ depends on 64BIT && PCI
select PHYLIB
select MDIO_THUNDER
---help---
config CAVIUM_PTP
tristate "Cavium PTP coprocessor as PTP clock"
- depends on 64BIT
+ depends on 64BIT && PCI
imply PTP_1588_CLOCK
default y
---help---
config LIQUIDIO
tristate "Cavium LiquidIO support"
- depends on 64BIT
+ depends on 64BIT && PCI
depends on MAY_USE_DEVLINK
imply PTP_1588_CLOCK
select FW_LOADER
*/
#define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000
+/* time to wait for possible in-flight requests in milliseconds */
+#define WAIT_INFLIGHT_REQUEST msecs_to_jiffies(1000)
+
struct lio_trusted_vf_ctx {
struct completion complete;
int status;
force_io_queues_off(oct);
/* To allow for in-flight requests */
- schedule_timeout_uninterruptible(100);
+ schedule_timeout_uninterruptible(WAIT_INFLIGHT_REQUEST);
if (wait_for_pending_requests(oct))
dev_err(&oct->pci_dev->dev, "There were pending requests\n");
static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu)
{
struct octeon_mgmt *p = netdev_priv(netdev);
- int size_without_fcs = new_mtu + OCTEON_MGMT_RX_HEADROOM;
+ int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN;
netdev->mtu = new_mtu;
- cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, size_without_fcs);
+ /* HW lifts the limit if the frame is VLAN tagged
+ * (+4 bytes per each tag, up to two tags)
+ */
+ cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, max_packet);
+ /* Set the hardware to truncate packets larger than the MTU. The jabber
+ * register must be set to a multiple of 8 bytes, so round up. JABBER is
+ * an unconditional limit, so we need to account for two possible VLAN
+ * tags.
+ */
cvmx_write_csr(p->agl + AGL_GMX_RX_JABBER,
- (size_without_fcs + 7) & 0xfff8);
+ (max_packet + 7 + VLAN_HLEN * 2) & 0xfff8);
return 0;
}
struct tasklet_struct qs_err_task;
struct work_struct reset_task;
struct nicvf_work rx_mode_work;
+ /* spinlock to protect workqueue arguments from concurrent access */
+ spinlock_t rx_mode_wq_lock;
/* PTP timestamp */
struct cavium_ptp *ptp_clock;
}
}
-static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
+static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
+ struct nicvf *nic)
{
- struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
- work.work);
- struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
union nic_mbx mbx = {};
int idx;
- if (!vf_work)
- return;
-
/* From the inside of VM code flow we have only 128 bits memory
* available to send message to host's PF, so send all mc addrs
* one by one, starting from flush command in case if kernel
mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
nicvf_send_msg_to_pf(nic, &mbx);
- if (vf_work->mode & BGX_XCAST_MCAST_FILTER) {
+ if (mode & BGX_XCAST_MCAST_FILTER) {
/* once enabling filtering, we need to signal to PF to add
* its' own LMAC to the filter to accept packets for it.
*/
}
/* check if we have any specific MACs to be added to PF DMAC filter */
- if (vf_work->mc) {
+ if (mc_addrs) {
/* now go through kernel list of MACs and add them one by one */
- for (idx = 0; idx < vf_work->mc->count; idx++) {
+ for (idx = 0; idx < mc_addrs->count; idx++) {
mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
- mbx.xcast.data.mac = vf_work->mc->mc[idx];
+ mbx.xcast.data.mac = mc_addrs->mc[idx];
nicvf_send_msg_to_pf(nic, &mbx);
}
- kfree(vf_work->mc);
+ kfree(mc_addrs);
}
/* and finally set rx mode for PF accordingly */
mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
- mbx.xcast.data.mode = vf_work->mode;
+ mbx.xcast.data.mode = mode;
nicvf_send_msg_to_pf(nic, &mbx);
}
+static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
+{
+ struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
+ work.work);
+ struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
+ u8 mode;
+ struct xcast_addr_list *mc;
+
+ if (!vf_work)
+ return;
+
+ /* Save message data locally to prevent them from
+ * being overwritten by next ndo_set_rx_mode call().
+ */
+ spin_lock(&nic->rx_mode_wq_lock);
+ mode = vf_work->mode;
+ mc = vf_work->mc;
+ vf_work->mc = NULL;
+ spin_unlock(&nic->rx_mode_wq_lock);
+
+ __nicvf_set_rx_mode_task(mode, mc, nic);
+}
+
static void nicvf_set_rx_mode(struct net_device *netdev)
{
struct nicvf *nic = netdev_priv(netdev);
}
}
}
+ spin_lock(&nic->rx_mode_wq_lock);
+ kfree(nic->rx_mode_work.mc);
nic->rx_mode_work.mc = mc_list;
nic->rx_mode_work.mode = mode;
- queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 2 * HZ);
+ queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0);
+ spin_unlock(&nic->rx_mode_wq_lock);
}
static const struct net_device_ops nicvf_netdev_ops = {
INIT_WORK(&nic->reset_task, nicvf_reset_task);
INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+ spin_lock_init(&nic->rx_mode_wq_lock);
err = register_netdev(netdev);
if (err) {
lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count);
lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs),
GFP_KERNEL);
+ if (!lmac->dmacs)
+ return -ENOMEM;
/* Enable lmac */
bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/nospec.h>
#include "common.h"
#include "cxgb3_ioctl.h"
if (t.qset_idx >= nqsets)
return -EINVAL;
+ t.qset_idx = array_index_nospec(t.qset_idx, nqsets);
q = &adapter->params.sge.qset[q1 + t.qset_idx];
t.rspq_size = q->rspq_size;
err = sysfs_create_group(&adapter->port[0]->dev.kobj,
&cxgb3_attr_group);
+ if (err) {
+ dev_err(&pdev->dev, "cannot create sysfs group\n");
+ goto out_close_led;
+ }
print_port_info(adapter, ai);
return 0;
+out_close_led:
+ t3_set_reg_field(adapter, A_T3DBG_GPIO_EN, F_GPIO0_OUT_VAL, 0);
+
out_free_dev:
iounmap(adapter->regs);
for (i = ai->nports0 + ai->nports1 - 1; i >= 0; --i)
OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid));
req->local_port = cpu_to_be16(f->fs.val.lport);
req->peer_port = cpu_to_be16(f->fs.val.fport);
- req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 |
- f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24;
- req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 |
- f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24;
+ memcpy(&req->local_ip, f->fs.val.lip, 4);
+ memcpy(&req->peer_ip, f->fs.val.fip, 4);
req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
f->fs.newvlan == VLAN_REWRITE) |
DELACK_V(f->fs.hitcnts) |
"Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n",
enable ? "set" : "unset", pi->port_id, i, -err);
else
- txq->dcb_prio = value;
+ txq->dcb_prio = enable ? value : 0;
}
}
adapter->geneve_port = 0;
t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0);
+ break;
default:
return;
}
t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A,
GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F);
+ break;
default:
return;
}
};
unsigned int part, manufacturer;
- unsigned int density, size;
+ unsigned int density, size = 0;
u32 flashid = 0;
int ret;
case 0x22: /* 256MB */
size = 1 << 28;
break;
-
- default:
- dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n",
- flashid, density);
- return -EINVAL;
}
break;
}
case 0x17: /* 64MB */
size = 1 << 26;
break;
- default:
- dev_err(adap->pdev_dev, "ISSI Flash Part has bad size, ID = %#x, Density code = %#x\n",
- flashid, density);
- return -EINVAL;
}
break;
}
case 0x18: /* 16MB */
size = 1 << 24;
break;
- default:
- dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n",
- flashid, density);
- return -EINVAL;
}
break;
}
case 0x18: /* 16MB */
size = 1 << 24;
break;
- default:
- dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n",
- flashid, density);
- return -EINVAL;
}
break;
}
- default:
- dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n",
- flashid);
- return -EINVAL;
+ }
+
+ /* If we didn't recognize the FLASH part, that's no real issue: the
+ * Hardware/Software contract says that Hardware will _*ALWAYS*_
+ * use a FLASH part which is at least 4MB in size and has 64KB
+ * sectors. The unrecognized FLASH part is likely to be much larger
+ * than 4MB, but that's all we really need.
+ */
+ if (size == 0) {
+ dev_warn(adap->pdev_dev, "Unknown Flash Part, ID = %#x, assuming 4MB\n",
+ flashid);
+ size = 1 << 22;
}
/* Store decoded Flash size and fall through into vetting code. */
config CS89x0
tristate "CS89x0 support"
depends on ISA || EISA || ARM
+ depends on !PPC32
---help---
Support for CS89x0 chipset based Ethernet cards. If you have a
network (Ethernet) card of this type, say Y and read the file
enic->rfs_h.max = enic->config.num_arfs;
enic->rfs_h.free = enic->rfs_h.max;
enic->rfs_h.toclean = 0;
- enic_rfs_timer_start(enic);
}
void enic_rfs_flw_tbl_free(struct enic *enic)
enic_rfs_timer_stop(enic);
spin_lock_bh(&enic->rfs_h.lock);
- enic->rfs_h.free = 0;
for (i = 0; i < (1 << ENIC_RFS_FLW_BITSHIFT); i++) {
struct hlist_head *hhead;
struct hlist_node *tmp;
enic_delfltr(enic, n->fltr_id);
hlist_del(&n->node);
kfree(n);
+ enic->rfs_h.free++;
}
}
spin_unlock_bh(&enic->rfs_h.lock);
{
struct enic *enic = netdev_priv(netdev);
unsigned int i;
- int err;
+ int err, ret;
err = enic_request_intr(enic);
if (err) {
vnic_intr_unmask(&enic->intr[i]);
enic_notify_timer_start(enic);
- enic_rfs_flw_tbl_init(enic);
+ enic_rfs_timer_start(enic);
return 0;
err_out_free_rq:
for (i = 0; i < enic->rq_count; i++) {
- err = vnic_rq_disable(&enic->rq[i]);
- if (err)
- return err;
- vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
+ ret = vnic_rq_disable(&enic->rq[i]);
+ if (!ret)
+ vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
}
enic_dev_notify_unset(enic);
err_out_free_intr:
return 0;
}
+static int _enic_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ bool running = netif_running(netdev);
+ int err = 0;
+
+ ASSERT_RTNL();
+ if (running) {
+ err = enic_stop(netdev);
+ if (err)
+ return err;
+ }
+
+ netdev->mtu = new_mtu;
+
+ if (running) {
+ err = enic_open(netdev);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
static int enic_change_mtu(struct net_device *netdev, int new_mtu)
{
struct enic *enic = netdev_priv(netdev);
- int running = netif_running(netdev);
if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
return -EOPNOTSUPP;
- if (running)
- enic_stop(netdev);
-
- netdev->mtu = new_mtu;
-
if (netdev->mtu > enic->port_mtu)
netdev_warn(netdev,
- "interface MTU (%d) set higher than port MTU (%d)\n",
- netdev->mtu, enic->port_mtu);
-
- if (running)
- enic_open(netdev);
+ "interface MTU (%d) set higher than port MTU (%d)\n",
+ netdev->mtu, enic->port_mtu);
- return 0;
+ return _enic_change_mtu(netdev, new_mtu);
}
static void enic_change_mtu_work(struct work_struct *work)
struct enic *enic = container_of(work, struct enic, change_mtu_work);
struct net_device *netdev = enic->netdev;
int new_mtu = vnic_dev_mtu(enic->vdev);
- int err;
- unsigned int i;
-
- new_mtu = max_t(int, ENIC_MIN_MTU, min_t(int, ENIC_MAX_MTU, new_mtu));
rtnl_lock();
-
- /* Stop RQ */
- del_timer_sync(&enic->notify_timer);
-
- for (i = 0; i < enic->rq_count; i++)
- napi_disable(&enic->napi[i]);
-
- vnic_intr_mask(&enic->intr[0]);
- enic_synchronize_irqs(enic);
- err = vnic_rq_disable(&enic->rq[0]);
- if (err) {
- rtnl_unlock();
- netdev_err(netdev, "Unable to disable RQ.\n");
- return;
- }
- vnic_rq_clean(&enic->rq[0], enic_free_rq_buf);
- vnic_cq_clean(&enic->cq[0]);
- vnic_intr_clean(&enic->intr[0]);
-
- /* Fill RQ with new_mtu-sized buffers */
- netdev->mtu = new_mtu;
- vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf);
- /* Need at least one buffer on ring to get going */
- if (vnic_rq_desc_used(&enic->rq[0]) == 0) {
- rtnl_unlock();
- netdev_err(netdev, "Unable to alloc receive buffers.\n");
- return;
- }
-
- /* Start RQ */
- vnic_rq_enable(&enic->rq[0]);
- napi_enable(&enic->napi[0]);
- vnic_intr_unmask(&enic->intr[0]);
- enic_notify_timer_start(enic);
-
+ (void)_enic_change_mtu(netdev, new_mtu);
rtnl_unlock();
netdev_info(netdev, "interface MTU set as %d\n", netdev->mtu);
timer_setup(&enic->notify_timer, enic_notify_timer, 0);
+ enic_rfs_flw_tbl_init(enic);
enic_set_rx_coal_setting(enic);
INIT_WORK(&enic->reset, enic_reset);
INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset);
*/
enic->port_mtu = enic->config.mtu;
- (void)enic_change_mtu(netdev, enic->port_mtu);
err = enic_set_mac_addr(netdev, enic->mac_addr);
if (err) {
/* MTU range: 68 - 9000 */
netdev->min_mtu = ENIC_MIN_MTU;
netdev->max_mtu = ENIC_MAX_MTU;
+ netdev->mtu = enic->port_mtu;
err = register_netdev(netdev);
if (err) {
if (unlikely(nd->state != ncsi_dev_state_functional))
return;
- netdev_info(nd->dev, "NCSI interface %s\n",
- nd->link_up ? "up" : "down");
+ netdev_dbg(nd->dev, "NCSI interface %s\n",
+ nd->link_up ? "up" : "down");
}
static void ftgmac100_setup_clk(struct ftgmac100 *priv)
/* Default alignment for start of data in an Rx FD */
#define DPAA_FD_DATA_ALIGNMENT 16
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
/* Values for the L3R field of the FM Parse Results
*/
/* L3 Type field: First IP Present IPv4 */
if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
nr_frags = skb_shinfo(skb)->nr_frags;
- dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_unmap_single(dev, addr,
+ qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
dma_dir);
/* The sgt buffer has been allocated with netdev_alloc_frag(),
void *sgt_buf;
/* get a page frag to store the SGTable */
- sz = SKB_DATA_ALIGN(priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags));
+ sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
sgt_buf = netdev_alloc_frag(sz);
if (unlikely(!sgt_buf)) {
netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
skbh = (struct sk_buff **)buffer_start;
*skbh = skb;
- addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
- dma_dir);
+ addr = dma_map_single(dev, buffer_start,
+ priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
if (unlikely(dma_mapping_error(dev, addr))) {
dev_err(dev, "DMA mapping failed");
err = -EINVAL;
#define HWP_HXS_PHE_REPORT 0x00000800
#define HWP_HXS_PCAC_PSTAT 0x00000100
#define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
struct fman_port_hwp_regs {
struct {
u32 ssa; /* Soft Sequence Attachment */
iowrite32be(0xffffffff, ®s->pmda[i].lcv);
}
+ /* Short packet padding removal from checksum calculation */
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa);
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
start_port_hwp(port);
}
config NET_VENDOR_HISILICON
bool "Hisilicon devices"
default y
- depends on (OF || ACPI) && HAS_DMA
+ depends on OF || ACPI
depends on ARM || ARM64 || COMPILE_TEST
---help---
If you have a network (Ethernet) card belonging to this class, say Y.
hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS,
nic_dev, link_status_event_handler);
+ SET_NETDEV_DEV(netdev, &pdev->dev);
err = register_netdev(netdev);
if (err) {
dev_err(&pdev->dev, "Failed to register netdev\n");
{
struct hinic_rq *rq = rxq->rq;
+ irq_set_affinity_hint(rq->irq, NULL);
free_irq(rq->irq, rxq);
rx_del_napi(rxq);
}
txq->txq_stats.tx_busy++;
u64_stats_update_end(&txq->txq_stats.syncp);
err = NETDEV_TX_BUSY;
+ wqe_size = 0;
goto flush_skbs;
}
return;
failure:
- dev_info(dev, "replenish pools failure\n");
+ if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
+ dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
pool->free_map[pool->next_free] = index;
pool->rx_buff[index].skb = NULL;
&tx_crq);
}
if (lpar_rc != H_SUCCESS) {
- dev_err(dev, "tx failed with code %ld\n", lpar_rc);
+ if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
+ dev_err_ratelimited(dev, "tx: send failed\n");
dev_kfree_skb_any(skb);
tx_buff->skb = NULL;
rc = ibmvnic_login(netdev);
if (rc) {
- adapter->state = VNIC_PROBED;
- return 0;
+ adapter->state = reset_state;
+ return rc;
}
if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
return crq;
}
+static void print_subcrq_error(struct device *dev, int rc, const char *func)
+{
+ switch (rc) {
+ case H_PARAMETER:
+ dev_warn_ratelimited(dev,
+ "%s failed: Send request is malformed or adapter failover pending. (rc=%d)\n",
+ func, rc);
+ break;
+ case H_CLOSED:
+ dev_warn_ratelimited(dev,
+ "%s failed: Backing queue closed. Adapter is down or failover pending. (rc=%d)\n",
+ func, rc);
+ break;
+ default:
+ dev_err_ratelimited(dev, "%s failed: (rc=%d)\n", func, rc);
+ break;
+ }
+}
+
static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
union sub_crq *sub_crq)
{
cpu_to_be64(u64_crq[2]),
cpu_to_be64(u64_crq[3]));
- if (rc) {
- if (rc == H_CLOSED)
- dev_warn(dev, "CRQ Queue closed\n");
- dev_err(dev, "Send error (rc=%d)\n", rc);
- }
+ if (rc)
+ print_subcrq_error(dev, rc, __func__);
return rc;
}
cpu_to_be64(remote_handle),
ioba, num_entries);
- if (rc) {
- if (rc == H_CLOSED)
- dev_warn(dev, "CRQ Queue closed\n");
- dev_err(dev, "Send (indirect) error (rc=%d)\n", rc);
- }
+ if (rc)
+ print_subcrq_error(dev, rc, __func__);
return rc;
}
to identify the adapter.
More specific information on configuring the driver is in
- <file:Documentation/networking/e100.txt>.
+ <file:Documentation/networking/e100.rst>.
To compile this driver as a module, choose M here. The module
will be called e100.
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.txt>.
+ <file:Documentation/networking/e1000.rst>.
To compile this driver as a module, choose M here. The module
will be called e1000.
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.txt>.
+ <file:Documentation/networking/e1000.rst>.
To compile this driver as a module, choose M here. The module
will be called igb.
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.txt>.
+ <file:Documentation/networking/e1000.rst>.
To compile this driver as a module, choose M here. The module
will be called igbvf.
unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
- SKB_DATA_ALIGN(I40E_SKB_PAD +
- (xdp->data_end -
- xdp->data_hard_start));
+ SKB_DATA_ALIGN(xdp->data_end -
+ xdp->data_hard_start);
#endif
struct sk_buff *skb;
return NULL;
/* update pointers within the skb to store the data */
- skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start));
+ skb_reserve(skb, xdp->data - xdp->data_hard_start);
__skb_put(skb, xdp->data_end - xdp->data);
if (metasize)
skb_metadata_set(skb, metasize);
return true;
}
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS 0
+#define I40E_XDP_CONSUMED BIT(0)
+#define I40E_XDP_TX BIT(1)
+#define I40E_XDP_REDIR BIT(2)
static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+ result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
break;
default:
bpf_warn_invalid_xdp_action(act);
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
struct sk_buff *skb = rx_ring->skb;
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
- bool failure = false, xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
+ bool failure = false;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -I40E_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & I40E_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & I40E_XDP_TX) {
struct i40e_ring *xdp_ring =
rx_ring->vsi->xdp_rings[rx_ring->queue_index];
i40e_xdp_ring_update_tail(xdp_ring);
- xdp_do_flush_map();
}
rx_ring->skb = skb;
#define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */
u32 *rss_key;
-#ifdef CONFIG_XFRM
+#ifdef CONFIG_XFRM_OFFLOAD
struct ixgbe_ipsec *ipsec;
-#endif /* CONFIG_XFRM */
+#endif /* CONFIG_XFRM_OFFLOAD */
};
static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
if (enable_addr != 0)
rar_high |= IXGBE_RAH_AV;
+ /* Record lower 32 bits of MAC address and then make
+ * sure that write is flushed to hardware before writing
+ * the upper 16 bits and setting the valid bit.
+ */
IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low);
+ IXGBE_WRITE_FLUSH(hw);
IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
return 0;
rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index));
rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV);
- IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
+ /* Clear the address valid bit and upper 16 bits of the address
+ * before clearing the lower bits. This way we aren't updating
+ * a live filter.
+ */
IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
+ IXGBE_WRITE_FLUSH(hw);
+ IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
/* clear VMDq pool/queue selection for this RAR */
hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL);
reg |= IXGBE_SECRXCTRL_RX_DIS;
IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg);
- IXGBE_WRITE_FLUSH(hw);
+ /* If both Tx and Rx are ready there are no packets
+ * that we need to flush so the loopback configuration
+ * below is not necessary.
+ */
+ t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) &
+ IXGBE_SECTXSTAT_SECTX_RDY;
+ r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
+ IXGBE_SECRXSTAT_SECRX_RDY;
+ if (t_rdy && r_rdy)
+ return;
/* If the tx fifo doesn't have link, but still has data,
* we can't clear the tx sec block. Set the MAC loopback
IXGBE_SECTXSTAT_SECTX_RDY;
r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
IXGBE_SECRXSTAT_SECRX_RDY;
- } while (!t_rdy && !r_rdy && limit--);
+ } while (!(t_rdy && r_rdy) && limit--);
/* undo loopback if we played with it earlier */
if (!link) {
}
itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
- if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) {
+ if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) {
netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n",
__func__, itd->sa_idx, xs->xso.offload_handle);
return 0;
**/
void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
{
+ struct ixgbe_hw *hw = &adapter->hw;
struct ixgbe_ipsec *ipsec;
+ u32 t_dis, r_dis;
size_t size;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+ if (hw->mac.type == ixgbe_mac_82598EB)
+ return;
+
+ /* If there is no support for either Tx or Rx offload
+ * we should not be advertising support for IPsec.
+ */
+ t_dis = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) &
+ IXGBE_SECTXSTAT_SECTX_OFF_DIS;
+ r_dis = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
+ IXGBE_SECRXSTAT_SECRX_OFF_DIS;
+ if (t_dis || r_dis)
return;
ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL);
adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops;
-#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
- NETIF_F_HW_ESP_TX_CSUM | \
- NETIF_F_GSO_ESP)
-
- adapter->netdev->features |= IXGBE_ESP_FEATURES;
- adapter->netdev->hw_enc_features |= IXGBE_ESP_FEATURES;
-
return;
err2:
}
#endif
+ /* To support macvlan offload we have to use num_tc to
+ * restrict the queues that can be used by the device.
+ * By doing this we can avoid reporting a false number of
+ * queues.
+ */
+ if (vmdq_i > 1)
+ netdev_set_num_tc(adapter->netdev, 1);
+
/* populate TC0 for use by pool 0 */
netdev_set_tc_queue(adapter->netdev, 0,
adapter->num_rx_queues_per_pool, 0);
return skb;
}
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED BIT(0)
+#define IXGBE_XDP_TX BIT(1)
+#define IXGBE_XDP_REDIR BIT(2)
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf);
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
if (!err)
- result = IXGBE_XDP_TX;
+ result = IXGBE_XDP_REDIR;
else
result = IXGBE_XDP_CONSUMED;
break;
unsigned int mss = 0;
#endif /* IXGBE_FCOE */
u16 cleaned_count = ixgbe_desc_unused(rx_ring);
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & IXGBE_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & IXGBE_XDP_TX) {
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
/* Force memory writes to complete before letting h/w
*/
wmb();
writel(ring->next_to_use, ring->tail);
-
- xdp_do_flush_map();
}
u64_stats_update_begin(&rx_ring->syncp);
#ifdef CONFIG_IXGBE_DCB
ixgbe_init_dcb(adapter);
#endif
+ ixgbe_init_ipsec_offload(adapter);
/* default flow control settings */
hw->fc.requested_mode = ixgbe_fc_full;
} else {
netdev_reset_tc(dev);
- /* To support macvlan offload we have to use num_tc to
- * restrict the queues that can be used by the device.
- * By doing this we can avoid reporting a false number of
- * queues.
- */
- if (!tc && adapter->num_rx_pools > 1)
- netdev_set_num_tc(dev, 1);
-
if (adapter->hw.mac.type == ixgbe_mac_82598EB)
adapter->hw.fc.requested_mode = adapter->last_lfc_mode;
* the TSO, so it's the exception.
*/
if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
-#ifdef CONFIG_XFRM
+#ifdef CONFIG_XFRM_OFFLOAD
if (!skb->sp)
#endif
features &= ~NETIF_F_TSO;
if (hw->mac.type >= ixgbe_mac_82599EB)
netdev->features |= NETIF_F_SCTP_CRC;
+#ifdef CONFIG_XFRM_OFFLOAD
+#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
+ NETIF_F_HW_ESP_TX_CSUM | \
+ NETIF_F_GSO_ESP)
+
+ if (adapter->ipsec)
+ netdev->features |= IXGBE_ESP_FEATURES;
+#endif
/* copy netdev features into list of user selectable features */
netdev->hw_features |= netdev->features |
NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_FCOE_MTU;
}
#endif /* IXGBE_FCOE */
- ixgbe_init_ipsec_offload(adapter);
-
if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
netdev->hw_features |= NETIF_F_LRO;
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
#define IXGBE_SECTXCTRL_STORE_FORWARD 0x00000004
#define IXGBE_SECTXSTAT_SECTX_RDY 0x00000001
-#define IXGBE_SECTXSTAT_ECC_TXERR 0x00000002
+#define IXGBE_SECTXSTAT_SECTX_OFF_DIS 0x00000002
+#define IXGBE_SECTXSTAT_ECC_TXERR 0x00000004
#define IXGBE_SECRXCTRL_SECRX_DIS 0x00000001
#define IXGBE_SECRXCTRL_RX_DIS 0x00000002
#define IXGBE_SECRXSTAT_SECRX_RDY 0x00000001
-#define IXGBE_SECRXSTAT_ECC_RXERR 0x00000002
+#define IXGBE_SECRXSTAT_SECRX_OFF_DIS 0x00000002
+#define IXGBE_SECRXSTAT_ECC_RXERR 0x00000004
/* LinkSec (MacSec) Registers */
#define IXGBE_LSECTXCAP 0x08A00
config MV643XX_ETH
tristate "Marvell Discovery (643XX) and Orion ethernet support"
- depends on (MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST) && INET
- depends on HAS_DMA
+ depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST
+ depends on INET
select PHYLIB
select MVMDIO
---help---
config MVNETA
tristate "Marvell Armada 370/38x/XP/37xx network interface support"
depends on ARCH_MVEBU || COMPILE_TEST
- depends on HAS_DMA
select MVMDIO
select PHYLINK
---help---
config MVPP2
tristate "Marvell Armada 375/7K/8K network interface support"
depends on ARCH_MVEBU || COMPILE_TEST
- depends on HAS_DMA
select MVMDIO
select PHYLINK
---help---
config PXA168_ETH
tristate "Marvell pxa168 ethernet support"
- depends on HAS_IOMEM && HAS_DMA
+ depends on HAS_IOMEM
depends on CPU_PXA168 || ARCH_BERLIN || COMPILE_TEST
select PHYLIB
---help---
rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
index = rx_desc - rxq->descs;
data = rxq->buf_virt_addr[index];
- phys_addr = rx_desc->buf_phys_addr;
+ phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
if (!mvneta_rxq_desc_is_first_last(rx_status) ||
(rx_status & MVNETA_RXD_ERR_SUMMARY)) {
{
const struct mlx4_en_frag_info *frag_info = priv->frag_info;
unsigned int truesize = 0;
+ bool release = true;
int nr, frag_size;
struct page *page;
dma_addr_t dma;
- bool release;
/* Collect used fragments while replacing them in the HW descriptors */
for (nr = 0;; frags++) {
release = page_count(page) != 1 ||
page_is_pfmemalloc(page) ||
page_to_nid(page) != numa_mem_id();
- } else {
+ } else if (!priv->rx_headroom) {
+ /* rx_headroom for non XDP setup is always 0.
+ * When XDP is set, the above condition will
+ * guarantee page is always released.
+ */
u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
frags->page_offset += sz_align;
u32 srqn = qp_get_srqn(qpc) & 0xffffff;
int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
struct res_srq *srq;
- int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+ int local_qpn = vhcr->in_modifier & 0xffffff;
err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
if (err)
int i;
buf->size = size;
- buf->npages = 1 << get_order(size);
+ buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
buf->page_shift = PAGE_SHIFT;
buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
GFP_KERNEL);
unsigned long flags;
bool poll_cmd = ent->polling;
int alloc_ret;
+ int cmd_mode;
sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
down(sem);
set_signature(ent, !cmd->checksum_disabled);
dump_command(dev, ent, 1);
ent->ts1 = ktime_get_ns();
+ cmd_mode = cmd->mode;
if (ent->callback)
schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
mmiowb();
/* if not in polling don't use ent after this point */
- if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+ if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
poll_timeout(ent);
/* make sure we read the descriptor after ownership is SW */
rmb();
{
struct mlx5_core_dev *dev = filp->private_data;
struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
- char outlen_str[8];
+ char outlen_str[8] = {0};
int outlen;
void *ptr;
int err;
if (copy_from_user(outlen_str, buf, count))
return -EFAULT;
- outlen_str[7] = 0;
-
err = sscanf(outlen_str, "%d", &outlen);
if (err < 0)
return err;
mlx5e_fp_handle_rx_cqe handle_rx_cqe;
mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
} rx_handlers;
- void (*netdev_registered_init)(struct mlx5e_priv *priv);
- void (*netdev_registered_remove)(struct mlx5e_priv *priv);
int max_tc;
};
HLIST_HEAD(del_list);
spin_lock_bh(&priv->fs.arfs.arfs_lock);
mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
- if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
- break;
if (!work_pending(&arfs_rule->arfs_work) &&
rps_may_expire_flow(priv->netdev,
arfs_rule->rxq, arfs_rule->flow_id,
arfs_rule->filter_id)) {
hlist_del_init(&arfs_rule->hlist);
hlist_add_head(&arfs_rule->hlist, &del_list);
+ if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+ break;
}
}
spin_unlock_bh(&priv->fs.arfs.arfs_lock);
skb->protocol != htons(ETH_P_IPV6))
return -EPROTONOSUPPORT;
+ if (skb->encapsulation)
+ return -EPROTONOSUPPORT;
+
arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
if (!arfs_t)
return -EPROTONOSUPPORT;
}
static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
- struct ieee_ets *ets)
+ struct ieee_ets *ets,
+ bool zero_sum_allowed)
{
bool have_ets_tc = false;
int bw_sum = 0;
}
if (have_ets_tc && bw_sum != 100) {
- netdev_err(netdev,
- "Failed to validate ETS: BW sum is illegal\n");
+ if (bw_sum || (!bw_sum && !zero_sum_allowed))
+ netdev_err(netdev,
+ "Failed to validate ETS: BW sum is illegal\n");
return -EINVAL;
}
return 0;
if (!MLX5_CAP_GEN(priv->mdev, ets))
return -EOPNOTSUPP;
- err = mlx5e_dbcnl_validate_ets(netdev, ets);
+ err = mlx5e_dbcnl_validate_ets(netdev, ets, false);
if (err)
return err;
bool is_new;
int err;
- if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
- return -EINVAL;
-
- if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
- return -EINVAL;
-
- if (!MLX5_DSCP_SUPPORTED(priv->mdev))
- return -EINVAL;
+ if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+ !MLX5_DSCP_SUPPORTED(priv->mdev))
+ return -EOPNOTSUPP;
- if (app->protocol >= MLX5E_MAX_DSCP)
+ if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+ (app->protocol >= MLX5E_MAX_DSCP))
return -EINVAL;
/* Save the old entry info */
struct mlx5e_priv *priv = netdev_priv(dev);
int err;
- if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
- return -EINVAL;
-
- if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
- return -EINVAL;
-
- if (!MLX5_DSCP_SUPPORTED(priv->mdev))
- return -EINVAL;
+ if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+ !MLX5_DSCP_SUPPORTED(priv->mdev))
+ return -EOPNOTSUPP;
- if (app->protocol >= MLX5E_MAX_DSCP)
+ if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+ (app->protocol >= MLX5E_MAX_DSCP))
return -EINVAL;
/* Skip if no dscp app entry */
ets.prio_tc[i]);
}
- err = mlx5e_dbcnl_validate_ets(netdev, &ets);
- if (err) {
- netdev_err(netdev,
- "%s, Failed to validate ETS: %d\n", __func__, err);
+ err = mlx5e_dbcnl_validate_ets(netdev, &ets, true);
+ if (err)
goto out;
- }
err = mlx5e_dcbnl_ieee_setets_core(priv, &ets);
if (err) {
{
int err;
- err = mlx5_set_trust_state(priv->mdev, trust_state);
+ err = mlx5_set_trust_state(priv->mdev, trust_state);
if (err)
return err;
priv->dcbx_dp.trust_state = trust_state;
struct mlx5_core_dev *mdev = priv->mdev;
int err;
+ priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP;
+
if (!MLX5_DSCP_SUPPORTED(mdev))
return 0;
mlx5e_activate_channels(&priv->channels);
netif_tx_start_all_queues(priv->netdev);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_add_sqs_fwd_rules(priv);
mlx5e_wait_channels_min_rx_wqes(&priv->channels);
{
mlx5e_redirect_rqts_to_drop(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_remove_sqs_fwd_rules(priv);
/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
if (!reset) {
params->sw_mtu = new_mtu;
- set_mtu_cb(priv);
+ if (set_mtu_cb)
+ set_mtu_cb(priv);
netdev->mtu = params->sw_mtu;
goto out;
}
mlx5e_set_netdev_dev_addr(netdev);
#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
- if (MLX5_VPORT_MANAGER(mdev))
+ if (MLX5_ESWITCH_MANAGER(mdev))
netdev->switchdev_ops = &mlx5e_switchdev_ops;
#endif
mlx5e_enable_async_events(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_register_vport_reps(priv);
if (netdev->reg_state != NETREG_REGISTERED)
queue_work(priv->wq, &priv->set_rx_mode_work);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_unregister_vport_reps(priv);
mlx5e_disable_async_events(priv);
return NULL;
#ifdef CONFIG_MLX5_ESWITCH
- if (MLX5_VPORT_MANAGER(mdev)) {
+ if (MLX5_ESWITCH_MANAGER(mdev)) {
rpriv = mlx5e_alloc_nic_rep_priv(mdev);
if (!rpriv) {
mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep;
- if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
return false;
rep = rpriv->rep;
static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- struct mlx5_eswitch_rep *rep = rpriv->rep;
+ struct mlx5_eswitch_rep *rep;
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+ return false;
+
+ rep = rpriv->rep;
if (rep && rep->vport != FDB_UPLINK_VPORT)
return true;
else
actions = flow->nic_attr->action;
+ if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
+ !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+ return false;
+
if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
return modify_header_match_supported(&parse_attr->spec, exts);
static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
{
struct mlx5_core_dev *fmdev, *pmdev;
- u16 func_id, peer_id;
+ u64 fsystem_guid, psystem_guid;
fmdev = priv->mdev;
pmdev = peer_priv->mdev;
- func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn));
- peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn));
+ mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid);
+ mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid);
- return (func_id == peer_id);
+ return (fsystem_guid == psystem_guid);
}
static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
/* Public E-Switch API */
-#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev))
+#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
+
int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
{
int err;
int i, enabled_events;
- if (!ESW_ALLOWED(esw))
- return 0;
-
- if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+ if (!ESW_ALLOWED(esw) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
return -EOPNOTSUPP;
int vport_num;
int err;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
esw_info(dev,
void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
{
- if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
+ if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
return;
esw_info(esw->dev, "cleanup\n");
u64 node_guid;
int err = 0;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
return -EINVAL;
{
struct mlx5_vport *evport;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport))
return -EINVAL;
u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
{
- return esw->mode;
+ return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
}
EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
return -EOPNOTSUPP;
- if (!MLX5_CAP_GEN(dev, vport_group_manager))
- return -EOPNOTSUPP;
+ if(!MLX5_ESWITCH_MANAGER(dev))
+ return -EPERM;
if (dev->priv.eswitch->mode == SRIOV_NONE)
return -EOPNOTSUPP;
#include <linux/mutex.h>
#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "fs_core.h"
if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
if (!fwd_next_prio_supported(ft))
return ERR_PTR(-EOPNOTSUPP);
- if (dest)
+ if (dest_num)
return ERR_PTR(-EINVAL);
mutex_lock(&root->chain_lock);
next_ft = find_next_chained_ft(prio);
goto err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
err = init_fdb_root_ns(steering);
if (err)
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
#include <linux/module.h>
#include "mlx5_core.h"
#include "../../mlxfw/mlxfw.h"
}
if (MLX5_CAP_GEN(dev, vport_group_manager) &&
- MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
if (err)
return err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
if (err)
return err;
void *ppriv)
{
struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ u16 max_mtu;
/* priv init */
priv->mdev = mdev;
priv->ppriv = ppriv;
mutex_init(&priv->state_lock);
+ mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+ netdev->mtu = max_mtu;
+
mlx5e_build_nic_params(mdev, &priv->channels.params,
profile->max_nch(mdev), netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
void mlx5_init_clock(struct mlx5_core_dev *mdev)
{
struct mlx5_clock *clock = &mdev->clock;
+ u64 overflow_cycles;
u64 ns;
u64 frac = 0;
u32 dev_freq;
/* Calculate period in seconds to call the overflow watchdog - to make
* sure counter is checked at least once every wrap around.
+ * The period is calculated as the minimum between max HW cycles count
+ * (The clock source mask) and max amount of cycles that can be
+ * multiplied by clock multiplier where the result doesn't exceed
+ * 64bits.
*/
- ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+ overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+ overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+
+ ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
frac, &frac);
- do_div(ns, NSEC_PER_SEC / 2 / HZ);
+ do_div(ns, NSEC_PER_SEC / HZ);
clock->overflow_period = ns;
mdev->clock_info_page = alloc_page(GFP_KERNEL);
#include <linux/etherdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "lib/mpfs.h"
int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
struct mlx5_mpfs *mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
{
struct mlx5_mpfs *mpfs = dev->priv.mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return;
WARN_ON(!hlist_empty(mpfs->hash));
u32 index;
int err;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
int err = 0;
u32 index;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
int inlen)
{
- u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 out[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
int outlen)
{
- u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 in[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
return -EBUSY;
}
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ goto enable_vfs_hca;
+
err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
if (err) {
mlx5_core_warn(dev,
return err;
}
+enable_vfs_hca:
for (vf = 0; vf < num_vfs; vf++) {
err = mlx5_core_enable_hca(dev, vf + 1);
if (err) {
}
out:
- mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+ if (MLX5_ESWITCH_MANAGER(dev))
+ mlx5_eswitch_disable_sriov(dev->priv.eswitch);
if (mlx5_wait_for_vf_pages(dev))
mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
return -EINVAL;
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return -EACCES;
- if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
- return -EOPNOTSUPP;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
return err;
}
-static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf,
- struct mlx5_wq_qp *qp)
+static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf,
+ struct mlx5_wq_qp *qp)
{
+ struct mlx5_frag_buf_ctrl *sq_fbc;
struct mlx5_frag_buf *rqb, *sqb;
- rqb = &qp->rq.fbc.frag_buf;
+ rqb = &qp->rq.fbc.frag_buf;
*rqb = *buf;
rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq);
- rqb->npages = 1 << get_order(rqb->size);
+ rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE);
- sqb = &qp->sq.fbc.frag_buf;
- *sqb = *buf;
- sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq);
- sqb->npages = 1 << get_order(sqb->size);
+ sq_fbc = &qp->sq.fbc;
+ sqb = &sq_fbc->frag_buf;
+ *sqb = *buf;
+ sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq);
+ sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE);
sqb->frags += rqb->npages; /* first part is for the rq */
+ if (sq_fbc->strides_offset)
+ sqb->frags--;
}
int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *qpc, struct mlx5_wq_qp *wq,
struct mlx5_wq_ctrl *wq_ctrl)
{
+ u32 sq_strides_offset;
int err;
mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
MLX5_GET(qpc, qpc, log_rq_size),
&wq->rq.fbc);
- mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB),
- MLX5_GET(qpc, qpc, log_sq_size),
- &wq->sq.fbc);
+
+ sq_strides_offset =
+ ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB;
+
+ mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB),
+ MLX5_GET(qpc, qpc, log_sq_size),
+ sq_strides_offset,
+ &wq->sq.fbc);
err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
if (err) {
goto err_db_free;
}
- mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq);
+ mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq);
wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR];
wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR];
config MLXSW_PCI
tristate "PCI bus implementation for Mellanox Technologies Switch ASICs"
- depends on PCI && HAS_DMA && HAS_IOMEM && MLXSW_CORE
+ depends on PCI && HAS_IOMEM && MLXSW_CORE
default m
---help---
This is PCI bus implementation for Mellanox Technologies Switch ASICs.
list_add(&resource->list, &block->resource_list);
}
+static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource)
+{
+ list_del(&resource->list);
+}
+
static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block)
{
struct mlxsw_afa_resource *resource, *tmp;
list_for_each_entry_safe(resource, tmp, &block->resource_list, list) {
- list_del(&resource->list);
resource->destructor(block, resource);
}
}
mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block,
struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref)
{
+ mlxsw_afa_resource_del(&fwd_entry_ref->resource);
mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry);
kfree(fwd_entry_ref);
}
mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block,
struct mlxsw_afa_counter *counter)
{
+ mlxsw_afa_resource_del(&counter->resource);
block->afa->ops->counter_index_put(block->afa->ops_priv,
counter->counter_index);
kfree(counter);
char *oneact;
char *actions;
- if (WARN_ON(block->finished))
- return NULL;
+ if (block->finished)
+ return ERR_PTR(-EINVAL);
if (block->cur_act_index + action_size >
block->afa->max_acts_per_set) {
struct mlxsw_afa_set *set;
*/
set = mlxsw_afa_set_create(false);
if (!set)
- return NULL;
+ return ERR_PTR(-ENOBUFS);
set->prev = block->cur_set;
block->cur_act_index = 0;
block->cur_set->next = set;
MLXSW_AFA_VLAN_CODE,
MLXSW_AFA_VLAN_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
MLXSW_AFA_TRAPDISC_CODE,
MLXSW_AFA_TRAPDISC_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0);
return 0;
MLXSW_AFA_TRAPDISC_CODE,
MLXSW_AFA_TRAPDISC_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
trap_id);
MLXSW_AFA_TRAPDISC_CODE,
MLXSW_AFA_TRAPDISC_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
trap_id);
mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block,
struct mlxsw_afa_mirror *mirror)
{
+ mlxsw_afa_resource_del(&mirror->resource);
block->afa->ops->mirror_del(block->afa->ops_priv,
mirror->local_in_port,
mirror->span_id,
char *act = mlxsw_afa_block_append_action(block,
MLXSW_AFA_TRAPDISC_CODE,
MLXSW_AFA_TRAPDISC_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0);
mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent);
act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
MLXSW_AFA_FORWARD_SIZE);
- if (!act) {
- err = -ENOBUFS;
+ if (IS_ERR(act)) {
+ err = PTR_ERR(act);
goto err_append_action;
}
mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS,
{
char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE,
MLXSW_AFA_POLCNT_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
counter_index);
return 0;
char *act = mlxsw_afa_block_append_action(block,
MLXSW_AFA_VIRFWD_CODE,
MLXSW_AFA_VIRFWD_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
return 0;
}
char *act = mlxsw_afa_block_append_action(block,
MLXSW_AFA_MCROUTER_CODE,
MLXSW_AFA_MCROUTER_SIZE);
- if (!act)
- return -ENOBUFS;
+ if (IS_ERR(act))
+ return PTR_ERR(act);
mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
expected_irif, min_mtu, rmid_valid, kvdl_index);
return 0;
int err;
/* No need to continue if only VLAN flags were changed */
- if (mlxsw_sp_port_vlan->bridge_port)
+ if (mlxsw_sp_port_vlan->bridge_port) {
+ mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
return 0;
+ }
err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port);
if (err)
static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info)
{
ifh[0] = IFH_INJ_BYPASS;
- ifh[1] = (0xff00 & info->port) >> 8;
+ ifh[1] = (0xf00 & info->port) >> 8;
ifh[2] = (0xff & info->port) << 24;
- ifh[3] = IFH_INJ_POP_CNT_DISABLE | (info->cpuq << 20) |
- (info->tag_type << 16) | info->vid;
+ ifh[3] = (info->tag_type << 16) | info->vid;
return 0;
}
QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
info.port = BIT(port->chip_port);
- info.cpuq = 0xff;
+ info.tag_type = IFH_TAG_TYPE_C;
+ info.vid = skb_vlan_tag_get(skb);
ocelot_gen_ifh(ifh, &info);
for (i = 0; i < IFH_LEN; i++)
- ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
+ ocelot_write_rix(ocelot, (__force u32)cpu_to_be32(ifh[i]),
+ QS_INJ_WR, grp);
count = (skb->len + 3) / 4;
last = skb->len % 4;
ret = nfp_net_bpf_offload(nn, prog, running, extack);
/* Stop offload if replace not possible */
- if (ret && prog)
- nfp_bpf_xdp_offload(app, nn, NULL, extack);
+ if (ret)
+ return ret;
- nn->dp.bpf_offload_xdp = prog && !ret;
+ nn->dp.bpf_offload_xdp = !!prog;
return ret;
}
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
return NFP_REPR_TYPE_VF;
}
- return NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC;
+ return __NFP_REPR_TYPE_MAX;
}
static struct net_device *
u8 port = 0;
repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port);
+ if (repr_type > NFP_REPR_TYPE_MAX)
+ return NULL;
reprs = rcu_dereference(app->reprs[repr_type]);
if (!reprs)
eth_hw_addr_random(nn->dp.netdev);
netif_keep_dst(nn->dp.netdev);
+ nn->vnic_no_name = true;
return 0;
NFP_FLOWER_MASK_MPLS_Q;
frame->mpls_lse = cpu_to_be32(t_mpls);
+ } else if (dissector_uses_key(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC)) {
+ /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+ * bit, which indicates an mpls ether type but without any
+ * mpls fields.
+ */
+ struct flow_dissector_key_basic *key_basic;
+
+ key_basic = skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ flow->key);
+ if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+ key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+ frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
}
}
case cpu_to_be16(ETH_P_ARP):
return -EOPNOTSUPP;
+ case cpu_to_be16(ETH_P_MPLS_UC):
+ case cpu_to_be16(ETH_P_MPLS_MC):
+ if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+ key_layer |= NFP_FLOWER_LAYER_MAC;
+ key_size += sizeof(struct nfp_flower_mac_mpls);
+ }
+ break;
+
/* Will be included in layer 2. */
case cpu_to_be16(ETH_P_8021Q):
break;
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
payload.dst_ipv4 = flow->daddr;
/* If entry has expired send dst IP with all other fields 0. */
- if (!(neigh->nud_state & NUD_VALID)) {
+ if (!(neigh->nud_state & NUD_VALID) || neigh->dead) {
nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
/* Trigger ARP to verify invalid neighbour state. */
neigh_event_send(neigh, NULL);
err = PTR_ERR_OR_ZERO(rt);
if (err)
return NOTIFY_DONE;
+
+ ip_rt_put(rt);
#else
return NOTIFY_DONE;
#endif
return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
pf->limit_vfs = ~0;
- pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */
/* Allow any setting for backwards compatibility if symbol not found */
if (err == -ENOENT)
return 0;
err = nfp_net_pci_probe(pf);
if (err)
- goto err_sriov_unlimit;
+ goto err_fw_unload;
err = nfp_hwmon_register(pf);
if (err) {
err_net_remove:
nfp_net_pci_remove(pf);
-err_sriov_unlimit:
- pci_sriov_set_totalvfs(pf->pdev, 0);
err_fw_unload:
kfree(pf->rtbl);
nfp_mip_close(pf->mip);
nfp_hwmon_unregister(pf);
nfp_pcie_sriov_disable(pdev);
- pci_sriov_set_totalvfs(pf->pdev, 0);
nfp_net_pci_remove(pf);
* @vnic_list: Entry on device vNIC list
* @pdev: Backpointer to PCI device
* @app: APP handle if available
+ * @vnic_no_name: For non-port PF vNIC make ndo_get_phys_port_name return
+ * -EOPNOTSUPP to keep backwards compatibility (set by app)
* @port: Pointer to nfp_port structure if vNIC is a port
* @app_priv: APP private data for this vNIC
*/
struct pci_dev *pdev;
struct nfp_app *app;
+ bool vnic_no_name;
+
struct nfp_port *port;
void *app_priv;
struct nfp_net *nn = netdev_priv(netdev);
int r;
- for (r = 0; r < nn->dp.num_r_vecs; r++) {
+ for (r = 0; r < nn->max_r_vecs; r++) {
struct nfp_net_r_vector *r_vec = &nn->r_vecs[r];
u64 data[3];
unsigned int start;
if (nn->port)
return nfp_port_get_phys_port_name(netdev, name, len);
- if (nn->dp.is_vf)
+ if (nn->dp.is_vf || nn->vnic_no_name)
return -EOPNOTSUPP;
n = snprintf(name, len, "n%d", nn->id);
err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res),
nfp_resource_address(state->res),
fwinf, sizeof(*fwinf));
- if (err < sizeof(*fwinf))
+ if (err < (int)sizeof(*fwinf))
goto err_release;
if (!nffw_res_flg_init_get(fwinf))
static int nfp_cpp_resource_find(struct nfp_cpp *cpp, struct nfp_resource *res)
{
- char name_pad[NFP_RESOURCE_ENTRY_NAME_SZ] = {};
struct nfp_resource_entry entry;
u32 cpp_id, key;
int ret, i;
cpp_id = NFP_CPP_ID(NFP_RESOURCE_TBL_TARGET, 3, 0); /* Atomic read */
- strncpy(name_pad, res->name, sizeof(name_pad));
-
/* Search for a matching entry */
- if (!memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8)) {
+ if (!strcmp(res->name, NFP_RESOURCE_TBL_NAME)) {
nfp_err(cpp, "Grabbing device lock not supported\n");
return -EOPNOTSUPP;
}
- key = crc32_posix(name_pad, sizeof(name_pad));
+ key = crc32_posix(res->name, NFP_RESOURCE_ENTRY_NAME_SZ);
for (i = 0; i < NFP_RESOURCE_TBL_ENTRIES; i++) {
u64 addr = NFP_RESOURCE_TBL_BASE +
struct qed_nvm_image_info {
u32 num_images;
struct bist_nvm_image_att *image_att;
+ bool valid;
};
#define DRV_MODULE_VERSION \
*type = DCBX_PROTOCOL_ROCE_V2;
} else {
*type = DCBX_MAX_PROTOCOL_TYPE;
- DP_ERR(p_hwfn,
- "No action required, App TLV id = 0x%x app_prio_bitmap = 0x%x\n",
- id, app_prio_bitmap);
+ DP_ERR(p_hwfn, "No action required, App TLV entry = 0x%x\n",
+ app_prio_bitmap);
return false;
}
p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
- ARRAY_SIZE(p_local->local_chassis_id));
+ sizeof(p_local->local_chassis_id));
memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
- ARRAY_SIZE(p_local->local_port_id));
+ sizeof(p_local->local_port_id));
}
static void
p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
- ARRAY_SIZE(p_remote->peer_chassis_id));
+ sizeof(p_remote->peer_chassis_id));
memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
- ARRAY_SIZE(p_remote->peer_port_id));
+ sizeof(p_remote->peer_port_id));
}
static int
*cap = 0x80;
break;
case DCB_CAP_ATTR_DCBX:
- *cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE |
- DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_STATIC);
+ *cap = (DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_VER_IEEE |
+ DCB_CAP_DCBX_STATIC);
break;
default:
*cap = false;
if (!dcbx_info)
return 0;
- if (dcbx_info->operational.enabled)
- mode |= DCB_CAP_DCBX_LLD_MANAGED;
if (dcbx_info->operational.ieee)
mode |= DCB_CAP_DCBX_VER_IEEE;
if (dcbx_info->operational.cee)
format_idx = header & MFW_TRACE_EVENTID_MASK;
/* Skip message if its index doesn't exist in the meta data */
- if (format_idx > s_mcp_trace_meta.formats_num) {
+ if (format_idx >= s_mcp_trace_meta.formats_num) {
u8 format_size =
(u8)((header & MFW_TRACE_PRM_SIZE_MASK) >>
MFW_TRACE_PRM_SIZE_SHIFT);
DP_INFO(p_hwfn, "Failed to update driver state\n");
rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
- QED_OV_ESWITCH_VEB);
+ QED_OV_ESWITCH_NONE);
if (rc)
DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
}
p_ramrod->common.update_approx_mcast_flg = 1;
for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
- u32 *p_bins = (u32 *)p_params->bins;
+ u32 *p_bins = p_params->bins;
p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]);
}
enum spq_mode comp_mode,
struct qed_spq_comp_cb *p_comp_data)
{
- unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
struct vport_update_ramrod_data *p_ramrod = NULL;
+ u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
u8 abs_vport_id = 0;
/* explicitly clear out the entire vector */
memset(&p_ramrod->approx_mcast.bins, 0,
sizeof(p_ramrod->approx_mcast.bins));
- memset(bins, 0, sizeof(unsigned long) *
- ETH_MULTICAST_MAC_BINS_IN_REGS);
+ memset(bins, 0, sizeof(bins));
/* filter ADD op is explicit set op and it removes
* any existing filters for the vport
*/
if (p_filter_cmd->opcode == QED_FILTER_ADD) {
for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) {
- u32 bit;
+ u32 bit, nbits;
bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
- __set_bit(bit, bins);
+ nbits = sizeof(u32) * BITS_PER_BYTE;
+ bins[bit / nbits] |= 1 << (bit % nbits);
}
/* Convert to correct endianity */
for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
struct vport_update_ramrod_mcast *p_ramrod_bins;
- u32 *p_bins = (u32 *)bins;
p_ramrod_bins = &p_ramrod->approx_mcast;
- p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]);
+ p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]);
}
}
u8 anti_spoofing_en;
u8 update_accept_any_vlan_flg;
u8 accept_any_vlan;
- unsigned long bins[8];
+ u32 bins[8];
struct qed_rss_params *rss_params;
struct qed_filter_accept_flags accept_flags;
struct qed_sge_tpa_params *sge_tpa_params;
skb = build_skb(buffer->data, 0);
if (!skb) {
- rc = -ENOMEM;
- goto out_post;
+ DP_INFO(cdev, "Failed to build SKB\n");
+ kfree(buffer->data);
+ goto out_post1;
}
data->u.placement_offset += NET_SKB_PAD;
cdev->ll2->cbs->rx_cb(cdev->ll2->cb_cookie, skb,
data->opaque_data_0,
data->opaque_data_1);
+ } else {
+ DP_VERBOSE(p_hwfn, (NETIF_MSG_RX_STATUS | NETIF_MSG_PKTDATA |
+ QED_MSG_LL2 | QED_MSG_STORAGE),
+ "Dropping the packet\n");
+ kfree(buffer->data);
}
+out_post1:
/* Update Buffer information and update FW producer */
buffer->data = new_data;
buffer->phys_addr = new_phys_addr;
goto err2;
}
- DP_INFO(cdev, "qed_probe completed successffuly\n");
+ DP_INFO(cdev, "qed_probe completed successfully\n");
return cdev;
/* Fastpath interrupts */
for (j = 0; j < 64; j++) {
if ((0x2ULL << j) & status) {
- hwfn->simd_proto_handler[j].func(
- hwfn->simd_proto_handler[j].token);
+ struct qed_simd_fp_handler *p_handler =
+ &hwfn->simd_proto_handler[j];
+
+ if (p_handler->func)
+ p_handler->func(p_handler->token);
+ else
+ DP_NOTICE(hwfn,
+ "Not calling fastpath handler as it is NULL [handler #%d, status 0x%llx]\n",
+ j, status);
+
status &= ~(0x2ULL << j);
rc = IRQ_HANDLED;
}
/* We want a minimum of one slowpath and one fastpath vector per hwfn */
cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
+ if (is_kdump_kernel()) {
+ DP_INFO(cdev,
+ "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+ cdev->int_params.in.min_msix_cnt);
+ cdev->int_params.in.num_vectors =
+ cdev->int_params.in.min_msix_cnt;
+ }
+
rc = qed_set_int_mode(cdev, false);
if (rc) {
DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
*o_mcp_resp = mb_params.mcp_resp;
*o_mcp_param = mb_params.mcp_param;
+ /* nvm_info needs to be updated */
+ p_hwfn->nvm_info.valid = false;
+
return 0;
}
break;
default:
p_link->speed = 0;
+ p_link->link_up = 0;
}
if (p_link->link_up && p_link->speed)
phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
phy_cfg.adv_speed = params->speed.advertised_speeds;
phy_cfg.loopback_mode = params->loopback_mode;
- if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) {
- if (params->eee.enable)
- phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
+
+ /* There are MFWs that share this capability regardless of whether
+ * this is feasible or not. And given that at the very least adv_caps
+ * would be set internally by qed, we want to make sure LFA would
+ * still work.
+ */
+ if ((p_hwfn->mcp_info->capabilities &
+ FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) {
+ phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
if (params->eee.tx_lpi_enable)
phy_cfg.eee_cfg |= EEE_CFG_TX_LPI;
if (params->eee.adv_caps & QED_EEE_1G_ADV)
int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
{
- struct qed_nvm_image_info *nvm_info = &p_hwfn->nvm_info;
+ struct qed_nvm_image_info nvm_info;
struct qed_ptt *p_ptt;
int rc;
u32 i;
+ if (p_hwfn->nvm_info.valid)
+ return 0;
+
p_ptt = qed_ptt_acquire(p_hwfn);
if (!p_ptt) {
DP_ERR(p_hwfn, "failed to acquire ptt\n");
}
/* Acquire from MFW the amount of available images */
- nvm_info->num_images = 0;
+ nvm_info.num_images = 0;
rc = qed_mcp_bist_nvm_get_num_images(p_hwfn,
- p_ptt, &nvm_info->num_images);
+ p_ptt, &nvm_info.num_images);
if (rc == -EOPNOTSUPP) {
DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n");
goto out;
- } else if (rc || !nvm_info->num_images) {
+ } else if (rc || !nvm_info.num_images) {
DP_ERR(p_hwfn, "Failed getting number of images\n");
goto err0;
}
- nvm_info->image_att = kmalloc_array(nvm_info->num_images,
- sizeof(struct bist_nvm_image_att),
- GFP_KERNEL);
- if (!nvm_info->image_att) {
+ nvm_info.image_att = kmalloc_array(nvm_info.num_images,
+ sizeof(struct bist_nvm_image_att),
+ GFP_KERNEL);
+ if (!nvm_info.image_att) {
rc = -ENOMEM;
goto err0;
}
/* Iterate over images and get their attributes */
- for (i = 0; i < nvm_info->num_images; i++) {
+ for (i = 0; i < nvm_info.num_images; i++) {
rc = qed_mcp_bist_nvm_get_image_att(p_hwfn, p_ptt,
- &nvm_info->image_att[i], i);
+ &nvm_info.image_att[i], i);
if (rc) {
DP_ERR(p_hwfn,
"Failed getting image index %d attributes\n", i);
}
DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n", i,
- nvm_info->image_att[i].len);
+ nvm_info.image_att[i].len);
}
out:
+ /* Update hwfn's nvm_info */
+ if (nvm_info.num_images) {
+ p_hwfn->nvm_info.num_images = nvm_info.num_images;
+ kfree(p_hwfn->nvm_info.image_att);
+ p_hwfn->nvm_info.image_att = nvm_info.image_att;
+ p_hwfn->nvm_info.valid = true;
+ }
+
qed_ptt_release(p_hwfn, p_ptt);
return 0;
err1:
- kfree(nvm_info->image_att);
+ kfree(nvm_info.image_att);
err0:
qed_ptt_release(p_hwfn, p_ptt);
return rc;
return -EINVAL;
}
+ qed_mcp_nvm_info_populate(p_hwfn);
for (i = 0; i < p_hwfn->nvm_info.num_images; i++)
if (type == p_hwfn->nvm_info.image_att[i].image_type)
break;
p_data->update_approx_mcast_flg = 1;
memcpy(p_data->bins, p_mcast_tlv->bins,
- sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+ sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
*tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST;
}
static int qed_sriov_enable(struct qed_dev *cdev, int num)
{
struct qed_iov_vf_init_params params;
+ struct qed_hwfn *hwfn;
+ struct qed_ptt *ptt;
int i, j, rc;
if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
/* Initialize HW for VF access */
for_each_hwfn(cdev, j) {
- struct qed_hwfn *hwfn = &cdev->hwfns[j];
- struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+ hwfn = &cdev->hwfns[j];
+ ptt = qed_ptt_acquire(hwfn);
/* Make sure not to use more than 16 queues per VF */
params.num_queues = min_t(int,
goto err;
}
+ hwfn = QED_LEADING_HWFN(cdev);
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt) {
+ DP_ERR(hwfn, "Failed to acquire ptt\n");
+ rc = -EBUSY;
+ goto err;
+ }
+
+ rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+ if (rc)
+ DP_INFO(cdev, "Failed to update eswitch mode\n");
+ qed_ptt_release(hwfn, ptt);
+
return num;
err:
resp_size += sizeof(struct pfvf_def_resp_tlv);
memcpy(p_mcast_tlv->bins, p_params->bins,
- sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+ sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
}
update_rx = p_params->accept_flags.update_rx_mode_config;
u32 bit;
bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
- __set_bit(bit, sp_params.bins);
+ sp_params.bins[bit / 32] |= 1 << (bit % 32);
}
}
struct channel_tlv tl;
u8 padding[4];
- u64 bins[8];
+ /* There are only 256 approx bins, and in HSI they're divided into
+ * 32-bit values. As old VFs used to set-bit to the values on its side,
+ * the upper half of the array is never expected to contain any data.
+ */
+ u64 bins[4];
+ u64 obsolete_bins[4];
};
struct vfpf_vport_update_accept_param_tlv {
{
struct qede_ptp *ptp = edev->ptp;
- if (!ptp)
- return -EIO;
+ if (!ptp) {
+ info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info->phc_index = -1;
+
+ return 0;
+ }
info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
SOF_TIMESTAMPING_RX_SOFTWARE |
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
ret = kstrtoul(buf, 16, &data);
+ if (ret)
+ return ret;
switch (data) {
case QLC_83XX_FLASH_SECTOR_ERASE_CMD:
}
sgmii_pdev = of_find_device_by_node(np);
+ of_node_put(np);
if (!sgmii_pdev) {
dev_err(&pdev->dev, "invalid internal-phy property\n");
return -ENODEV;
return ret;
}
- netif_start_queue(qca->net_dev);
+ /* SPI thread takes care of TX queue */
return 0;
}
qca->net_dev->stats.tx_errors++;
/* Trigger tx queue flush and QCA7000 reset */
qca->sync = QCASPI_SYNC_UNKNOWN;
+
+ if (qca->spi_thread)
+ wake_up_process(qca->spi_thread);
}
static int
if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) ||
(qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) {
- dev_info(&spi->dev, "Invalid clkspeed: %d\n",
- qcaspi_clkspeed);
+ dev_err(&spi->dev, "Invalid clkspeed: %d\n",
+ qcaspi_clkspeed);
return -EINVAL;
}
if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) ||
(qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) {
- dev_info(&spi->dev, "Invalid burst len: %d\n",
- qcaspi_burst_len);
+ dev_err(&spi->dev, "Invalid burst len: %d\n",
+ qcaspi_burst_len);
return -EINVAL;
}
if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) ||
(qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) {
- dev_info(&spi->dev, "Invalid pluggable: %d\n",
- qcaspi_pluggable);
+ dev_err(&spi->dev, "Invalid pluggable: %d\n",
+ qcaspi_pluggable);
return -EINVAL;
}
}
if (register_netdev(qcaspi_devs)) {
- dev_info(&spi->dev, "Unable to register net device %s\n",
- qcaspi_devs->name);
+ dev_err(&spi->dev, "Unable to register net device %s\n",
+ qcaspi_devs->name);
free_netdev(qcaspi_devs);
return -EFAULT;
}
{
struct rtl8169_private *tp = netdev_priv(dev);
- rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), dev);
+ rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), tp);
}
#endif
return rc;
}
- /* override BIOS settings, use userspace tools to enable WOL */
- __rtl8169_set_wol(tp, 0);
+ tp->saved_wolopts = __rtl8169_get_wol(tp);
if (rtl_tbi_enabled(tp)) {
tp->set_speed = rtl8169_set_speed_tbi;
NETIF_F_HW_VLAN_CTAG_RX;
dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
NETIF_F_HIGHDMA;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
tp->cp_cmd |= RxChkSum | RxVlan;
config SH_ETH
tristate "Renesas SuperH Ethernet support"
- depends on HAS_DMA
depends on ARCH_RENESAS || SUPERH || COMPILE_TEST
select CRC32
select MII
config RAVB
tristate "Renesas Ethernet AVB support"
- depends on HAS_DMA
depends on ARCH_RENESAS || COMPILE_TEST
select CRC32
select MII
struct ravb_private *priv = netdev_priv(ndev);
struct phy_device *phydev = ndev->phydev;
bool new_state = false;
+ unsigned long flags;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ /* Disable TX and RX right over here, if E-MAC change is ignored */
+ if (priv->no_avb_link)
+ ravb_rcv_snd_disable(ndev);
if (phydev->link) {
if (phydev->duplex != priv->duplex) {
ravb_modify(ndev, ECMR, ECMR_TXF, 0);
new_state = true;
priv->link = phydev->link;
- if (priv->no_avb_link)
- ravb_rcv_snd_enable(ndev);
}
} else if (priv->link) {
new_state = true;
priv->link = 0;
priv->speed = 0;
priv->duplex = -1;
- if (priv->no_avb_link)
- ravb_rcv_snd_disable(ndev);
}
+ /* Enable TX and RX right over here, if E-MAC change is ignored */
+ if (priv->no_avb_link && phydev->link)
+ ravb_rcv_snd_enable(ndev);
+
+ mmiowb();
+ spin_unlock_irqrestore(&priv->lock, flags);
+
if (new_state && netif_msg_link(priv))
phy_print_status(phydev);
}
return 0;
}
-static int ravb_get_link_ksettings(struct net_device *ndev,
- struct ethtool_link_ksettings *cmd)
-{
- struct ravb_private *priv = netdev_priv(ndev);
- unsigned long flags;
-
- if (!ndev->phydev)
- return -ENODEV;
-
- spin_lock_irqsave(&priv->lock, flags);
- phy_ethtool_ksettings_get(ndev->phydev, cmd);
- spin_unlock_irqrestore(&priv->lock, flags);
-
- return 0;
-}
-
-static int ravb_set_link_ksettings(struct net_device *ndev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct ravb_private *priv = netdev_priv(ndev);
- unsigned long flags;
- int error;
-
- if (!ndev->phydev)
- return -ENODEV;
-
- spin_lock_irqsave(&priv->lock, flags);
-
- /* Disable TX and RX */
- ravb_rcv_snd_disable(ndev);
-
- error = phy_ethtool_ksettings_set(ndev->phydev, cmd);
- if (error)
- goto error_exit;
-
- if (cmd->base.duplex == DUPLEX_FULL)
- priv->duplex = 1;
- else
- priv->duplex = 0;
-
- ravb_set_duplex(ndev);
-
-error_exit:
- mdelay(1);
-
- /* Enable TX and RX */
- ravb_rcv_snd_enable(ndev);
-
- mmiowb();
- spin_unlock_irqrestore(&priv->lock, flags);
-
- return error;
-}
-
-static int ravb_nway_reset(struct net_device *ndev)
-{
- struct ravb_private *priv = netdev_priv(ndev);
- int error = -ENODEV;
- unsigned long flags;
-
- if (ndev->phydev) {
- spin_lock_irqsave(&priv->lock, flags);
- error = phy_start_aneg(ndev->phydev);
- spin_unlock_irqrestore(&priv->lock, flags);
- }
-
- return error;
-}
-
static u32 ravb_get_msglevel(struct net_device *ndev)
{
struct ravb_private *priv = netdev_priv(ndev);
}
static const struct ethtool_ops ravb_ethtool_ops = {
- .nway_reset = ravb_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_msglevel = ravb_get_msglevel,
.set_msglevel = ravb_set_msglevel,
.get_link = ethtool_op_get_link,
.get_ringparam = ravb_get_ringparam,
.set_ringparam = ravb_set_ringparam,
.get_ts_info = ravb_get_ts_info,
- .get_link_ksettings = ravb_get_link_ksettings,
- .set_link_ksettings = ravb_set_link_ksettings,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
.get_wol = ravb_get_wol,
.set_wol = ravb_set_wol,
};
{
struct sh_eth_private *mdp = netdev_priv(ndev);
struct phy_device *phydev = ndev->phydev;
+ unsigned long flags;
int new_state = 0;
+ spin_lock_irqsave(&mdp->lock, flags);
+
+ /* Disable TX and RX right over here, if E-MAC change is ignored */
+ if (mdp->cd->no_psr || mdp->no_ether_link)
+ sh_eth_rcv_snd_disable(ndev);
+
if (phydev->link) {
if (phydev->duplex != mdp->duplex) {
new_state = 1;
sh_eth_modify(ndev, ECMR, ECMR_TXF, 0);
new_state = 1;
mdp->link = phydev->link;
- if (mdp->cd->no_psr || mdp->no_ether_link)
- sh_eth_rcv_snd_enable(ndev);
}
} else if (mdp->link) {
new_state = 1;
mdp->link = 0;
mdp->speed = 0;
mdp->duplex = -1;
- if (mdp->cd->no_psr || mdp->no_ether_link)
- sh_eth_rcv_snd_disable(ndev);
}
+ /* Enable TX and RX right over here, if E-MAC change is ignored */
+ if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
+ sh_eth_rcv_snd_enable(ndev);
+
+ mmiowb();
+ spin_unlock_irqrestore(&mdp->lock, flags);
+
if (new_state && netif_msg_link(mdp))
phy_print_status(phydev);
}
return 0;
}
-static int sh_eth_get_link_ksettings(struct net_device *ndev,
- struct ethtool_link_ksettings *cmd)
-{
- struct sh_eth_private *mdp = netdev_priv(ndev);
- unsigned long flags;
-
- if (!ndev->phydev)
- return -ENODEV;
-
- spin_lock_irqsave(&mdp->lock, flags);
- phy_ethtool_ksettings_get(ndev->phydev, cmd);
- spin_unlock_irqrestore(&mdp->lock, flags);
-
- return 0;
-}
-
-static int sh_eth_set_link_ksettings(struct net_device *ndev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct sh_eth_private *mdp = netdev_priv(ndev);
- unsigned long flags;
- int ret;
-
- if (!ndev->phydev)
- return -ENODEV;
-
- spin_lock_irqsave(&mdp->lock, flags);
-
- /* disable tx and rx */
- sh_eth_rcv_snd_disable(ndev);
-
- ret = phy_ethtool_ksettings_set(ndev->phydev, cmd);
- if (ret)
- goto error_exit;
-
- if (cmd->base.duplex == DUPLEX_FULL)
- mdp->duplex = 1;
- else
- mdp->duplex = 0;
-
- if (mdp->cd->set_duplex)
- mdp->cd->set_duplex(ndev);
-
-error_exit:
- mdelay(1);
-
- /* enable tx and rx */
- sh_eth_rcv_snd_enable(ndev);
-
- spin_unlock_irqrestore(&mdp->lock, flags);
-
- return ret;
-}
-
/* If it is ever necessary to increase SH_ETH_REG_DUMP_MAX_REGS, the
* version must be bumped as well. Just adding registers up to that
* limit is fine, as long as the existing register indices don't
pm_runtime_put_sync(&mdp->pdev->dev);
}
-static int sh_eth_nway_reset(struct net_device *ndev)
-{
- struct sh_eth_private *mdp = netdev_priv(ndev);
- unsigned long flags;
- int ret;
-
- if (!ndev->phydev)
- return -ENODEV;
-
- spin_lock_irqsave(&mdp->lock, flags);
- ret = phy_start_aneg(ndev->phydev);
- spin_unlock_irqrestore(&mdp->lock, flags);
-
- return ret;
-}
-
static u32 sh_eth_get_msglevel(struct net_device *ndev)
{
struct sh_eth_private *mdp = netdev_priv(ndev);
static const struct ethtool_ops sh_eth_ethtool_ops = {
.get_regs_len = sh_eth_get_regs_len,
.get_regs = sh_eth_get_regs,
- .nway_reset = sh_eth_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_msglevel = sh_eth_get_msglevel,
.set_msglevel = sh_eth_set_msglevel,
.get_link = ethtool_op_get_link,
.get_sset_count = sh_eth_get_sset_count,
.get_ringparam = sh_eth_get_ringparam,
.set_ringparam = sh_eth_set_ringparam,
- .get_link_ksettings = sh_eth_get_link_ksettings,
- .set_link_ksettings = sh_eth_set_link_ksettings,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
.get_wol = sh_eth_get_wol,
.set_wol = sh_eth_set_wol,
};
return -EPROTONOSUPPORT;
}
-static s32 efx_ef10_filter_insert(struct efx_nic *efx,
- struct efx_filter_spec *spec,
- bool replace_equal)
+static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx,
+ struct efx_filter_spec *spec,
+ bool replace_equal)
{
DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
struct efx_ef10_nic_data *nic_data = efx->nic_data;
bool is_mc_recip;
s32 rc;
- down_read(&efx->filter_sem);
+ WARN_ON(!rwsem_is_locked(&efx->filter_sem));
table = efx->filter_state;
down_write(&table->lock);
if (rss_locked)
mutex_unlock(&efx->rss_lock);
up_write(&table->lock);
- up_read(&efx->filter_sem);
return rc;
}
+static s32 efx_ef10_filter_insert(struct efx_nic *efx,
+ struct efx_filter_spec *spec,
+ bool replace_equal)
+{
+ s32 ret;
+
+ down_read(&efx->filter_sem);
+ ret = efx_ef10_filter_insert_locked(efx, spec, replace_equal);
+ up_read(&efx->filter_sem);
+
+ return ret;
+}
+
static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
{
/* no need to do anything here on EF10 */
EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID);
efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr);
- rc = efx_ef10_filter_insert(efx, &spec, true);
+ rc = efx_ef10_filter_insert_locked(efx, &spec, true);
if (rc < 0) {
if (rollback) {
netif_info(efx, drv, efx->net_dev,
efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
eth_broadcast_addr(baddr);
efx_filter_set_eth_local(&spec, vlan->vid, baddr);
- rc = efx_ef10_filter_insert(efx, &spec, true);
+ rc = efx_ef10_filter_insert_locked(efx, &spec, true);
if (rc < 0) {
netif_warn(efx, drv, efx->net_dev,
"Broadcast filter insert failed rc=%d\n", rc);
if (vlan->vid != EFX_FILTER_VID_UNSPEC)
efx_filter_set_eth_local(&spec, vlan->vid, NULL);
- rc = efx_ef10_filter_insert(efx, &spec, true);
+ rc = efx_ef10_filter_insert_locked(efx, &spec, true);
if (rc < 0) {
const char *um = multicast ? "Multicast" : "Unicast";
const char *encap_name = "";
filter_flags, 0);
eth_broadcast_addr(baddr);
efx_filter_set_eth_local(&spec, vlan->vid, baddr);
- rc = efx_ef10_filter_insert(efx, &spec, true);
+ rc = efx_ef10_filter_insert_locked(efx, &spec, true);
if (rc < 0) {
netif_warn(efx, drv, efx->net_dev,
"Broadcast filter insert failed rc=%d\n",
up_write(&efx->filter_sem);
}
-static void efx_restore_filters(struct efx_nic *efx)
-{
- down_read(&efx->filter_sem);
- efx->type->filter_table_restore(efx);
- up_read(&efx->filter_sem);
-}
/**************************************************************************
*
efx_disable_interrupts(efx);
mutex_lock(&efx->mac_lock);
+ down_write(&efx->filter_sem);
mutex_lock(&efx->rss_lock);
if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
method != RESET_TYPE_DATAPATH)
if (efx->type->rx_restore_rss_contexts)
efx->type->rx_restore_rss_contexts(efx);
mutex_unlock(&efx->rss_lock);
- down_read(&efx->filter_sem);
- efx_restore_filters(efx);
- up_read(&efx->filter_sem);
+ efx->type->filter_table_restore(efx);
+ up_write(&efx->filter_sem);
if (efx->type->sriov_reset)
efx->type->sriov_reset(efx);
efx->port_initialized = false;
mutex_unlock(&efx->rss_lock);
+ up_write(&efx->filter_sem);
mutex_unlock(&efx->mac_lock);
return rc;
return true;
}
+static
struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
const struct efx_filter_spec *spec)
{
efx_init_napi(efx);
+ down_write(&efx->filter_sem);
rc = efx->type->init(efx);
+ up_write(&efx->filter_sem);
if (rc) {
netif_err(efx, probe, efx->net_dev,
"failed to initialise NIC\n");
rc = efx->type->reset(efx, RESET_TYPE_ALL);
if (rc)
return rc;
+ down_write(&efx->filter_sem);
rc = efx->type->init(efx);
+ up_write(&efx->filter_sem);
if (rc)
return rc;
rc = efx_pm_thaw(dev);
if (!state)
return -ENOMEM;
efx->filter_state = state;
+ init_rwsem(&state->lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
config DWMAC_SOCFPGA
tristate "SOCFPGA dwmac support"
default ARCH_SOCFPGA
- depends on OF && (ARCH_SOCFPGA || COMPILE_TEST)
+ depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST)
select MFD_SYSCON
help
Support for ethernet controller on Altera SOCFPGA
dwmac->data = (const struct meson8b_dwmac_data *)
of_device_get_match_data(&pdev->dev);
- if (!dwmac->data)
- return -EINVAL;
-
+ if (!dwmac->data) {
+ ret = -EINVAL;
+ goto err_remove_config_dt;
+ }
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
dwmac->regs = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(dwmac->regs)) {
struct device *dev;
struct regmap *sys_mgr_base_addr;
struct reset_control *stmmac_rst;
+ struct reset_control *stmmac_ocp_rst;
void __iomem *splitter_base;
bool f2h_ptp_ref_clk;
struct tse_pcs pcs;
val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
/* Assert reset to the enet controller before changing the phy mode */
- if (dwmac->stmmac_rst)
- reset_control_assert(dwmac->stmmac_rst);
+ reset_control_assert(dwmac->stmmac_ocp_rst);
+ reset_control_assert(dwmac->stmmac_rst);
regmap_read(sys_mgr_base_addr, reg_offset, &ctrl);
ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift);
/* Deassert reset for the phy configuration to be sampled by
* the enet controller, and operation to start in requested mode
*/
- if (dwmac->stmmac_rst)
- reset_control_deassert(dwmac->stmmac_rst);
+ reset_control_deassert(dwmac->stmmac_ocp_rst);
+ reset_control_deassert(dwmac->stmmac_rst);
if (phymode == PHY_INTERFACE_MODE_SGMII) {
if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) {
dev_err(dwmac->dev, "Unable to initialize TSE PCS");
goto err_remove_config_dt;
}
+ dwmac->stmmac_ocp_rst = devm_reset_control_get_optional(dev, "stmmaceth-ocp");
+ if (IS_ERR(dwmac->stmmac_ocp_rst)) {
+ ret = PTR_ERR(dwmac->stmmac_ocp_rst);
+ dev_err(dev, "error getting reset control of ocp %d\n", ret);
+ goto err_remove_config_dt;
+ }
+
+ reset_control_deassert(dwmac->stmmac_ocp_rst);
+
ret = socfpga_dwmac_parse_data(dwmac, dev);
if (ret) {
dev_err(dev, "Unable to parse OF data\n");
* is done in the "stmmac files"
*/
-/* struct emac_variant - Descrive dwmac-sun8i hardware variant
+/* struct emac_variant - Describe dwmac-sun8i hardware variant
* @default_syscon_value: The default value of the EMAC register in syscon
* This value is used for disabling properly EMAC
* and used as a good starting value in case of the
}
}
+static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+ u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+ value &= ~DMA_RBSZ_MASK;
+ value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK;
+
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+}
+
const struct stmmac_dma_ops dwmac4_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .set_bfsize = dwmac4_set_bfsize,
};
const struct stmmac_dma_ops dwmac410_dma_ops = {
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .set_bfsize = dwmac4_set_bfsize,
};
/* DMA Rx Channel X Control register defines */
#define DMA_CONTROL_SR BIT(0)
+#define DMA_RBSZ_MASK GENMASK(14, 1)
+#define DMA_RBSZ_SHIFT 1
/* Interrupt status per channel */
#define DMA_CHAN_STATUS_REB GENMASK(21, 19)
return ret;
}
- /* Run quirks, if needed */
- if (entry->quirks) {
- ret = entry->quirks(priv);
- if (ret)
- return ret;
- }
-
+ /* Save quirks, if needed for posterior use */
+ priv->hwif_quirks = entry->quirks;
return 0;
}
void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+ void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
};
#define stmmac_reset(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
#define stmmac_enable_tso(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_set_dma_bfsize(__priv, __args...) \
+ stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
struct mac_device_info;
struct net_device;
struct net_device *dev;
struct device *device;
struct mac_device_info *hw;
+ int (*hwif_quirks)(struct stmmac_priv *priv);
struct mutex lock;
/* RX Queue */
#include "dwmac1000.h"
#include "hwif.h"
-#define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x)
+#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES)
#define TSO_MAX_BUFF_SIZE (SZ_16K - 1)
/* Module parameters */
static int stmmac_init_phy(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
struct phy_device *phydev;
char phy_id_fmt[MII_BUS_ID_SIZE + 3];
char bus_id[MII_BUS_ID_SIZE];
phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full);
+ /*
+ * Half-duplex mode not supported with multiqueue
+ * half-duplex can only works with single queue
+ */
+ if (tx_cnt > 1)
+ phydev->supported &= ~(SUPPORTED_1000baseT_Half |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_10baseT_Half);
+
/*
* Broken HW is sometimes missing the pull-up resistor on the
* MDIO line, which results in reads to non-existent devices returning
stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
rxfifosz, qmode);
+ stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz,
+ chan);
}
for (chan = 0; chan < tx_channels_count; chan++) {
static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb)
{
- struct ethhdr *ehdr;
+ struct vlan_ethhdr *veth;
+ __be16 vlan_proto;
u16 vlanid;
- if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) ==
- NETIF_F_HW_VLAN_CTAG_RX &&
- !__vlan_get_tag(skb, &vlanid)) {
+ veth = (struct vlan_ethhdr *)skb->data;
+ vlan_proto = veth->h_vlan_proto;
+
+ if ((vlan_proto == htons(ETH_P_8021Q) &&
+ dev->features & NETIF_F_HW_VLAN_CTAG_RX) ||
+ (vlan_proto == htons(ETH_P_8021AD) &&
+ dev->features & NETIF_F_HW_VLAN_STAG_RX)) {
/* pop the vlan tag */
- ehdr = (struct ethhdr *)skb->data;
- memmove(skb->data + VLAN_HLEN, ehdr, ETH_ALEN * 2);
+ vlanid = ntohs(veth->h_vlan_TCI);
+ memmove(skb->data + VLAN_HLEN, veth, ETH_ALEN * 2);
skb_pull(skb, VLAN_HLEN);
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid);
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlanid);
}
}
if (priv->dma_cap.tsoen)
dev_info(priv->device, "TSO supported\n");
+ /* Run HW quirks, if any */
+ if (priv->hwif_quirks) {
+ ret = priv->hwif_quirks(priv);
+ if (ret)
+ return ret;
+ }
+
return 0;
}
ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
#ifdef STMMAC_VLAN_TAG_USED
/* Both mac100 and gmac support receive VLAN tag detection */
- ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
#endif
priv->msg_enable = netif_msg_init(debug, default_msg_level);
return -ENOMEM;
/* Enable pci device */
- ret = pcim_enable_device(pdev);
+ ret = pci_enable_device(pdev);
if (ret) {
dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n",
__func__);
static void stmmac_pci_remove(struct pci_dev *pdev)
{
stmmac_dvr_remove(&pdev->dev);
+ pci_disable_device(pdev);
}
-static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume);
+static int stmmac_pci_suspend(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ int ret;
+
+ ret = stmmac_suspend(dev);
+ if (ret)
+ return ret;
+
+ ret = pci_save_state(pdev);
+ if (ret)
+ return ret;
+
+ pci_disable_device(pdev);
+ pci_wake_from_d3(pdev, true);
+ return 0;
+}
+
+static int stmmac_pci_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ int ret;
+
+ pci_restore_state(pdev);
+ pci_set_power_state(pdev, PCI_D0);
+
+ ret = pci_enable_device(pdev);
+ if (ret)
+ return ret;
+
+ pci_set_master(pdev);
+
+ return stmmac_resume(dev);
+}
+
+static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume);
/* synthetic ID, no official vendor */
#define PCI_VENDOR_ID_STMMAC 0x700
/**
* stmmac_axi_setup - parse DT parameters for programming the AXI register
* @pdev: platform device
- * @priv: driver private struct.
* Description:
* if required, from device-tree the AXI internal register can be tuned
* by using platform parameters.
#include <linux/sungem_phy.h>
#include "sungem.h"
-/* Stripping FCS is causing problems, disabled for now */
-#undef STRIP_FCS
+#define STRIP_FCS
#define DEFAULT_MSG (NETIF_MSG_DRV | \
NETIF_MSG_PROBE | \
writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW);
writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK);
val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
- ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+ (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
writel(val, gp->regs + RXDMA_CFG);
if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN)
writel(((5 & RXDMA_BLANK_IPKTS) |
struct net_device *dev = gp->dev;
int entry, drops, work_done = 0;
u32 done;
- __sum16 csum;
if (netif_msg_rx_status(gp))
printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n",
skb = copy_skb;
}
- csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
- skb->csum = csum_unfold(csum);
- skb->ip_summed = CHECKSUM_COMPLETE;
+ if (likely(dev->features & NETIF_F_RXCSUM)) {
+ __sum16 csum;
+
+ csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
+ skb->csum = csum_unfold(csum);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ }
skb->protocol = eth_type_trans(skb, gp->dev);
napi_gro_receive(&gp->napi, skb);
writel(0, gp->regs + TXDMA_KICK);
val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
- ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+ (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
writel(val, gp->regs + RXDMA_CFG);
writel(desc_dma >> 32, gp->regs + RXDMA_DBHI);
pci_set_drvdata(pdev, dev);
/* We can do scatter/gather and HW checksum */
- dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM;
- dev->features |= dev->hw_features | NETIF_F_RXCSUM;
+ dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+ dev->features = dev->hw_features;
if (pci_using_dac)
dev->features |= NETIF_F_HIGHDMA;
int i;
for (i = 0; i < cpsw->data.slaves; i++) {
- if (vid == cpsw->slaves[i].port_vlan)
- return -EINVAL;
+ if (vid == cpsw->slaves[i].port_vlan) {
+ ret = -EINVAL;
+ goto err;
+ }
}
}
dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
ret = cpsw_add_vlan_ale_entry(priv, vid);
-
+err:
pm_runtime_put(cpsw->dev);
return ret;
}
for (i = 0; i < cpsw->data.slaves; i++) {
if (vid == cpsw->slaves[i].port_vlan)
- return -EINVAL;
+ goto err;
}
}
dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0);
- if (ret != 0)
- return ret;
-
- ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
- HOST_PORT_NUM, ALE_VLAN, vid);
- if (ret != 0)
- return ret;
-
- ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
- 0, ALE_VLAN, vid);
+ ret |= cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+ HOST_PORT_NUM, ALE_VLAN, vid);
+ ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
+ 0, ALE_VLAN, vid);
+err:
pm_runtime_put(cpsw->dev);
return ret;
}
idx = cpsw_ale_match_addr(ale, addr, (flags & ALE_VLAN) ? vid : 0);
if (idx < 0)
- return -EINVAL;
+ return -ENOENT;
cpsw_ale_read(ale, idx, ale_entry);
* devices (e.g. cpsw switches) use plain old memory. Descriptor pools
* abstract out these details
*/
-int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
+static int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
{
struct cpdma_params *cpdma_params = &ctlr->params;
struct cpdma_desc_pool *pool;
return -EOPNOTSUPP;
}
+static int match_first_device(struct device *dev, void *data)
+{
+ if (dev->parent && dev->parent->of_node)
+ return of_device_is_compatible(dev->parent->of_node,
+ "ti,davinci_mdio");
+
+ return !strncmp(dev_name(dev), "davinci_mdio", 12);
+}
+
/**
* emac_dev_open - EMAC device open
* @ndev: The DaVinci EMAC network adapter
/* use the first phy on the bus if pdata did not give us a phy id */
if (!phydev && !priv->phy_id) {
- phy = bus_find_device_by_name(&mdio_bus_type, NULL,
- "davinci_mdio");
+ /* NOTE: we can't use bus_find_device_by_name() here because
+ * the device name is not guaranteed to be 'davinci_mdio'. On
+ * some systems it can be 'davinci_mdio.0' so we need to use
+ * strncmp() against the first part of the string to correctly
+ * match it.
+ */
+ phy = bus_find_device(&mdio_bus_type, NULL, NULL,
+ match_first_device);
if (phy) {
priv->phy_id = dev_name(phy);
if (!priv->phy_id || !*priv->phy_id)
ret = of_mdiobus_register(bus, np1);
if (ret) {
mdiobus_free(bus);
+ lp->mii_bus = NULL;
return ret;
}
return 0;
* @phy_node: pointer to the PHY device node
* @mii_bus: pointer to the MII bus
* @last_link: last link status
- * @has_mdio: indicates whether MDIO is included in the HW
*/
struct net_local {
struct mii_bus *mii_bus;
int last_link;
- bool has_mdio;
};
bus->write = xemaclite_mdio_write;
bus->parent = dev;
- lp->mii_bus = bus;
-
rc = of_mdiobus_register(bus, np);
if (rc) {
dev_err(dev, "Failed to register mdio bus.\n");
goto err_register;
}
+ lp->mii_bus = bus;
+
return 0;
err_register:
xemaclite_update_address(lp, ndev->dev_addr);
lp->phy_node = of_parse_phandle(ofdev->dev.of_node, "phy-handle", 0);
- rc = xemaclite_mdio_setup(lp, &ofdev->dev);
- if (rc)
- dev_warn(&ofdev->dev, "error registering MDIO bus\n");
+ xemaclite_mdio_setup(lp, &ofdev->dev);
dev_info(dev, "MAC address is now %pM\n", ndev->dev_addr);
struct net_local *lp = netdev_priv(ndev);
/* Un-register the mii_bus, if configured */
- if (lp->has_mdio) {
+ if (lp->mii_bus) {
mdiobus_unregister(lp->mii_bus);
mdiobus_free(lp->mii_bus);
lp->mii_bus = NULL;
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
static const char banner[] __initconst = KERN_INFO \
"AX.25: bpqether driver version 004\n";
-static char bcast_addr[6]={0xFF,0xFF,0xFF,0xFF,0xFF,0xFF};
-
-static char bpq_eth_addr[6];
-
static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
static int bpq_device_event(struct notifier_block *, unsigned long, void *);
bpq->ethdev = edev;
bpq->axdev = ndev;
- memcpy(bpq->dest_addr, bcast_addr, sizeof(bpq_eth_addr));
- memcpy(bpq->acpt_addr, bcast_addr, sizeof(bpq_eth_addr));
+ eth_broadcast_addr(bpq->dest_addr);
+ eth_broadcast_addr(bpq->acpt_addr);
err = register_netdevice(ndev);
if (err)
tristate "Microsoft Hyper-V virtual network driver"
depends on HYPERV
select UCS2_STRING
- select FAILOVER
help
Select this option to enable the Hyper-V virtual network driver.
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
struct hv_device *device_ctx;
/* netvsc_device */
struct netvsc_device __rcu *nvdev;
+ /* list of netvsc net_devices */
+ struct list_head list;
/* reconfigure work */
struct delayed_work dwork;
/* last reconfig time */
u32 vf_alloc;
/* Serial number of the VF to team with */
u32 vf_serial;
-
- struct failover *failover;
};
/* Per channel data */
struct ndis_ipsecv2_offload {
u32 encap;
- u16 ip6;
- u16 ip4opt;
- u16 ip6ext;
- u16 ah;
- u16 esp;
- u16 ah_esp;
- u16 xport;
- u16 tun;
- u16 xport_tun;
- u16 lso;
- u16 extseq;
+ u8 ip6;
+ u8 ip4opt;
+ u8 ip6ext;
+ u8 ah;
+ u8 esp;
+ u8 ah_esp;
+ u8 xport;
+ u8 tun;
+ u8 xport_tun;
+ u8 lso;
+ u8 extseq;
u32 udp_esp;
u32 auth;
u32 crypto;
};
struct ndis_rsc_offload {
- u16 ip4;
- u16 ip6;
+ u8 ip4;
+ u8 ip6;
};
struct ndis_encap_offload {
VM_PKT_DATA_INBAND, 0);
}
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+ struct netvsc_device *nvdev =
+ container_of(w, struct netvsc_device, subchan_work);
+ struct rndis_device *rdev;
+ int i, ret;
+
+ /* Avoid deadlock with device removal already under RTNL */
+ if (!rtnl_trylock()) {
+ schedule_work(w);
+ return;
+ }
+
+ rdev = nvdev->extension;
+ if (rdev) {
+ ret = rndis_set_subchannel(rdev->ndev, nvdev);
+ if (ret == 0) {
+ netif_device_attach(rdev->ndev);
+ } else {
+ /* fallback to only primary channel */
+ for (i = 1; i < nvdev->num_chn; i++)
+ netif_napi_del(&nvdev->chan_table[i].napi);
+
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ rtnl_unlock();
+}
+
static struct netvsc_device *alloc_net_device(void)
{
struct netvsc_device *net_device;
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
- INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+ INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
return net_device;
}
struct hv_device *device = netvsc_channel_to_device(channel);
struct net_device *ndev = hv_get_drvdata(device);
int work_done = 0;
+ int ret;
/* If starting a new interval */
if (!nvchan->desc)
nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
}
- /* If send of pending receive completions suceeded
- * and did not exhaust NAPI budget this time
- * and not doing busy poll
+ /* Send any pending receive completions */
+ ret = send_recv_completions(ndev, net_device, nvchan);
+
+ /* If it did not exhaust NAPI budget this time
+ * and not doing busy poll
* then re-enable host interrupts
- * and reschedule if ring is not empty.
+ * and reschedule if ring is not empty
+ * or sending receive completion failed.
*/
- if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
- work_done < budget &&
+ if (work_done < budget &&
napi_complete_done(napi, work_done) &&
- hv_end_read(&channel->inbound) &&
+ (ret || hv_end_read(&channel->inbound)) &&
napi_schedule_prep(napi)) {
hv_begin_read(&channel->inbound);
__napi_schedule(napi);
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
-#include <net/failover.h>
#include "hyperv_net.h"
module_param(debug, int, 0444);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+static LIST_HEAD(netvsc_dev_list);
+
static void netvsc_change_rx_flags(struct net_device *net, int change)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
if (IS_ERR(nvdev))
return PTR_ERR(nvdev);
- /* Note: enable and attach happen when sub-channels setup */
+ if (nvdev->num_chn > 1) {
+ ret = rndis_set_subchannel(ndev, nvdev);
+
+ /* if unavailable, just proceed with one queue */
+ if (ret) {
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ /* In any case device is now ready */
+ netif_device_attach(ndev);
+ /* Note: enable and attach happen when sub-channels setup */
netif_carrier_off(ndev);
if (netif_running(ndev)) {
rtnl_unlock();
}
+static struct net_device *get_netvsc_bymac(const u8 *mac)
+{
+ struct net_device_context *ndev_ctx;
+
+ list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
+ struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx);
+
+ if (ether_addr_equal(mac, dev->perm_addr))
+ return dev;
+ }
+
+ return NULL;
+}
+
+static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
+{
+ struct net_device_context *net_device_ctx;
+ struct net_device *dev;
+
+ dev = netdev_master_upper_dev_get(vf_netdev);
+ if (!dev || dev->netdev_ops != &device_ops)
+ return NULL; /* not a netvsc device */
+
+ net_device_ctx = netdev_priv(dev);
+ if (!rtnl_dereference(net_device_ctx->nvdev))
+ return NULL; /* device is removed */
+
+ return dev;
+}
+
/* Called when VF is injecting data into network stack.
* Change the associated network device from VF to netvsc.
* note: already called with rcu_read_lock
return RX_HANDLER_ANOTHER;
}
+static int netvsc_vf_join(struct net_device *vf_netdev,
+ struct net_device *ndev)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ int ret;
+
+ ret = netdev_rx_handler_register(vf_netdev,
+ netvsc_vf_handle_frame, ndev);
+ if (ret != 0) {
+ netdev_err(vf_netdev,
+ "can not register netvsc VF receive handler (err = %d)\n",
+ ret);
+ goto rx_handler_failed;
+ }
+
+ ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+ NULL, NULL, NULL);
+ if (ret != 0) {
+ netdev_err(vf_netdev,
+ "can not set master device %s (err = %d)\n",
+ ndev->name, ret);
+ goto upper_link_failed;
+ }
+
+ /* set slave flag before open to prevent IPv6 addrconf */
+ vf_netdev->flags |= IFF_SLAVE;
+
+ schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+
+ call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
+
+ netdev_info(vf_netdev, "joined to %s\n", ndev->name);
+ return 0;
+
+upper_link_failed:
+ netdev_rx_handler_unregister(vf_netdev);
+rx_handler_failed:
+ return ret;
+}
+
static void __netvsc_vf_setup(struct net_device *ndev,
struct net_device *vf_netdev)
{
rtnl_unlock();
}
-static int netvsc_pre_register_vf(struct net_device *vf_netdev,
- struct net_device *ndev)
+static int netvsc_register_vf(struct net_device *vf_netdev)
{
+ struct net_device *ndev;
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
+ int ret;
+
+ if (vf_netdev->addr_len != ETH_ALEN)
+ return NOTIFY_DONE;
+
+ /*
+ * We will use the MAC address to locate the synthetic interface to
+ * associate with the VF interface. If we don't find a matching
+ * synthetic interface, move on.
+ */
+ ndev = get_netvsc_bymac(vf_netdev->perm_addr);
+ if (!ndev)
+ return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
- return -ENODEV;
+ return NOTIFY_DONE;
- return 0;
-}
-
-static int netvsc_register_vf(struct net_device *vf_netdev,
- struct net_device *ndev)
-{
- struct net_device_context *ndev_ctx = netdev_priv(ndev);
-
- /* set slave flag before open to prevent IPv6 addrconf */
- vf_netdev->flags |= IFF_SLAVE;
+ /* if syntihetic interface is a different namespace,
+ * then move the VF to that namespace; join will be
+ * done again in that context.
+ */
+ if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
+ ret = dev_change_net_namespace(vf_netdev,
+ dev_net(ndev), "eth%d");
+ if (ret)
+ netdev_err(vf_netdev,
+ "could not move to same namespace as %s: %d\n",
+ ndev->name, ret);
+ else
+ netdev_info(vf_netdev,
+ "VF moved to namespace with: %s\n",
+ ndev->name);
+ return NOTIFY_DONE;
+ }
- schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+ netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
- call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
-
- netdev_info(vf_netdev, "joined to %s\n", ndev->name);
+ if (netvsc_vf_join(vf_netdev, ndev) != 0)
+ return NOTIFY_DONE;
dev_hold(vf_netdev);
- rcu_assign_pointer(ndev_ctx->vf_netdev, vf_netdev);
-
- return 0;
+ rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
+ return NOTIFY_OK;
}
/* VF up/down change detected, schedule to change data path */
-static int netvsc_vf_changed(struct net_device *vf_netdev,
- struct net_device *ndev)
+static int netvsc_vf_changed(struct net_device *vf_netdev)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
+ struct net_device *ndev;
bool vf_is_up = netif_running(vf_netdev);
+ ndev = get_netvsc_byref(vf_netdev);
+ if (!ndev)
+ return NOTIFY_DONE;
+
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev)
- return -ENODEV;
+ return NOTIFY_DONE;
netvsc_switch_datapath(ndev, vf_is_up);
netdev_info(ndev, "Data path switched %s VF: %s\n",
vf_is_up ? "to" : "from", vf_netdev->name);
- return 0;
+ return NOTIFY_OK;
}
-static int netvsc_pre_unregister_vf(struct net_device *vf_netdev,
- struct net_device *ndev)
+static int netvsc_unregister_vf(struct net_device *vf_netdev)
{
+ struct net_device *ndev;
struct net_device_context *net_device_ctx;
- net_device_ctx = netdev_priv(ndev);
- cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
-
- return 0;
-}
-
-static int netvsc_unregister_vf(struct net_device *vf_netdev,
- struct net_device *ndev)
-{
- struct net_device_context *net_device_ctx;
+ ndev = get_netvsc_byref(vf_netdev);
+ if (!ndev)
+ return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
+ cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
+ netdev_rx_handler_unregister(vf_netdev);
+ netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
dev_put(vf_netdev);
- return 0;
+ return NOTIFY_OK;
}
-static struct failover_ops netvsc_failover_ops = {
- .slave_pre_register = netvsc_pre_register_vf,
- .slave_register = netvsc_register_vf,
- .slave_pre_unregister = netvsc_pre_unregister_vf,
- .slave_unregister = netvsc_unregister_vf,
- .slave_link_change = netvsc_vf_changed,
- .slave_handle_frame = netvsc_vf_handle_frame,
-};
-
static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
+ if (nvdev->num_chn > 1)
+ schedule_work(&nvdev->subchan_work);
+
/* hw_features computed in rndis_netdev_set_hwcaps() */
net->features = net->hw_features |
NETIF_F_HIGHDMA | NETIF_F_SG |
else
net->max_mtu = ETH_DATA_LEN;
- ret = register_netdev(net);
+ rtnl_lock();
+ ret = register_netdevice(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
goto register_failed;
}
- net_device_ctx->failover = failover_register(net, &netvsc_failover_ops);
- if (IS_ERR(net_device_ctx->failover)) {
- ret = PTR_ERR(net_device_ctx->failover);
- goto err_failover;
- }
-
- return ret;
+ list_add(&net_device_ctx->list, &netvsc_dev_list);
+ rtnl_unlock();
+ return 0;
-err_failover:
- unregister_netdev(net);
register_failed:
+ rtnl_unlock();
rndis_filter_device_remove(dev, nvdev);
rndis_failed:
free_percpu(net_device_ctx->vf_stats);
rtnl_lock();
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev)
- failover_slave_unregister(vf_netdev);
+ netvsc_unregister_vf(vf_netdev);
if (nvdev)
rndis_filter_device_remove(dev, nvdev);
unregister_netdevice(net);
-
- failover_unregister(ndev_ctx->failover);
+ list_del(&ndev_ctx->list);
rtnl_unlock();
rcu_read_unlock();
.remove = netvsc_remove,
};
+/*
+ * On Hyper-V, every VF interface is matched with a corresponding
+ * synthetic interface. The synthetic interface is presented first
+ * to the guest. When the corresponding VF instance is registered,
+ * we will take care of switching the data path.
+ */
+static int netvsc_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+
+ /* Skip our own events */
+ if (event_dev->netdev_ops == &device_ops)
+ return NOTIFY_DONE;
+
+ /* Avoid non-Ethernet type devices */
+ if (event_dev->type != ARPHRD_ETHER)
+ return NOTIFY_DONE;
+
+ /* Avoid Vlan dev with same MAC registering as VF */
+ if (is_vlan_dev(event_dev))
+ return NOTIFY_DONE;
+
+ /* Avoid Bonding master dev with same MAC registering as VF */
+ if ((event_dev->priv_flags & IFF_BONDING) &&
+ (event_dev->flags & IFF_MASTER))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ return netvsc_register_vf(event_dev);
+ case NETDEV_UNREGISTER:
+ return netvsc_unregister_vf(event_dev);
+ case NETDEV_UP:
+ case NETDEV_DOWN:
+ return netvsc_vf_changed(event_dev);
+ default:
+ return NOTIFY_DONE;
+ }
+}
+
+static struct notifier_block netvsc_netdev_notifier = {
+ .notifier_call = netvsc_netdev_event,
+};
+
static void __exit netvsc_drv_exit(void)
{
+ unregister_netdevice_notifier(&netvsc_netdev_notifier);
vmbus_driver_unregister(&netvsc_drv);
}
if (ret)
return ret;
+ register_netdevice_notifier(&netvsc_netdev_notifier);
return 0;
}
* This breaks overlap of processing the host message for the
* new primary channel with the initialization of sub-channels.
*/
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
{
- struct netvsc_device *nvdev
- = container_of(w, struct netvsc_device, subchan_work);
struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
- struct net_device_context *ndev_ctx;
- struct rndis_device *rdev;
- struct net_device *ndev;
- struct hv_device *hv_dev;
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct hv_device *hv_dev = ndev_ctx->device_ctx;
+ struct rndis_device *rdev = nvdev->extension;
int i, ret;
- if (!rtnl_trylock()) {
- schedule_work(w);
- return;
- }
-
- rdev = nvdev->extension;
- if (!rdev)
- goto unlock; /* device was removed */
-
- ndev = rdev->ndev;
- ndev_ctx = netdev_priv(ndev);
- hv_dev = ndev_ctx->device_ctx;
+ ASSERT_RTNL();
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret) {
netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
- goto failed;
+ return ret;
}
wait_for_completion(&nvdev->channel_init_wait);
if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "sub channel request failed\n");
- goto failed;
+ return -EIO;
}
nvdev->num_chn = 1 +
for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
ndev_ctx->tx_table[i] = i % nvdev->num_chn;
- netif_device_attach(ndev);
- rtnl_unlock();
- return;
-
-failed:
- /* fallback to only primary channel */
- for (i = 1; i < nvdev->num_chn; i++)
- netif_napi_del(&nvdev->chan_table[i].napi);
-
- nvdev->max_chn = 1;
- nvdev->num_chn = 1;
-
- netif_device_attach(ndev);
-unlock:
- rtnl_unlock();
+ return 0;
}
static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
netif_napi_add(net, &net_device->chan_table[i].napi,
netvsc_poll, NAPI_POLL_WEIGHT);
- if (net_device->num_chn > 1)
- schedule_work(&net_device->subchan_work);
+ return net_device;
out:
- /* if unavailable, just proceed with one queue */
- if (ret) {
- net_device->max_chn = 1;
- net_device->num_chn = 1;
- }
-
- /* No sub channels, device is ready */
- if (net_device->num_chn == 1)
- netif_device_attach(net);
-
- return net_device;
+ /* setting up multiple channels failed */
+ net_device->max_chn = 1;
+ net_device->num_chn = 1;
+ return 0;
err_dev_remv:
rndis_filter_device_remove(dev, net_device);
struct spi_message stat_msg;
struct spi_transfer stat_xfer;
struct dentry *debugfs_root;
+ struct delayed_work work;
+ struct workqueue_struct *wqueue;
unsigned long flags;
int tx_stat;
bool promiscuous;
/* Wait until the ACK is sent */
adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__);
adf7242_clear_irqstat(lp);
+ mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
return adf7242_cmd(lp, CMD_RC_RX);
}
+static void adf7242_rx_cal_work(struct work_struct *work)
+{
+ struct adf7242_local *lp =
+ container_of(work, struct adf7242_local, work.work);
+
+ /* Reissuing RC_RX every 400ms - to adjust for offset
+ * drift in receiver (datasheet page 61, OCL section)
+ */
+
+ if (!test_bit(FLAG_XMIT, &lp->flags)) {
+ adf7242_cmd(lp, CMD_RC_PHY_RDY);
+ adf7242_cmd_rx(lp);
+ }
+}
+
static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm)
{
struct adf7242_local *lp = hw->priv;
enable_irq(lp->spi->irq);
set_bit(FLAG_START, &lp->flags);
- return adf7242_cmd(lp, CMD_RC_RX);
+ return adf7242_cmd_rx(lp);
}
static void adf7242_stop(struct ieee802154_hw *hw)
struct adf7242_local *lp = hw->priv;
disable_irq(lp->spi->irq);
+ cancel_delayed_work_sync(&lp->work);
adf7242_cmd(lp, CMD_RC_IDLE);
clear_bit(FLAG_START, &lp->flags);
adf7242_clear_irqstat(lp);
adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8);
adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16);
- return adf7242_cmd(lp, CMD_RC_RX);
+ if (test_bit(FLAG_START, &lp->flags))
+ return adf7242_cmd_rx(lp);
+ else
+ return adf7242_cmd(lp, CMD_RC_PHY_RDY);
}
static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw,
/* ensure existing instances of the IRQ handler have completed */
disable_irq(lp->spi->irq);
set_bit(FLAG_XMIT, &lp->flags);
+ cancel_delayed_work_sync(&lp->work);
reinit_completion(&lp->tx_complete);
adf7242_cmd(lp, CMD_RC_PHY_RDY);
adf7242_clear_irqstat(lp);
unsigned int xmit;
u8 irq1;
+ mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1);
if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA)))
spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg);
spi_set_drvdata(spi, lp);
+ INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work);
+ lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev),
+ WQ_MEM_RECLAIM);
ret = adf7242_hw_init(lp);
if (ret)
if (!IS_ERR_OR_NULL(lp->debugfs_root))
debugfs_remove_recursive(lp->debugfs_root);
+ cancel_delayed_work_sync(&lp->work);
+ destroy_workqueue(lp->wqueue);
+
ieee802154_unregister_hw(lp->hw);
mutex_destroy(&lp->bmux);
ieee802154_free_hw(lp->hw);
static int
at86rf230_ed(struct ieee802154_hw *hw, u8 *level)
{
- BUG_ON(!level);
+ WARN_ON(!level);
*level = 0xbe;
return 0;
}
if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
u16 addr = le16_to_cpu(filt->short_addr);
- dev_vdbg(&lp->spi->dev,
- "at86rf230_set_hw_addr_filt called for saddr\n");
+ dev_vdbg(&lp->spi->dev, "%s called for saddr\n", __func__);
__at86rf230_write(lp, RG_SHORT_ADDR_0, addr);
__at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8);
}
if (changed & IEEE802154_AFILT_PANID_CHANGED) {
u16 pan = le16_to_cpu(filt->pan_id);
- dev_vdbg(&lp->spi->dev,
- "at86rf230_set_hw_addr_filt called for pan id\n");
+ dev_vdbg(&lp->spi->dev, "%s called for pan id\n", __func__);
__at86rf230_write(lp, RG_PAN_ID_0, pan);
__at86rf230_write(lp, RG_PAN_ID_1, pan >> 8);
}
u8 i, addr[8];
memcpy(addr, &filt->ieee_addr, 8);
- dev_vdbg(&lp->spi->dev,
- "at86rf230_set_hw_addr_filt called for IEEE addr\n");
+ dev_vdbg(&lp->spi->dev, "%s called for IEEE addr\n", __func__);
for (i = 0; i < 8; i++)
__at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]);
}
if (changed & IEEE802154_AFILT_PANC_CHANGED) {
- dev_vdbg(&lp->spi->dev,
- "at86rf230_set_hw_addr_filt called for panc change\n");
+ dev_vdbg(&lp->spi->dev, "%s called for panc change\n", __func__);
if (filt->pan_coord)
at86rf230_write_subreg(lp, SR_AACK_I_AM_COORD, 1);
else
return at86rf230_write_subreg(lp, SR_CCA_MODE, val);
}
-
static int
at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
{
static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
{
- BUG_ON(!level);
+ WARN_ON(!level);
*level = 0xbe;
return 0;
*/
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/spi/spi.h>
#include <linux/workqueue.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <linux/skbuff.h>
#include <linux/of_gpio.h>
#include <linux/regmap.h>
{
struct ipvl_dev *ipvlan;
struct net_device *mdev = port->dev;
- int err = 0;
+ unsigned int flags;
+ int err;
ASSERT_RTNL();
if (port->mode != nval) {
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+ err = dev_change_flags(ipvlan->dev,
+ flags | IFF_NOARP);
+ } else {
+ err = dev_change_flags(ipvlan->dev,
+ flags & ~IFF_NOARP);
+ }
+ if (unlikely(err))
+ goto fail;
+ }
if (nval == IPVLAN_MODE_L3S) {
/* New mode is L3S */
err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = &ipvl_l3mdev_ops;
mdev->priv_flags |= IFF_L3MDEV_MASTER;
} else
- return err;
+ goto fail;
} else if (port->mode == IPVLAN_MODE_L3S) {
/* Old mode was L3S */
mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = NULL;
}
- list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
- if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
- ipvlan->dev->flags |= IFF_NOARP;
- else
- ipvlan->dev->flags &= ~IFF_NOARP;
- }
port->mode = nval;
}
+ return 0;
+
+fail:
+ /* Undo the flags changes that have been done so far. */
+ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (port->mode == IPVLAN_MODE_L3 ||
+ port->mode == IPVLAN_MODE_L3S)
+ dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+ else
+ dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+ }
+
return err;
}
ipvlan->phy_dev = phy_dev;
ipvlan->dev = dev;
ipvlan->sfeatures = IPVLAN_FEATURES;
- ipvlan_adjust_mtu(ipvlan, phy_dev);
+ if (!tb[IFLA_MTU])
+ ipvlan_adjust_mtu(ipvlan, phy_dev);
INIT_LIST_HEAD(&ipvlan->addrs);
spin_lock_init(&ipvlan->addrs_lock);
{
ether_setup(dev);
+ dev->max_mtu = ETH_MAX_MTU;
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
dev->netdev_ops = &ipvlan_netdev_ops;
netif_addr_lock_bh(failover_dev);
dev_uc_sync_multiple(slave_dev, failover_dev);
- dev_uc_sync_multiple(slave_dev, failover_dev);
+ dev_mc_sync_multiple(slave_dev, failover_dev);
netif_addr_unlock_bh(failover_dev);
err = vlan_vids_add_by_dev(slave_dev, failover_dev);
struct net *net = nsim_to_net(ns);
bool *reg_devlink = net_generic(net, nsim_devlink_id);
+ devlink_resources_unregister(ns->devlink, NULL);
devlink_unregister(ns->devlink);
devlink_free(ns->devlink);
ns->devlink = NULL;
if (err < 0)
return err;
- err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
}
return err;
#define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS BIT(12)
#define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE BIT(14)
-#define MII_88E1121_PHY_LED_CTRL 16
+#define MII_PHY_LED_CTRL 16
#define MII_88E1121_PHY_LED_DEF 0x0030
+#define MII_88E1510_PHY_LED_DEF 0x1177
#define MII_M1011_PHY_STATUS 0x11
#define MII_M1011_PHY_STATUS_1000 0x8000
return err;
}
+static void marvell_config_led(struct phy_device *phydev)
+{
+ u16 def_config;
+ int err;
+
+ switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) {
+ /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
+ case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R):
+ case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1318S):
+ def_config = MII_88E1121_PHY_LED_DEF;
+ break;
+ /* Default PHY LED config:
+ * LED[0] .. 1000Mbps Link
+ * LED[1] .. 100Mbps Link
+ * LED[2] .. Blink, Activity
+ */
+ case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510):
+ def_config = MII_88E1510_PHY_LED_DEF;
+ break;
+ default:
+ return;
+ }
+
+ err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL,
+ def_config);
+ if (err < 0)
+ pr_warn("Fail to config marvell phy LED.\n");
+}
+
static int marvell_config_init(struct phy_device *phydev)
{
+ /* Set defalut LED */
+ marvell_config_led(phydev);
+
/* Set registers from marvell,reg-init DT property */
return marvell_of_reg_init(phydev);
}
return genphy_soft_reset(phydev);
}
-static int m88e1121_config_init(struct phy_device *phydev)
-{
- int err;
-
- /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
- err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE,
- MII_88E1121_PHY_LED_CTRL,
- MII_88E1121_PHY_LED_DEF);
- if (err < 0)
- return err;
-
- /* Set marvell,reg-init configuration from device tree */
- return marvell_config_init(phydev);
-}
-
static int m88e1318_config_init(struct phy_device *phydev)
{
if (phy_interrupt_is_valid(phydev)) {
return err;
}
- return m88e1121_config_init(phydev);
+ return marvell_config_init(phydev);
}
static int m88e1510_config_init(struct phy_device *phydev)
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.probe = &m88e1121_probe,
- .config_init = &m88e1121_config_init,
+ .config_init = &marvell_config_init,
.config_aneg = &m88e1121_config_aneg,
.read_status = &marvell_read_status,
.ack_interrupt = &marvell_ack_interrupt,
#include <linux/platform_device.h>
#include <linux/mdio-bitbang.h>
#include <linux/mdio-gpio.h>
-#include <linux/gpio.h>
#include <linux/gpio/consumer.h>
-
-#include <linux/of_gpio.h>
#include <linux/of_mdio.h>
struct mdio_gpio_info {
static int mdio_mux_iproc_remove(struct platform_device *pdev)
{
- struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+ struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
mdio_mux_uninit(md->mux_handle);
mdiobus_unregister(md->mii_bus);
* negotiation may already be done and aneg interrupt may not be
* generated.
*/
- if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+ if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
err = phy_aneg_done(phydev);
if (err > 0) {
trigger = true;
static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
{
- /* The default values for phydev->supported are provided by the PHY
- * driver "features" member, we want to reset to sane defaults first
- * before supporting higher speeds.
- */
- phydev->supported &= PHY_DEFAULT_FEATURES;
+ phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
+ PHY_10BT_FEATURES);
switch (max_speed) {
default:
}
if (bus->started)
bus->socket_ops->start(bus->sfp);
- bus->netdev->sfp_bus = bus;
bus->registered = true;
return 0;
}
if (bus->phydev && ops && ops->disconnect_phy)
ops->disconnect_phy(bus->upstream);
}
- bus->netdev->sfp_bus = NULL;
bus->registered = false;
}
}
EXPORT_SYMBOL_GPL(sfp_upstream_stop);
+static void sfp_upstream_clear(struct sfp_bus *bus)
+{
+ bus->upstream_ops = NULL;
+ bus->upstream = NULL;
+ bus->netdev->sfp_bus = NULL;
+ bus->netdev = NULL;
+}
+
/**
* sfp_register_upstream() - Register the neighbouring device
* @fwnode: firmware node for the SFP bus
bus->upstream_ops = ops;
bus->upstream = upstream;
bus->netdev = ndev;
+ ndev->sfp_bus = bus;
- if (bus->sfp)
+ if (bus->sfp) {
ret = sfp_register_bus(bus);
+ if (ret)
+ sfp_upstream_clear(bus);
+ }
rtnl_unlock();
}
rtnl_lock();
if (bus->sfp)
sfp_unregister_bus(bus);
- bus->upstream = NULL;
- bus->netdev = NULL;
+ sfp_upstream_clear(bus);
rtnl_unlock();
sfp_bus_put(bus);
}
EXPORT_SYMBOL_GPL(sfp_module_remove);
+static void sfp_socket_clear(struct sfp_bus *bus)
+{
+ bus->sfp_dev = NULL;
+ bus->sfp = NULL;
+ bus->socket_ops = NULL;
+}
+
struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
const struct sfp_socket_ops *ops)
{
bus->sfp = sfp;
bus->socket_ops = ops;
- if (bus->netdev)
+ if (bus->netdev) {
ret = sfp_register_bus(bus);
+ if (ret)
+ sfp_socket_clear(bus);
+ }
rtnl_unlock();
}
rtnl_lock();
if (bus->netdev)
sfp_unregister_bus(bus);
- bus->sfp_dev = NULL;
- bus->sfp = NULL;
- bus->socket_ops = NULL;
+ sfp_socket_clear(bus);
rtnl_unlock();
sfp_bus_put(bus);
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppoe_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
case XDP_TX:
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
- if (tun_xdp_tx(tun->dev, &xdp))
+ if (tun_xdp_tx(tun->dev, &xdp) < 0)
goto err_redirect;
rcu_read_unlock();
local_bh_enable();
priv->presvd_phy_advertise);
/* Restore BMCR */
+ if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
+ priv->presvd_phy_bmcr |= BMCR_ANRESTART;
+
asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
priv->presvd_phy_bmcr);
- mii_nway_restart(&dev->mii);
priv->presvd_phy_advertise = 0;
priv->presvd_phy_bmcr = 0;
}
atomic_set(&ctx->stop, 1);
- if (hrtimer_active(&ctx->tx_timer))
- hrtimer_cancel(&ctx->tx_timer);
+ hrtimer_cancel(&ctx->tx_timer);
tasklet_kill(&ctx->bh);
#define DEFAULT_RX_CSUM_ENABLE (true)
#define DEFAULT_TSO_CSUM_ENABLE (true)
#define DEFAULT_VLAN_FILTER_ENABLE (true)
+#define DEFAULT_VLAN_RX_OFFLOAD (true)
#define TX_OVERHEAD (8)
#define RXW_PADDING 2
mod_timer(&dev->stat_monitor,
jiffies + STAT_UPDATE_TIMER);
}
+
+ tasklet_schedule(&dev->bh);
}
return ret;
if ((ll_mtu % dev->maxpacket) == 0)
return -EDOM;
- ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
netdev->mtu = new_mtu;
}
if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_;
+ else
+ pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_;
+
+ if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_;
else
pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_;
buf |= FCT_TX_CTL_EN_;
ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
- ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev,
+ dev->net->mtu + VLAN_ETH_HLEN);
ret = lan78xx_read_reg(dev, MAC_RX, &buf);
buf |= MAC_RX_RXEN_;
if (DEFAULT_TSO_CSUM_ENABLE)
dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG;
+ if (DEFAULT_VLAN_RX_OFFLOAD)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+ if (DEFAULT_VLAN_FILTER_ENABLE)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
dev->net->hw_features = dev->net->features;
ret = lan78xx_setup_irq_domain(dev);
struct sk_buff *skb,
u32 rx_cmd_a, u32 rx_cmd_b)
{
+ /* HW Checksum offload appears to be flawed if used when not stripping
+ * VLAN headers. Drop back to S/W checksums under these conditions.
+ */
if (!(dev->net->features & NETIF_F_RXCSUM) ||
- unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) {
+ unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+ ((rx_cmd_a & RX_CMD_A_FVTG_) &&
+ !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
skb->ip_summed = CHECKSUM_NONE;
} else {
skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_));
}
}
+static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev,
+ struct sk_buff *skb,
+ u32 rx_cmd_a, u32 rx_cmd_b)
+{
+ if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (rx_cmd_a & RX_CMD_A_FVTG_))
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ (rx_cmd_b & 0xffff));
+}
+
static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
{
int status;
if (skb->len == size) {
lan78xx_rx_csum_offload(dev, skb,
rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb,
+ rx_cmd_a, rx_cmd_b);
skb_trim(skb, skb->len - 4); /* remove fcs */
skb->truesize = size + sizeof(struct sk_buff);
skb_set_tail_pointer(skb2, size);
lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
skb_trim(skb2, skb2->len - 4); /* remove fcs */
skb2->truesize = size + sizeof(struct sk_buff);
pkt_cnt = 0;
count = 0;
length = 0;
+ spin_lock_irqsave(&tqp->lock, flags);
for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) {
if (skb_is_gso(skb)) {
if (pkt_cnt) {
}
count = 1;
length = skb->len - TX_OVERHEAD;
- skb2 = skb_dequeue(tqp);
+ __skb_unlink(skb, tqp);
+ spin_unlock_irqrestore(&tqp->lock, flags);
goto gso_skb;
}
skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32));
pkt_cnt++;
}
+ spin_unlock_irqrestore(&tqp->lock, flags);
/* copy to a single skb */
skb = alloc_skb(skb_totallen, GFP_ATOMIC);
{QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
{QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */
{QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */
+ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */
{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */
+ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */
{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */
#ifdef CONFIG_PM_SLEEP
unregister_pm_notifier(&tp->pm_notifier);
#endif
- napi_disable(&tp->napi);
+ if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+ napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
(netdev->flags & IFF_ALLMULTI)) {
rx_creg &= 0xfffe;
rx_creg |= 0x0002;
- dev_info(&netdev->dev, "%s: allmulti set\n", netdev->name);
+ dev_dbg(&netdev->dev, "%s: allmulti set\n", netdev->name);
} else {
/* ~RX_MULTICAST, ~RX_PROMISCUOUS */
rx_creg &= 0x00fc;
module_param(turbo_mode, bool, 0644);
MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
+static int smsc75xx_link_ok_nopm(struct usbnet *dev);
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev);
+
static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index,
u32 *data, int in_pm)
{
return -EIO;
}
+ /* phy workaround for gig link */
+ smsc75xx_phy_gig_workaround(dev);
+
smsc75xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE,
ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP |
ADVERTISE_PAUSE_ASYM);
return -EIO;
}
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev)
+{
+ struct mii_if_info *mii = &dev->mii;
+ int ret = 0, timeout = 0;
+ u32 buf, link_up = 0;
+
+ /* Set the phy in Gig loopback */
+ smsc75xx_mdio_write(dev->net, mii->phy_id, MII_BMCR, 0x4040);
+
+ /* Wait for the link up */
+ do {
+ link_up = smsc75xx_link_ok_nopm(dev);
+ usleep_range(10000, 20000);
+ timeout++;
+ } while ((!link_up) && (timeout < 1000));
+
+ if (timeout >= 1000) {
+ netdev_warn(dev->net, "Timeout waiting for PHY link up\n");
+ return -EIO;
+ }
+
+ /* phy reset */
+ ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+ if (ret < 0) {
+ netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", ret);
+ return ret;
+ }
+
+ buf |= PMT_CTL_PHY_RST;
+
+ ret = smsc75xx_write_reg(dev, PMT_CTL, buf);
+ if (ret < 0) {
+ netdev_warn(dev->net, "Failed to write PMT_CTL: %d\n", ret);
+ return ret;
+ }
+
+ timeout = 0;
+ do {
+ usleep_range(10000, 20000);
+ ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+ if (ret < 0) {
+ netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n",
+ ret);
+ return ret;
+ }
+ timeout++;
+ } while ((buf & PMT_CTL_PHY_RST) && (timeout < 100));
+
+ if (timeout >= 100) {
+ netdev_warn(dev->net, "timeout waiting for PHY Reset\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
static int smsc75xx_reset(struct usbnet *dev)
{
struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
/* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
#define VIRTIO_XDP_HEADROOM 256
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX BIT(0)
+#define VIRTIO_XDP_REDIR BIT(1)
+
/* RX packet size EWMA. The average packet size is used to determine the packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
* at once, the weight is chosen so that the EWMA will be insensitive to short-
struct receive_queue *rq,
void *buf, void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit,
+ unsigned int *rbytes)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
int err;
len -= vi->hdr_len;
+ *rbytes += len;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
err = xdp_do_redirect(dev, &xdp, xdp_prog);
if (err)
goto err_xdp;
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
rcu_read_unlock();
goto xdp_xmit;
default:
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf,
- unsigned int len)
+ unsigned int len,
+ unsigned int *rbytes)
{
struct page *page = buf;
struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+ *rbytes += len - vi->hdr_len;
if (unlikely(!skb))
goto err;
void *buf,
void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit,
+ unsigned int *rbytes)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
int err;
head_skb = NULL;
+ *rbytes += len - vi->hdr_len;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
goto err_buf;
}
+ *rbytes += len;
page = virt_to_head_page(buf);
truesize = mergeable_ctx_to_truesize(ctx);
dev->stats.rx_length_errors++;
break;
}
+ *rbytes += len;
page = virt_to_head_page(buf);
put_page(page);
}
return NULL;
}
-static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
+ void *buf, unsigned int len, void **ctx,
+ unsigned int *xdp_xmit, unsigned int *rbytes)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
struct virtio_net_hdr_mrg_rxbuf *hdr;
- int ret;
if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
pr_debug("%s: short packet %i\n", dev->name, len);
} else {
put_page(virt_to_head_page(buf));
}
- return 0;
+ return;
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
+ skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
+ rbytes);
else if (vi->big_packets)
- skb = receive_big(dev, vi, rq, buf, len);
+ skb = receive_big(dev, vi, rq, buf, len, rbytes);
else
- skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
+ skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
if (unlikely(!skb))
- return 0;
+ return;
hdr = skb_vnet_hdr(skb);
- ret = skb->len;
-
if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
skb->ip_summed = CHECKSUM_UNNECESSARY;
ntohs(skb->protocol), skb->len, skb->pkt_type);
napi_gro_receive(&rq->napi, skb);
- return ret;
+ return;
frame_err:
dev->stats.rx_frame_errors++;
dev_kfree_skb(skb);
- return 0;
}
/* Unlike mergeable buffers, all buffers are allocated to the
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+ unsigned int *xdp_xmit)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int len, received = 0, bytes = 0;
while (received < budget &&
(buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
- bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
+ receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
received++;
}
} else {
while (received < budget &&
(buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
+ receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
received++;
}
}
struct virtnet_info *vi = rq->vq->vdev->priv;
struct send_queue *sq;
unsigned int received, qp;
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
virtnet_poll_cleantx(rq);
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit) {
+ if (xdp_xmit & VIRTIO_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & VIRTIO_XDP_TX) {
qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
smp_processor_id();
sq = &vi->sq[qp];
virtqueue_kick(sq->vq);
- xdp_do_flush_map();
}
return received;
flush = 0;
out:
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
}
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+ const u8 *mac, __u16 state,
+ __be32 src_vni, __u8 ndm_flags)
+{
+ struct vxlan_fdb *f;
+
+ f = kmalloc(sizeof(*f), GFP_ATOMIC);
+ if (!f)
+ return NULL;
+ f->state = state;
+ f->flags = ndm_flags;
+ f->updated = f->used = jiffies;
+ f->vni = src_vni;
+ INIT_LIST_HEAD(&f->remotes);
+ memcpy(f->eth_addr, mac, ETH_ALEN);
+
+ return f;
+}
+
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+ const u8 *mac, union vxlan_addr *ip,
+ __u16 state, __be16 port, __be32 src_vni,
+ __be32 vni, __u32 ifindex, __u8 ndm_flags,
+ struct vxlan_fdb **fdb)
+{
+ struct vxlan_rdst *rd = NULL;
+ struct vxlan_fdb *f;
+ int rc;
+
+ if (vxlan->cfg.addrmax &&
+ vxlan->addrcnt >= vxlan->cfg.addrmax)
+ return -ENOSPC;
+
+ netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+ f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+ if (!f)
+ return -ENOMEM;
+
+ rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+ if (rc < 0) {
+ kfree(f);
+ return rc;
+ }
+
+ ++vxlan->addrcnt;
+ hlist_add_head_rcu(&f->hlist,
+ vxlan_fdb_head(vxlan, mac, src_vni));
+
+ *fdb = f;
+
+ return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
__be16 port, __be32 src_vni, __be32 vni,
if (!(flags & NLM_F_CREATE))
return -ENOENT;
- if (vxlan->cfg.addrmax &&
- vxlan->addrcnt >= vxlan->cfg.addrmax)
- return -ENOSPC;
-
/* Disallow replace to add a multicast entry */
if ((flags & NLM_F_REPLACE) &&
(is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
return -EOPNOTSUPP;
netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
- f = kmalloc(sizeof(*f), GFP_ATOMIC);
- if (!f)
- return -ENOMEM;
-
- notify = 1;
- f->state = state;
- f->flags = ndm_flags;
- f->updated = f->used = jiffies;
- f->vni = src_vni;
- INIT_LIST_HEAD(&f->remotes);
- memcpy(f->eth_addr, mac, ETH_ALEN);
-
- rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
- if (rc < 0) {
- kfree(f);
+ rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+ vni, ifindex, ndm_flags, &f);
+ if (rc < 0)
return rc;
- }
-
- ++vxlan->addrcnt;
- hlist_add_head_rcu(&f->hlist,
- vxlan_fdb_head(vxlan, mac, src_vni));
+ notify = 1;
}
if (notify) {
kfree(f);
}
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+ bool do_notify)
{
netdev_dbg(vxlan->dev,
"delete %pM\n", f->eth_addr);
--vxlan->addrcnt;
- vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+ if (do_notify)
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
call_rcu(&f->rcu, vxlan_fdb_free);
return -EAFNOSUPPORT;
spin_lock_bh(&vxlan->hash_lock);
- err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+ err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
port, src_vni, vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock);
goto out;
}
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
out:
return 0;
/* close off race between vxlan_flush and incoming packets */
if (netif_running(dev))
- vxlan_fdb_create(vxlan, src_mac, src_ip,
+ vxlan_fdb_update(vxlan, src_mac, src_ip,
NUD_REACHABLE,
NLM_F_EXCL|NLM_F_CREATE,
vxlan->cfg.dst_port,
"garbage collect %pM\n",
f->eth_addr);
f->state = NUD_STALE;
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
} else if (time_before(timeout, next_timer))
next_timer = timeout;
}
spin_lock_bh(&vxlan->hash_lock);
f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
if (f)
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
spin_unlock_bh(&vxlan->hash_lock);
}
continue;
/* the all_zeros_mac entry is deleted at vxlan_uninit */
if (!is_zero_ether_addr(f->eth_addr))
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
}
}
spin_unlock_bh(&vxlan->hash_lock);
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_fdb *f = NULL;
int err;
err = vxlan_dev_configure(net, dev, conf, false, extack);
err = vxlan_fdb_create(vxlan, all_zeros_mac,
&vxlan->default_dst.remote_ip,
NUD_REACHABLE | NUD_PERMANENT,
- NLM_F_EXCL | NLM_F_CREATE,
vxlan->cfg.dst_port,
vxlan->default_dst.remote_vni,
vxlan->default_dst.remote_vni,
vxlan->default_dst.remote_ifindex,
- NTF_SELF);
+ NTF_SELF, &f);
if (err)
return err;
}
err = register_netdevice(dev);
+ if (err)
+ goto errout;
+
+ err = rtnl_configure_link(dev, NULL);
if (err) {
- vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
- return err;
+ unregister_netdevice(dev);
+ goto errout;
}
+ /* notify default fdb entry */
+ if (f)
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
list_add(&vxlan->next, &vn->vxlan_list);
return 0;
+errout:
+ if (f)
+ vxlan_fdb_destroy(vxlan, f, false);
+ return err;
}
static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
struct vxlan_rdst *dst = &vxlan->default_dst;
struct vxlan_rdst old_dst;
struct vxlan_config conf;
+ struct vxlan_fdb *f = NULL;
int err;
err = vxlan_nl2conf(tb, data,
err = vxlan_fdb_create(vxlan, all_zeros_mac,
&dst->remote_ip,
NUD_REACHABLE | NUD_PERMANENT,
- NLM_F_CREATE | NLM_F_APPEND,
vxlan->cfg.dst_port,
dst->remote_vni,
dst->remote_vni,
dst->remote_ifindex,
- NTF_SELF);
+ NTF_SELF, &f);
if (err) {
spin_unlock_bh(&vxlan->hash_lock);
return err;
}
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
}
spin_unlock_bh(&vxlan->hash_lock);
}
case 0x001:
printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name);
break;
- case 0x010:
+ case 0x002:
printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name);
break;
default:
ath10k_mac_max_vht_nss(vht_mcs_mask)));
if (changed & IEEE80211_RC_BW_CHANGED) {
- ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d\n",
- sta->addr, bw);
+ enum wmi_phy_mode mode;
+
+ mode = chan_to_phymode(&def);
+ ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n",
+ sta->addr, bw, mode);
+
+ err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
+ WMI_PEER_PHYMODE, mode);
+ if (err) {
+ ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n",
+ sta->addr, mode, err);
+ goto exit;
+ }
err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
WMI_PEER_CHAN_WIDTH, bw);
sta->addr);
}
+exit:
mutex_unlock(&ar->conf_mutex);
}
WMI_PEER_NSS = 0x5,
WMI_PEER_USE_4ADDR = 0x6,
WMI_PEER_DEBUG = 0xa,
+ WMI_PEER_PHYMODE = 0xd,
WMI_PEER_DUMMY_VAR = 0xff, /* dummy parameter for STA PS workaround */
};
-/*
+/*
* Copyright (c) 2018, The Linux Foundation. All rights reserved.
*
* Permission to use, copy, modify, and/or distribute this software for any
bool "PCIE bus interface support for FullMAC driver"
depends on BRCMFMAC
depends on PCI
- depends on HAS_DMA
select BRCMFMAC_PROTO_MSGBUF
select FW_LOADER
---help---
fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY;
fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM;
fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL;
- fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus);
+ /* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */
+ fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1;
fwreq->bus_nr = devinfo->pdev->bus->number;
return fwreq;
brcmf_dbg(TRACE, "Enter\n");
if (bus) {
+ /* Stop watchdog task */
+ if (bus->watchdog_tsk) {
+ send_sig(SIGTERM, bus->watchdog_tsk, 1);
+ kthread_stop(bus->watchdog_tsk);
+ bus->watchdog_tsk = NULL;
+ }
+
/* De-register interrupt handler */
brcmf_sdiod_intr_unregister(bus->sdiodev);
.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
};
+const struct iwl_cfg iwl9260_killer_2ac_cfg = {
+ .name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)",
+ .fw_name_pre = IWL9260A_FW_PRE,
+ .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE,
+ IWL_DEVICE_9000,
+ .ht_params = &iwl9000_ht_params,
+ .nvm_ver = IWL9000_NVM_VERSION,
+ .nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+};
+
const struct iwl_cfg iwl9270_2ac_cfg = {
.name = "Intel(R) Dual Band Wireless AC 9270",
.fw_name_pre = IWL9260A_FW_PRE,
.soc_latency = 5000,
};
+const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = {
+ .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)",
+ .fw_name_pre = IWL9000A_FW_PRE,
+ .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+ .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+ IWL_DEVICE_9000,
+ .ht_params = &iwl9000_ht_params,
+ .nvm_ver = IWL9000_NVM_VERSION,
+ .nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+ .integrated = true,
+ .soc_latency = 5000,
+};
+
+const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = {
+ .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)",
+ .fw_name_pre = IWL9000A_FW_PRE,
+ .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+ .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+ IWL_DEVICE_9000,
+ .ht_params = &iwl9000_ht_params,
+ .nvm_ver = IWL9000_NVM_VERSION,
+ .nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+ .integrated = true,
+ .soc_latency = 5000,
+};
+
const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = {
.name = "Intel(R) Dual Band Wireless AC 9460",
.fw_name_pre = IWL9000A_FW_PRE,
.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
};
+const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = {
+ .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)",
+ .fw_name_pre = IWL9000A_FW_PRE,
+ .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+ .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+ IWL_DEVICE_9000,
+ .ht_params = &iwl9000_ht_params,
+ .nvm_ver = IWL9000_NVM_VERSION,
+ .nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+ .integrated = true,
+ .soc_latency = 5000,
+ .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
+};
+
+const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = {
+ .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)",
+ .fw_name_pre = IWL9000A_FW_PRE,
+ .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE,
+ .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE,
+ IWL_DEVICE_9000,
+ .ht_params = &iwl9000_ht_params,
+ .nvm_ver = IWL9000_NVM_VERSION,
+ .nvm_calib_ver = IWL9000_TX_POWER_VERSION,
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+ .integrated = true,
+ .soc_latency = 5000,
+ .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
+};
+
MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
extern const struct iwl_cfg iwl4165_2ac_cfg;
extern const struct iwl_cfg iwl9160_2ac_cfg;
extern const struct iwl_cfg iwl9260_2ac_cfg;
+extern const struct iwl_cfg iwl9260_killer_2ac_cfg;
extern const struct iwl_cfg iwl9270_2ac_cfg;
extern const struct iwl_cfg iwl9460_2ac_cfg;
extern const struct iwl_cfg iwl9560_2ac_cfg;
extern const struct iwl_cfg iwl9461_2ac_cfg_soc;
extern const struct iwl_cfg iwl9462_2ac_cfg_soc;
extern const struct iwl_cfg iwl9560_2ac_cfg_soc;
+extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc;
+extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc;
extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk;
extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk;
extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk;
extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk;
+extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk;
+extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk;
extern const struct iwl_cfg iwl22000_2ac_cfg_hr;
extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
{IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x1420, iwl9460_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x2526, 0x1550, iwl9260_killer_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)},
{IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)},
{IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)},
{IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x31DC, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x31DC, 0x1030, iwl9560_2ac_cfg_shared_clk)},
{IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)},
+ {IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)},
{IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)},
{IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)},
{IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)},
{IWL_PCI_DEVICE(0x34F0, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x34F0, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x34F0, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x34F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x34F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x9DF0, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0x9DF0, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x9DF0, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA370, 0x1010, iwl9260_2ac_cfg)},
{IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)},
hwsim_wq = alloc_workqueue("hwsim_wq", 0, 0);
if (!hwsim_wq)
return -ENOMEM;
- rhashtable_init(&hwsim_radios_rht, &hwsim_rht_params);
+
+ err = rhashtable_init(&hwsim_radios_rht, &hwsim_rht_params);
+ if (err)
+ goto out_free_wq;
err = register_pernet_device(&hwsim_net_ops);
if (err)
- return err;
+ goto out_free_rht;
err = platform_driver_register(&mac80211_hwsim_driver);
if (err)
platform_driver_unregister(&mac80211_hwsim_driver);
out_unregister_pernet:
unregister_pernet_device(&hwsim_net_ops);
+out_free_rht:
+ rhashtable_destroy(&hwsim_radios_rht);
+out_free_wq:
+ destroy_workqueue(hwsim_wq);
return err;
}
module_init(init_mac80211_hwsim);
MWIFIEX_FUNC_SHUTDOWN);
}
- if (adapter->workqueue)
- flush_workqueue(adapter->workqueue);
-
- mwifiex_usb_free(card);
-
mwifiex_dbg(adapter, FATAL,
"%s: removing card\n", __func__);
mwifiex_remove_card(adapter);
{
struct usb_card_rec *card = (struct usb_card_rec *)adapter->card;
+ mwifiex_usb_free(card);
+
mwifiex_usb_cleanup_tx_aggr(adapter);
card->adapter = NULL;
*/
spin_lock_bh(&dev->con_mon_lock);
avg_rssi = ewma_rssi_read(&dev->avg_rssi);
- WARN_ON_ONCE(avg_rssi == 0);
+ spin_unlock_bh(&dev->con_mon_lock);
+ if (avg_rssi == 0)
+ return;
+
avg_rssi = -avg_rssi;
if (avg_rssi <= -70)
val -= 0x20;
else if (avg_rssi <= -60)
val -= 0x10;
- spin_unlock_bh(&dev->con_mon_lock);
if (val != mt7601u_bbp_rr(dev, 66))
mt7601u_bbp_wr(dev, 66, val);
config QTNFMAC_PEARL_PCIE
tristate "Quantenna QSR10g PCIe support"
default n
- depends on HAS_DMA && PCI && CFG80211
+ depends on PCI && CFG80211
select QTNFMAC
select FW_LOADER
select CRC32
vif = qtnf_mac_get_base_vif(mac);
if (!vif) {
pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
- ret = -EFAULT;
- goto out;
+ return -EFAULT;
}
if (vif->wdev.iftype != NL80211_IFTYPE_STATION) {
}
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw)
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq)
{
struct rtl_priv *rtlpriv = rtl_priv(hw);
del_timer_sync(&rtlpriv->works.watchdog_timer);
- cancel_delayed_work(&rtlpriv->works.watchdog_wq);
- cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
- cancel_delayed_work(&rtlpriv->works.ps_work);
- cancel_delayed_work(&rtlpriv->works.ps_rfon_wq);
- cancel_delayed_work(&rtlpriv->works.fwevt_wq);
- cancel_delayed_work(&rtlpriv->works.c2hcmd_wq);
+ cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq);
+ if (ips_wq)
+ cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+ else
+ cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
+ cancel_delayed_work_sync(&rtlpriv->works.ps_work);
+ cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq);
+ cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq);
+ cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq);
}
EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work);
void rtl_deinit_rfkill(struct ieee80211_hw *hw);
void rtl_watch_dog_timer_callback(struct timer_list *t);
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw);
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq);
bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx);
int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht,
firmware->size);
rtlpriv->rtlhal.wowlan_fwsize = firmware->size;
}
- rtlpriv->rtlhal.fwsize = firmware->size;
release_firmware(firmware);
}
/* reset sec info */
rtl_cam_reset_sec_info(hw);
- rtl_deinit_deferred_work(hw);
+ rtl_deinit_deferred_work(hw, false);
}
rtlpriv->intf_ops->adapter_stop(hw);
ieee80211_unregister_hw(hw);
rtlmac->mac80211_registered = 0;
} else {
- rtl_deinit_deferred_work(hw);
+ rtl_deinit_deferred_work(hw, false);
rtlpriv->intf_ops->adapter_stop(hw);
}
rtlpriv->cfg->ops->disable_interrupt(hw);
struct rtl_priv *rtlpriv = rtl_priv(hw);
/*<1> Stop all timer */
- rtl_deinit_deferred_work(hw);
+ rtl_deinit_deferred_work(hw, true);
/*<2> Disable Interrupt */
rtlpriv->cfg->ops->disable_interrupt(hw);
struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
enum rf_pwrstate rtstate;
- cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+ cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
mutex_lock(&rtlpriv->locks.ips_mutex);
if (ppsc->inactiveps) {
ieee80211_unregister_hw(hw);
rtlmac->mac80211_registered = 0;
} else {
- rtl_deinit_deferred_work(hw);
+ rtl_deinit_deferred_work(hw, false);
rtlpriv->intf_ops->adapter_stop(hw);
}
/*deinit rfkill */
/* IRQ name is queue name with "-tx" or "-rx" appended */
#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+static DECLARE_WAIT_QUEUE_HEAD(module_load_q);
static DECLARE_WAIT_QUEUE_HEAD(module_unload_q);
struct netfront_stats {
static int netfront_tx_slot_available(struct netfront_queue *queue)
{
return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) <
- (NET_TX_RING_SIZE - MAX_SKB_FRAGS - 2);
+ (NET_TX_RING_SIZE - XEN_NETIF_NR_SLOTS_MIN - 1);
}
static void xennet_maybe_wake_tx(struct netfront_queue *queue)
RING_IDX cons = queue->rx.rsp_cons;
struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
grant_ref_t ref = xennet_get_rx_ref(queue, cons);
- int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
+ int max = XEN_NETIF_NR_SLOTS_MIN + (rx->status <= RX_COPY_THRESHOLD);
int slots = 1;
int err = 0;
unsigned long ret;
struct sk_buff *skb,
struct sk_buff_head *list)
{
- struct skb_shared_info *shinfo = skb_shinfo(skb);
RING_IDX cons = queue->rx.rsp_cons;
struct sk_buff *nskb;
RING_GET_RESPONSE(&queue->rx, ++cons);
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
- if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+ if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
BUG_ON(pull_to <= skb_headlen(skb));
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
}
- BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+ BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);
- skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+ skb_frag_page(nfrag),
rx->offset, rx->status, PAGE_SIZE);
skb_shinfo(nskb)->nr_frags = 0;
netif_carrier_off(netdev);
xenbus_switch_state(dev, XenbusStateInitialising);
+ wait_event(module_load_q,
+ xenbus_read_driver_state(dev->otherend) !=
+ XenbusStateClosed &&
+ xenbus_read_driver_state(dev->otherend) !=
+ XenbusStateUnknown);
return netdev;
exit:
err = xen_net_read_mac(dev, info->netdev->dev_addr);
if (err) {
xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
- goto out;
+ goto out_unlocked;
}
rtnl_lock();
xennet_destroy_queues(info);
out:
rtnl_unlock();
+out_unlocked:
device_unregister(&dev->dev);
return err;
}
/* talk_to_netback() sets the correct number of queues */
num_queues = dev->real_num_tx_queues;
- rtnl_lock();
- netdev_update_features(dev);
- rtnl_unlock();
-
if (dev->reg_state == NETREG_UNINITIALIZED) {
err = register_netdev(dev);
if (err) {
}
}
+ rtnl_lock();
+ netdev_update_features(dev);
+ rtnl_unlock();
+
/*
* All public and private state should now be sane. Get
* ready to start sending and receiving packets and give the driver
struct sk_buff *skb = NULL;
if (!urb->status) {
- skb = alloc_skb(urb->actual_length, GFP_KERNEL);
+ skb = alloc_skb(urb->actual_length, GFP_ATOMIC);
if (!skb) {
nfc_err(&phy->udev->dev, "failed to alloc memory\n");
} else {
if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
/* request for response for sent packet directly */
- rc = pn533_submit_urb_for_response(phy, GFP_ATOMIC);
+ rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
if (rc)
goto error;
} else if (dev->protocol_type == PN533_PROTO_REQ_ACK_RESP) {
// Copyright (C) 2017 Finn Thain
#include <linux/device.h>
+#include <linux/dma-mapping.h>
#include <linux/list.h>
#include <linux/nubus.h>
#include <linux/seq_file.h>
board->dev.release = nubus_device_release;
board->dev.bus = &nubus_bus_type;
dev_set_name(&board->dev, "slot.%X", board->slot);
+ board->dev.dma_mask = &board->dev.coherent_dma_mask;
+ dma_set_mask(&board->dev, DMA_BIT_MASK(32));
return device_register(&board->dev);
}
return -EIO;
if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
return -EIO;
+ return 0;
}
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
blk_queue_logical_block_size(q, pmem_sector_size(ndns));
blk_queue_max_hw_sectors(q, UINT_MAX);
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ if (pmem->pfn_flags & PFN_MAP)
+ blk_queue_flag_set(QUEUE_FLAG_DAX, q);
q->queuedata = pmem;
disk = alloc_disk_node(0, nid);
static void nvme_ns_remove(struct nvme_ns *ns);
static int nvme_revalidate_disk(struct gendisk *disk);
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+ unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+ /*
+ * Revalidating a dead namespace sets capacity to 0. This will end
+ * buffered writers dirtying pages that can't be synced.
+ */
+ if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+ return;
+ revalidate_disk(ns->disk);
+ blk_set_queue_dying(ns->queue);
+ /* Forcibly unquiesce queues to avoid blocking dispatch */
+ blk_mq_unquiesce_queue(ns->queue);
+}
static void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
static void nvme_enable_aen(struct nvme_ctrl *ctrl)
{
- u32 result;
+ u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
int status;
- status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
- ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+ if (!supported_aens)
+ return;
+
+ status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+ NULL, 0, &result);
if (status)
dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
- ctrl->oaes & NVME_AEN_SUPPORTED);
+ supported_aens);
}
static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
static void nvme_update_formats(struct nvme_ctrl *ctrl)
{
- struct nvme_ns *ns, *next;
- LIST_HEAD(rm_list);
+ struct nvme_ns *ns;
- down_write(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
- if (ns->disk && nvme_revalidate_disk(ns->disk)) {
- list_move_tail(&ns->list, &rm_list);
- }
- }
- up_write(&ctrl->namespaces_rwsem);
+ down_read(&ctrl->namespaces_rwsem);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ if (ns->disk && nvme_revalidate_disk(ns->disk))
+ nvme_set_queue_dying(ns);
+ up_read(&ctrl->namespaces_rwsem);
- list_for_each_entry_safe(ns, next, &rm_list, list)
- nvme_ns_remove(ns);
+ nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
}
static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
- (void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+ (void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
0, &cmd.result, timeout);
nvme_passthru_end(ctrl, effects);
u32 max_segments =
(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
+ max_segments = min_not_zero(max_segments, ctrl->max_segments);
blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
}
* Verify that the subsystem actually supports multiple
* controllers, else bail out.
*/
- if (!ctrl->opts->discovery_nqn &&
+ if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
dev_err(ctrl->device,
"ignoring ctrl due to duplicate subnqn (%s).\n",
down_write(&ctrl->namespaces_rwsem);
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
- if (ns->head->ns_id > nsid)
+ if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
list_move_tail(&ns->list, &rm_list);
}
up_write(&ctrl->namespaces_rwsem);
nvme_remove_invalid_namespaces(ctrl, nn);
}
-static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
{
size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
__le32 *log;
- int error, i;
- bool ret = false;
+ int error;
log = kzalloc(log_size, GFP_KERNEL);
if (!log)
- return false;
+ return;
+ /*
+ * We need to read the log to clear the AEN, but we don't want to rely
+ * on it for the changed namespace information as userspace could have
+ * raced with us in reading the log page, which could cause us to miss
+ * updates.
+ */
error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
- if (error) {
+ if (error)
dev_warn(ctrl->device,
"reading changed ns log failed: %d\n", error);
- goto out_free_log;
- }
-
- if (log[0] == cpu_to_le32(0xffffffff))
- goto out_free_log;
-
- for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
- u32 nsid = le32_to_cpu(log[i]);
-
- if (nsid == 0)
- break;
- dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
- nvme_validate_ns(ctrl, nsid);
- }
- ret = true;
-out_free_log:
kfree(log);
- return ret;
}
static void nvme_scan_work(struct work_struct *work)
WARN_ON_ONCE(!ctrl->tagset);
if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
- if (nvme_scan_changed_ns_log(ctrl))
- goto out_sort_namespaces;
dev_info(ctrl->device, "rescanning namespaces.\n");
+ nvme_clear_changed_ns_log(ctrl);
}
if (nvme_identify_ctrl(ctrl, &id))
nvme_scan_ns_sequential(ctrl, nn);
out_free_id:
kfree(id);
-out_sort_namespaces:
down_write(&ctrl->namespaces_rwsem);
list_sort(NULL, &ctrl->namespaces, ns_cmp);
up_write(&ctrl->namespaces_rwsem);
if (ctrl->admin_q)
blk_mq_unquiesce_queue(ctrl->admin_q);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
- /*
- * Revalidating a dead namespace sets capacity to 0. This will
- * end buffered writers dirtying pages that can't be synced.
- */
- if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
- continue;
- revalidate_disk(ns->disk);
- blk_set_queue_dying(ns->queue);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ nvme_set_queue_dying(ns);
- /* Forcibly unquiesce queues to avoid blocking dispatch */
- blk_mq_unquiesce_queue(ns->queue);
- }
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set)
-{
- if (!ctrl->ops->reinit_request)
- return 0;
-
- return blk_mq_tagset_iter(set, set->driver_data,
- ctrl->ops->reinit_request);
-}
-EXPORT_SYMBOL_GPL(nvme_reinit_tagset);
-
int __init nvme_core_init(void)
{
int result = -ENOMEM;
return NULL;
}
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
- bool queue_live, bool is_connected)
+/*
+ * For something we're not in a state to send to the device the default action
+ * is to busy it and retry it after the controller state is recovered. However,
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
+ *
+ * Note: commands used to initialize the controller will be marked for failfast.
+ * Note: nvme cli/ioctl commands are marked for failfast.
+ */
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+ struct request *rq)
+{
+ if (ctrl->state != NVME_CTRL_DELETING &&
+ ctrl->state != NVME_CTRL_DEAD &&
+ !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+ return BLK_STS_RESOURCE;
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+ return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);
+
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+ bool queue_live)
{
- struct nvme_command *cmd = nvme_req(rq)->cmd;
+ struct nvme_request *req = nvme_req(rq);
- if (likely(ctrl->state == NVME_CTRL_LIVE && is_connected))
- return BLK_STS_OK;
+ /*
+ * If we are in some state of setup or teardown only allow
+ * internally generated commands.
+ */
+ if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
+ return false;
+ /*
+ * Only allow commands on a live queue, except for the connect command,
+ * which is require to set the queue live in the appropinquate states.
+ */
switch (ctrl->state) {
case NVME_CTRL_NEW:
case NVME_CTRL_CONNECTING:
- case NVME_CTRL_DELETING:
- /*
- * This is the case of starting a new or deleting an association
- * but connectivity was lost before it was fully created or torn
- * down. We need to error the commands used to initialize the
- * controller so the reconnect can go into a retry attempt. The
- * commands should all be marked REQ_FAILFAST_DRIVER, which will
- * hit the reject path below. Anything else will be queued while
- * the state settles.
- */
- if (!is_connected)
- break;
-
- /*
- * If queue is live, allow only commands that are internally
- * generated pass through. These are commands on the admin
- * queue to initialize the controller. This will reject any
- * ioctl admin cmds received while initializing.
- */
- if (queue_live && !(nvme_req(rq)->flags & NVME_REQ_USERCMD))
- return BLK_STS_OK;
-
- /*
- * If the queue is not live, allow only a connect command. This
- * will reject any ioctl admin cmd as well as initialization
- * commands if the controller reverted the queue to non-live.
- */
- if (!queue_live && blk_rq_is_passthrough(rq) &&
- cmd->common.opcode == nvme_fabrics_command &&
- cmd->fabrics.fctype == nvme_fabrics_type_connect)
- return BLK_STS_OK;
+ if (req->cmd->common.opcode == nvme_fabrics_command &&
+ req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
+ return true;
break;
default:
break;
+ case NVME_CTRL_DEAD:
+ return false;
}
- /*
- * Any other new io is something we're not in a state to send to the
- * device. Default action is to busy it and retry it after the
- * controller state is recovered. However, anything marked for failfast
- * or nvme multipath is immediately failed. Note: commands used to
- * initialize the controller will be marked for failfast.
- * Note: nvme cli/ioctl commands are marked for failfast.
- */
- if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
- return BLK_STS_RESOURCE;
- nvme_req(rq)->status = NVME_SC_ABORT_REQ;
- return BLK_STS_IOERR;
+ return queue_live;
}
-EXPORT_SYMBOL_GPL(nvmf_check_if_ready);
+EXPORT_SYMBOL_GPL(__nvmf_check_ready);
static const match_table_t opt_tokens = {
{ NVMF_OPT_TRANSPORT, "transport=%s" },
void nvmf_free_options(struct nvmf_ctrl_options *opts);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl,
- struct request *rq, bool queue_live, bool is_connected);
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+ struct request *rq);
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+ bool queue_live);
+
+static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+ bool queue_live)
+{
+ if (likely(ctrl->state == NVME_CTRL_LIVE ||
+ ctrl->state == NVME_CTRL_ADMIN_ONLY))
+ return true;
+ return __nvmf_check_ready(ctrl, rq, queue_live);
+}
#endif /* _NVME_FABRICS_H */
struct nvme_fc_rport *rport;
u32 cnum;
+ bool ioq_live;
bool assoc_active;
u64 association_id;
static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
-static int
-nvme_fc_reinit_request(void *data, struct request *rq)
-{
- struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
- struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
-
- memset(cmdiu, 0, sizeof(*cmdiu));
- cmdiu->scsi_id = NVME_CMD_SCSI_ID;
- cmdiu->fc_id = NVME_CMD_FC_ID;
- cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32));
- memset(&op->rsp_iu, 0, sizeof(op->rsp_iu));
-
- return 0;
-}
-
static void
__nvme_fc_exit_request(struct nvme_fc_ctrl *ctrl,
struct nvme_fc_fcp_op *op)
*/
queue->connection_id = 0;
+ atomic_set(&queue->csn, 1);
}
static void
struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
struct nvme_command *sqe = &cmdiu->sqe;
enum nvmefc_fcp_datadir io_dir;
+ bool queue_ready = test_bit(NVME_FC_Q_LIVE, &queue->flags);
u32 data_len;
blk_status_t ret;
- ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
- test_bit(NVME_FC_Q_LIVE, &queue->flags),
- ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE);
- if (unlikely(ret))
- return ret;
+ if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
+ !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+ return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
ret = nvme_setup_cmd(ns, rq, sqe);
if (ret)
if (ret)
goto out_delete_hw_queues;
+ ctrl->ioq_live = true;
+
return 0;
out_delete_hw_queues:
}
static int
-nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
+nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl)
{
struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
unsigned int nr_io_queues;
if (ctrl->ctrl.queue_count == 1)
return 0;
- nvme_fc_init_io_queues(ctrl);
-
- ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
- if (ret)
- goto out_free_io_queues;
-
ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
if (ret)
goto out_free_io_queues;
* Create the admin queue
*/
- nvme_fc_init_queue(ctrl, 0);
-
ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
NVME_AQ_DEPTH);
if (ret)
if (ret)
goto out_delete_hw_queue;
- if (ctrl->ctrl.state != NVME_CTRL_NEW)
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
ret = nvmf_connect_admin_queue(&ctrl->ctrl);
if (ret)
*/
if (ctrl->ctrl.queue_count > 1) {
- if (ctrl->ctrl.state == NVME_CTRL_NEW)
+ if (!ctrl->ioq_live)
ret = nvme_fc_create_io_queues(ctrl);
else
- ret = nvme_fc_reinit_io_queues(ctrl);
+ ret = nvme_fc_recreate_io_queues(ctrl);
if (ret)
goto out_term_aen_ops;
}
* use blk_mq_tagset_busy_itr() and the transport routine to
* terminate the exchanges.
*/
- if (ctrl->ctrl.state != NVME_CTRL_NEW)
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
/* re-enable the admin_q so anything new can fast fail */
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ /* resume the io queues so that things will fast fail */
+ nvme_start_queues(&ctrl->ctrl);
+
nvme_fc_ctlr_inactive_on_rport(ctrl);
}
* waiting for io to terminate
*/
nvme_fc_delete_association(ctrl);
-
- /* resume the io queues so that things will fast fail */
- nvme_start_queues(nctrl);
}
static void
.submit_async_event = nvme_fc_submit_async_event,
.delete_ctrl = nvme_fc_delete_ctrl,
.get_address = nvmf_get_address,
- .reinit_request = nvme_fc_reinit_request,
};
static void
nvme_fc_reconnect_or_delete(ctrl, ret);
else
dev_info(ctrl->ctrl.device,
- "NVME-FC{%d}: controller reconnect complete\n",
+ "NVME-FC{%d}: controller connect complete\n",
ctrl->cnum);
}
{
struct nvme_fc_ctrl *ctrl;
unsigned long flags;
- int ret, idx, retry;
+ int ret, idx;
if (!(rport->remoteport.port_role &
(FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
}
ctrl->ctrl.opts = opts;
+ ctrl->ctrl.nr_reconnects = 0;
INIT_LIST_HEAD(&ctrl->ctrl_list);
ctrl->lport = lport;
ctrl->rport = rport;
ctrl->dev = lport->dev;
ctrl->cnum = idx;
+ ctrl->ioq_live = false;
ctrl->assoc_active = false;
init_waitqueue_head(&ctrl->ioabort_wait);
ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
+ ctrl->ctrl.cntlid = 0xffff;
ret = -ENOMEM;
ctrl->queues = kcalloc(ctrl->ctrl.queue_count,
if (!ctrl->queues)
goto out_free_ida;
+ nvme_fc_init_queue(ctrl, 0);
+
memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
spin_unlock_irqrestore(&rport->lock, flags);
- /*
- * It's possible that transactions used to create the association
- * may fail. Examples: CreateAssociation LS or CreateIOConnection
- * LS gets dropped/corrupted/fails; or a frame gets dropped or a
- * command times out for one of the actions to init the controller
- * (Connect, Get/Set_Property, Set_Features, etc). Many of these
- * transport errors (frame drop, LS failure) inherently must kill
- * the association. The transport is coded so that any command used
- * to create the association (prior to a LIVE state transition
- * while NEW or CONNECTING) will fail if it completes in error or
- * times out.
- *
- * As such: as the connect request was mostly likely due to a
- * udev event that discovered the remote port, meaning there is
- * not an admin or script there to restart if the connect
- * request fails, retry the initial connection creation up to
- * three times before giving up and declaring failure.
- */
- for (retry = 0; retry < 3; retry++) {
- ret = nvme_fc_create_association(ctrl);
- if (!ret)
- break;
- }
-
- if (ret) {
- nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
- cancel_work_sync(&ctrl->ctrl.reset_work);
- cancel_delayed_work_sync(&ctrl->connect_work);
-
- /* couldn't schedule retry - fail out */
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) ||
+ !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
dev_err(ctrl->ctrl.device,
- "NVME-FC{%d}: Connect retry failed\n", ctrl->cnum);
-
- ctrl->ctrl.opts = NULL;
+ "NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum);
+ goto fail_ctrl;
+ }
- /* initiate nvme ctrl ref counting teardown */
- nvme_uninit_ctrl(&ctrl->ctrl);
+ nvme_get_ctrl(&ctrl->ctrl);
- /* Remove core ctrl ref. */
+ if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
nvme_put_ctrl(&ctrl->ctrl);
-
- /* as we're past the point where we transition to the ref
- * counting teardown path, if we return a bad pointer here,
- * the calling routine, thinking it's prior to the
- * transition, will do an rport put. Since the teardown
- * path also does a rport put, we do an extra get here to
- * so proper order/teardown happens.
- */
- nvme_fc_rport_get(rport);
-
- if (ret > 0)
- ret = -EIO;
- return ERR_PTR(ret);
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: failed to schedule initial connect\n",
+ ctrl->cnum);
+ goto fail_ctrl;
}
- nvme_get_ctrl(&ctrl->ctrl);
+ flush_delayed_work(&ctrl->connect_work);
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
return &ctrl->ctrl;
+fail_ctrl:
+ nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+ cancel_work_sync(&ctrl->ctrl.reset_work);
+ cancel_delayed_work_sync(&ctrl->connect_work);
+
+ ctrl->ctrl.opts = NULL;
+
+ /* initiate nvme ctrl ref counting teardown */
+ nvme_uninit_ctrl(&ctrl->ctrl);
+
+ /* Remove core ctrl ref. */
+ nvme_put_ctrl(&ctrl->ctrl);
+
+ /* as we're past the point where we transition to the ref
+ * counting teardown path, if we return a bad pointer here,
+ * the calling routine, thinking it's prior to the
+ * transition, will do an rport put. Since the teardown
+ * path also does a rport put, we do an extra get here to
+ * so proper order/teardown happens.
+ */
+ nvme_fc_rport_get(rport);
+
+ return ERR_PTR(-EIO);
+
out_cleanup_admin_q:
blk_cleanup_queue(ctrl->ctrl.admin_q);
out_free_admin_tag_set:
*/
#include <linux/moduleparam.h>
+#include <trace/events/block.h>
#include "nvme.h"
static bool multipath = true;
if (likely(ns)) {
bio->bi_disk = ns->disk;
bio->bi_opf |= REQ_NVME_MPATH;
+ trace_block_bio_remap(bio->bi_disk->queue, bio,
+ disk_devt(ns->head->disk),
+ bio->bi_iter.bi_sector);
ret = direct_make_request(bio);
} else if (!list_empty_careful(&head->list)) {
dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");
u64 cap;
u32 page_size;
u32 max_hw_sectors;
+ u32 max_segments;
u16 oncs;
u16 oacs;
u16 nssa;
void (*submit_async_event)(struct nvme_ctrl *ctrl);
void (*delete_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
- int (*reinit_request)(void *data, struct request *rq);
void (*stop_ctrl)(struct nvme_ctrl *ctrl);
};
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
void nvme_start_freeze(struct nvme_ctrl *ctrl);
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+/*
+ * These can be higher, but we need to ensure that any command doesn't
+ * require an sg allocation that needs more than a page of data.
+ */
+#define NVME_MAX_KB_SZ 4096
+#define NVME_MAX_SEGS 127
+
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0);
struct nvme_ctrl ctrl;
struct completion ioq_wait;
+ mempool_t *iod_mempool;
+
/* shadow doorbell buffer support: */
u32 *dbbuf_dbs;
dma_addr_t dbbuf_dbs_dma_addr;
iod->use_sgl = nvme_pci_use_sgls(dev, rq);
if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
- size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg,
- iod->use_sgl);
-
- iod->sg = kmalloc(alloc_size, GFP_ATOMIC);
+ iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
if (!iod->sg)
return BLK_STS_RESOURCE;
} else {
}
if (iod->sg != iod->inline_sg)
- kfree(iod->sg);
+ mempool_free(iod->sg, dev->iod_mempool);
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
free_opal_dev(dev->ctrl.opal_dev);
+ mempool_destroy(dev->iod_mempool);
kfree(dev);
}
nvme_get_ctrl(&dev->ctrl);
nvme_dev_disable(dev, false);
+ nvme_kill_queues(&dev->ctrl);
if (!queue_work(nvme_wq, &dev->remove_work))
nvme_put_ctrl(&dev->ctrl);
}
if (result)
goto out;
+ /*
+ * Limit the max command size to prevent iod->sg allocations going
+ * over a single page.
+ */
+ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+ dev->ctrl.max_segments = NVME_MAX_SEGS;
+
result = nvme_init_identify(&dev->ctrl);
if (result)
goto out;
struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
struct pci_dev *pdev = to_pci_dev(dev->dev);
- nvme_kill_queues(&dev->ctrl);
if (pci_get_drvdata(pdev))
device_release_driver(&pdev->dev);
nvme_put_ctrl(&dev->ctrl);
int node, result = -ENOMEM;
struct nvme_dev *dev;
unsigned long quirks = id->driver_data;
+ size_t alloc_size;
node = dev_to_node(&pdev->dev);
if (node == NUMA_NO_NODE)
quirks |= check_vendor_combination_bug(pdev);
+ /*
+ * Double check that our mempool alloc size will cover the biggest
+ * command we support.
+ */
+ alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
+ NVME_MAX_SEGS, true);
+ WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+
+ dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
+ mempool_kfree,
+ (void *) alloc_size,
+ GFP_KERNEL, node);
+ if (!dev->iod_mempool) {
+ result = -ENOMEM;
+ goto release_pools;
+ }
+
result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
quirks);
if (result)
- goto release_pools;
+ goto release_mempool;
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
return 0;
+ release_mempool:
+ mempool_destroy(dev->iod_mempool);
release_pools:
nvme_release_prp_pools(dev);
unmap:
if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
return;
- if (nvme_rdma_queue_idx(queue) == 0) {
- nvme_rdma_free_qe(queue->device->dev,
- &queue->ctrl->async_event_sqe,
- sizeof(struct nvme_command), DMA_TO_DEVICE);
- }
-
nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
}
set = &ctrl->tag_set;
memset(set, 0, sizeof(*set));
set->ops = &nvme_rdma_mq_ops;
- set->queue_depth = nctrl->opts->queue_size;
+ set->queue_depth = nctrl->sqsize + 1;
set->reserved_tags = 1; /* fabric connect */
set->numa_node = NUMA_NO_NODE;
set->flags = BLK_MQ_F_SHOULD_MERGE;
static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_queue(&ctrl->queues[0]);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.admin_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
}
+ if (ctrl->async_event_sqe.data) {
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
+ ctrl->async_event_sqe.data = NULL;
+ }
nvme_rdma_free_queue(&ctrl->queues[0]);
}
ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
+ error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
+ if (error)
+ goto out_free_queue;
+
if (new) {
ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
if (IS_ERR(ctrl->ctrl.admin_tagset)) {
error = PTR_ERR(ctrl->ctrl.admin_tagset);
- goto out_free_queue;
+ goto out_free_async_qe;
}
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
if (error)
goto out_stop_queue;
- error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
- &ctrl->async_event_sqe, sizeof(struct nvme_command),
- DMA_TO_DEVICE);
- if (error)
- goto out_stop_queue;
-
return 0;
out_stop_queue:
out_free_tagset:
if (new)
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+out_free_async_qe:
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
out_free_queue:
nvme_rdma_free_queue(&ctrl->queues[0]);
return error;
static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_io_queues(ctrl);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.connect_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
list_del(&ctrl->list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
- kfree(ctrl->queues);
nvmf_free_options(nctrl->opts);
free_ctrl:
+ kfree(ctrl->queues);
kfree(ctrl);
}
return;
destroy_admin:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, false);
requeue:
dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, false);
}
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, false);
count = ib_dma_map_sg(ibdev, req->sg_table.sgl, req->nents,
rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
if (unlikely(count <= 0)) {
- sg_free_table_chained(&req->sg_table, true);
- return -EIO;
+ ret = -EIO;
+ goto out_free_table;
}
if (count == 1) {
if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
blk_rq_payload_bytes(rq) <=
- nvme_rdma_inline_data_size(queue))
- return nvme_rdma_map_sg_inline(queue, req, c);
+ nvme_rdma_inline_data_size(queue)) {
+ ret = nvme_rdma_map_sg_inline(queue, req, c);
+ goto out;
+ }
- if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
- return nvme_rdma_map_sg_single(queue, req, c);
+ if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+ ret = nvme_rdma_map_sg_single(queue, req, c);
+ goto out;
+ }
}
- return nvme_rdma_map_sg_fr(queue, req, c, count);
+ ret = nvme_rdma_map_sg_fr(queue, req, c, count);
+out:
+ if (unlikely(ret))
+ goto out_unmap_sg;
+
+ return 0;
+
+out_unmap_sg:
+ ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
+ req->nents, rq_data_dir(rq) ==
+ WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+out_free_table:
+ sg_free_table_chained(&req->sg_table, true);
+ return ret;
}
static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
struct nvme_rdma_qe *sqe = &req->sqe;
struct nvme_command *c = sqe->data;
struct ib_device *dev;
+ bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags);
blk_status_t ret;
int err;
WARN_ON_ONCE(rq->tag < 0);
- ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
- test_bit(NVME_RDMA_Q_LIVE, &queue->flags), true);
- if (unlikely(ret))
- return ret;
+ if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+ return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
dev = queue->device->dev;
ib_dma_sync_single_for_cpu(dev, sqe->dma,
{
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, shutdown);
nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
goto out_free_ctrl;
}
- ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
- 0 /* no quirks, we're perfect! */);
- if (ret)
- goto out_free_ctrl;
-
INIT_DELAYED_WORK(&ctrl->reconnect_work,
nvme_rdma_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues),
GFP_KERNEL);
if (!ctrl->queues)
- goto out_uninit_ctrl;
+ goto out_free_ctrl;
+
+ ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+ 0 /* no quirks, we're perfect! */);
+ if (ret)
+ goto out_kfree_queues;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
WARN_ON_ONCE(!changed);
ret = nvme_rdma_configure_admin_queue(ctrl, true);
if (ret)
- goto out_kfree_queues;
+ goto out_uninit_ctrl;
/* sanity check icdoff */
if (ctrl->ctrl.icdoff) {
goto out_remove_admin_queue;
}
- if (opts->queue_size > ctrl->ctrl.maxcmd) {
- /* warn if maxcmd is lower than queue_size */
- dev_warn(ctrl->ctrl.device,
- "queue_size %zu > ctrl maxcmd %u, clamping down\n",
- opts->queue_size, ctrl->ctrl.maxcmd);
- opts->queue_size = ctrl->ctrl.maxcmd;
- }
-
+ /* only warn if argument is too large here, will clamp later */
if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
- /* warn if sqsize is lower than queue_size */
dev_warn(ctrl->ctrl.device,
"queue_size %zu > ctrl sqsize %u, clamping down\n",
opts->queue_size, ctrl->ctrl.sqsize + 1);
- opts->queue_size = ctrl->ctrl.sqsize + 1;
+ }
+
+ /* warn if maxcmd is lower than sqsize+1 */
+ if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+ dev_warn(ctrl->ctrl.device,
+ "sqsize %u > ctrl maxcmd %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+ ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
}
if (opts->nr_io_queues) {
return &ctrl->ctrl;
out_remove_admin_queue:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, true);
-out_kfree_queues:
- kfree(ctrl->queues);
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
if (ret > 0)
ret = -EIO;
return ERR_PTR(ret);
+out_kfree_queues:
+ kfree(ctrl->queues);
out_free_ctrl:
kfree(ctrl);
return ERR_PTR(ret);
else
status = nvmet_get_smart_log_nsid(req, log);
if (status)
- goto out;
+ goto out_free_log;
status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+out_free_log:
+ kfree(log);
out:
nvmet_req_complete(req, status);
}
{
struct nvmet_ns *ns = to_nvmet_ns(item);
struct nvmet_subsys *subsys = ns->subsys;
+ size_t len;
int ret;
mutex_lock(&subsys->lock);
if (ns->enabled)
goto out_unlock;
- kfree(ns->device_path);
+ ret = -EINVAL;
+ len = strcspn(page, "\n");
+ if (!len)
+ goto out_unlock;
+ kfree(ns->device_path);
ret = -ENOMEM;
- ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
+ ns->device_path = kstrndup(page, len, GFP_KERNEL);
if (!ns->device_path)
goto out_unlock;
goto out_unlock;
ret = nvmet_bdev_ns_enable(ns);
- if (ret)
+ if (ret == -ENOTBLK)
ret = nvmet_file_ns_enable(ns);
if (ret)
goto out_unlock;
}
ctrl->csts = NVME_CSTS_RDY;
+
+ /*
+ * Controllers that are not yet enabled should not really enforce the
+ * keep alive timeout, but we still want to track a timeout and cleanup
+ * in case a host died before it enabled the controller. Hence, simply
+ * reset the keep alive timer when the controller is enabled.
+ */
+ mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
}
static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
struct work_struct work;
} __aligned(sizeof(unsigned long long));
+/* desired maximum for a single sequence - if sg list allows it */
#define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024)
-#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE)
enum nvmet_fcp_datadir {
NVMET_FCP_NODATA,
struct nvme_fc_cmd_iu cmdiubuf;
struct nvme_fc_ersp_iu rspiubuf;
dma_addr_t rspdma;
+ struct scatterlist *next_sg;
struct scatterlist *data_sg;
int data_sg_cnt;
u32 offset;
INIT_LIST_HEAD(&newrec->assoc_list);
kref_init(&newrec->ref);
ida_init(&newrec->assoc_cnt);
- newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS,
- template->max_sgl_segments);
+ newrec->max_sg_cnt = template->max_sgl_segments;
ret = nvmet_fc_alloc_ls_iodlist(newrec);
if (ret) {
((fod->io_dir == NVMET_FCP_WRITE) ?
DMA_FROM_DEVICE : DMA_TO_DEVICE));
/* note: write from initiator perspective */
+ fod->next_sg = fod->data_sg;
return 0;
struct nvmet_fc_fcp_iod *fod, u8 op)
{
struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+ struct scatterlist *sg = fod->next_sg;
unsigned long flags;
- u32 tlen;
+ u32 remaininglen = fod->req.transfer_len - fod->offset;
+ u32 tlen = 0;
int ret;
fcpreq->op = op;
fcpreq->offset = fod->offset;
fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
- tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
- (fod->req.transfer_len - fod->offset));
+ /*
+ * for next sequence:
+ * break at a sg element boundary
+ * attempt to keep sequence length capped at
+ * NVMET_FC_MAX_SEQ_LENGTH but allow sequence to
+ * be longer if a single sg element is larger
+ * than that amount. This is done to avoid creating
+ * a new sg list to use for the tgtport api.
+ */
+ fcpreq->sg = sg;
+ fcpreq->sg_cnt = 0;
+ while (tlen < remaininglen &&
+ fcpreq->sg_cnt < tgtport->max_sg_cnt &&
+ tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) {
+ fcpreq->sg_cnt++;
+ tlen += sg_dma_len(sg);
+ sg = sg_next(sg);
+ }
+ if (tlen < remaininglen && fcpreq->sg_cnt == 0) {
+ fcpreq->sg_cnt++;
+ tlen += min_t(u32, sg_dma_len(sg), remaininglen);
+ sg = sg_next(sg);
+ }
+ if (tlen < remaininglen)
+ fod->next_sg = sg;
+ else
+ fod->next_sg = NULL;
+
fcpreq->transfer_length = tlen;
fcpreq->transferred_length = 0;
fcpreq->fcp_error = 0;
fcpreq->rsplen = 0;
- fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE];
- fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE);
-
/*
* If the last READDATA request: check if LLDD supports
* combined xfr with response.
struct nvme_loop_queue *queue = hctx->driver_data;
struct request *req = bd->rq;
struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
+ bool queue_ready = test_bit(NVME_LOOP_Q_LIVE, &queue->flags);
blk_status_t ret;
- ret = nvmf_check_if_ready(&queue->ctrl->ctrl, req,
- test_bit(NVME_LOOP_Q_LIVE, &queue->flags), true);
- if (unlikely(ret))
- return ret;
+ if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
+ return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
ret = nvme_setup_cmd(ns, req, &iod->cmd);
if (ret)
return cell;
}
+ /* NULL cell_id only allowed for device tree; invalid otherwise */
+ if (!cell_id)
+ return ERR_PTR(-EINVAL);
+
return nvmem_cell_get_from_list(cell_id);
}
EXPORT_SYMBOL_GPL(nvmem_cell_get);
* - the phandle lookup overhead reduction provided by the cache
* will likely be less
*/
-static void of_populate_phandle_cache(void)
+void of_populate_phandle_cache(void)
{
unsigned long flags;
u32 cache_entries;
raw_spin_unlock_irqrestore(&devtree_lock, flags);
}
-#ifndef CONFIG_MODULES
-static int __init of_free_phandle_cache(void)
+int of_free_phandle_cache(void)
{
unsigned long flags;
return 0;
}
+#if !defined(CONFIG_MODULES)
late_initcall_sync(of_free_phandle_cache);
#endif
#if defined(CONFIG_OF_OVERLAY)
void of_overlay_mutex_lock(void);
void of_overlay_mutex_unlock(void);
+int of_free_phandle_cache(void);
+void of_populate_phandle_cache(void);
#else
static inline void of_overlay_mutex_lock(void) {};
static inline void of_overlay_mutex_unlock(void) {};
goto err_free_overlay_changeset;
}
+ of_populate_phandle_cache();
+
ret = __of_changeset_apply_notify(&ovcs->cset);
if (ret)
pr_err("overlay changeset entry notify error %d\n", ret);
list_del(&ovcs->ovcs_list);
+ /*
+ * Disable phandle cache. Avoids race condition that would arise
+ * from removing cache entry when the associated node is deleted.
+ */
+ of_free_phandle_cache();
+
ret_apply = 0;
ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
+
+ of_populate_phandle_cache();
+
if (ret) {
if (ret_apply)
devicetree_state_flags |= DTSF_REVERT_FAIL;
}
/* Scaling up? Scale voltage before frequency */
- if (freq > old_freq) {
+ if (freq >= old_freq) {
ret = _set_opp_voltage(dev, reg, new_supply);
if (ret)
goto restore_voltage;
drive, PLIP link (Parallel Line Internet Protocol is mainly used to
create a mini network by connecting the parallel ports of two local
machines) etc., then you need to say Y here; please read
- <file:Documentation/parport.txt> and
+ <file:Documentation/admin-guide/parport.rst> and
<file:drivers/parport/BUGS-parport>.
For extensive information about drivers for many devices attaching
the module will be called parport.
If you have more than one parallel port and want to specify which
port and IRQ to be used by this driver at module load time, take a
- look at <file:Documentation/parport.txt>.
+ look at <file:Documentation/admin-guide/parport.rst>.
If unsure, say Y.
As well as actually having a FIFO, or DMA capability, the kernel
will need to know which IRQ the parallel port has. By default,
parallel port interrupts will not be used, and so neither will the
- FIFO. See <file:Documentation/parport.txt> to find out how to
+ FIFO. See <file:Documentation/admin-guide/parport.rst> to find out how to
specify which IRQ/DMA to use.
config PARPORT_PC_SUPERIO
obj-$(CONFIG_PCI_ECAM) += ecam.o
obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
-obj-y += controller/
-obj-y += switch/
-
# Endpoint library must be initialized before its users
obj-$(CONFIG_PCI_ENDPOINT) += endpoint/
+obj-y += controller/
+obj-y += switch/
+
ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
return;
}
- dev->is_added = 1;
+ pci_dev_assign_added(dev, true);
}
EXPORT_SYMBOL_GPL(pci_bus_add_device);
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip already-added devices */
- if (dev->is_added)
+ if (pci_dev_is_added(dev))
continue;
pci_bus_add_device(dev);
}
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip if device attach failed */
- if (!dev->is_added)
+ if (!pci_dev_is_added(dev))
continue;
child = dev->subordinate;
if (child)
depends on OF
select PCI_HOST_COMMON
select IRQ_DOMAIN
- select PCI_DOMAINS
help
Say Y here if you want to support a simple generic PCI host
controller, such as the one emulated by kvmtool.
config PCIE_IPROC
tristate
- select PCI_DOMAINS
help
This enables the iProc PCIe core controller support for Broadcom's
iProc family of SoCs. An appropriate bus interface driver needs
config PCIE_ALTERA
bool "Altera PCIe controller"
depends on ARM || NIOS2 || COMPILE_TEST
- select PCI_DOMAINS
help
Say Y here if you want to enable PCIe controller support on Altera
FPGA.
depends on PCI && PCI_MSI_IRQ_DOMAIN
select PCIE_DW_HOST
select PCIE_DW_PLAT
- default y
help
Enables support for the PCIe controller in the Designware IP to
work in host mode. There are two instances of PCIe controller in
resource_list_for_each_entry_safe(win, tmp, &bridge->windows) {
switch (resource_type(win->res)) {
case IORESOURCE_IO:
- ret = pci_remap_iospace(win->res, pp->io_base);
+ ret = devm_pci_remap_iospace(dev, win->res,
+ pp->io_base);
if (ret) {
dev_warn(dev, "Error %d: failed to map resource %pR\n",
ret, win->res);
0, 0xF8000000, 0,
lower_32_bits(res->start),
OB_PCIE_IO);
- err = pci_remap_iospace(res, iobase);
+ err = devm_pci_remap_iospace(dev, res, iobase);
if (err) {
dev_warn(dev, "error %d: failed to map resource %pR\n",
err, res);
irq = of_irq_get(intc, 0);
if (irq <= 0) {
dev_err(p->dev, "failed to get parent IRQ\n");
+ of_node_put(intc);
return irq ?: -EINVAL;
}
p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX,
&faraday_pci_irqdomain_ops, p);
+ of_node_put(intc);
if (!p->irqdomain) {
dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n");
return -EINVAL;
dev_err(dev, "illegal IO mem size\n");
return -EINVAL;
}
- ret = pci_remap_iospace(io, io_base);
+ ret = devm_pci_remap_iospace(dev, io, io_base);
if (ret) {
dev_warn(dev, "error %d: failed to map resource %pR\n",
ret, io);
struct pci_bus *pbus;
struct pci_dev *pdev;
struct cpumask *dest;
+ unsigned long flags;
struct compose_comp_ctxt comp;
struct tran_int_desc *int_desc;
struct {
* the channel callback directly when channel->target_cpu is
* the current CPU. When the higher level interrupt code
* calls us with interrupt enabled, let's add the
- * local_bh_disable()/enable() to avoid race.
+ * local_irq_save()/restore() to avoid race:
+ * hv_pci_onchannelcallback() can also run in tasklet.
*/
- local_bh_disable();
+ local_irq_save(flags);
if (hbus->hdev->channel->target_cpu == smp_processor_id())
hv_pci_onchannelcallback(hbus);
- local_bh_enable();
+ local_irq_restore(flags);
if (hpdev->state == hv_pcichild_ejecting) {
dev_err_once(&hbus->hdev->device,
v3->io_bus_addr = io->start - win->offset;
dev_dbg(dev, "I/O window %pR, bus addr %pap\n",
io, &v3->io_bus_addr);
- ret = pci_remap_iospace(io, io_base);
+ ret = devm_pci_remap_iospace(dev, io, io_base);
if (ret) {
dev_warn(dev,
"error %d: failed to map resource %pR\n",
switch (resource_type(res)) {
case IORESOURCE_IO:
- err = pci_remap_iospace(res, iobase);
+ err = devm_pci_remap_iospace(dev, res, iobase);
if (err) {
dev_warn(dev, "error %d: failed to map resource %pR\n",
err, res);
case IORESOURCE_IO:
xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base,
res->start - window->offset);
- ret = pci_remap_iospace(res, io_base);
+ ret = devm_pci_remap_iospace(dev, res, io_base);
if (ret < 0)
return ret;
break;
if (err < 0)
return err;
- pci_remap_iospace(&pcie->pio, pcie->io.start);
+ devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
return 0;
}
#define CFG_WINDOW_TYPE 0
#define IO_WINDOW_TYPE 1
#define MEM_WINDOW_TYPE 2
-#define IB_WIN_SIZE (256 * 1024 * 1024 * 1024)
+#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024)
#define MAX_PIO_WINDOWS 8
/* Parameters for the waiting for link up routine */
if (err)
return err;
- return phy_power_on(pcie->phy);
+ err = phy_power_on(pcie->phy);
+ if (err)
+ phy_exit(pcie->phy);
+
+ return err;
}
static int rcar_msi_alloc(struct rcar_msi *chip)
if (rcar_pcie_hw_init(pcie)) {
dev_info(dev, "PCIe link down\n");
err = -ENODEV;
- goto err_clk_disable;
+ goto err_phy_shutdown;
}
data = rcar_pci_read_reg(pcie, MACSR);
dev_err(dev,
"failed to enable MSI support: %d\n",
err);
- goto err_clk_disable;
+ goto err_phy_shutdown;
}
}
if (IS_ENABLED(CONFIG_PCI_MSI))
rcar_pcie_teardown_msi(pcie);
+err_phy_shutdown:
+ if (pcie->phy) {
+ phy_power_off(pcie->phy);
+ phy_exit(pcie->phy);
+ }
+
err_clk_disable:
clk_disable_unprepare(pcie->bus_clk);
PCI_NUM_INTX,
&legacy_domain_ops,
pcie);
-
+ of_node_put(legacy_intc_node);
if (!pcie->legacy_irq_domain) {
dev_err(dev, "failed to create IRQ domain\n");
return -ENOMEM;
port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
&intx_domain_ops,
port);
+ of_node_put(pcie_intc_node);
if (!port->leg_domain) {
dev_err(dev, "Failed to get a INTx IRQ domain\n");
return -ENODEV;
}
EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
+static void pci_epf_remove_cfs(struct pci_epf_driver *driver)
+{
+ struct config_group *group, *tmp;
+
+ if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+ return;
+
+ mutex_lock(&pci_epf_mutex);
+ list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry)
+ pci_ep_cfs_remove_epf_group(group);
+ list_del(&driver->epf_group);
+ mutex_unlock(&pci_epf_mutex);
+}
+
/**
* pci_epf_unregister_driver() - unregister the PCI EPF driver
* @driver: the PCI EPF driver that has to be unregistered
*/
void pci_epf_unregister_driver(struct pci_epf_driver *driver)
{
- struct config_group *group;
-
- mutex_lock(&pci_epf_mutex);
- list_for_each_entry(group, &driver->epf_group, group_entry)
- pci_ep_cfs_remove_epf_group(group);
- list_del(&driver->epf_group);
- mutex_unlock(&pci_epf_mutex);
+ pci_epf_remove_cfs(driver);
driver_unregister(&driver->driver);
}
EXPORT_SYMBOL_GPL(pci_epf_unregister_driver);
+static int pci_epf_add_cfs(struct pci_epf_driver *driver)
+{
+ struct config_group *group;
+ const struct pci_epf_device_id *id;
+
+ if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+ return 0;
+
+ INIT_LIST_HEAD(&driver->epf_group);
+
+ id = driver->id_table;
+ while (id->name[0]) {
+ group = pci_ep_cfs_add_epf_group(id->name);
+ if (IS_ERR(group)) {
+ pci_epf_remove_cfs(driver);
+ return PTR_ERR(group);
+ }
+
+ mutex_lock(&pci_epf_mutex);
+ list_add_tail(&group->group_entry, &driver->epf_group);
+ mutex_unlock(&pci_epf_mutex);
+ id++;
+ }
+
+ return 0;
+}
+
/**
* __pci_epf_register_driver() - register a new PCI EPF driver
* @driver: structure representing PCI EPF driver
struct module *owner)
{
int ret;
- struct config_group *group;
- const struct pci_epf_device_id *id;
if (!driver->ops)
return -EINVAL;
if (ret)
return ret;
- INIT_LIST_HEAD(&driver->epf_group);
-
- id = driver->id_table;
- while (id->name[0]) {
- group = pci_ep_cfs_add_epf_group(id->name);
- mutex_lock(&pci_epf_mutex);
- list_add_tail(&group->group_entry, &driver->epf_group);
- mutex_unlock(&pci_epf_mutex);
- id++;
- }
+ pci_epf_add_cfs(driver);
return 0;
}
* All rights reserved.
*
* Send feedback to <kristen.c.accardi@intel.com>
- *
*/
#include <linux/module.h>
return 0;
/* If _OSC exists, we should not evaluate OSHP */
+
+ /*
+ * If there's no ACPI host bridge (i.e., ACPI support is compiled
+ * into the kernel but the hardware platform doesn't support ACPI),
+ * there's nothing to do here.
+ */
host = pci_find_host_bridge(pdev->bus);
root = acpi_pci_find_root(ACPI_HANDLE(&host->dev));
+ if (!root)
+ return 0;
+
if (root->osc_support_set)
goto no_control;
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Assume that newly added devices are powered on already. */
- if (!dev->is_added)
+ if (!pci_dev_is_added(dev))
dev->current_state = PCI_D0;
}
sriov_release(dev);
}
+/**
+ * pci_iov_remove - clean up SR-IOV state after PF driver is detached
+ * @dev: the PCI device
+ */
+void pci_iov_remove(struct pci_dev *dev)
+{
+ struct pci_sriov *iov = dev->sriov;
+
+ if (!dev->is_physfn)
+ return;
+
+ iov->driver_max_VFs = iov->total_VFs;
+ if (iov->num_VFs)
+ pci_warn(dev, "driver left SR-IOV enabled after remove\n");
+}
+
/**
* pci_iov_update_resource - update a VF BAR
* @dev: the PCI device
switch (resource_type(res)) {
case IORESOURCE_IO:
- err = pci_remap_iospace(res, iobase);
+ err = devm_pci_remap_iospace(dev, res, iobase);
if (err) {
dev_warn(dev, "error %d: failed to map resource %pR\n",
err, res);
{
struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
+ /*
+ * In some cases (eg. Samsung 305V4A) leaving a bridge in suspend over
+ * system-wide suspend/resume confuses the platform firmware, so avoid
+ * doing that, unless the bridge has a driver that should take care of
+ * the PM handling. According to Section 16.1.6 of ACPI 6.2, endpoint
+ * devices are expected to be in D3 before invoking the S3 entry path
+ * from the firmware, so they should not be affected by this issue.
+ */
+ if (pci_is_bridge(dev) && !dev->driver &&
+ acpi_target_system_state() != ACPI_STATE_S0)
+ return true;
+
if (!adev || !acpi_device_power_manageable(adev))
return false;
}
pcibios_free_irq(pci_dev);
pci_dev->driver = NULL;
+ pci_iov_remove(pci_dev);
}
/* Undo the runtime PM settings in local_pci_probe() */
}
EXPORT_SYMBOL(pci_unmap_iospace);
+static void devm_pci_unmap_iospace(struct device *dev, void *ptr)
+{
+ struct resource **res = ptr;
+
+ pci_unmap_iospace(*res);
+}
+
+/**
+ * devm_pci_remap_iospace - Managed pci_remap_iospace()
+ * @dev: Generic device to remap IO address for
+ * @res: Resource describing the I/O space
+ * @phys_addr: physical address of range to be mapped
+ *
+ * Managed pci_remap_iospace(). Map is automatically unmapped on driver
+ * detach.
+ */
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+ phys_addr_t phys_addr)
+{
+ const struct resource **ptr;
+ int error;
+
+ ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
+
+ error = pci_remap_iospace(res, phys_addr);
+ if (error) {
+ devres_free(ptr);
+ } else {
+ *ptr = res;
+ devres_add(dev, ptr);
+ }
+
+ return error;
+}
+EXPORT_SYMBOL(devm_pci_remap_iospace);
+
/**
* devm_pci_remap_cfgspace - Managed pci_remap_cfgspace()
* @dev: Generic device to remap IO address for
/* pci_dev priv_flags */
#define PCI_DEV_DISCONNECTED 0
+#define PCI_DEV_ADDED 1
static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
{
return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags);
}
+static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
+{
+ assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added);
+}
+
+static inline bool pci_dev_is_added(const struct pci_dev *dev)
+{
+ return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
+}
+
#ifdef CONFIG_PCI_ATS
void pci_restore_ats_state(struct pci_dev *dev);
#else
#ifdef CONFIG_PCI_IOV
int pci_iov_init(struct pci_dev *dev);
void pci_iov_release(struct pci_dev *dev);
+void pci_iov_remove(struct pci_dev *dev);
void pci_iov_update_resource(struct pci_dev *dev, int resno);
resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
void pci_restore_iov_state(struct pci_dev *dev);
}
static inline void pci_iov_release(struct pci_dev *dev)
+{
+}
+static inline void pci_iov_remove(struct pci_dev *dev)
{
}
static inline void pci_restore_iov_state(struct pci_dev *dev)
parent = udev->subordinate;
pci_lock_rescan_remove();
+ pci_dev_get(dev);
list_for_each_entry_safe_reverse(pdev, temp, &parent->devices,
bus_list) {
pci_dev_get(pdev);
pci_info(dev, "Device recovery from fatal error failed\n");
}
+ pci_dev_put(dev);
pci_unlock_rescan_remove();
}
dev = pci_scan_single_device(bus, devfn);
if (!dev)
return 0;
- if (!dev->is_added)
+ if (!pci_dev_is_added(dev))
nr++;
for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) {
dev = pci_scan_single_device(bus, devfn + fn);
if (dev) {
- if (!dev->is_added)
+ if (!pci_dev_is_added(dev))
nr++;
dev->multifunction = 1;
}
{
pci_pme_active(dev, false);
- if (dev->is_added) {
+ if (pci_dev_is_added(dev)) {
device_release_driver(&dev->dev);
pci_proc_detach_device(dev);
pci_remove_sysfs_dev_files(dev);
- dev->is_added = 0;
+
+ pci_dev_assign_added(dev, false);
}
if (dev->bus->self)
case PMU_TYPE_IOB:
return devm_kasprintf(dev, GFP_KERNEL, "iob%d", id);
case PMU_TYPE_IOB_SLOW:
- return devm_kasprintf(dev, GFP_KERNEL, "iob-slow%d", id);
+ return devm_kasprintf(dev, GFP_KERNEL, "iob_slow%d", id);
case PMU_TYPE_MCB:
return devm_kasprintf(dev, GFP_KERNEL, "mcb%d", id);
case PMU_TYPE_MC:
{
void __iomem *ctrl = params->ctrl_regs;
+ USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE);
+ /* 1 millisecond - for USB clocks to settle down */
+ usleep_range(1000, 2000);
+
if (BRCM_ID(params->family_id) == 0x7366) {
/*
* The PHY3_SOFT_RESETB bits default to the wrong state.
ddata = container_of(work, struct phy_mdm6600, status_work.work);
dev = ddata->dev;
- error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES,
+ error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES,
ddata->status_gpios->desc,
values);
if (error)
return;
- for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) {
+ for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) {
val |= values[i] << i;
dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n",
__func__, i, values[i], val);
unsigned long flags;
unsigned int param;
u32 reg, bit, width, arg;
- int ret, i;
+ int ret = 0, i;
info = &pctrl->soc->padinfo[pin];
const struct nsp_pin_function *func;
const struct nsp_pin_group *grp;
- if (grp_select > pinctrl->num_groups ||
- func_select > pinctrl->num_functions)
+ if (grp_select >= pinctrl->num_groups ||
+ func_select >= pinctrl->num_functions)
return -EINVAL;
func = &pinctrl->functions[func_select];
return PTR_ERR(pinctrl->base0);
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (!res)
+ return -EINVAL;
pinctrl->base1 = devm_ioremap_nocache(&pdev->dev, res->start,
resource_size(res));
if (!pinctrl->base1) {
}
static int dt_to_map_one_config(struct pinctrl *p,
- struct pinctrl_dev *pctldev,
+ struct pinctrl_dev *hog_pctldev,
const char *statename,
struct device_node *np_config)
{
+ struct pinctrl_dev *pctldev = NULL;
struct device_node *np_pctldev;
const struct pinctrl_ops *ops;
int ret;
return -EPROBE_DEFER;
}
/* If we're creating a hog we can use the passed pctldev */
- if (pctldev && (np_pctldev == p->dev->of_node))
+ if (hog_pctldev && (np_pctldev == p->dev->of_node)) {
+ pctldev = hog_pctldev;
break;
+ }
pctldev = get_pinctrl_dev_from_of_node(np_pctldev);
if (pctldev)
break;
static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio)
{
- struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+ struct mtk_pinctrl *hw = gpiochip_get_data(chip);
int value, err;
err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value);
static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value)
{
- struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+ struct mtk_pinctrl *hw = gpiochip_get_data(chip);
mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value);
}
struct mtk_pinctrl *hw = gpiochip_get_data(chip);
unsigned long eint_n;
+ if (!hw->eint)
+ return -ENOTSUPP;
+
eint_n = offset;
return mtk_eint_find_irq(hw->eint, eint_n);
unsigned long eint_n;
u32 debounce;
- if (pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE)
+ if (!hw->eint ||
+ pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE)
return -ENOTSUPP;
debounce = pinconf_to_config_argument(config);
if (ret < 0)
return ret;
- ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
- chip->ngpio);
- if (ret < 0) {
- gpiochip_remove(chip);
- return ret;
+ /* Just for backward compatible for these old pinctrl nodes without
+ * "gpio-ranges" property. Otherwise, called directly from a
+ * DeviceTree-supported pinctrl driver is DEPRECATED.
+ * Please see Section 2.1 of
+ * Documentation/devicetree/bindings/gpio/gpio.txt on how to
+ * bind pinctrl and gpio drivers via the "gpio-ranges" property.
+ */
+ if (!of_find_property(np, "gpio-ranges", NULL)) {
+ ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
+ chip->ngpio);
+ if (ret < 0) {
+ gpiochip_remove(chip);
+ return ret;
+ }
}
return 0;
mtk_desc.custom_conf_items = mtk_conf_items;
#endif
- hw->pctrl = devm_pinctrl_register(&pdev->dev, &mtk_desc, hw);
- if (IS_ERR(hw->pctrl))
- return PTR_ERR(hw->pctrl);
+ err = devm_pinctrl_register_and_init(&pdev->dev, &mtk_desc, hw,
+ &hw->pctrl);
+ if (err)
+ return err;
/* Setup groups descriptions per SoC types */
err = mtk_build_groups(hw);
if (err) {
dev_err(&pdev->dev, "Failed to build groups\n");
- return 0;
+ return err;
}
/* Setup functions descriptions per SoC types */
return err;
}
- err = mtk_build_gpiochip(hw, pdev->dev.of_node);
- if (err) {
- dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+ /* For able to make pinctrl_claim_hogs, we must not enable pinctrl
+ * until all groups and functions are being added one.
+ */
+ err = pinctrl_enable(hw->pctrl);
+ if (err)
return err;
- }
err = mtk_build_eint(hw, pdev);
if (err)
dev_warn(&pdev->dev,
"Failed to add EINT, but pinctrl still can work\n");
+ /* Build gpiochip should be after pinctrl_enable is done */
+ err = mtk_build_gpiochip(hw, pdev->dev.of_node);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+ return err;
+ }
+
platform_set_drvdata(pdev, hw);
return 0;
return -ENOMEM;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res) {
- dev_err(&pdev->dev, "Unable to get eint resource\n");
- return -ENODEV;
- }
-
pctl->eint->base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(pctl->eint->base))
return PTR_ERR(pctl->eint->base);
ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input);
} else {
ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false);
- ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, input);
+ ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input);
ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, false);
}
mux_bytes = pcs->width / BITS_PER_BYTE;
- if (!pcs->saved_vals)
+ if (!pcs->saved_vals) {
pcs->saved_vals = devm_kzalloc(pcs->dev, pcs->size, GFP_ATOMIC);
+ if (!pcs->saved_vals)
+ return -ENOMEM;
+ }
switch (pcs->width) {
case 64:
if (!pcs)
return -EINVAL;
- if (pcs->flags & PCS_CONTEXT_LOSS_OFF)
- pcs_save_context(pcs);
+ if (pcs->flags & PCS_CONTEXT_LOSS_OFF) {
+ int ret;
+
+ ret = pcs_save_context(pcs);
+ if (ret < 0)
+ return ret;
+ }
return pinctrl_force_sleep(pcs->pctl);
}
#include "core.h"
#include "sh_pfc.h"
-#define CFG_FLAGS SH_PFC_PIN_CFG_DRIVE_STRENGTH
-
#define CPU_ALL_PORT(fn, sfx) \
- PORT_GP_CFG_22(0, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
- PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS), \
- PORT_GP_CFG_17(2, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
- PORT_GP_CFG_17(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
- PORT_GP_CFG_6(4, fn, sfx, CFG_FLAGS), \
- PORT_GP_CFG_15(5, fn, sfx, CFG_FLAGS)
+ PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \
+ PORT_GP_28(1, fn, sfx), \
+ PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \
+ PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \
+ PORT_GP_6(4, fn, sfx), \
+ PORT_GP_15(5, fn, sfx)
/*
* F_() : just information
* FM() : macro for FN_xxx / xxx_MARK
case PRID_REV_LOONGSON3B_R2:
reg = ((reg >> 8) & 0xff) - 100;
break;
- case PRID_REV_LOONGSON3A_R3:
+ case PRID_REV_LOONGSON3A_R3_0:
+ case PRID_REV_LOONGSON3A_R3_1:
reg = (reg & 0xffff)*731/0x4000 - 273;
break;
}
function keys, wireless LED, LCD backlight level.
It may also provide some sysfs files described in
- <file:Documentation/ABI/testing/sysfs-platform-samsung-laptop>
+ <file:Documentation/ABI/testing/sysfs-driver-samsung-laptop>
To compile this driver as a module, choose M here: the module
will be called samsung-laptop.
dell_fill_request(&buffer, token->location, 0, 0, 0);
ret = dell_send_request(&buffer,
CLASS_TOKEN_READ, SELECT_TOKEN_AC);
- if (ret)
+ if (ret == 0)
max_intensity = buffer.output[3];
}
case PTP_PF_PHYSYNC:
if (chan != 0)
return -EINVAL;
+ break;
default:
return -EINVAL;
}
}
pct = &sysoff->ts[0];
for (i = 0; i < sysoff->n_samples; i++) {
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
pct->sec = ts.tv_sec;
pct->nsec = ts.tv_nsec;
pct++;
pct->nsec = ts.tv_nsec;
pct++;
}
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
pct->sec = ts.tv_sec;
pct->nsec = ts.tv_nsec;
if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff)))
pr_err("ioremap ptp registers failed\n");
goto no_ioremap;
}
- getnstimeofday64(&now);
+ ktime_get_real_ts64(&now);
ptp_qoriq_settime(&qoriq_ptp->caps, &now);
tmr_ctrl =
struct elf32_hdr *ehdr;
phys_addr_t mpss_reloc;
phys_addr_t boot_addr;
- phys_addr_t min_addr = (phys_addr_t)ULLONG_MAX;
+ phys_addr_t min_addr = PHYS_ADDR_MAX;
phys_addr_t max_addr = 0;
bool relocate = false;
char seg_name[10];
return err;
/* full-function RTCs won't have such missing fields */
- if (rtc_valid_tm(&alarm->time) == 0)
+ if (rtc_valid_tm(&alarm->time) == 0) {
+ rtc_add_offset(rtc, &alarm->time);
return 0;
+ }
/* get the "after" timestamp, to detect wrapped fields */
err = rtc_read_time(rtc, &now);
if (err)
return err;
- rtc_subtract_offset(rtc, &alarm->time);
scheduled = rtc_tm_to_time64(&alarm->time);
/* Make sure we're not setting alarms in the past */
* over right here, before we set the alarm.
*/
+ rtc_subtract_offset(rtc, &alarm->time);
+
if (!rtc->ops)
err = -ENODEV;
else if (!rtc->ops->set_alarm)
mutex_unlock(&rtc->ops_lock);
- rtc_add_offset(rtc, &alarm->time);
return err;
}
EXPORT_SYMBOL_GPL(rtc_set_alarm);
}
retval = rtc_register_device(mrst_rtc.rtc);
- if (retval) {
- retval = PTR_ERR(mrst_rtc.rtc);
+ if (retval)
goto cleanup0;
- }
dev_dbg(dev, "initialised\n");
return 0;
#define DASD_DIAG_MOD "dasd_diag_mod"
+static unsigned int queue_depth = 32;
+static unsigned int nr_hw_queues = 4;
+
+module_param(queue_depth, uint, 0444);
+MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices");
+
+module_param(nr_hw_queues, uint, 0444);
+MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices");
+
/*
* SECTION: exported variables of dasd.c
*/
static void dasd_setup_queue(struct dasd_block *);
static void dasd_free_queue(struct dasd_block *);
static int dasd_flush_block_queue(struct dasd_block *);
-static void dasd_device_tasklet(struct dasd_device *);
-static void dasd_block_tasklet(struct dasd_block *);
+static void dasd_device_tasklet(unsigned long);
+static void dasd_block_tasklet(unsigned long);
static void do_kick_device(struct work_struct *);
static void do_restore_device(struct work_struct *);
static void do_reload_device(struct work_struct *);
dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE);
spin_lock_init(&device->mem_lock);
atomic_set(&device->tasklet_scheduled, 0);
- tasklet_init(&device->tasklet,
- (void (*)(unsigned long)) dasd_device_tasklet,
+ tasklet_init(&device->tasklet, dasd_device_tasklet,
(unsigned long) device);
INIT_LIST_HEAD(&device->ccw_queue);
timer_setup(&device->timer, dasd_device_timeout, 0);
atomic_set(&block->open_count, -1);
atomic_set(&block->tasklet_scheduled, 0);
- tasklet_init(&block->tasklet,
- (void (*)(unsigned long)) dasd_block_tasklet,
+ tasklet_init(&block->tasklet, dasd_block_tasklet,
(unsigned long) block);
INIT_LIST_HEAD(&block->ccw_queue);
spin_lock_init(&block->queue_lock);
device->hosts_dentry = pde;
}
-/*
- * Allocate memory for a channel program with 'cplength' channel
- * command words and 'datasize' additional space. There are two
- * variantes: 1) dasd_kmalloc_request uses kmalloc to get the needed
- * memory and 2) dasd_smalloc_request uses the static ccw memory
- * that gets allocated for each device.
- */
-struct dasd_ccw_req *dasd_kmalloc_request(int magic, int cplength,
- int datasize,
- struct dasd_device *device)
-{
- struct dasd_ccw_req *cqr;
-
- /* Sanity checks */
- BUG_ON(datasize > PAGE_SIZE ||
- (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
-
- cqr = kzalloc(sizeof(struct dasd_ccw_req), GFP_ATOMIC);
- if (cqr == NULL)
- return ERR_PTR(-ENOMEM);
- cqr->cpaddr = NULL;
- if (cplength > 0) {
- cqr->cpaddr = kcalloc(cplength, sizeof(struct ccw1),
- GFP_ATOMIC | GFP_DMA);
- if (cqr->cpaddr == NULL) {
- kfree(cqr);
- return ERR_PTR(-ENOMEM);
- }
- }
- cqr->data = NULL;
- if (datasize > 0) {
- cqr->data = kzalloc(datasize, GFP_ATOMIC | GFP_DMA);
- if (cqr->data == NULL) {
- kfree(cqr->cpaddr);
- kfree(cqr);
- return ERR_PTR(-ENOMEM);
- }
- }
- cqr->magic = magic;
- set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
- dasd_get_device(device);
- return cqr;
-}
-EXPORT_SYMBOL(dasd_kmalloc_request);
-
-struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength,
- int datasize,
- struct dasd_device *device)
+struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, int datasize,
+ struct dasd_device *device,
+ struct dasd_ccw_req *cqr)
{
unsigned long flags;
- struct dasd_ccw_req *cqr;
- char *data;
- int size;
+ char *data, *chunk;
+ int size = 0;
- size = (sizeof(struct dasd_ccw_req) + 7L) & -8L;
if (cplength > 0)
size += cplength * sizeof(struct ccw1);
if (datasize > 0)
size += datasize;
+ if (!cqr)
+ size += (sizeof(*cqr) + 7L) & -8L;
+
spin_lock_irqsave(&device->mem_lock, flags);
- cqr = (struct dasd_ccw_req *)
- dasd_alloc_chunk(&device->ccw_chunks, size);
+ data = chunk = dasd_alloc_chunk(&device->ccw_chunks, size);
spin_unlock_irqrestore(&device->mem_lock, flags);
- if (cqr == NULL)
+ if (!chunk)
return ERR_PTR(-ENOMEM);
- memset(cqr, 0, sizeof(struct dasd_ccw_req));
- data = (char *) cqr + ((sizeof(struct dasd_ccw_req) + 7L) & -8L);
- cqr->cpaddr = NULL;
+ if (!cqr) {
+ cqr = (void *) data;
+ data += (sizeof(*cqr) + 7L) & -8L;
+ }
+ memset(cqr, 0, sizeof(*cqr));
+ cqr->mem_chunk = chunk;
if (cplength > 0) {
- cqr->cpaddr = (struct ccw1 *) data;
- data += cplength*sizeof(struct ccw1);
- memset(cqr->cpaddr, 0, cplength*sizeof(struct ccw1));
+ cqr->cpaddr = data;
+ data += cplength * sizeof(struct ccw1);
+ memset(cqr->cpaddr, 0, cplength * sizeof(struct ccw1));
}
- cqr->data = NULL;
if (datasize > 0) {
cqr->data = data;
memset(cqr->data, 0, datasize);
}
EXPORT_SYMBOL(dasd_smalloc_request);
-/*
- * Free memory of a channel program. This function needs to free all the
- * idal lists that might have been created by dasd_set_cda and the
- * struct dasd_ccw_req itself.
- */
-void dasd_kfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device)
-{
- struct ccw1 *ccw;
-
- /* Clear any idals used for the request. */
- ccw = cqr->cpaddr;
- do {
- clear_normalized_cda(ccw);
- } while (ccw++->flags & (CCW_FLAG_CC | CCW_FLAG_DC));
- kfree(cqr->cpaddr);
- kfree(cqr->data);
- kfree(cqr);
- dasd_put_device(device);
-}
-EXPORT_SYMBOL(dasd_kfree_request);
-
void dasd_sfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device)
{
unsigned long flags;
spin_lock_irqsave(&device->mem_lock, flags);
- dasd_free_chunk(&device->ccw_chunks, cqr);
+ dasd_free_chunk(&device->ccw_chunks, cqr->mem_chunk);
spin_unlock_irqrestore(&device->mem_lock, flags);
dasd_put_device(device);
}
}
}
+static void __dasd_process_cqr(struct dasd_device *device,
+ struct dasd_ccw_req *cqr)
+{
+ char errorstring[ERRORLENGTH];
+
+ switch (cqr->status) {
+ case DASD_CQR_SUCCESS:
+ cqr->status = DASD_CQR_DONE;
+ break;
+ case DASD_CQR_ERROR:
+ cqr->status = DASD_CQR_NEED_ERP;
+ break;
+ case DASD_CQR_CLEARED:
+ cqr->status = DASD_CQR_TERMINATED;
+ break;
+ default:
+ /* internal error 12 - wrong cqr status*/
+ snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
+ dev_err(&device->cdev->dev,
+ "An error occurred in the DASD device driver, "
+ "reason=%s\n", errorstring);
+ BUG();
+ }
+ if (cqr->callback)
+ cqr->callback(cqr, cqr->callback_data);
+}
+
/*
* the cqrs from the final queue are returned to the upper layer
* by setting a dasd_block state and calling the callback function
struct list_head *l, *n;
struct dasd_ccw_req *cqr;
struct dasd_block *block;
- void (*callback)(struct dasd_ccw_req *, void *data);
- void *callback_data;
- char errorstring[ERRORLENGTH];
list_for_each_safe(l, n, final_queue) {
cqr = list_entry(l, struct dasd_ccw_req, devlist);
list_del_init(&cqr->devlist);
block = cqr->block;
- callback = cqr->callback;
- callback_data = cqr->callback_data;
- if (block)
+ if (!block) {
+ __dasd_process_cqr(device, cqr);
+ } else {
spin_lock_bh(&block->queue_lock);
- switch (cqr->status) {
- case DASD_CQR_SUCCESS:
- cqr->status = DASD_CQR_DONE;
- break;
- case DASD_CQR_ERROR:
- cqr->status = DASD_CQR_NEED_ERP;
- break;
- case DASD_CQR_CLEARED:
- cqr->status = DASD_CQR_TERMINATED;
- break;
- default:
- /* internal error 12 - wrong cqr status*/
- snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
- dev_err(&device->cdev->dev,
- "An error occurred in the DASD device driver, "
- "reason=%s\n", errorstring);
- BUG();
- }
- if (cqr->callback != NULL)
- (callback)(cqr, callback_data);
- if (block)
+ __dasd_process_cqr(device, cqr);
spin_unlock_bh(&block->queue_lock);
+ }
}
}
/*
* Acquire the device lock and process queues for the device.
*/
-static void dasd_device_tasklet(struct dasd_device *device)
+static void dasd_device_tasklet(unsigned long data)
{
+ struct dasd_device *device = (struct dasd_device *) data;
struct list_head final_queue;
atomic_set (&device->tasklet_scheduled, 0);
* block layer request queue, creates ccw requests, enqueues them on
* a dasd_device and processes ccw requests that have been returned.
*/
-static void dasd_block_tasklet(struct dasd_block *block)
+static void dasd_block_tasklet(unsigned long data)
{
+ struct dasd_block *block = (struct dasd_block *) data;
struct list_head final_queue;
struct list_head *l, *n;
struct dasd_ccw_req *cqr;
cqr->callback_data = req;
cqr->status = DASD_CQR_FILLED;
cqr->dq = dq;
- *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr;
blk_mq_start_request(req);
spin_lock(&block->queue_lock);
unsigned long flags;
int rc = 0;
- cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req));
+ cqr = blk_mq_rq_to_pdu(req);
if (!cqr)
return BLK_EH_DONE;
int rc;
block->tag_set.ops = &dasd_mq_ops;
- block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *);
- block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
- block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
+ block->tag_set.cmd_size = sizeof(struct dasd_ccw_req);
+ block->tag_set.nr_hw_queues = nr_hw_queues;
+ block->tag_set.queue_depth = queue_depth;
block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+ block->tag_set.numa_node = NUMA_NO_NODE;
rc = blk_mq_alloc_tag_set(&block->tag_set);
if (rc)
struct ccw1 *ccw;
unsigned long *idaw;
- cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device);
+ cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device,
+ NULL);
if (IS_ERR(cqr)) {
/* internal error 13 - Allocating the RDC request failed*/
int rc;
unsigned long flags;
- cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data)),
- device);
+ device, NULL);
if (IS_ERR(cqr))
return PTR_ERR(cqr);
cqr->startdev = device;
lcu->flags |= NEED_UAC_UPDATE;
spin_unlock_irqrestore(&lcu->lock, flags);
}
- dasd_kfree_request(cqr, cqr->memdev);
+ dasd_sfree_request(cqr, cqr->memdev);
return rc;
}
struct ccw1 *ccw;
cqr = lcu->rsu_cqr;
- strncpy((char *) &cqr->magic, "ECKD", 4);
+ memcpy((char *) &cqr->magic, "ECKD", 4);
ASCEBC((char *) &cqr->magic, 4);
ccw = cqr->cpaddr;
ccw->cmd_code = DASD_ECKD_CCW_RSCK;
if (!devmap) {
/* This bus_id is new. */
new->devindex = dasd_max_devindex++;
- strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
+ strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
new->features = features;
new->device = NULL;
list_add(&new->list, &dasd_hashlists[hash]);
/* Build the request */
datasize = sizeof(struct dasd_diag_req) +
count*sizeof(struct dasd_diag_bio);
- cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
}
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* RCD */,
0, /* use rcd_buf as data ara */
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate RCD request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_features)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", "Could not "
"allocate initialization request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ ,
sizeof(struct dasd_psf_ssc_data),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
struct dasd_eckd_private *private = device->private;
int i;
+ if (!private)
+ return;
+
dasd_alias_disconnect_device_from_lcu(device);
private->ned = NULL;
private->sneq = NULL;
cplength = 8;
datasize = sizeof(struct DE_eckd_data) + 2*sizeof(struct LO_eckd_data);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device,
+ NULL);
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
static int dasd_eckd_online_to_ready(struct dasd_device *device)
{
- cancel_work_sync(&device->reload_device);
- cancel_work_sync(&device->kick_validate);
+ if (cancel_work_sync(&device->reload_device))
+ dasd_put_device(device);
+ if (cancel_work_sync(&device->kick_validate))
+ dasd_put_device(device);
+
return 0;
};
*/
itcw_size = itcw_calc_size(0, count, 0);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev,
+ NULL);
if (IS_ERR(cqr))
return cqr;
cplength += count;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, NULL);
if (IS_ERR(cqr))
return cqr;
}
/* Allocate the format ccw request. */
fcp = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength,
- datasize, startdev);
+ datasize, startdev, NULL);
if (IS_ERR(fcp))
return fcp;
}
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
dcw = itcw_add_dcw(itcw, pfx_cmd, 0,
&pfxdata, sizeof(pfxdata), total_data_size);
- return PTR_RET(dcw);
+ return PTR_ERR_OR_ZERO(dcw);
}
static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
/* Allocate the ccw request. */
itcw_size = itcw_calc_size(0, ctidaw, 0);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength,
- datasize, startdev);
+ datasize, startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
useglobal = 0;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1,
- sizeof(struct dasd_snid_data), device);
+ sizeof(struct dasd_snid_data), device,
+ NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_perf_stats_t)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate initialization request");
psf1 = psf_data[1];
/* setup CCWs for PSF + RSSD */
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2 , 0, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2, 0, device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate initialization request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_messages)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
"Could not allocate read message buffer request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
sizeof(struct dasd_psf_prssd_data) + 1,
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
"Could not allocate read message buffer request");
int rc;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ ,
- sizeof(struct dasd_psf_cuir_response),
- device);
+ sizeof(struct dasd_psf_cuir_response),
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
ktime_get_real_ts64(&ts);
header.tv_sec = ts.tv_sec;
header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
- strncpy(header.busid, dev_name(&device->cdev->dev),
+ strlcpy(header.busid, dev_name(&device->cdev->dev),
DASD_EER_BUSID_SIZE);
spin_lock_irqsave(&bufferlock, flags);
ktime_get_real_ts64(&ts);
header.tv_sec = ts.tv_sec;
header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
- strncpy(header.busid, dev_name(&device->cdev->dev),
+ strlcpy(header.busid, dev_name(&device->cdev->dev),
DASD_EER_BUSID_SIZE);
spin_lock_irqsave(&bufferlock, flags);
* is a new ccw in device->eer_cqr. Free the "old"
* snss request now.
*/
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
}
/*
if (rc)
goto out;
- cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */,
- SNSS_DATA_SIZE, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */,
+ SNSS_DATA_SIZE, device, NULL);
if (IS_ERR(cqr)) {
rc = -ENOMEM;
cqr = NULL;
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
if (cqr)
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
return rc;
}
in_use = test_and_clear_bit(DASD_FLAG_EER_IN_USE, &device->flags);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
if (cqr && !in_use)
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
}
/*
datasize = sizeof(struct DE_fba_data) +
nr_ccws * (sizeof(struct LO_fba_data) + sizeof(struct ccw1));
- cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
datasize += (count - 1)*sizeof(struct LO_fba_data);
}
/* Allocate the ccw request. */
- cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
struct dasd_ccw_req {
unsigned int magic; /* Eye catcher */
+ int intrc; /* internal error, e.g. from start_IO */
struct list_head devlist; /* for dasd_device request queue */
struct list_head blocklist; /* for dasd_block request queue */
-
- /* Where to execute what... */
struct dasd_block *block; /* the originating block device */
struct dasd_device *memdev; /* the device used to allocate this */
struct dasd_device *startdev; /* device the request is started on */
struct dasd_device *basedev; /* base device if no block->base */
void *cpaddr; /* address of ccw or tcw */
+ short retries; /* A retry counter */
unsigned char cpmode; /* 0 = cmd mode, 1 = itcw */
char status; /* status of this request */
- short retries; /* A retry counter */
+ char lpm; /* logical path mask */
unsigned long flags; /* flags of this request */
struct dasd_queue *dq;
-
- /* ... and how */
unsigned long starttime; /* jiffies time of request start */
unsigned long expires; /* expiration period in jiffies */
- char lpm; /* logical path mask */
void *data; /* pointer to data area */
-
- /* these are important for recovering erroneous requests */
- int intrc; /* internal error, e.g. from start_IO */
struct irb irb; /* device status in case of an error */
struct dasd_ccw_req *refers; /* ERP-chain queueing. */
void *function; /* originating ERP action */
+ void *mem_chunk;
- /* these are for statistics only */
unsigned long buildclk; /* TOD-clock of request generation */
unsigned long startclk; /* TOD-clock of request start */
unsigned long stopclk; /* TOD-clock of request interrupt */
unsigned long endclk; /* TOD-clock of request termination */
- /* Callback that is called after reaching final status. */
void (*callback)(struct dasd_ccw_req *, void *data);
void *callback_data;
};
#define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */
#define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */
-/*
- * There is no reliable way to determine the number of available CPUs on
- * LPAR but there is no big performance difference between 1 and the
- * maximum CPU number.
- * 64 is a good trade off performance wise.
- */
-#define DASD_NR_HW_QUEUES 64
-#define DASD_MAX_LCU_DEV 256
#define DASD_REQ_PER_DEV 4
/* Signature for error recovery functions. */
extern struct kmem_cache *dasd_page_cache;
struct dasd_ccw_req *
-dasd_kmalloc_request(int , int, int, struct dasd_device *);
-struct dasd_ccw_req *
-dasd_smalloc_request(int , int, int, struct dasd_device *);
-void dasd_kfree_request(struct dasd_ccw_req *, struct dasd_device *);
+dasd_smalloc_request(int, int, int, struct dasd_device *, struct dasd_ccw_req *);
void dasd_sfree_request(struct dasd_ccw_req *, struct dasd_device *);
void dasd_wakeup_cb(struct dasd_ccw_req *, void *);
-static inline int
-dasd_kmalloc_set_cda(struct ccw1 *ccw, void *cda, struct dasd_device *device)
-{
- return set_normalized_cda(ccw, cda);
-}
-
struct dasd_device *dasd_alloc_device(void);
void dasd_free_device(struct dasd_device *);
bdev->tag_set.nr_hw_queues = nr_requests;
bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+ bdev->tag_set.numa_node = NUMA_NO_NODE;
ret = blk_mq_alloc_tag_set(&bdev->tag_set);
if (ret)
KCOV_INSTRUMENT_sclp_early_core.o := n
UBSAN_SANITIZE_sclp_early_core.o := n
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o += -march=z900
-endif
-
CFLAGS_sclp_early_core.o += -D__NO_FORTIFY
CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_EXPOLINE)
int cmd, int perm)
{
struct kbentry tmp;
+ unsigned long kb_index, kb_table;
ushort *key_map, val, ov;
if (copy_from_user(&tmp, user_kbe, sizeof(struct kbentry)))
return -EFAULT;
+ kb_index = (unsigned long) tmp.kb_index;
#if NR_KEYS < 256
- if (tmp.kb_index >= NR_KEYS)
+ if (kb_index >= NR_KEYS)
return -EINVAL;
#endif
+ kb_table = (unsigned long) tmp.kb_table;
#if MAX_NR_KEYMAPS < 256
- if (tmp.kb_table >= MAX_NR_KEYMAPS)
+ if (kb_table >= MAX_NR_KEYMAPS)
return -EINVAL;
+ kb_table = array_index_nospec(kb_table , MAX_NR_KEYMAPS);
#endif
switch (cmd) {
case KDGKBENT:
- key_map = kbd->key_maps[tmp.kb_table];
+ key_map = kbd->key_maps[kb_table];
if (key_map) {
- val = U(key_map[tmp.kb_index]);
+ val = U(key_map[kb_index]);
if (KTYP(val) >= KBD_NR_TYPES)
val = K_HOLE;
} else
- val = (tmp.kb_index ? K_HOLE : K_NOSUCHMAP);
+ val = (kb_index ? K_HOLE : K_NOSUCHMAP);
return put_user(val, &user_kbe->kb_value);
case KDSKBENT:
if (!perm)
return -EPERM;
- if (!tmp.kb_index && tmp.kb_value == K_NOSUCHMAP) {
+ if (!kb_index && tmp.kb_value == K_NOSUCHMAP) {
/* disallocate map */
- key_map = kbd->key_maps[tmp.kb_table];
+ key_map = kbd->key_maps[kb_table];
if (key_map) {
- kbd->key_maps[tmp.kb_table] = NULL;
+ kbd->key_maps[kb_table] = NULL;
kfree(key_map);
}
break;
if (KVAL(tmp.kb_value) > kbd_max_vals[KTYP(tmp.kb_value)])
return -EINVAL;
- if (!(key_map = kbd->key_maps[tmp.kb_table])) {
+ if (!(key_map = kbd->key_maps[kb_table])) {
int j;
key_map = kmalloc(sizeof(plain_map),
GFP_KERNEL);
if (!key_map)
return -ENOMEM;
- kbd->key_maps[tmp.kb_table] = key_map;
+ kbd->key_maps[kb_table] = key_map;
for (j = 0; j < NR_KEYS; j++)
key_map[j] = U(K_HOLE);
}
- ov = U(key_map[tmp.kb_index]);
+ ov = U(key_map[kb_index]);
if (tmp.kb_value == ov)
break; /* nothing to do */
/*
if (((ov == K_SAK) || (tmp.kb_value == K_SAK)) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
- key_map[tmp.kb_index] = U(tmp.kb_value);
+ key_map[kb_index] = U(tmp.kb_value);
break;
}
return 0;
struct appldata_product_id id;
int rc;
- strncpy(id.prod_nr, "LNXAPPL", 7);
+ memcpy(id.prod_nr, "LNXAPPL", 7);
id.prod_fn = myhdr->applid;
id.record_nr = myhdr->record_num;
id.version_nr = myhdr->version;
.priority = INT_MAX,
};
-static int proc_handler_callhome(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *count,
- loff_t *ppos)
-{
- unsigned long val;
- int len, rc;
- char buf[3];
-
- if (!*count || (*ppos && !write)) {
- *count = 0;
- return 0;
- }
- if (!write) {
- len = snprintf(buf, sizeof(buf), "%d\n", callhome_enabled);
- rc = copy_to_user(buffer, buf, sizeof(buf));
- if (rc != 0)
- return -EFAULT;
- } else {
- len = *count;
- rc = kstrtoul_from_user(buffer, len, 0, &val);
- if (rc)
- return rc;
- if (val != 0 && val != 1)
- return -EINVAL;
- callhome_enabled = val;
- }
- *count = len;
- *ppos += len;
- return 0;
-}
+static int zero;
+static int one = 1;
static struct ctl_table callhome_table[] = {
{
.procname = "callhome",
+ .data = &callhome_enabled,
+ .maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_handler_callhome,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
},
{}
};
static void ext_to_int_kekl(struct tape390_kekl *in,
struct tape3592_kekl *out)
{
- int i;
+ int len;
memset(out, 0, sizeof(*out));
if (in->type == TAPE390_KEKL_TYPE_HASH)
out->flags |= 0x40;
if (in->type_on_tape == TAPE390_KEKL_TYPE_HASH)
out->flags |= 0x80;
- strncpy(out->label, in->label, 64);
- for (i = strlen(in->label); i < sizeof(out->label); i++)
- out->label[i] = ' ';
+ len = min(sizeof(out->label), strlen(in->label));
+ memcpy(out->label, in->label, len);
+ memset(out->label + len, ' ', sizeof(out->label) - len);
ASCEBC(out->label, sizeof(out->label));
}
if (!tcd)
return ERR_PTR(-ENOMEM);
- strncpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
+ strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/'))
*s = '!';
- strncpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
+ strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/'))
*s = '!';
tcd->class_device = device_create(tape_class, device,
tcd->char_device->dev, NULL,
"%s", tcd->device_name);
- rc = PTR_RET(tcd->class_device);
+ rc = PTR_ERR_OR_ZERO(tcd->class_device);
if (rc)
goto fail_with_cdev;
rc = sysfs_create_link(
# The following is required for define_trace.h to find ./trace.h
CFLAGS_trace.o := -I$(src)
+CFLAGS_vfio_ccw_fsm.o := -I$(src)
obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \
fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o
{
struct channel_subsystem *css = css_by_id(chpid.cssid);
struct channel_path *chp;
- int ret;
+ int ret = 0;
+ mutex_lock(&css->mutex);
if (chp_is_registered(chpid))
- return 0;
- chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
- if (!chp)
- return -ENOMEM;
+ goto out;
+ chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
+ if (!chp) {
+ ret = -ENOMEM;
+ goto out;
+ }
/* fill in status, etc. */
chp->chpid = chpid;
chp->state = 1;
put_device(&chp->dev);
goto out;
}
- mutex_lock(&css->mutex);
+
if (css->cm_enabled) {
ret = chp_add_cmg_attr(chp);
if (ret) {
device_unregister(&chp->dev);
- mutex_unlock(&css->mutex);
goto out;
}
}
css->chps[chpid.id] = chp;
- mutex_unlock(&css->mutex);
goto out;
out_free:
kfree(chp);
out:
+ mutex_unlock(&css->mutex);
return ret;
}
switch (crw0->erc) {
case CRW_ERC_IPARM: /* Path has come. */
case CRW_ERC_INIT:
- if (!chp_is_registered(chpid))
- chp_new(chpid);
+ chp_new(chpid);
chsc_chp_online(chpid);
break;
case CRW_ERC_PERRI: /* Path has gone. */
u16 sch; /* subchannel */
u8 chpid[8]; /* chpids 0-7 */
u16 fla[8]; /* full link addresses 0-7 */
-} __attribute__ ((packed));
+} __packed __aligned(PAGE_SIZE);
int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
{
struct chsc_sei_nt2_area nt2_area;
u8 nt_area[PAGE_SIZE - 24];
} u;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
/*
* Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
u32 : 4;
u32 fmt : 4;
u32 : 16;
- } __attribute__ ((packed)) *secm_area;
+ } *secm_area;
unsigned long flags;
int ret, ccode;
u32 cmg : 8;
u32 zeroes3;
u32 data[NR_MEASUREMENT_CHARS];
- } __attribute__ ((packed)) *scmc_area;
+ } *scmc_area;
chp->shared = -1;
chp->cmg = -1;
u8 cssid;
u32 : 24;
} list[0];
- } __packed *sdcal_area;
+ } *sdcal_area;
int ret;
spin_lock_irq(&chsc_page_lock);
u32 reserved4;
u32 general_char[510];
u32 chsc_char[508];
- } __attribute__ ((packed)) *scsc_area;
+ } *scsc_area;
spin_lock_irqsave(&chsc_page_lock, flags);
memset(chsc_page, 0, PAGE_SIZE);
unsigned int rsvd3[3];
u64 clock_delta;
unsigned int rsvd4[2];
- } __attribute__ ((packed)) *rr;
+ } *rr;
int rc;
memset(page, 0, PAGE_SIZE);
unsigned int rsvd0[3];
struct chsc_header response;
char data[];
- } __attribute__ ((packed)) *rr;
+ } *rr;
int rc;
memset(page, 0, PAGE_SIZE);
u32 word3;
struct chsc_header response;
u32 word[11];
- } __attribute__ ((packed)) *siosl_area;
+ } *siosl_area;
unsigned long flags;
int ccode;
int rc;
#define NR_MEASUREMENT_CHARS 5
struct cmg_chars {
u32 values[NR_MEASUREMENT_CHARS];
-} __attribute__ ((packed));
+};
#define NR_MEASUREMENT_ENTRIES 8
struct cmg_entry {
u32 values[NR_MEASUREMENT_ENTRIES];
-} __attribute__ ((packed));
+};
struct channel_path_desc_fmt1 {
u8 flags;
u8 s:1;
u8 f:1;
u32 zeros[2];
-} __attribute__ ((packed));
+};
struct channel_path_desc_fmt3 {
struct channel_path_desc_fmt1 fmt1_desc;
u32:7;
u32 pnso:1; /* bit 116 */
u32:11;
-}__attribute__((packed));
+} __packed;
extern struct css_chsc_char css_chsc_characteristics;
struct chsc_header response;
u32:32;
struct qdio_ssqd_desc qdio_ssqd;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
struct chsc_scssc_area {
struct chsc_header request;
u32 reserved[1004];
struct chsc_header response;
u32:32;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
struct chsc_scpd {
struct chsc_header request;
struct chsc_header response;
u32:32;
u8 data[0];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
struct chsc_sda_area {
struct chsc_header request;
u32 reserved2[10];
u64 restok;
struct sale scmal[248];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
struct qdio_brinfo_entry_l2 l2[0];
} entries;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
int chsc_pnso_brinfo(struct subchannel_id schid,
struct chsc_pnso_area *brinfo_area,
}
EXPORT_SYMBOL_GPL(cio_disable_subchannel);
-static int cio_check_devno_blacklisted(struct subchannel *sch)
-{
- if (is_blacklisted(sch->schid.ssid, sch->schib.pmcw.dev)) {
- /*
- * This device must not be known to Linux. So we simply
- * say that there is no device and return ENODEV.
- */
- CIO_MSG_EVENT(6, "Blacklisted device detected "
- "at devno %04X, subchannel set %x\n",
- sch->schib.pmcw.dev, sch->schid.ssid);
- return -ENODEV;
- }
- return 0;
-}
-
-/**
- * cio_validate_subchannel - basic validation of subchannel
- * @sch: subchannel structure to be filled out
- * @schid: subchannel id
- *
- * Find out subchannel type and initialize struct subchannel.
- * Return codes:
- * 0 on success
- * -ENXIO for non-defined subchannels
- * -ENODEV for invalid subchannels or blacklisted devices
- * -EIO for subchannels in an invalid subchannel set
- */
-int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
-{
- char dbf_txt[15];
- int ccode;
- int err;
-
- sprintf(dbf_txt, "valsch%x", schid.sch_no);
- CIO_TRACE_EVENT(4, dbf_txt);
-
- /*
- * The first subchannel that is not-operational (ccode==3)
- * indicates that there aren't any more devices available.
- * If stsch gets an exception, it means the current subchannel set
- * is not valid.
- */
- ccode = stsch(schid, &sch->schib);
- if (ccode) {
- err = (ccode == 3) ? -ENXIO : ccode;
- goto out;
- }
- sch->st = sch->schib.pmcw.st;
- sch->schid = schid;
-
- switch (sch->st) {
- case SUBCHANNEL_TYPE_IO:
- case SUBCHANNEL_TYPE_MSG:
- if (!css_sch_is_valid(&sch->schib))
- err = -ENODEV;
- else
- err = cio_check_devno_blacklisted(sch);
- break;
- default:
- err = 0;
- }
- if (err)
- goto out;
-
- CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
- sch->schid.ssid, sch->schid.sch_no, sch->st);
-out:
- return err;
-}
-
/*
* do_cio_interrupt() handles all normal I/O device IRQ's
*/
{
struct subchannel_id schid;
struct subchannel *sch;
+ struct schib schib;
int sch_no, ret;
sch_no = cio_get_console_sch_no();
}
init_subchannel_id(&schid);
schid.sch_no = sch_no;
- sch = css_alloc_subchannel(schid);
+ ret = stsch(schid, &schib);
+ if (ret)
+ return ERR_PTR(-ENODEV);
+
+ sch = css_alloc_subchannel(schid, &schib);
if (IS_ERR(sch))
return sch;
#define to_subchannel(n) container_of(n, struct subchannel, dev)
-extern int cio_validate_subchannel (struct subchannel *, struct subchannel_id);
extern int cio_enable_subchannel(struct subchannel *, u32);
extern int cio_disable_subchannel (struct subchannel *);
extern int cio_cancel (struct subchannel *);
#include "css.h"
#include "cio.h"
+#include "blacklist.h"
#include "cio_debug.h"
#include "ioasm.h"
#include "chsc.h"
kfree(sch);
}
-struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
+static int css_validate_subchannel(struct subchannel_id schid,
+ struct schib *schib)
+{
+ int err;
+
+ switch (schib->pmcw.st) {
+ case SUBCHANNEL_TYPE_IO:
+ case SUBCHANNEL_TYPE_MSG:
+ if (!css_sch_is_valid(schib))
+ err = -ENODEV;
+ else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+ CIO_MSG_EVENT(6, "Blacklisted device detected "
+ "at devno %04X, subchannel set %x\n",
+ schib->pmcw.dev, schid.ssid);
+ err = -ENODEV;
+ } else
+ err = 0;
+ break;
+ default:
+ err = 0;
+ }
+ if (err)
+ goto out;
+
+ CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
+ schid.ssid, schid.sch_no, schib->pmcw.st);
+out:
+ return err;
+}
+
+struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
+ struct schib *schib)
{
struct subchannel *sch;
int ret;
+ ret = css_validate_subchannel(schid, schib);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
sch = kzalloc(sizeof(*sch), GFP_KERNEL | GFP_DMA);
if (!sch)
return ERR_PTR(-ENOMEM);
- ret = cio_validate_subchannel(sch, schid);
- if (ret < 0)
- goto err;
+ sch->schid = schid;
+ sch->schib = *schib;
+ sch->st = schib->pmcw.st;
ret = css_sch_create_locks(sch);
if (ret)
for (i = 0; i < 8; i++) {
mask = 0x80 >> i;
if (ssd->path_mask & mask)
- if (!chp_is_registered(ssd->chpid[i]))
- chp_new(ssd->chpid[i]);
+ chp_new(ssd->chpid[i]);
}
}
return ret;
}
-static int css_probe_device(struct subchannel_id schid)
+static int css_probe_device(struct subchannel_id schid, struct schib *schib)
{
struct subchannel *sch;
int ret;
- sch = css_alloc_subchannel(schid);
+ sch = css_alloc_subchannel(schid, schib);
if (IS_ERR(sch))
return PTR_ERR(sch);
static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
{
struct schib schib;
+ int ccode;
if (!slow) {
/* Will be done on the slow path. */
return -EAGAIN;
}
- if (stsch(schid, &schib)) {
- /* Subchannel is not provided. */
- return -ENXIO;
- }
- if (!css_sch_is_valid(&schib)) {
- /* Unusable - ignore. */
- return 0;
- }
- CIO_MSG_EVENT(4, "event: sch 0.%x.%04x, new\n", schid.ssid,
- schid.sch_no);
+ /*
+ * The first subchannel that is not-operational (ccode==3)
+ * indicates that there aren't any more devices available.
+ * If stsch gets an exception, it means the current subchannel set
+ * is not valid.
+ */
+ ccode = stsch(schid, &schib);
+ if (ccode)
+ return (ccode == 3) ? -ENXIO : ccode;
- return css_probe_device(schid);
+ return css_probe_device(schid, &schib);
}
static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
if (ret)
goto out_wq;
+ /* Register subchannels which are already in use. */
+ cio_register_early_subchannels();
+ /* Start initial subchannel evaluation. */
+ css_schedule_eval_all();
+
return ret;
out_wq:
destroy_workqueue(cio_work_q);
*/
static int __init channel_subsystem_init_sync(void)
{
- /* Register subchannels which are already in use. */
- cio_register_early_subchannels();
- /* Start initial subchannel evaluation. */
- css_schedule_eval_all();
css_complete_work();
return 0;
}
extern void css_sch_device_unregister(struct subchannel *);
extern int css_register_subchannel(struct subchannel *);
-extern struct subchannel *css_alloc_subchannel(struct subchannel_id);
+extern struct subchannel *css_alloc_subchannel(struct subchannel_id,
+ struct schib *schib);
extern struct subchannel *get_subchannel_by_schid(struct subchannel_id);
extern int css_init_done;
extern int max_ssid;
unsigned long phys_aob = 0;
if (!q->use_cq)
- goto out;
+ return 0;
if (!q->aobs[bufnr]) {
struct qaob *aob = qdio_allocate_aob();
q->aobs[bufnr] = aob;
}
if (q->aobs[bufnr]) {
- q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
q->sbal_state[bufnr].aob = q->aobs[bufnr];
q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
phys_aob = virt_to_phys(q->aobs[bufnr]);
WARN_ON_ONCE(phys_aob & 0xFF);
}
-out:
+ q->sbal_state[bufnr].flags = 0;
return phys_aob;
}
__field(u16, schno)
__field(u16, devno)
__field_struct(struct schib, schib)
+ __field(u8, pmcw_ena)
+ __field(u8, pmcw_st)
+ __field(u8, pmcw_dnv)
+ __field(u16, pmcw_dev)
+ __field(u8, pmcw_lpm)
+ __field(u8, pmcw_pnom)
+ __field(u8, pmcw_lpum)
+ __field(u8, pmcw_pim)
+ __field(u8, pmcw_pam)
+ __field(u8, pmcw_pom)
+ __field(u64, pmcw_chpid)
__field(int, cc)
),
TP_fast_assign(
__entry->schno = schid.sch_no;
__entry->devno = schib->pmcw.dev;
__entry->schib = *schib;
+ __entry->pmcw_ena = schib->pmcw.ena;
+ __entry->pmcw_st = schib->pmcw.ena;
+ __entry->pmcw_dnv = schib->pmcw.dnv;
+ __entry->pmcw_dev = schib->pmcw.dev;
+ __entry->pmcw_lpm = schib->pmcw.lpm;
+ __entry->pmcw_pnom = schib->pmcw.pnom;
+ __entry->pmcw_lpum = schib->pmcw.lpum;
+ __entry->pmcw_pim = schib->pmcw.pim;
+ __entry->pmcw_pam = schib->pmcw.pam;
+ __entry->pmcw_pom = schib->pmcw.pom;
+ memcpy(&__entry->pmcw_chpid, &schib->pmcw.chpid, 8);
__entry->cc = cc;
),
TP_printk("schid=%x.%x.%04x cc=%d ena=%d st=%d dnv=%d dev=%04x "
"lpm=0x%02x pnom=0x%02x lpum=0x%02x pim=0x%02x pam=0x%02x "
"pom=0x%02x chpids=%016llx",
__entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
- __entry->schib.pmcw.ena, __entry->schib.pmcw.st,
- __entry->schib.pmcw.dnv, __entry->schib.pmcw.dev,
- __entry->schib.pmcw.lpm, __entry->schib.pmcw.pnom,
- __entry->schib.pmcw.lpum, __entry->schib.pmcw.pim,
- __entry->schib.pmcw.pam, __entry->schib.pmcw.pom,
- *((u64 *) __entry->schib.pmcw.chpid)
+ __entry->pmcw_ena, __entry->pmcw_st,
+ __entry->pmcw_dnv, __entry->pmcw_dev,
+ __entry->pmcw_lpm, __entry->pmcw_pnom,
+ __entry->pmcw_lpum, __entry->pmcw_pim,
+ __entry->pmcw_pam, __entry->pmcw_pom,
+ __entry->pmcw_chpid
)
);
__field(u8, ssid)
__field(u16, schno)
__field_struct(struct irb, irb)
+ __field(u8, scsw_dcc)
+ __field(u8, scsw_pno)
+ __field(u8, scsw_fctl)
+ __field(u8, scsw_actl)
+ __field(u8, scsw_stctl)
+ __field(u8, scsw_dstat)
+ __field(u8, scsw_cstat)
__field(int, cc)
),
TP_fast_assign(
__entry->ssid = schid.ssid;
__entry->schno = schid.sch_no;
__entry->irb = *irb;
+ __entry->scsw_dcc = scsw_cc(&irb->scsw);
+ __entry->scsw_pno = scsw_pno(&irb->scsw);
+ __entry->scsw_fctl = scsw_fctl(&irb->scsw);
+ __entry->scsw_actl = scsw_actl(&irb->scsw);
+ __entry->scsw_stctl = scsw_stctl(&irb->scsw);
+ __entry->scsw_dstat = scsw_dstat(&irb->scsw);
+ __entry->scsw_cstat = scsw_cstat(&irb->scsw);
__entry->cc = cc;
),
TP_printk("schid=%x.%x.%04x cc=%d dcc=%d pno=%d fctl=0x%x actl=0x%x "
"stctl=0x%x dstat=0x%x cstat=0x%x",
__entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
- scsw_cc(&__entry->irb.scsw), scsw_pno(&__entry->irb.scsw),
- scsw_fctl(&__entry->irb.scsw), scsw_actl(&__entry->irb.scsw),
- scsw_stctl(&__entry->irb.scsw),
- scsw_dstat(&__entry->irb.scsw), scsw_cstat(&__entry->irb.scsw)
+ __entry->scsw_dcc, __entry->scsw_pno,
+ __entry->scsw_fctl, __entry->scsw_actl,
+ __entry->scsw_stctl,
+ __entry->scsw_dstat, __entry->scsw_cstat
)
);
__field(u8, cssid)
__field(u8, ssid)
__field(u16, schno)
+ __field(u8, adapter_IO)
+ __field(u8, isc)
+ __field(u8, type)
),
TP_fast_assign(
__entry->cc = cc;
__entry->cssid = __entry->tpi_info.schid.cssid;
__entry->ssid = __entry->tpi_info.schid.ssid;
__entry->schno = __entry->tpi_info.schid.sch_no;
+ __entry->adapter_IO = __entry->tpi_info.adapter_IO;
+ __entry->isc = __entry->tpi_info.isc;
+ __entry->type = __entry->tpi_info.type;
),
TP_printk("schid=%x.%x.%04x cc=%d a=%d isc=%d type=%d",
__entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
- __entry->tpi_info.adapter_IO, __entry->tpi_info.isc,
- __entry->tpi_info.type
+ __entry->adapter_IO, __entry->isc,
+ __entry->type
)
);
__field(u8, cssid)
__field(u8, ssid)
__field(u16, schno)
+ __field(u8, isc)
+ __field(u8, type)
),
TP_fast_assign(
__entry->tpi_info = *tpi_info;
- __entry->cssid = __entry->tpi_info.schid.cssid;
- __entry->ssid = __entry->tpi_info.schid.ssid;
- __entry->schno = __entry->tpi_info.schid.sch_no;
+ __entry->cssid = tpi_info->schid.cssid;
+ __entry->ssid = tpi_info->schid.ssid;
+ __entry->schno = tpi_info->schid.sch_no;
+ __entry->isc = tpi_info->isc;
+ __entry->type = tpi_info->type;
),
TP_printk("schid=%x.%x.%04x isc=%d type=%d",
__entry->cssid, __entry->ssid, __entry->schno,
- __entry->tpi_info.isc, __entry->tpi_info.type
+ __entry->isc, __entry->type
)
);
TP_ARGS(tpi_info),
TP_STRUCT__entry(
__field_struct(struct tpi_info, tpi_info)
+ __field(u8, isc)
),
TP_fast_assign(
__entry->tpi_info = *tpi_info;
+ __entry->isc = tpi_info->isc;
),
- TP_printk("isc=%d", __entry->tpi_info.isc)
+ TP_printk("isc=%d", __entry->isc)
);
/**
TP_STRUCT__entry(
__field_struct(struct crw, crw)
__field(int, cc)
+ __field(u8, slct)
+ __field(u8, oflw)
+ __field(u8, chn)
+ __field(u8, rsc)
+ __field(u8, anc)
+ __field(u8, erc)
+ __field(u16, rsid)
),
TP_fast_assign(
__entry->crw = *crw;
__entry->cc = cc;
+ __entry->slct = crw->slct;
+ __entry->oflw = crw->oflw;
+ __entry->chn = crw->chn;
+ __entry->rsc = crw->rsc;
+ __entry->anc = crw->anc;
+ __entry->erc = crw->erc;
+ __entry->rsid = crw->rsid;
),
TP_printk("cc=%d slct=%d oflw=%d chn=%d rsc=%d anc=%d erc=0x%x "
"rsid=0x%x",
- __entry->cc, __entry->crw.slct, __entry->crw.oflw,
- __entry->crw.chn, __entry->crw.rsc, __entry->crw.anc,
- __entry->crw.erc, __entry->crw.rsid
+ __entry->cc, __entry->slct, __entry->oflw,
+ __entry->chn, __entry->rsc, __entry->anc,
+ __entry->erc, __entry->rsid
)
);
#define CCWCHAIN_LEN_MAX 256
struct pfn_array {
+ /* Starting guest physical I/O address. */
unsigned long pa_iova;
+ /* Array that stores PFNs of the pages need to pin. */
unsigned long *pa_iova_pfn;
+ /* Array that receives PFNs of the pages pinned. */
unsigned long *pa_pfn;
+ /* Number of pages pinned from @pa_iova. */
int pa_nr;
};
};
/*
- * pfn_array_pin() - pin user pages in memory
+ * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory
* @pa: pfn_array on which to perform the operation
* @mdev: the mediated device to perform pin/unpin operations
+ * @iova: target guest physical address
+ * @len: number of bytes that should be pinned from @iova
*
- * Attempt to pin user pages in memory.
+ * Attempt to allocate memory for PFNs, and pin user pages in memory.
*
* Usage of pfn_array:
- * @pa->pa_iova starting guest physical I/O address. Assigned by caller.
- * @pa->pa_iova_pfn array that stores PFNs of the pages need to pin. Allocated
- * by caller.
- * @pa->pa_pfn array that receives PFNs of the pages pinned. Allocated by
- * caller.
- * @pa->pa_nr number of pages from @pa->pa_iova to pin. Assigned by
- * caller.
- * number of pages pinned. Assigned by callee.
+ * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in
+ * this structure will be filled in by this function.
*
* Returns:
* Number of pages pinned on success.
- * If @pa->pa_nr is 0 or negative, returns 0.
+ * If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially,
+ * returns -EINVAL.
* If no pages were pinned, returns -errno.
*/
-static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
-{
- int i, ret;
-
- if (pa->pa_nr <= 0) {
- pa->pa_nr = 0;
- return 0;
- }
-
- pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
- for (i = 1; i < pa->pa_nr; i++)
- pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
-
- ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
- IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
-
- if (ret > 0 && ret != pa->pa_nr) {
- vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
- pa->pa_nr = 0;
- return 0;
- }
-
- return ret;
-}
-
-/* Unpin the pages before releasing the memory. */
-static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
-{
- vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
- pa->pa_nr = 0;
- kfree(pa->pa_iova_pfn);
-}
-
-/* Alloc memory for PFNs, then pin pages with them. */
static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
u64 iova, unsigned int len)
{
- int ret = 0;
+ int i, ret = 0;
if (!len)
return 0;
- if (pa->pa_nr)
+ if (pa->pa_nr || pa->pa_iova_pfn)
return -EINVAL;
pa->pa_iova = iova;
return -ENOMEM;
pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
- ret = pfn_array_pin(pa, mdev);
+ pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
+ for (i = 1; i < pa->pa_nr; i++)
+ pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
- if (ret > 0)
- return ret;
- else if (!ret)
+ ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+ IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
+
+ if (ret < 0) {
+ goto err_out;
+ } else if (ret > 0 && ret != pa->pa_nr) {
+ vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
ret = -EINVAL;
+ goto err_out;
+ }
+ return ret;
+
+err_out:
+ pa->pa_nr = 0;
kfree(pa->pa_iova_pfn);
+ pa->pa_iova_pfn = NULL;
return ret;
}
+/* Unpin the pages before releasing the memory. */
+static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+{
+ vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+ pa->pa_nr = 0;
+ kfree(pa->pa_iova_pfn);
+}
+
static int pfn_array_table_init(struct pfn_array_table *pat, int nr)
{
pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL);
* This is the chain length not considering any TICs.
* You need to do a new round for each TIC target.
*
+ * The program is also validated for absence of not yet supported
+ * indirect data addressing scenarios.
+ *
* Returns: the length of the ccw chain or -errno.
*/
static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
do {
cnt++;
+ /*
+ * As we don't want to fail direct addressing even if the
+ * orb specified one of the unsupported formats, we defer
+ * checking for IDAWs in unsupported formats to here.
+ */
+ if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw))
+ return -EOPNOTSUPP;
+
if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw)))
break;
struct ccw1 *ccw;
struct pfn_array_table *pat;
unsigned long *idaws;
- int idaw_nr;
+ int ret;
ccw = chain->ch_ccw + idx;
* needed when translating a direct ccw to a idal ccw.
*/
pat = chain->ch_pat + idx;
- if (pfn_array_table_init(pat, 1))
- return -ENOMEM;
- idaw_nr = pfn_array_alloc_pin(pat->pat_pa, cp->mdev,
- ccw->cda, ccw->count);
- if (idaw_nr < 0)
- return idaw_nr;
+ ret = pfn_array_table_init(pat, 1);
+ if (ret)
+ goto out_init;
+
+ ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count);
+ if (ret < 0)
+ goto out_init;
/* Translate this direct ccw to a idal ccw. */
- idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
+ idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
if (!idaws) {
- pfn_array_table_unpin_free(pat, cp->mdev);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_unpin;
}
ccw->cda = (__u32) virt_to_phys(idaws);
ccw->flags |= CCW_FLAG_IDA;
pfn_array_table_idal_create_words(pat, idaws);
return 0;
+
+out_unpin:
+ pfn_array_table_unpin_free(pat, cp->mdev);
+out_init:
+ ccw->cda = 0;
+ return ret;
}
static int ccwchain_fetch_idal(struct ccwchain *chain,
pat = chain->ch_pat + idx;
ret = pfn_array_table_init(pat, idaw_nr);
if (ret)
- return ret;
+ goto out_init;
/* Translate idal ccw to use new allocated idaws. */
idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL);
kfree(idaws);
out_unpin:
pfn_array_table_unpin_free(pat, cp->mdev);
+out_init:
+ ccw->cda = 0;
return ret;
}
/*
* XXX:
* Only support prefetch enable mode now.
- * Only support 64bit addressing idal.
- * Only support 4k IDAW.
*/
- if (!orb->cmd.pfch || !orb->cmd.c64 || orb->cmd.i2k)
+ if (!orb->cmd.pfch)
return -EOPNOTSUPP;
INIT_LIST_HEAD(&cp->ccwchain_list);
ret = ccwchain_loop_tic(chain, cp);
if (ret)
cp_unpin_free(cp);
+ /* It is safe to force: if not set but idals used
+ * ccwchain_calc_length returns an error.
+ */
+ cp->orb.cmd.c64 = 1;
return ret;
}
{
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
unsigned long flags;
+ int rc = -EAGAIN;
spin_lock_irqsave(sch->lock, flags);
if (!device_is_registered(&sch->dev))
if (cio_update_schib(sch)) {
vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+ rc = 0;
goto out_unlock;
}
private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
VFIO_CCW_STATE_STANDBY;
}
+ rc = 0;
out_unlock:
spin_unlock_irqrestore(sch->lock, flags);
- return 0;
+ return rc;
}
static struct css_device_id vfio_ccw_sch_ids[] = {
#include "ioasm.h"
#include "vfio_ccw_private.h"
+#define CREATE_TRACE_POINTS
+#include "vfio_ccw_trace.h"
+
static int fsm_io_helper(struct vfio_ccw_private *private)
{
struct subchannel *sch;
*/
cio_disable_subchannel(sch);
}
+inline struct subchannel_id get_schid(struct vfio_ccw_private *p)
+{
+ return p->sch->schid;
+}
/*
* Deal with the ccw command request from the userspace.
union scsw *scsw = &private->scsw;
struct ccw_io_region *io_region = &private->io_region;
struct mdev_device *mdev = private->mdev;
+ char *errstr = "request";
private->state = VFIO_CCW_STATE_BOXED;
/* Don't try to build a cp if transport mode is specified. */
if (orb->tm.b) {
io_region->ret_code = -EOPNOTSUPP;
+ errstr = "transport mode";
goto err_out;
}
io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
orb);
- if (io_region->ret_code)
+ if (io_region->ret_code) {
+ errstr = "cp init";
goto err_out;
+ }
io_region->ret_code = cp_prefetch(&private->cp);
if (io_region->ret_code) {
+ errstr = "cp prefetch";
cp_free(&private->cp);
goto err_out;
}
/* Start channel program and wait for I/O interrupt. */
io_region->ret_code = fsm_io_helper(private);
if (io_region->ret_code) {
+ errstr = "cp fsm_io_helper";
cp_free(&private->cp);
goto err_out;
}
err_out:
private->state = VFIO_CCW_STATE_IDLE;
+ trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private),
+ io_region->ret_code, errstr);
}
/*
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * Tracepoints for vfio_ccw driver
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ * Halil Pasic <pasic@linux.vnet.ibm.com>
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vfio_ccw
+
+#if !defined(_VFIO_CCW_TRACE_) || defined(TRACE_HEADER_MULTI_READ)
+#define _VFIO_CCW_TRACE_
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(vfio_ccw_io_fctl,
+ TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr),
+ TP_ARGS(fctl, schid, errno, errstr),
+
+ TP_STRUCT__entry(
+ __field(int, fctl)
+ __field_struct(struct subchannel_id, schid)
+ __field(int, errno)
+ __field(char*, errstr)
+ ),
+
+ TP_fast_assign(
+ __entry->fctl = fctl;
+ __entry->schid = schid;
+ __entry->errno = errno;
+ __entry->errstr = errstr;
+ ),
+
+ TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s",
+ __entry->schid.cssid,
+ __entry->schid.ssid,
+ __entry->schid.sch_no,
+ __entry->fctl,
+ __entry->errno,
+ __entry->errstr)
+);
+
+#endif /* _VFIO_CCW_TRACE_ */
+
+/* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE vfio_ccw_trace
+
+#include <trace/define_trace.h>
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * Adjunct processor bus inline assemblies.
- */
-
-#ifndef _AP_ASM_H_
-#define _AP_ASM_H_
-
-#include <asm/isc.h>
-
-/**
- * ap_intructions_available() - Test if AP instructions are available.
- *
- * Returns 0 if the AP instructions are installed.
- */
-static inline int ap_instructions_available(void)
-{
- register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
- register unsigned long reg1 asm ("1") = -ENODEV;
- register unsigned long reg2 asm ("2") = 0UL;
-
- asm volatile(
- " .long 0xb2af0000\n" /* PQAP(TAPQ) */
- "0: la %1,0\n"
- "1:\n"
- EX_TABLE(0b, 1b)
- : "+d" (reg0), "+d" (reg1), "+d" (reg2) : : "cc");
- return reg1;
-}
-
-/**
- * ap_tapq(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
-{
- register unsigned long reg0 asm ("0") = qid;
- register struct ap_queue_status reg1 asm ("1");
- register unsigned long reg2 asm ("2") = 0UL;
-
- asm volatile(".long 0xb2af0000" /* PQAP(TAPQ) */
- : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
- if (info)
- *info = reg2;
- return reg1;
-}
-
-/**
- * ap_pqap_rapq(): Reset adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
-{
- register unsigned long reg0 asm ("0") = qid | 0x01000000UL;
- register struct ap_queue_status reg1 asm ("1");
- register unsigned long reg2 asm ("2") = 0UL;
-
- asm volatile(
- ".long 0xb2af0000" /* PQAP(RAPQ) */
- : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
- return reg1;
-}
-
-/**
- * ap_aqic(): Control interruption for a specific AP.
- * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- */
-static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
- struct ap_qirq_ctrl qirqctrl,
- void *ind)
-{
- register unsigned long reg0 asm ("0") = qid | (3UL << 24);
- register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
- register struct ap_queue_status reg1_out asm ("1");
- register void *reg2 asm ("2") = ind;
-
- asm volatile(
- ".long 0xb2af0000" /* PQAP(AQIC) */
- : "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
- :
- : "cc");
- return reg1_out;
-}
-
-/**
- * ap_qci(): Get AP configuration data
- *
- * Returns 0 on success, or -EOPNOTSUPP.
- */
-static inline int ap_qci(void *config)
-{
- register unsigned long reg0 asm ("0") = 0x04000000UL;
- register unsigned long reg1 asm ("1") = -EINVAL;
- register void *reg2 asm ("2") = (void *) config;
-
- asm volatile(
- ".long 0xb2af0000\n" /* PQAP(QCI) */
- "0: la %1,0\n"
- "1:\n"
- EX_TABLE(0b, 1b)
- : "+d" (reg0), "+d" (reg1), "+d" (reg2)
- :
- : "cc", "memory");
-
- return reg1;
-}
-
-/*
- * union ap_qact_ap_info - used together with the
- * ap_aqic() function to provide a convenient way
- * to handle the ap info needed by the qact function.
- */
-union ap_qact_ap_info {
- unsigned long val;
- struct {
- unsigned int : 3;
- unsigned int mode : 3;
- unsigned int : 26;
- unsigned int cat : 8;
- unsigned int : 8;
- unsigned char ver[2];
- };
-};
-
-/**
- * ap_qact(): Query AP combatibility type.
- * @qid: The AP queue number
- * @apinfo: On input the info about the AP queue. On output the
- * alternate AP queue info provided by the qact function
- * in GR2 is stored in.
- *
- * Returns AP queue status. Check response_code field for failures.
- */
-static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
- union ap_qact_ap_info *apinfo)
-{
- register unsigned long reg0 asm ("0") = qid | (5UL << 24)
- | ((ifbit & 0x01) << 22);
- register unsigned long reg1_in asm ("1") = apinfo->val;
- register struct ap_queue_status reg1_out asm ("1");
- register unsigned long reg2 asm ("2") = 0;
-
- asm volatile(
- ".long 0xb2af0000" /* PQAP(QACT) */
- : "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
- : : "cc");
- apinfo->val = reg2;
- return reg1_out;
-}
-
-/**
- * ap_nqap(): Send message to adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: The program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on NQAP can't happen because the L bit is 1.
- * Condition code 2 on NQAP also means the send is incomplete,
- * because a segment boundary was reached. The NQAP is repeated.
- */
-static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
- unsigned long long psmid,
- void *msg, size_t length)
-{
- register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
- register struct ap_queue_status reg1 asm ("1");
- register unsigned long reg2 asm ("2") = (unsigned long) msg;
- register unsigned long reg3 asm ("3") = (unsigned long) length;
- register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
- register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
- asm volatile (
- "0: .long 0xb2ad0042\n" /* NQAP */
- " brc 2,0b"
- : "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
- : "d" (reg4), "d" (reg5)
- : "cc", "memory");
- return reg1;
-}
-
-/**
- * ap_dqap(): Receive message from adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on DQAP means the receive has taken place
- * but only partially. The response is incomplete, hence the
- * DQAP is repeated.
- * Condition code 2 on DQAP also means the receive is incomplete,
- * this time because a segment boundary was reached. Again, the
- * DQAP is repeated.
- * Note that gpr2 is used by the DQAP instruction to keep track of
- * any 'residual' length, in case the instruction gets interrupted.
- * Hence it gets zeroed before the instruction.
- */
-static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
- unsigned long long *psmid,
- void *msg, size_t length)
-{
- register unsigned long reg0 asm("0") = qid | 0x80000000UL;
- register struct ap_queue_status reg1 asm ("1");
- register unsigned long reg2 asm("2") = 0UL;
- register unsigned long reg4 asm("4") = (unsigned long) msg;
- register unsigned long reg5 asm("5") = (unsigned long) length;
- register unsigned long reg6 asm("6") = 0UL;
- register unsigned long reg7 asm("7") = 0UL;
-
-
- asm volatile(
- "0: .long 0xb2ae0064\n" /* DQAP */
- " brc 6,0b\n"
- : "+d" (reg0), "=d" (reg1), "+d" (reg2),
- "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
- : : "cc", "memory");
- *psmid = (((unsigned long long) reg6) << 32) + reg7;
- return reg1;
-}
-
-#endif /* _AP_ASM_H_ */
#include <linux/debugfs.h>
#include "ap_bus.h"
-#include "ap_asm.h"
#include "ap_debug.h"
/*
return 0;
}
-/**
- * ap_test_queue(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
- int tbit,
- unsigned long *info)
-{
- if (tbit)
- qid |= 1UL << 23; /* set T bit*/
- return ap_tapq(qid, info);
-}
-EXPORT_SYMBOL(ap_test_queue);
-
/*
* ap_query_configuration(): Fetch cryptographic config info
*
* is returned, e.g. if the PQAP(QCI) instruction is not
* available, the return value will be -EOPNOTSUPP.
*/
-int ap_query_configuration(struct ap_config_info *info)
+static inline int ap_query_configuration(struct ap_config_info *info)
{
if (!ap_configuration_available())
return -EOPNOTSUPP;
return 0;
mutex_lock(&ap_poll_thread_mutex);
ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
- rc = PTR_RET(ap_poll_kthread);
+ rc = PTR_ERR_OR_ZERO(ap_poll_kthread);
if (rc)
ap_poll_kthread = NULL;
mutex_unlock(&ap_poll_thread_mutex);
/* Create /sys/devices/ap. */
ap_root_device = root_device_register("ap");
- rc = PTR_RET(ap_root_device);
+ rc = PTR_ERR_OR_ZERO(ap_root_device);
if (rc)
goto out_bus;
#include <linux/device.h>
#include <linux/types.h>
+#include <asm/isc.h>
#include <asm/ap.h>
#define AP_DEVICES 256 /* Number of AP devices. */
#include <asm/facility.h>
#include "ap_bus.h"
-#include "ap_asm.h"
/*
* AP card related attributes.
#include <asm/facility.h>
#include "ap_bus.h"
-#include "ap_asm.h"
-
-/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
- */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
- struct ap_qirq_ctrl qirqctrl,
- void *ind)
-{
- return ap_aqic(qid, qirqctrl, ind);
-}
-EXPORT_SYMBOL(ap_queue_irq_ctrl);
/**
* ap_queue_enable_interruption(): Enable interruption on an AP queue.
/* fill request cprb param block with FQ request */
preqparm = (struct fqreqparm *) preqcblk->req_parmb;
memcpy(preqparm->subfunc_code, "FQ", 2);
- strncpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
+ memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
preqparm->rule_array_len =
sizeof(preqparm->rule_array_len) + sizeof(preqparm->rule_array);
preqparm->lv1.len = sizeof(preqparm->lv1);
static DEVICE_ATTR(online, 0644, zcrypt_card_online_show,
zcrypt_card_online_store);
+static ssize_t zcrypt_card_load_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct zcrypt_card *zc = to_ap_card(dev)->private;
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_card_load_show, NULL);
+
static struct attribute *zcrypt_card_attrs[] = {
&dev_attr_type.attr,
&dev_attr_online.attr,
+ &dev_attr_load.attr,
NULL,
};
* @mex: pointer to user input data
* @p: pointer to memory area for the key
*
- * Returns the size of the key area or -EFAULT
+ * Returns the size of the key area or negative errno value.
*/
static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
{
unsigned char *temp;
int i;
+ /*
+ * The inputdatalength was a selection criteria in the dispatching
+ * function zcrypt_rsa_modexpo(). However, do a plausibility check
+ * here to make sure the following copy_from_user() can't be utilized
+ * to compromise the system.
+ */
+ if (WARN_ON_ONCE(mex->inputdatalength > 512))
+ return -EINVAL;
+
memset(key, 0, sizeof(*key));
key->pubHdr = static_pub_hdr;
struct cca_public_sec *pub;
int short_len, long_len, pad_len, key_len, size;
+ /*
+ * The inputdatalength was a selection criteria in the dispatching
+ * function zcrypt_rsa_crt(). However, do a plausibility check
+ * here to make sure the following copy_from_user() can't be utilized
+ * to compromise the system.
+ */
+ if (WARN_ON_ONCE(crt->inputdatalength > 512))
+ return -EINVAL;
+
memset(key, 0, sizeof(*key));
short_len = (crt->inputdatalength + 1) / 2;
* @ap_msg: pointer to AP message
* @mex: pointer to user input data
*
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
*/
static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
struct ap_message *ap_msg,
} __packed * msg = ap_msg->message;
int size;
+ /*
+ * The inputdatalength was a selection criteria in the dispatching
+ * function zcrypt_rsa_modexpo(). However, make sure the following
+ * copy_from_user() never exceeds the allocated buffer space.
+ */
+ if (WARN_ON_ONCE(mex->inputdatalength > PAGE_SIZE))
+ return -EINVAL;
+
/* VUD.ciphertext */
msg->length = mex->inputdatalength + 2;
if (copy_from_user(msg->text, mex->inputdata, mex->inputdatalength))
* @ap_msg: pointer to AP message
* @crt: pointer to user input data
*
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
*/
static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
struct ap_message *ap_msg,
} __packed * msg = ap_msg->message;
int size;
+ /*
+ * The inputdatalength was a selection criteria in the dispatching
+ * function zcrypt_rsa_crt(). However, make sure the following
+ * copy_from_user() never exceeds the allocated buffer space.
+ */
+ if (WARN_ON_ONCE(crt->inputdatalength > PAGE_SIZE))
+ return -EINVAL;
+
/* VUD.ciphertext */
msg->length = crt->inputdatalength + 2;
if (copy_from_user(msg->text, crt->inputdata, crt->inputdatalength))
static DEVICE_ATTR(online, 0644, zcrypt_queue_online_show,
zcrypt_queue_online_store);
+static ssize_t zcrypt_queue_load_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_queue_load_show, NULL);
+
static struct attribute *zcrypt_queue_attrs[] = {
&dev_attr_online.attr,
+ &dev_attr_load.attr,
NULL,
};
/*some helper functions*/
#define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+ unsigned int elements)
+{
+ unsigned int i;
+
+ for (i = 0; i < elements; i++)
+ memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+ buf->element[14].sflags = 0;
+ buf->element[15].sflags = 0;
+}
+
/**
* qeth_get_elements_for_range() - find number of SBALEs to cover range.
* @start: Start of the address range.
__u16, __u16,
enum qeth_prot_versions);
int qeth_set_features(struct net_device *, netdev_features_t);
-void qeth_recover_features(struct net_device *dev);
+void qeth_enable_hw_features(struct net_device *dev);
netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
netdev_features_t qeth_features_check(struct sk_buff *skb,
struct net_device *dev,
struct qeth_qdio_out_buffer *buf,
enum iucv_tx_notify notification);
static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
- struct qeth_qdio_out_buffer *buf,
- enum qeth_qdio_buffer_states newbufstate);
static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
struct workqueue_struct *qeth_wq;
struct qaob *aob;
struct qeth_qdio_out_buffer *buffer;
enum iucv_tx_notify notification;
+ unsigned int i;
aob = (struct qaob *) phys_to_virt(phys_aob_addr);
QETH_CARD_TEXT(card, 5, "haob");
qeth_notify_skbs(buffer->q, buffer, notification);
buffer->aob = NULL;
- qeth_clear_output_buffer(buffer->q, buffer,
- QETH_QDIO_BUF_HANDLED_DELAYED);
+ /* Free dangling allocations. The attached skbs are handled by
+ * qeth_cleanup_handled_pending().
+ */
+ for (i = 0;
+ i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+ i++) {
+ if (aob->sba[i] && buffer->is_header[i])
+ kmem_cache_free(qeth_core_header_cache,
+ (void *) aob->sba[i]);
+ }
+ atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
- /* from here on: do not touch buffer anymore */
qdio_release_aob(aob);
}
QETH_CARD_TEXT(queue->card, 5, "aob");
QETH_CARD_TEXT_(queue->card, 5, "%lx",
virt_to_phys(buffer->aob));
+
+ /* prepare the queue slot for re-use: */
+ qeth_scrub_qdio_buffer(buffer->buffer,
+ QETH_MAX_BUFFER_ELEMENTS(card));
if (qeth_init_qdio_out_buf(queue, bidx)) {
QETH_CARD_TEXT(card, 2, "outofbuf");
qeth_schedule_recovery(card);
goto out;
}
- ccw_device_get_id(CARD_RDEV(card), &id);
+ ccw_device_get_id(CARD_DDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
NETIF_F_IPV6_CSUM)
/**
- * qeth_recover_features() - Restore device features after recovery
- * @dev: the recovering net_device
- *
- * Caller must hold rtnl lock.
+ * qeth_enable_hw_features() - (Re-)Enable HW functions for device features
+ * @dev: a net_device
*/
-void qeth_recover_features(struct net_device *dev)
+void qeth_enable_hw_features(struct net_device *dev)
{
- netdev_features_t features = dev->features;
struct qeth_card *card = dev->ml_priv;
+ netdev_features_t features;
+ rtnl_lock();
+ features = dev->features;
/* force-off any feature that needs an IPA sequence.
* netdev_update_features() will restart them.
*/
dev->features &= ~QETH_HW_FEATURES;
netdev_update_features(dev);
-
- if (features == dev->features)
- return;
- dev_warn(&card->gdev->dev,
- "Device recovery failed to restore all offload features\n");
+ if (features != dev->features)
+ dev_warn(&card->gdev->dev,
+ "Device recovery failed to restore all offload features\n");
+ rtnl_unlock();
}
-EXPORT_SYMBOL_GPL(qeth_recover_features);
+EXPORT_SYMBOL_GPL(qeth_enable_hw_features);
int qeth_set_features(struct net_device *dev, netdev_features_t features)
{
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
int rc;
static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
int rc;
return -ERESTARTSYS;
}
+ /* avoid racing against concurrent state change: */
+ if (!mutex_trylock(&card->conf_mutex))
+ return -EAGAIN;
+
if (!qeth_card_hw_is_reachable(card)) {
ether_addr_copy(dev->dev_addr, addr->sa_data);
- return 0;
+ goto out_unlock;
}
/* don't register the same address twice */
if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
+ goto out_unlock;
/* add the new address, switch over, drop the old */
rc = qeth_l2_send_setmac(card, addr->sa_data);
if (rc)
- return rc;
+ goto out_unlock;
ether_addr_copy(old_addr, dev->dev_addr);
ether_addr_copy(dev->dev_addr, addr->sa_data);
if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
qeth_l2_remove_mac(card, old_addr);
card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- return 0;
+
+out_unlock:
+ mutex_unlock(&card->conf_mutex);
+ return rc;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
netif_carrier_off(card->dev);
qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
if (recovery_mode &&
card->info.type != QETH_CARD_TYPE_OSN) {
}
/* this also sets saved unicast addresses */
qeth_l2_set_rx_mode(card->dev);
- rtnl_lock();
- qeth_recover_features(card->dev);
- rtnl_unlock();
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
netif_carrier_on(card->dev);
else
netif_carrier_off(card->dev);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
rtnl_lock();
if (recovery_mode)
else
dev_open(card->dev);
qeth_l3_set_rx_mode(card->dev);
- qeth_recover_features(card->dev);
rtnl_unlock();
}
qeth_trace_features(card);
token = strsep(&str, ",");
if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
goto err_out;
- strncpy(busid, token, ZFCP_BUS_ID_SIZE);
+ strlcpy(busid, token, ZFCP_BUS_ID_SIZE);
token = strsep(&str, ",");
if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn))
* the recommended way for applications to use the coprocessor, and
* the driver interface is not intended for general use.
*
- * See Documentation/sparc/oradax/oracle_dax.txt for more details.
+ * See Documentation/sparc/oradax/oracle-dax.txt for more details.
*/
#include <linux/uaccess.h>
u32 lun_count, nexus;
u32 i, bus, target;
u8 expose_flag, attribs;
- u8 devtype;
lun_count = aac_get_safw_phys_lun_count(dev);
continue;
if (expose_flag != 0) {
- devtype = AAC_DEVTYPE_RAID_MEMBER;
- goto update_devtype;
+ dev->hba_map[bus][target].devtype =
+ AAC_DEVTYPE_RAID_MEMBER;
+ continue;
}
if (nexus != 0 && (attribs & 8)) {
- devtype = AAC_DEVTYPE_NATIVE_RAW;
+ dev->hba_map[bus][target].devtype =
+ AAC_DEVTYPE_NATIVE_RAW;
dev->hba_map[bus][target].rmw_nexus =
nexus;
} else
- devtype = AAC_DEVTYPE_ARC_RAW;
+ dev->hba_map[bus][target].devtype =
+ AAC_DEVTYPE_ARC_RAW;
dev->hba_map[bus][target].scan_counter = dev->scan_counter;
aac_set_safw_target_qd(dev, bus, target);
-
-update_devtype:
- dev->hba_map[bus][target].devtype = devtype;
}
}
{
const struct cxlflash_backend_ops *ops = NULL;
-#ifdef CONFIG_OCXL
+#ifdef CONFIG_OCXL_BASE
if (ddv->flags & CXLFLASH_OCXL_DEV)
ops = &cxlflash_ocxl_ops;
#endif
-#ifdef CONFIG_CXL
+#ifdef CONFIG_CXL_BASE
if (!(ddv->flags & CXLFLASH_OCXL_DEV))
ops = &cxlflash_cxl_ops;
#endif
const struct file_operations *fops,
void *priv, int flags)
{
- struct qstr this;
- struct path path;
struct file *file;
- struct inode *inode = NULL;
+ struct inode *inode;
int rc;
if (fops->owner && !try_module_get(fops->owner)) {
goto err3;
}
- this.name = name;
- this.len = strlen(name);
- this.hash = 0;
- path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
- if (!path.dentry) {
- dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
- rc = -ENOMEM;
- goto err4;
- }
-
- path.mnt = mntget(ocxlflash_vfs_mount);
- d_instantiate(path.dentry, inode);
-
- file = alloc_file(&path, OPEN_FMODE(flags), fops);
+ file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+ flags & (O_ACCMODE | O_NONBLOCK), fops);
if (IS_ERR(file)) {
rc = PTR_ERR(file);
dev_err(dev, "%s: alloc_file failed rc=%d\n",
__func__, rc);
- goto err5;
+ goto err4;
}
- file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
file->private_data = priv;
out:
return file;
-err5:
- path_put(&path);
err4:
iput(inode);
err3:
case ELS_LOGO:
if (fip->mode == FIP_MODE_VN2VN) {
if (fip->state != FIP_ST_VNMP_UP)
- return -EINVAL;
+ goto drop;
if (ntoh24(fh->fh_d_id) == FC_FID_FLOGI)
- return -EINVAL;
+ goto drop;
} else {
if (fip->state != FIP_ST_ENABLED)
return 0;
fip->send(fip, skb);
return -EINPROGRESS;
drop:
- kfree_skb(skb);
LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n",
op, ntoh24(fh->fh_d_id));
+ kfree_skb(skb);
return -EINVAL;
}
EXPORT_SYMBOL(fcoe_ctlr_els_send);
struct ext_report_lun_entry *rle = &rlep->LUN[rle_index];
u16 bmic_device_index = 0;
- bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
-
- encl_dev->sas_address =
+ encl_dev->eli =
hpsa_get_enclosure_logical_identifier(h, scsi3addr);
+ bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
+
if (encl_dev->target == -1 || encl_dev->lun == -1) {
rc = IO_OK;
goto out;
static int
hpsa_sas_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
{
- *identifier = rphy->identify.sas_address;
+ struct Scsi_Host *shost = phy_to_shost(rphy);
+ struct ctlr_info *h;
+ struct hpsa_scsi_dev_t *sd;
+
+ if (!shost)
+ return -ENXIO;
+
+ h = shost_to_hba(shost);
+
+ if (!h)
+ return -ENXIO;
+
+ sd = hpsa_find_device_by_sas_rphy(h, rphy);
+ if (!sd)
+ return -ENXIO;
+
+ *identifier = sd->eli;
+
return 0;
}
#define RAID_CTLR_LUNID "\0\0\0\0\0\0\0\0"
unsigned char device_id[16]; /* from inquiry pg. 0x83 */
u64 sas_address;
+ u64 eli; /* from report diags. */
unsigned char vendor[8]; /* bytes 8-15 of inquiry data */
unsigned char model[16]; /* bytes 16-31 of inquiry data */
unsigned char rev; /* byte 2 of inquiry data */
ioa_cfg->hrrq[i].allow_interrupts = 0;
spin_unlock(&ioa_cfg->hrrq[i]._lock);
}
- wmb();
/* Set interrupt mask to stop all new interrupts */
if (ioa_cfg->sis64)
ioa_cfg->hrrq[i].allow_interrupts = 1;
spin_unlock(&ioa_cfg->hrrq[i]._lock);
}
- wmb();
if (ioa_cfg->sis64) {
/* Set the adapter to the correct endian mode. */
writel(IPR_ENDIAN_SWAP_KEY, ioa_cfg->regs.endian_swap_reg);
FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
fc_rport_state(rdata));
+ rdata->flags &= ~FC_RP_STARTED;
fc_rport_enter_delete(rdata, RPORT_EV_STOP);
mutex_unlock(&rdata->rp_mutex);
kref_put(&rdata->kref, fc_rport_destroy);
*/
if (opcode != ISCSI_OP_SCSI_DATA_OUT) {
iscsi_conn_printk(KERN_INFO, conn,
- "task [op %x/%x itt "
+ "task [op %x itt "
"0x%x/0x%x] "
"rejected.\n",
- task->hdr->opcode, opcode,
- task->itt, task->hdr_itt);
+ opcode, task->itt,
+ task->hdr_itt);
return -EACCES;
}
/*
*/
if (conn->session->fast_abort) {
iscsi_conn_printk(KERN_INFO, conn,
- "task [op %x/%x itt "
+ "task [op %x itt "
"0x%x/0x%x] fast abort.\n",
- task->hdr->opcode, opcode,
- task->itt, task->hdr_itt);
+ opcode, task->itt,
+ task->hdr_itt);
return -EACCES;
}
break;
spinlock_t *writeq_lock)
{
unsigned long flags;
- __u64 data_out = b;
spin_lock_irqsave(writeq_lock, flags);
- writel((u32)(data_out), addr);
- writel((u32)(data_out >> 32), (addr + 4));
+ __raw_writel((u32)(b), addr);
+ __raw_writel((u32)(b >> 32), (addr + 4));
mmiowb();
spin_unlock_irqrestore(writeq_lock, flags);
}
static inline void
_base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
{
- writeq(b, addr);
+ __raw_writeq(b, addr);
+ mmiowb();
}
#else
static inline void
/* send message 32-bits at a time */
for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) {
- writel((u32)(request[i]), &ioc->chip->Doorbell);
+ writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell);
if ((_base_wait_for_doorbell_ack(ioc, 5)))
failed = 1;
}
}
/* read the first two 16-bits, it gives the total length of the reply */
- reply[0] = (u16)(readl(&ioc->chip->Doorbell)
+ reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell)
& MPI2_DOORBELL_DATA_MASK);
writel(0, &ioc->chip->HostInterruptStatus);
if ((_base_wait_for_doorbell_int(ioc, 5))) {
ioc->name, __LINE__);
return -EFAULT;
}
- reply[1] = (u16)(readl(&ioc->chip->Doorbell)
+ reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell)
& MPI2_DOORBELL_DATA_MASK);
writel(0, &ioc->chip->HostInterruptStatus);
if (i >= reply_bytes/2) /* overflow case */
readl(&ioc->chip->Doorbell);
else
- reply[i] = (u16)(readl(&ioc->chip->Doorbell)
+ reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell)
& MPI2_DOORBELL_DATA_MASK);
writel(0, &ioc->chip->HostInterruptStatus);
}
init_completion(&qedf->flogi_compl);
+ status = qed_ops->common->update_drv_state(qedf->cdev, true);
+ if (status)
+ QEDF_ERR(&(qedf->dbg_ctx),
+ "Failed to send drv state to MFW.\n");
+
memset(&link_params, 0, sizeof(struct qed_link_params));
link_params.link_up = true;
status = qed_ops->common->set_link(qedf->cdev, &link_params);
static void __qedf_remove(struct pci_dev *pdev, int mode)
{
struct qedf_ctx *qedf;
+ int rc;
if (!pdev) {
QEDF_ERR(NULL, "pdev is NULL.\n");
qed_ops->common->set_power_state(qedf->cdev, PCI_D0);
pci_set_drvdata(pdev, NULL);
}
+
+ rc = qed_ops->common->update_drv_state(qedf->cdev, false);
+ if (rc)
+ QEDF_ERR(&(qedf->dbg_ctx),
+ "Failed to send drv state to MFW.\n");
+
qed_ops->common->slowpath_stop(qedf->cdev);
qed_ops->common->remove(qedf->cdev);
ipv6_en = !!(block->generic.ctrl_flags &
NVM_ISCSI_CFG_GEN_IPV6_ENABLED);
- snprintf(tgt->iscsi_name, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n",
+ snprintf(tgt->iscsi_name, sizeof(tgt->iscsi_name), "%s\n",
block->target[index].target_name.byte);
tgt->ipv6_en = ipv6_en;
static void __qedi_remove(struct pci_dev *pdev, int mode)
{
struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+ int rval;
if (qedi->tmf_thread) {
flush_workqueue(qedi->tmf_thread);
if (mode == QEDI_MODE_NORMAL)
qedi_free_iscsi_pf_param(qedi);
+ rval = qedi_ops->common->update_drv_state(qedi->cdev, false);
+ if (rval)
+ QEDI_ERR(&qedi->dbg_ctx, "Failed to send drv state to MFW\n");
+
if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
qedi_ops->common->slowpath_stop(qedi->cdev);
qedi_ops->common->remove(qedi->cdev);
if (qedi_setup_boot_info(qedi))
QEDI_ERR(&qedi->dbg_ctx,
"No iSCSI boot target configured\n");
+
+ rc = qedi_ops->common->update_drv_state(qedi->cdev, true);
+ if (rc)
+ QEDI_ERR(&qedi->dbg_ctx,
+ "Failed to send drv state to MFW\n");
+
}
return 0;
msleep(1000);
qla24xx_disable_vp(vha);
+ qla2x00_wait_for_sess_deletion(vha);
vha->flags.delete_progress = 1;
dma_addr_t rsp_dma;
u32 req_size;
u32 rsp_size;
+ u32 req_allocated_size;
+ u32 rsp_allocated_size;
void *req;
void *rsp;
port_id_t id;
int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
int qla24xx_async_abort_cmd(srb_t *);
int qla24xx_post_relogin_work(struct scsi_qla_host *vha);
+void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *);
/*
* Global Functions in qla_mid.c source file.
/* please ignore kernel warning. otherwise, we have mem leak. */
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xd041,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xd042,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xd041,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xd042,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xd041,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xd042,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xd041,
"%s: Failed to allocate ct_sns request.\n",
sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xd042,
"%s: Failed to allocate ct_sns request.\n",
{
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
/* please ignore kernel warning. otherwise, we have mem leak. */
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xd041,
"Failed to allocate ct_sns request.\n");
sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xd042,
"Failed to allocate ct_sns request.\n");
return rval;
done_free_sp:
+ spin_lock_irqsave(&vha->hw->vport_slock, flags);
+ list_del(&sp->elem);
+ spin_unlock_irqrestore(&vha->hw->vport_slock, flags);
+
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
sizeof(struct ct_sns_pkt),
*/
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
/* please ignore kernel warning. Otherwise, we have mem leak. */
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
done_free_sp:
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
sp->u.iocb_cmd.u.ctarg.req = dma_zalloc_coherent(
&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt),
&sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.req) {
ql_log(ql_log_warn, vha, 0xffff,
"Failed to allocate ct_sns request.\n");
sp->u.iocb_cmd.u.ctarg.rsp = dma_zalloc_coherent(
&vha->hw->pdev->dev, rspsz,
&sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
if (!sp->u.iocb_cmd.u.ctarg.rsp) {
ql_log(ql_log_warn, vha, 0xffff,
"Failed to allocate ct_sns request.\n");
done_free_sp:
if (sp->u.iocb_cmd.u.ctarg.req) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
sp->u.iocb_cmd.u.ctarg.req,
sp->u.iocb_cmd.u.ctarg.req_dma);
sp->u.iocb_cmd.u.ctarg.req = NULL;
}
if (sp->u.iocb_cmd.u.ctarg.rsp) {
dma_free_coherent(&vha->hw->pdev->dev,
- sizeof(struct ct_sns_pkt),
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
sp->u.iocb_cmd.u.ctarg.rsp,
sp->u.iocb_cmd.u.ctarg.rsp_dma);
sp->u.iocb_cmd.u.ctarg.rsp = NULL;
conflict_fcport =
qla2x00_find_fcport_by_wwpn(vha,
e->port_name, 0);
- ql_dbg(ql_dbg_disc, vha, 0x20e6,
- "%s %d %8phC post del sess\n",
- __func__, __LINE__,
- conflict_fcport->port_name);
- qlt_schedule_sess_for_deletion
- (conflict_fcport);
+ if (conflict_fcport) {
+ qlt_schedule_sess_for_deletion
+ (conflict_fcport);
+ ql_dbg(ql_dbg_disc, vha, 0x20e6,
+ "%s %d %8phC post del sess\n",
+ __func__, __LINE__,
+ conflict_fcport->port_name);
+ }
}
/* FW already picked this loop id for another fcport */
wait_for_completion(&tm_iocb->u.tmf.comp);
- rval = tm_iocb->u.tmf.comp_status == CS_COMPLETE ?
- QLA_SUCCESS : QLA_FUNCTION_FAILED;
+ rval = tm_iocb->u.tmf.data;
- if ((rval != QLA_SUCCESS) || tm_iocb->u.tmf.data) {
- ql_dbg(ql_dbg_taskm, vha, 0x8030,
+ if (rval != QLA_SUCCESS) {
+ ql_log(ql_log_warn, vha, 0x8030,
"TM IOCB failed (%x).\n", rval);
}
sp->fcport = fcport;
sp->iocbs = 1;
sp->vha = qpair->vha;
+ INIT_LIST_HEAD(&sp->elem);
+
done:
if (!sp)
QLA_QPAIR_MARK_NOT_BUSY(qpair);
req_cnt = 1;
handle = 0;
- if (!sp)
- goto skip_cmd_array;
-
- /* Check for room in outstanding command list. */
- handle = req->current_outstanding_cmd;
- for (index = 1; index < req->num_outstanding_cmds; index++) {
- handle++;
- if (handle == req->num_outstanding_cmds)
- handle = 1;
- if (!req->outstanding_cmds[handle])
- break;
- }
- if (index == req->num_outstanding_cmds) {
- ql_log(ql_log_warn, vha, 0x700b,
- "No room on outstanding cmd array.\n");
- goto queuing_error;
- }
-
- /* Prep command array. */
- req->current_outstanding_cmd = handle;
- req->outstanding_cmds[handle] = sp;
- sp->handle = handle;
-
- /* Adjust entry-counts as needed. */
- if (sp->type != SRB_SCSI_CMD)
+ if (sp && (sp->type != SRB_SCSI_CMD)) {
+ /* Adjust entry-counts as needed. */
req_cnt = sp->iocbs;
+ }
-skip_cmd_array:
/* Check for room on request queue. */
if (req->cnt < req_cnt + 2) {
if (qpair->use_shadow_reg)
if (req->cnt < req_cnt + 2)
goto queuing_error;
+ if (sp) {
+ /* Check for room in outstanding command list. */
+ handle = req->current_outstanding_cmd;
+ for (index = 1; index < req->num_outstanding_cmds; index++) {
+ handle++;
+ if (handle == req->num_outstanding_cmds)
+ handle = 1;
+ if (!req->outstanding_cmds[handle])
+ break;
+ }
+ if (index == req->num_outstanding_cmds) {
+ ql_log(ql_log_warn, vha, 0x700b,
+ "No room on outstanding cmd array.\n");
+ goto queuing_error;
+ }
+
+ /* Prep command array. */
+ req->current_outstanding_cmd = handle;
+ req->outstanding_cmds[handle] = sp;
+ sp->handle = handle;
+ }
+
/* Prep packet */
req->cnt -= req_cnt;
pkt = req->ring_ptr;
pkt->handle = handle;
}
+ return pkt;
+
queuing_error:
qpair->tgt_counters.num_alloc_iocb_failed++;
return pkt;
unsigned long flags;
fc_port_t *fcport = NULL;
+ if (!vha->hw->flags.fw_started)
+ return;
+
/* Setup to process RIO completion. */
handle_cnt = 0;
if (IS_CNA_CAPABLE(ha))
mbx_cmd_t *mcp = &mc;
struct qla_hw_data *ha = vha->hw;
+ if (!ha->flags.fw_started)
+ return QLA_SUCCESS;
+
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3,
"Entered %s.\n", __func__);
mbx_cmd_t *mcp = &mc;
struct qla_hw_data *ha = vha->hw;
+ if (!ha->flags.fw_started)
+ return QLA_SUCCESS;
+
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6,
"Entered %s.\n", __func__);
qla24xx_disable_vp(scsi_qla_host_t *vha)
{
unsigned long flags;
- int ret;
+ int ret = QLA_SUCCESS;
+ fc_port_t *fcport;
+
+ if (vha->hw->flags.fw_started)
+ ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
- ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
atomic_set(&vha->loop_state, LOOP_DOWN);
atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
+ list_for_each_entry(fcport, &vha->vp_fcports, list)
+ fcport->logout_on_delete = 0;
+
+ qla2x00_mark_all_devices_lost(vha, 0);
/* Remove port id from vp target map */
spin_lock_irqsave(&vha->hw->hardware_lock, flags);
static int qla2xxx_map_queues(struct Scsi_Host *shost);
static void qla2x00_destroy_deferred_work(struct qla_hw_data *);
+
struct scsi_host_template qla2xxx_driver_template = {
.module = THIS_MODULE,
.name = QLA2XXX_DRIVER_NAME,
* qla2x00_wait_for_sess_deletion can only be called from remove_one.
* it has dependency on UNLOADING flag to stop device discovery
*/
-static void
+void
qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
{
qla2x00_mark_all_devices_lost(vha, 0);
"req->req_q_in=%p req->req_q_out=%p rsp->rsp_q_in=%p rsp->rsp_q_out=%p.\n",
req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out);
+ ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
+
if (ha->isp_ops->initialize_adapter(base_vha)) {
ql_log(ql_log_fatal, base_vha, 0x00d6,
"Failed to initialize adapter - Adapter flags %x.\n",
host->can_queue, base_vha->req,
base_vha->mgmt_svr_loop_id, host->sg_tablesize);
- ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
-
if (ha->mqenable) {
bool mq = false;
bool startit = false;
base_vha = pci_get_drvdata(pdev);
ha = base_vha->hw;
+ ql_log(ql_log_info, base_vha, 0xb079,
+ "Removing driver\n");
/* Indicate device removal to prevent future board_disable and wait
* until any pending board_disable has completed. */
}
qla2x00_wait_for_hba_ready(base_vha);
+ if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) {
+ if (ha->flags.fw_started)
+ qla2x00_abort_isp_cleanup(base_vha);
+ } else if (!IS_QLAFX00(ha)) {
+ if (IS_QLA8031(ha)) {
+ ql_dbg(ql_dbg_p3p, base_vha, 0xb07e,
+ "Clearing fcoe driver presence.\n");
+ if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS)
+ ql_dbg(ql_dbg_p3p, base_vha, 0xb079,
+ "Error while clearing DRV-Presence.\n");
+ }
+
+ qla2x00_try_to_stop_firmware(base_vha);
+ }
+
qla2x00_wait_for_sess_deletion(base_vha);
/*
qla2x00_delete_all_vps(ha, base_vha);
- if (IS_QLA8031(ha)) {
- ql_dbg(ql_dbg_p3p, base_vha, 0xb07e,
- "Clearing fcoe driver presence.\n");
- if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS)
- ql_dbg(ql_dbg_p3p, base_vha, 0xb079,
- "Error while clearing DRV-Presence.\n");
- }
-
qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16);
qla2x00_dfs_remove(base_vha);
qla2x00_stop_timer(vha);
qla25xx_delete_queues(vha);
-
- if (ha->flags.fce_enabled)
- qla2x00_disable_fce_trace(vha, NULL, NULL);
-
- if (ha->eft)
- qla2x00_disable_eft_trace(vha);
-
- if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) {
- if (ha->flags.fw_started)
- qla2x00_abort_isp_cleanup(vha);
- } else {
- if (ha->flags.fw_started) {
- /* Stop currently executing firmware. */
- qla2x00_try_to_stop_firmware(vha);
- ha->flags.fw_started = 0;
- }
- }
-
vha->flags.online = 0;
/* turn-off interrupts on the card */
set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags);
}
- if (test_and_clear_bit(ISP_ABORT_NEEDED,
- &base_vha->dpc_flags)) {
+ if (test_and_clear_bit
+ (ISP_ABORT_NEEDED, &base_vha->dpc_flags) &&
+ !test_bit(UNLOADING, &base_vha->dpc_flags)) {
ql_dbg(ql_dbg_dpc, base_vha, 0x4007,
"ISP abort scheduled.\n");
if (IS_P3P_TYPE(ha))
return QLA_SUCCESS;
+ if (!ha->flags.fw_started)
+ return QLA_SUCCESS;
+
ha->beacon_blink_led = 0;
if (IS_QLA2031(ha) || IS_QLA27XX(ha))
void qlt_schedule_sess_for_deletion(struct fc_port *sess)
{
struct qla_tgt *tgt = sess->tgt;
- struct qla_hw_data *ha = sess->vha->hw;
unsigned long flags;
if (sess->disc_state == DSC_DELETE_PEND)
return;
}
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (sess->deleted == QLA_SESS_DELETED)
sess->logout_on_delete = 0;
+ spin_lock_irqsave(&sess->vha->work_lock, flags);
if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ spin_unlock_irqrestore(&sess->vha->work_lock, flags);
return;
}
sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ spin_unlock_irqrestore(&sess->vha->work_lock, flags);
sess->disc_state = DSC_DELETE_PEND;
int k = sdebug_add_host;
stop_all_queued();
- free_all_queued();
for (; k; k--)
sdebug_remove_adapter();
+ free_all_queued();
driver_unregister(&sdebug_driverfs_driver);
bus_unregister(&pseudo_lld_bus);
root_device_unregister(pseudo_primary);
rtn = host->hostt->eh_timed_out(scmd);
if (rtn == BLK_EH_DONE) {
+ /*
+ * For blk-mq, we must set the request state to complete now
+ * before sending the request to the scsi error handler. This
+ * will prevent a use-after-free in the event the LLD manages
+ * to complete the request before the error handler finishes
+ * processing this timed out request.
+ *
+ * If the request was already completed, then the LLD beat the
+ * time out handler from transferring the request to the scsi
+ * error handler. In that case we can return immediately as no
+ * further action is required.
+ */
+ if (req->q->mq_ops && !blk_mq_mark_complete(req))
+ return rtn;
if (scsi_abort_command(scmd) != SUCCESS) {
set_host_byte(scmd, DID_TIME_OUT);
scsi_eh_scmd_add(scmd);
/* the blk_end_sync_io() doesn't check the error */
if (inflight)
- blk_mq_complete_request(req);
+ __blk_complete_request(req);
return BLK_EH_DONE;
}
* Check that all zones of the device are equal. The last zone can however
* be smaller. The zone size must also be a power of two number of LBAs.
*
- * Returns the zone size in bytes upon success or an error code upon failure.
+ * Returns the zone size in number of blocks upon success or an error code
+ * upon failure.
*/
static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
{
unsigned char *rec;
unsigned int buf_len;
unsigned int list_length;
- int ret;
+ s64 ret;
u8 same;
/* Get a buffer */
#include <linux/atomic.h>
#include <linux/ratelimit.h>
#include <linux/uio.h>
+#include <linux/cred.h> /* for sg_check_file_access() */
#include "scsi.h"
#include <scsi/scsi_dbg.h>
sdev_prefix_printk(prefix, (sdp)->device, \
(sdp)->disk->disk_name, fmt, ##a)
+/*
+ * The SCSI interfaces that use read() and write() as an asynchronous variant of
+ * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways
+ * to trigger read() and write() calls from various contexts with elevated
+ * privileges. This can lead to kernel memory corruption (e.g. if these
+ * interfaces are called through splice()) and privilege escalation inside
+ * userspace (e.g. if a process with access to such a device passes a file
+ * descriptor to a SUID binary as stdin/stdout/stderr).
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static int sg_check_file_access(struct file *filp, const char *caller)
+{
+ if (filp->f_cred != current_real_cred()) {
+ pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+ caller, task_tgid_vnr(current), current->comm);
+ return -EPERM;
+ }
+ if (uaccess_kernel()) {
+ pr_err_once("%s: process %d (%s) called from kernel context, this is not allowed.\n",
+ caller, task_tgid_vnr(current), current->comm);
+ return -EACCES;
+ }
+ return 0;
+}
+
static int sg_allow_access(struct file *filp, unsigned char *cmd)
{
struct sg_fd *sfp = filp->private_data;
struct sg_header *old_hdr = NULL;
int retval = 0;
+ /*
+ * This could cause a response to be stranded. Close the associated
+ * file descriptor to free up any resources being held.
+ */
+ retval = sg_check_file_access(filp, __func__);
+ if (retval)
+ return retval;
+
if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
return -ENXIO;
SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
struct sg_header old_hdr;
sg_io_hdr_t *hp;
unsigned char cmnd[SG_MAX_CDB_SIZE];
+ int retval;
- if (unlikely(uaccess_kernel()))
- return -EINVAL;
+ retval = sg_check_file_access(filp, __func__);
+ if (retval)
+ return retval;
if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
return -ENXIO;
*
* With scsi-mq enabled, there are a fixed number of preallocated
* requests equal in number to shost->can_queue. If all of the
- * preallocated requests are already in use, then using GFP_ATOMIC with
- * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL
- * will cause blk_get_request() to sleep until an active command
- * completes, freeing up a request. Neither option is ideal, but
- * GFP_KERNEL is the better choice to prevent userspace from getting an
- * unexpected EWOULDBLOCK.
- *
- * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually
- * does not sleep except under memory pressure.
+ * preallocated requests are already in use, then blk_get_request()
+ * will sleep until an active command completes, freeing up a request.
+ * Although waiting in an asynchronous interface is less than ideal, we
+ * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might
+ * not expect an EWOULDBLOCK from this condition.
*/
rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
write_lock_irqsave(&sdp->sfd_lock, iflags);
if (atomic_read(&sdp->detaching)) {
write_unlock_irqrestore(&sdp->sfd_lock, iflags);
+ kfree(sfp);
return ERR_PTR(-ENODEV);
}
list_add_tail(&sfp->sfd_siblings, &sdp->sfds);
static int sr_block_open(struct block_device *bdev, fmode_t mode)
{
struct scsi_cd *cd;
+ struct scsi_device *sdev;
int ret = -ENXIO;
+ cd = scsi_cd_get(bdev->bd_disk);
+ if (!cd)
+ goto out;
+
+ sdev = cd->device;
+ scsi_autopm_get_device(sdev);
check_disk_change(bdev);
mutex_lock(&sr_mutex);
- cd = scsi_cd_get(bdev->bd_disk);
- if (cd) {
- ret = cdrom_open(&cd->cdi, bdev, mode);
- if (ret)
- scsi_cd_put(cd);
- }
+ ret = cdrom_open(&cd->cdi, bdev, mode);
mutex_unlock(&sr_mutex);
+
+ scsi_autopm_put_device(sdev);
+ if (ret)
+ scsi_cd_put(cd);
+
+out:
return ret;
}
if (ret)
goto out;
+ scsi_autopm_get_device(sdev);
+
/*
* Send SCSI addressing ioctls directly to mid level, send other
* ioctls to cdrom/block level.
case SCSI_IOCTL_GET_IDLUN:
case SCSI_IOCTL_GET_BUS_NUMBER:
ret = scsi_ioctl(sdev, cmd, argp);
- goto out;
+ goto put;
}
ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
if (ret != -ENOSYS)
- goto out;
+ goto put;
ret = scsi_ioctl(sdev, cmd, argp);
+put:
+ scsi_autopm_put_device(sdev);
+
out:
mutex_unlock(&sr_mutex);
return ret;
(btstat == BTSTAT_SUCCESS ||
btstat == BTSTAT_LINKED_COMMAND_COMPLETED ||
btstat == BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG)) {
- cmd->result = (DID_OK << 16) | sdstat;
- if (sdstat == SAM_STAT_CHECK_CONDITION && cmd->sense_buffer)
- cmd->result |= (DRIVER_SENSE << 24);
+ if (sdstat == SAM_STAT_COMMAND_TERMINATED) {
+ cmd->result = (DID_RESET << 16);
+ } else {
+ cmd->result = (DID_OK << 16) | sdstat;
+ if (sdstat == SAM_STAT_CHECK_CONDITION &&
+ cmd->sense_buffer)
+ cmd->result |= (DRIVER_SENSE << 24);
+ }
} else
switch (btstat) {
case BTSTAT_SUCCESS:
static int scsifront_sdev_configure(struct scsi_device *sdev)
{
struct vscsifrnt_info *info = shost_priv(sdev->host);
+ int err;
- if (info && current == info->curr)
- xenbus_printf(XBT_NIL, info->dev->nodename,
+ if (info && current == info->curr) {
+ err = xenbus_printf(XBT_NIL, info->dev->nodename,
info->dev_state_path, "%d", XenbusStateConnected);
+ if (err) {
+ xenbus_dev_error(info->dev, err,
+ "%s: writing dev_state_path", __func__);
+ return err;
+ }
+ }
return 0;
}
static void scsifront_sdev_destroy(struct scsi_device *sdev)
{
struct vscsifrnt_info *info = shost_priv(sdev->host);
+ int err;
- if (info && current == info->curr)
- xenbus_printf(XBT_NIL, info->dev->nodename,
+ if (info && current == info->curr) {
+ err = xenbus_printf(XBT_NIL, info->dev->nodename,
info->dev_state_path, "%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing dev_state_path", __func__);
+ }
}
static struct scsi_host_template scsifront_sht = {
if (scsi_add_device(info->host, chn, tgt, lun)) {
dev_err(&dev->dev, "scsi_add_device\n");
- xenbus_printf(XBT_NIL, dev->nodename,
+ err = xenbus_printf(XBT_NIL, dev->nodename,
info->dev_state_path,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(dev, err,
+ "%s: writing dev_state_path", __func__);
}
break;
case VSCSIFRONT_OP_DEL_LUN:
}
break;
case VSCSIFRONT_OP_READD_LUN:
- if (device_state == XenbusStateConnected)
- xenbus_printf(XBT_NIL, dev->nodename,
+ if (device_state == XenbusStateConnected) {
+ err = xenbus_printf(XBT_NIL, dev->nodename,
info->dev_state_path,
"%d", XenbusStateConnected);
+ if (err)
+ xenbus_dev_error(dev, err,
+ "%s: writing dev_state_path", __func__);
+ }
break;
default:
break;
#define GPC_PGC_SW2ISO_SHIFT 0x8
#define GPC_PGC_SW_SHIFT 0x0
+#define GPC_PGC_PCI_PDN 0x200
+#define GPC_PGC_PCI_SR 0x20c
+
#define GPC_PGC_GPU_PDN 0x260
#define GPC_PGC_GPU_PUPSCR 0x264
#define GPC_PGC_GPU_PDNSCR 0x268
+#define GPC_PGC_GPU_SR 0x26c
+
+#define GPC_PGC_DISP_PDN 0x240
+#define GPC_PGC_DISP_SR 0x24c
#define GPU_VPU_PUP_REQ BIT(1)
#define GPU_VPU_PDN_REQ BIT(0)
{ }
};
+static const struct regmap_range yes_ranges[] = {
+ regmap_reg_range(GPC_CNTR, GPC_CNTR),
+ regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR),
+ regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR),
+ regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR),
+};
+
+static const struct regmap_access_table access_table = {
+ .yes_ranges = yes_ranges,
+ .n_yes_ranges = ARRAY_SIZE(yes_ranges),
+};
+
static const struct regmap_config imx_gpc_regmap_config = {
.reg_bits = 32,
.val_bits = 32,
.reg_stride = 4,
+ .rd_table = &access_table,
+ .wr_table = &access_table,
.max_register = 0x2ac,
};
#define GPC_M4_PU_PDN_FLG 0x1bc
-
-#define PGC_MIPI 4
-#define PGC_PCIE 5
-#define PGC_USB_HSIC 8
+/*
+ * The PGC offset values in Reference Manual
+ * (Rev. 1, 01/2018 and the older ones) GPC chapter's
+ * GPC_PGC memory map are incorrect, below offset
+ * values are from design RTL.
+ */
+#define PGC_MIPI 16
+#define PGC_PCIE 17
+#define PGC_USB_HSIC 20
#define GPC_PGC_CTRL(n) (0x800 + (n) * 0x40)
#define GPC_PGC_SR(n) (GPC_PGC_CTRL(n) + 0xc)
config QCOM_COMMAND_DB
bool "Qualcomm Command DB"
- depends on (ARCH_QCOM && OF) || COMPILE_TEST
+ depends on ARCH_QCOM || COMPILE_TEST
+ depends on OF_RESERVED_MEM
help
Command DB queries shared memory by key string for shared system
resources. Platform drivers that require to set state of a shared
const struct elf32_phdr *phdrs;
const struct elf32_phdr *phdr;
const struct elf32_hdr *ehdr;
- phys_addr_t min_addr = (phys_addr_t)ULLONG_MAX;
+ phys_addr_t min_addr = PHYS_ADDR_MAX;
phys_addr_t max_addr = 0;
int i;
const struct elf32_hdr *ehdr;
const struct firmware *seg_fw;
phys_addr_t mem_reloc;
- phys_addr_t min_addr = (phys_addr_t)ULLONG_MAX;
+ phys_addr_t min_addr = PHYS_ADDR_MAX;
phys_addr_t max_addr = 0;
size_t fw_name_len;
ssize_t offset;
static bool has_cpg_mstp;
-static void __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
+static int __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
{
struct generic_pm_domain *genpd = &pd->genpd;
const char *name = pd->genpd.name;
struct dev_power_governor *gov = &simple_qos_governor;
+ int error;
if (pd->flags & PD_CPU) {
/*
rcar_sysc_power_up(&pd->ch);
finalize:
- pm_genpd_init(genpd, gov, false);
+ error = pm_genpd_init(genpd, gov, false);
+ if (error)
+ pr_err("Failed to init PM domain %s: %d\n", name, error);
+
+ return error;
}
static const struct of_device_id rcar_sysc_matches[] __initconst = {
pr_debug("%pOF: syscier = 0x%08x\n", np, syscier);
iowrite32(syscier, base + SYSCIER);
+ /*
+ * First, create all PM domains
+ */
for (i = 0; i < info->num_areas; i++) {
const struct rcar_sysc_area *area = &info->areas[i];
struct rcar_sysc_pd *pd;
pd->ch.isr_bit = area->isr_bit;
pd->flags = area->flags;
- rcar_sysc_pd_setup(pd);
- if (area->parent >= 0)
- pm_genpd_add_subdomain(domains->domains[area->parent],
- &pd->genpd);
+ error = rcar_sysc_pd_setup(pd);
+ if (error)
+ goto out_put;
domains->domains[area->isr_bit] = &pd->genpd;
}
+ /*
+ * Second, link all PM domains to their parents
+ */
+ for (i = 0; i < info->num_areas; i++) {
+ const struct rcar_sysc_area *area = &info->areas[i];
+
+ if (!area->name || area->parent < 0)
+ continue;
+
+ error = pm_genpd_add_subdomain(domains->domains[area->parent],
+ domains->domains[area->isr_bit]);
+ if (error)
+ pr_warn("Failed to add PM subdomain %s to parent %u\n",
+ area->name, area->parent);
+ }
+
error = of_genpd_add_provider_onecell(np, &domains->onecell_data);
out_put:
*
* @stream: Soundwire stream
*
- * Documentation/soundwire/stream.txt explains this API in detail
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
*/
int sdw_prepare_stream(struct sdw_stream_runtime *stream)
{
*
* @stream: Soundwire stream
*
- * Documentation/soundwire/stream.txt explains this API in detail
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
*/
int sdw_enable_stream(struct sdw_stream_runtime *stream)
{
*
* @stream: Soundwire stream
*
- * Documentation/soundwire/stream.txt explains this API in detail
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
*/
int sdw_disable_stream(struct sdw_stream_runtime *stream)
{
*
* @stream: Soundwire stream
*
- * Documentation/soundwire/stream.txt explains this API in detail
+ * Documentation/driver-api/soundwire/stream.rst explains this API in detail
*/
int sdw_deprepare_stream(struct sdw_stream_runtime *stream)
{
fput(asma->file);
goto out;
}
+ } else {
+ vma_set_anonymous(vma);
}
if (vma->vm_file)
struct page **tmp = pages;
if (!pages)
- return NULL;
+ return ERR_PTR(-ENOMEM);
if (buffer->flags & ION_FLAG_CACHED)
pgprot = PAGE_KERNEL;
/* Make sure D/A update mode is direct update */
outb(0, dev->iobase + DAQP_AUX_REG);
- for (i = 0; i > insn->n; i++) {
+ for (i = 0; i < insn->n; i++) {
unsigned int val = data[i];
int ret;
This document provides an overview the Linux DPIO driver, its
subcomponents, and its APIs.
-See Documentation/dpaa2/overview.txt for a general overview of DPAA2
+See Documentation/networking/dpaa2/overview.rst for a general overview of DPAA2
and the general DPAA2 driver architecture in Linux.
Driver Overview
memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN);
if (dev->flags & IFF_PROMISC) {
- hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
- MCAST_FILTER_PROMISC);
+ hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+ MCAST_FILTER_PROMISC);
goto spin_unlock;
}
if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) ||
(dev->flags & IFF_ALLMULTI)) {
- hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
- MCAST_FILTER_MCASTALL);
+ hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+ MCAST_FILTER_MCASTALL);
goto spin_unlock;
}
ETH_ALEN * mc_count);
} else {
priv->sme_i.sme_flag |= SME_MULTICAST;
- hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
- MCAST_FILTER_MCAST);
+ hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+ MCAST_FILTER_MCAST);
}
spin_unlock:
From the initial code review:
The main thing you need to do is to implement all the controls using the
-control framework (see Documentation/video4linux/v4l2-controls.txt).
+control framework (see Documentation/media/kapi/v4l2-controls.rst).
Most drivers are by now converted to the control framework, so you will
find many examples of how to do this in drivers/media/radio.
* (at your option) any later version.
*/
-#include <asm/cacheflush.h>
#include <linux/clk.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <media/v4l2-ioctl.h>
#include <media/v4l2-mc.h>
+#include <asm/cacheflush.h>
+
#include "iss_video.h"
#include "iss.h"
36057/36067 PCI controller chipset. This includes the Iomega
Buz, Pinnacle DC10+ and the Linux Media Labs LML33. There is
a driver homepage at <http://mjpeg.sf.net/driver-zoran/>. For
- more information, check <file:Documentation/video4linux/Zoran>.
+ more information, check <file:Documentation/media/v4l-drivers/zoran.rst>.
To compile this driver as a module, choose M here: the
module will be called zr36067.
select LIB80211
select LIB80211_CRYPT_WEP
select LIB80211_CRYPT_CCMP
- select LIB80211_CRYPT_TKIP
---help---
This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N.
If built as a module, it will be called r8188eu.
#include <mon.h>
#include <wifi.h>
#include <linux/vmalloc.h>
-#include <net/lib80211.h>
#define ETHERNET_HEADER_SIZE 14 /* Ethernet Header Length */
#define LLC_HEADER_SIZE 6 /* LLC Header Length */
static int recvframe_chkmic(struct adapter *adapter,
struct recv_frame *precvframe)
{
- int res = _SUCCESS;
- struct rx_pkt_attrib *prxattrib = &precvframe->attrib;
- struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta);
+ int i, res = _SUCCESS;
+ u32 datalen;
+ u8 miccode[8];
+ u8 bmic_err = false, brpt_micerror = true;
+ u8 *pframe, *payload, *pframemic;
+ u8 *mickey;
+ struct sta_info *stainfo;
+ struct rx_pkt_attrib *prxattrib = &precvframe->attrib;
+ struct security_priv *psecuritypriv = &adapter->securitypriv;
+
+ struct mlme_ext_priv *pmlmeext = &adapter->mlmeextpriv;
+ struct mlme_ext_info *pmlmeinfo = &(pmlmeext->mlmext_info);
+
+ stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]);
if (prxattrib->encrypt == _TKIP_) {
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+ ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__));
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+ ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+ __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+ prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5]));
+
+ /* calculate mic code */
if (stainfo) {
- int key_idx;
- const int iv_len = 8, icv_len = 4, key_length = 32;
- struct sk_buff *skb = precvframe->pkt;
- u8 key[32], iv[8], icv[4], *pframe = skb->data;
- void *crypto_private = NULL;
- struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
- struct security_priv *psecuritypriv = &adapter->securitypriv;
-
if (IS_MCAST(prxattrib->ra)) {
if (!psecuritypriv) {
res = _FAIL;
DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__);
goto exit;
}
- key_idx = prxattrib->key_index;
- memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
- memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+ mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0];
+
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+ ("\n %s: bcmc key\n", __func__));
} else {
- key_idx = 0;
- memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
- memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+ mickey = &stainfo->dot11tkiprxmickey.skey[0];
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("\n %s: unicast key\n", __func__));
}
- if (!crypto_ops) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
+ /* icv_len included the mic code */
+ datalen = precvframe->pkt->len-prxattrib->hdrlen -
+ prxattrib->iv_len-prxattrib->icv_len-8;
+ pframe = precvframe->pkt->data;
+ payload = pframe+prxattrib->hdrlen+prxattrib->iv_len;
- memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
- memcpy(icv, pframe + skb->len - icv_len, icv_len);
- memmove(pframe + iv_len, pframe, prxattrib->hdrlen);
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len));
+ rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0],
+ (unsigned char)prxattrib->priority); /* care the length of the data */
- skb_pull(skb, iv_len);
- skb_trim(skb, skb->len - icv_len);
+ pframemic = payload+datalen;
- crypto_private = crypto_ops->init(key_idx);
- if (!crypto_private) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
- if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
- if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) {
- res = _FAIL;
- goto exit_lib80211_tkip;
+ bmic_err = false;
+
+ for (i = 0; i < 8; i++) {
+ if (miccode[i] != *(pframemic+i)) {
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ",
+ __func__, i, miccode[i], i, *(pframemic + i)));
+ bmic_err = true;
+ }
}
- memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
- skb_push(skb, iv_len);
- skb_put(skb, icv_len);
+ if (bmic_err) {
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+ *(pframemic-8), *(pframemic-7), *(pframemic-6),
+ *(pframemic-5), *(pframemic-4), *(pframemic-3),
+ *(pframemic-2), *(pframemic-1)));
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+ *(pframemic-16), *(pframemic-15), *(pframemic-14),
+ *(pframemic-13), *(pframemic-12), *(pframemic-11),
+ *(pframemic-10), *(pframemic-9)));
+ {
+ uint i;
- memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
- memcpy(pframe + skb->len - icv_len, icv, icv_len);
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("\n ======demp packet (len=%d)======\n",
+ precvframe->pkt->len));
+ for (i = 0; i < precvframe->pkt->len; i += 8) {
+ RT_TRACE(_module_rtl871x_recv_c_,
+ _drv_err_,
+ ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x",
+ *(precvframe->pkt->data+i),
+ *(precvframe->pkt->data+i+1),
+ *(precvframe->pkt->data+i+2),
+ *(precvframe->pkt->data+i+3),
+ *(precvframe->pkt->data+i+4),
+ *(precvframe->pkt->data+i+5),
+ *(precvframe->pkt->data+i+6),
+ *(precvframe->pkt->data+i+7)));
+ }
+ RT_TRACE(_module_rtl871x_recv_c_,
+ _drv_err_,
+ ("\n ====== demp packet end [len=%d]======\n",
+ precvframe->pkt->len));
+ RT_TRACE(_module_rtl871x_recv_c_,
+ _drv_err_,
+ ("\n hrdlen=%d,\n",
+ prxattrib->hdrlen));
+ }
-exit_lib80211_tkip:
- if (crypto_ops && crypto_private)
- crypto_ops->deinit(crypto_private);
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+ ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ",
+ prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+ prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey));
+
+ /* double check key_index for some timing issue , */
+ /* cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */
+ if ((IS_MCAST(prxattrib->ra) == true) && (prxattrib->key_index != pmlmeinfo->key_index))
+ brpt_micerror = false;
+
+ if ((prxattrib->bdecrypted) && (brpt_micerror)) {
+ rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra));
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+ DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+ } else {
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+ DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+ }
+ res = _FAIL;
+ } else {
+ /* mic checked ok */
+ if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) {
+ psecuritypriv->bcheck_grpkey = true;
+ RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true"));
+ }
+ }
} else {
RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
("%s: rtw_get_stainfo==NULL!!!\n", __func__));
}
+
+ skb_trim(precvframe->pkt, precvframe->pkt->len - 8);
}
exit:
+
return res;
}
return res;
}
+/* The hlen isn't include the IV */
u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe)
-{
- struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib;
- u32 res = _SUCCESS;
+{ /* exclude ICV */
+ u16 pnl;
+ u32 pnh;
+ u8 rc4key[16];
+ u8 ttkey[16];
+ u8 crc[4];
+ struct arc4context mycontext;
+ int length;
+
+ u8 *pframe, *payload, *iv, *prwskey;
+ union pn48 dot11txpn;
+ struct sta_info *stainfo;
+ struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib;
+ struct security_priv *psecuritypriv = &padapter->securitypriv;
+ u32 res = _SUCCESS;
+
+
+ pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data;
/* 4 start to decrypt recvframe */
if (prxattrib->encrypt == _TKIP_) {
- struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta);
-
+ stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]);
if (stainfo) {
- int key_idx;
- const int iv_len = 8, icv_len = 4, key_length = 32;
- void *crypto_private = NULL;
- struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt;
- u8 key[32], iv[8], icv[4], *pframe = skb->data;
- struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
- struct security_priv *psecuritypriv = &padapter->securitypriv;
-
if (IS_MCAST(prxattrib->ra)) {
if (!psecuritypriv->binstallGrpkey) {
res = _FAIL;
DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__);
goto exit;
}
- key_idx = prxattrib->key_index;
- memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
- memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+ prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey;
} else {
- key_idx = 0;
- memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
- memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+ RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__));
+ prwskey = &stainfo->dot118021x_UncstKey.skey[0];
}
- if (!crypto_ops) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
+ iv = pframe+prxattrib->hdrlen;
+ payload = pframe+prxattrib->iv_len+prxattrib->hdrlen;
+ length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len;
- memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
- memcpy(icv, pframe + skb->len - icv_len, icv_len);
+ GET_TKIP_PN(iv, dot11txpn);
- crypto_private = crypto_ops->init(key_idx);
- if (!crypto_private) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
- if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
- if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) {
- res = _FAIL;
- goto exit_lib80211_tkip;
- }
+ pnl = (u16)(dot11txpn.val);
+ pnh = (u32)(dot11txpn.val>>16);
- memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
- skb_push(skb, iv_len);
- skb_put(skb, icv_len);
+ phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh);
+ phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl);
- memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
- memcpy(pframe + skb->len - icv_len, icv, icv_len);
+ /* 4 decrypt payload include icv */
-exit_lib80211_tkip:
- if (crypto_ops && crypto_private)
- crypto_ops->deinit(crypto_private);
+ arcfour_init(&mycontext, rc4key, 16);
+ arcfour_encrypt(&mycontext, payload, payload, length);
+
+ *((__le32 *)crc) = getcrc32(payload, length-4);
+
+ if (crc[3] != payload[length-1] ||
+ crc[2] != payload[length-2] ||
+ crc[1] != payload[length-3] ||
+ crc[0] != payload[length-4]) {
+ RT_TRACE(_module_rtl871x_security_c_, _drv_err_,
+ ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n",
+ &crc, &payload[length-4]));
+ res = _FAIL;
+ }
} else {
RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n"));
res = _FAIL;
return _FAIL;
- if (len > MAX_IE_SZ)
+ if (len < 0 || len > MAX_IE_SZ)
return _FAIL;
pbss_network->IELength = len;
return;
pci_read_config_byte(rtlpci->pdev, 0x70f, &tmp);
- pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | BIT(7));
+ pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | ASPM_L1_LATENCY << 3);
pci_read_config_byte(rtlpci->pdev, 0x719, &tmp);
pci_write_config_byte(rtlpci->pdev, 0x719, tmp | BIT(3) | BIT(4));
#define RTL_USB_MAX_RX_COUNT 100
#define QBSS_LOAD_SIZE 5
#define MAX_WMMELE_LENGTH 64
+#define ASPM_L1_LATENCY 7
#define TOTAL_CAM_ENTRY 32
int chars_sent = 0;
char __user *cp;
char *init;
+ size_t bytes_per_ch = unicode ? 3 : 1;
u16 ch;
int empty;
unsigned long flags;
DEFINE_WAIT(wait);
+ if (count < bytes_per_ch)
+ return -EINVAL;
+
spin_lock_irqsave(&speakup_info.spinlock, flags);
while (1) {
prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE);
init = get_initstring();
/* Keep 3 bytes available for a 16bit UTF-8-encoded character */
- while (chars_sent <= count - 3) {
+ while (chars_sent <= count - bytes_per_ch) {
if (speakup_info.flushing) {
speakup_info.flushing = 0;
ch = '\x18';
config TYPEC_RT1711H
tristate "Richtek RT1711H Type-C chip driver"
+ depends on I2C
select TYPEC_TCPCI
help
Richtek RT1711H Type-C chip driver that works with
struct iscsi_param *param;
u32 mrdsl, mbl;
u32 max_npdu, max_iso_npdu;
+ u32 max_iso_payload;
if (conn->login->leading_connection) {
param = iscsi_find_param_from_key(MAXBURSTLENGTH,
mrdsl = conn_ops->MaxRecvDataSegmentLength;
max_npdu = mbl / mrdsl;
- max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD /
- (ISCSI_HDR_LEN + mrdsl +
+ max_iso_payload = rounddown(CXGBIT_MAX_ISO_PAYLOAD, csk->emss);
+
+ max_iso_npdu = max_iso_payload /
+ (ISCSI_HDR_LEN + mrdsl +
cxgbit_digest_len[csk->submode]);
csk->max_iso_npdu = min(max_npdu, max_iso_npdu);
if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl)
conn_ops->MaxRecvDataSegmentLength = cdev->mdsl;
+ if (cxgbit_set_digest(csk))
+ return -1;
+
if (conn->login->leading_connection) {
param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL,
conn->param_list);
if (is_t5(cdev->lldi.adapter_type))
goto enable_ddp;
else
- goto enable_digest;
+ return 0;
}
if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) {
}
}
-enable_digest:
- if (cxgbit_set_digest(csk))
- return -1;
-
return 0;
}
* Check for overflow of 8byte PRI READ_KEYS payload and
* next reservation key list descriptor.
*/
- if ((add_len + 8) > (cmd->data_length - 8))
- break;
-
- put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
- off += 8;
+ if (off + 8 <= cmd->data_length) {
+ put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
+ off += 8;
+ }
+ /*
+ * SPC5r17: 6.16.2 READ KEYS service action
+ * The ADDITIONAL LENGTH field indicates the number of bytes in
+ * the Reservation key list. The contents of the ADDITIONAL
+ * LENGTH field are not altered based on the allocation length
+ */
add_len += 8;
}
spin_unlock(&dev->t10_pr.registration_lock);
}
static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
- bool bidi)
+ bool bidi, uint32_t read_len)
{
struct se_cmd *se_cmd = cmd->se_cmd;
int i, dbi;
for_each_sg(data_sg, sg, data_nents, i) {
int sg_remaining = sg->length;
to = kmap_atomic(sg_page(sg)) + sg->offset;
- while (sg_remaining > 0) {
+ while (sg_remaining > 0 && read_len > 0) {
if (block_remaining == 0) {
if (from)
kunmap_atomic(from);
}
copy_bytes = min_t(size_t, sg_remaining,
block_remaining);
+ if (read_len < copy_bytes)
+ copy_bytes = read_len;
offset = DATA_BLOCK_SIZE - block_remaining;
tcmu_flush_dcache_range(from, copy_bytes);
memcpy(to + sg->length - sg_remaining, from + offset,
sg_remaining -= copy_bytes;
block_remaining -= copy_bytes;
+ read_len -= copy_bytes;
}
kunmap_atomic(to - sg->offset);
+ if (read_len == 0)
+ break;
}
if (from)
kunmap_atomic(from);
{
struct se_cmd *se_cmd = cmd->se_cmd;
struct tcmu_dev *udev = cmd->tcmu_dev;
+ bool read_len_valid = false;
+ uint32_t read_len = se_cmd->data_length;
/*
* cmd has been completed already from timeout, just reclaim
pr_warn("TCMU: Userspace set UNKNOWN_OP flag on se_cmd %p\n",
cmd->se_cmd);
entry->rsp.scsi_status = SAM_STAT_CHECK_CONDITION;
- } else if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
+ goto done;
+ }
+
+ if (se_cmd->data_direction == DMA_FROM_DEVICE &&
+ (entry->hdr.uflags & TCMU_UFLAG_READ_LEN) && entry->rsp.read_len) {
+ read_len_valid = true;
+ if (entry->rsp.read_len < read_len)
+ read_len = entry->rsp.read_len;
+ }
+
+ if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
transport_copy_sense_to_cmd(se_cmd, entry->rsp.sense_buffer);
- } else if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ if (!read_len_valid )
+ goto done;
+ else
+ se_cmd->se_cmd_flags |= SCF_TREAT_READ_AS_NORMAL;
+ }
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
/* Get Data-In buffer before clean up */
- gather_data_area(udev, cmd, true);
+ gather_data_area(udev, cmd, true, read_len);
} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
- gather_data_area(udev, cmd, false);
+ gather_data_area(udev, cmd, false, read_len);
} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
/* TODO: */
} else if (se_cmd->data_direction != DMA_NONE) {
se_cmd->data_direction);
}
- target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
+done:
+ if (read_len_valid) {
+ pr_debug("read_len = %d\n", read_len);
+ target_complete_cmd_with_length(cmd->se_cmd,
+ entry->rsp.scsi_status, read_len);
+ } else
+ target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
out:
cmd->se_cmd = NULL;
/* Initialise the mailbox of the ring buffer */
mb = udev->mb_addr;
mb->version = TCMU_MAILBOX_VERSION;
- mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC;
+ mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC | TCMU_MAILBOX_FLAG_CAP_READ_LEN;
mb->cmdr_off = CMDR_OFF;
mb->cmdr_size = udev->cmdr_size;
goto err_free_acl;
}
ret = tb->cm_ops->set_boot_acl(tb, acl, tb->nboot_acl);
+ if (!ret) {
+ /* Notify userspace about the change */
+ kobject_uevent(&tb->dev.kobj, KOBJ_CHANGE);
+ }
mutex_unlock(&tb->lock);
err_free_acl:
struct mutex output_lock;
};
+#define MASK(x) ((x) & (N_TTY_BUF_SIZE - 1))
+
static inline size_t read_cnt(struct n_tty_data *ldata)
{
return ldata->read_head - ldata->read_tail;
static inline unsigned char echo_buf(struct n_tty_data *ldata, size_t i)
{
+ smp_rmb(); /* Matches smp_wmb() in add_echo_byte(). */
return ldata->echo_buf[i & (N_TTY_BUF_SIZE - 1)];
}
static void reset_buffer_flags(struct n_tty_data *ldata)
{
ldata->read_head = ldata->canon_head = ldata->read_tail = 0;
- ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0;
ldata->commit_head = 0;
- ldata->echo_mark = 0;
ldata->line_start = 0;
ldata->erasing = 0;
old_space = space = tty_write_room(tty);
tail = ldata->echo_tail;
- while (ldata->echo_commit != tail) {
+ while (MASK(ldata->echo_commit) != MASK(tail)) {
c = echo_buf(ldata, tail);
if (c == ECHO_OP_START) {
unsigned char op;
int no_space_left = 0;
+ /*
+ * Since add_echo_byte() is called without holding
+ * output_lock, we might see only portion of multi-byte
+ * operation.
+ */
+ if (MASK(ldata->echo_commit) == MASK(tail + 1))
+ goto not_yet_stored;
/*
* If the buffer byte is the start of a multi-byte
* operation, get the next byte, which is either the
unsigned int num_chars, num_bs;
case ECHO_OP_ERASE_TAB:
+ if (MASK(ldata->echo_commit) == MASK(tail + 2))
+ goto not_yet_stored;
num_chars = echo_buf(ldata, tail + 2);
/*
/* If the echo buffer is nearly full (so that the possibility exists
* of echo overrun before the next commit), then discard enough
* data at the tail to prevent a subsequent overrun */
- while (ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
+ while (ldata->echo_commit > tail &&
+ ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
if (echo_buf(ldata, tail) == ECHO_OP_START) {
if (echo_buf(ldata, tail + 1) == ECHO_OP_ERASE_TAB)
tail += 3;
tail++;
}
+ not_yet_stored:
ldata->echo_tail = tail;
return old_space - space;
}
size_t nr, old, echoed;
size_t head;
+ mutex_lock(&ldata->output_lock);
head = ldata->echo_head;
ldata->echo_mark = head;
old = ldata->echo_commit - ldata->echo_tail;
* is over the threshold (and try again each time another
* block is accumulated) */
nr = head - ldata->echo_tail;
- if (nr < ECHO_COMMIT_WATERMARK || (nr % ECHO_BLOCK > old % ECHO_BLOCK))
+ if (nr < ECHO_COMMIT_WATERMARK ||
+ (nr % ECHO_BLOCK > old % ECHO_BLOCK)) {
+ mutex_unlock(&ldata->output_lock);
return;
+ }
- mutex_lock(&ldata->output_lock);
ldata->echo_commit = head;
echoed = __process_echoes(tty);
mutex_unlock(&ldata->output_lock);
static inline void add_echo_byte(unsigned char c, struct n_tty_data *ldata)
{
- *echo_buf_addr(ldata, ldata->echo_head++) = c;
+ *echo_buf_addr(ldata, ldata->echo_head) = c;
+ smp_wmb(); /* Matches smp_rmb() in echo_buf(). */
+ ldata->echo_head++;
}
/**
}
seen_alnums = 0;
- while (ldata->read_head != ldata->canon_head) {
+ while (MASK(ldata->read_head) != MASK(ldata->canon_head)) {
head = ldata->read_head;
/* erase a single possibly multibyte character */
do {
head--;
c = read_buf(ldata, head);
- } while (is_continuation(c, tty) && head != ldata->canon_head);
+ } while (is_continuation(c, tty) &&
+ MASK(head) != MASK(ldata->canon_head));
/* do not partially erase */
if (is_continuation(c, tty))
* This info is used to go back the correct
* number of columns.
*/
- while (tail != ldata->canon_head) {
+ while (MASK(tail) != MASK(ldata->canon_head)) {
tail--;
c = read_buf(ldata, tail);
if (c == '\t') {
finish_erasing(ldata);
echo_char(c, tty);
echo_char_raw('\n', ldata);
- while (tail != ldata->read_head) {
+ while (MASK(tail) != MASK(ldata->read_head)) {
echo_char(read_buf(ldata, tail), tty);
tail++;
}
struct n_tty_data *ldata;
/* Currently a malloc failure here can panic */
- ldata = vmalloc(sizeof(*ldata));
+ ldata = vzalloc(sizeof(*ldata));
if (!ldata)
- goto err;
+ return -ENOMEM;
ldata->overrun_time = jiffies;
mutex_init(&ldata->atomic_read_lock);
mutex_init(&ldata->output_lock);
tty->disc_data = ldata;
- reset_buffer_flags(tty->disc_data);
- ldata->column = 0;
- ldata->canon_column = 0;
- ldata->num_overrun = 0;
- ldata->no_room = 0;
- ldata->lnext = 0;
tty->closing = 0;
/* indicate buffer work may resume */
clear_bit(TTY_LDISC_HALTED, &tty->flags);
n_tty_set_termios(tty, NULL);
tty_unthrottle(tty);
-
return 0;
-err:
- return -ENOMEM;
}
static inline int input_available_p(struct tty_struct *tty, int poll)
tail = ldata->read_tail;
nr = head - tail;
/* Skip EOF-chars.. */
- while (head != tail) {
+ while (MASK(head) != MASK(tail)) {
if (test_bit(tail & (N_TTY_BUF_SIZE - 1), ldata->read_flags) &&
read_buf(ldata, tail) == __DISABLED_CHAR)
nr--;
static void __exit serdev_exit(void)
{
bus_unregister(&serdev_bus_type);
+ ida_destroy(&ctrl_ida);
}
module_exit(serdev_exit);
/* multi-io cards handled by parport_serial */
{ PCI_DEVICE(0x4348, 0x7053), }, /* WCH CH353 2S1P */
{ PCI_DEVICE(0x4348, 0x5053), }, /* WCH CH353 1S1P */
- { PCI_DEVICE(0x4348, 0x7173), }, /* WCH CH355 4S */
{ PCI_DEVICE(0x1c00, 0x3250), }, /* WCH CH382 2S1P */
- { PCI_DEVICE(0x1c00, 0x3470), }, /* WCH CH384 4S */
/* Moxa Smartio MUE boards handled by 8250_moxa */
{ PCI_VDEVICE(MOXA, 0x1024), },
i = -EIO;
tty_ldisc_deref(ld);
- if (i > 0)
- tty_update_time(&inode->i_atime);
+ if (i > 0) {
+ struct timespec ts;
+
+ ts = timespec64_to_timespec(inode->i_atime);
+ tty_update_time(&ts);
+ inode->i_atime = timespec_to_timespec64(ts);
+ }
return i;
}
cond_resched();
}
if (written) {
- tty_update_time(&file_inode(file)->i_mtime);
+ struct timespec ts;
+
+ ts = timespec64_to_timespec(file_inode(file)->i_mtime);
+ tty_update_time(&ts);
+ file_inode(file)->i_mtime = timespec_to_timespec64(ts);
ret = written;
}
out:
if (!*vc->vc_uni_pagedir_loc)
con_set_default_unimap(vc);
- vc->vc_screenbuf = kmalloc(vc->vc_screenbuf_size, GFP_KERNEL);
+ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
if (!vc->vc_screenbuf)
goto err_free;
if (new_screen_size > (4 << 20))
return -EINVAL;
- newscreen = kmalloc(new_screen_size, GFP_USER);
+ newscreen = kzalloc(new_screen_size, GFP_USER);
if (!newscreen)
return -ENOMEM;
struct device_attribute *attr, char *buf)
{
struct uio_device *idev = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", idev->info->name);
+ int ret;
+
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ ret = -EINVAL;
+ dev_err(dev, "the device has been unregistered\n");
+ goto out;
+ }
+
+ ret = sprintf(buf, "%s\n", idev->info->name);
+
+out:
+ mutex_unlock(&idev->info_lock);
+ return ret;
}
static DEVICE_ATTR_RO(name);
struct device_attribute *attr, char *buf)
{
struct uio_device *idev = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", idev->info->version);
+ int ret;
+
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ ret = -EINVAL;
+ dev_err(dev, "the device has been unregistered\n");
+ goto out;
+ }
+
+ ret = sprintf(buf, "%s\n", idev->info->version);
+
+out:
+ mutex_unlock(&idev->info_lock);
+ return ret;
}
static DEVICE_ATTR_RO(version);
static irqreturn_t uio_interrupt(int irq, void *dev_id)
{
struct uio_device *idev = (struct uio_device *)dev_id;
- irqreturn_t ret = idev->info->handler(irq, idev->info);
+ irqreturn_t ret;
+ mutex_lock(&idev->info_lock);
+
+ ret = idev->info->handler(irq, idev->info);
if (ret == IRQ_HANDLED)
uio_event_notify(idev->info);
+ mutex_unlock(&idev->info_lock);
return ret;
}
struct uio_device *idev;
struct uio_listener *listener;
int ret = 0;
- unsigned long flags;
mutex_lock(&minor_lock);
idev = idr_find(&uio_idr, iminor(inode));
listener->event_count = atomic_read(&idev->event);
filep->private_data = listener;
- spin_lock_irqsave(&idev->info_lock, flags);
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ mutex_unlock(&idev->info_lock);
+ ret = -EINVAL;
+ goto err_alloc_listener;
+ }
+
if (idev->info && idev->info->open)
ret = idev->info->open(idev->info, inode);
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
if (ret)
goto err_infoopen;
int ret = 0;
struct uio_listener *listener = filep->private_data;
struct uio_device *idev = listener->dev;
- unsigned long flags;
- spin_lock_irqsave(&idev->info_lock, flags);
+ mutex_lock(&idev->info_lock);
if (idev->info && idev->info->release)
ret = idev->info->release(idev->info, inode);
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
module_put(idev->owner);
kfree(listener);
struct uio_listener *listener = filep->private_data;
struct uio_device *idev = listener->dev;
__poll_t ret = 0;
- unsigned long flags;
- spin_lock_irqsave(&idev->info_lock, flags);
+ mutex_lock(&idev->info_lock);
if (!idev->info || !idev->info->irq)
ret = -EIO;
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
if (ret)
return ret;
DECLARE_WAITQUEUE(wait, current);
ssize_t retval = 0;
s32 event_count;
- unsigned long flags;
- spin_lock_irqsave(&idev->info_lock, flags);
+ mutex_lock(&idev->info_lock);
if (!idev->info || !idev->info->irq)
retval = -EIO;
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
if (retval)
return retval;
struct uio_device *idev = listener->dev;
ssize_t retval;
s32 irq_on;
- unsigned long flags;
- spin_lock_irqsave(&idev->info_lock, flags);
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ retval = -EINVAL;
+ goto out;
+ }
+
if (!idev->info || !idev->info->irq) {
retval = -EIO;
goto out;
retval = idev->info->irqcontrol(idev->info, irq_on);
out:
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
return retval ? retval : sizeof(s32);
}
struct page *page;
unsigned long offset;
void *addr;
+ int ret = 0;
+ int mi;
- int mi = uio_find_mem_index(vmf->vma);
- if (mi < 0)
- return VM_FAULT_SIGBUS;
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ ret = VM_FAULT_SIGBUS;
+ goto out;
+ }
+
+ mi = uio_find_mem_index(vmf->vma);
+ if (mi < 0) {
+ ret = VM_FAULT_SIGBUS;
+ goto out;
+ }
/*
* We need to subtract mi because userspace uses offset = N*PAGE_SIZE
page = vmalloc_to_page(addr);
get_page(page);
vmf->page = page;
- return 0;
+
+out:
+ mutex_unlock(&idev->info_lock);
+
+ return ret;
}
static const struct vm_operations_struct uio_logical_vm_ops = {
struct uio_device *idev = vma->vm_private_data;
int mi = uio_find_mem_index(vma);
struct uio_mem *mem;
+
if (mi < 0)
return -EINVAL;
mem = idev->info->mem + mi;
vma->vm_private_data = idev;
+ mutex_lock(&idev->info_lock);
+ if (!idev->info) {
+ ret = -EINVAL;
+ goto out;
+ }
+
mi = uio_find_mem_index(vma);
- if (mi < 0)
- return -EINVAL;
+ if (mi < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
requested_pages = vma_pages(vma);
actual_pages = ((idev->info->mem[mi].addr & ~PAGE_MASK)
+ idev->info->mem[mi].size + PAGE_SIZE -1) >> PAGE_SHIFT;
- if (requested_pages > actual_pages)
- return -EINVAL;
+ if (requested_pages > actual_pages) {
+ ret = -EINVAL;
+ goto out;
+ }
if (idev->info->mmap) {
ret = idev->info->mmap(idev->info, vma);
- return ret;
+ goto out;
}
switch (idev->info->mem[mi].memtype) {
case UIO_MEM_PHYS:
- return uio_mmap_physical(vma);
+ ret = uio_mmap_physical(vma);
+ break;
case UIO_MEM_LOGICAL:
case UIO_MEM_VIRTUAL:
- return uio_mmap_logical(vma);
+ ret = uio_mmap_logical(vma);
+ break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
+
+out:
+ mutex_unlock(&idev->info_lock);
+ return 0;
}
static const struct file_operations uio_fops = {
idev->owner = owner;
idev->info = info;
- spin_lock_init(&idev->info_lock);
+ mutex_init(&idev->info_lock);
init_waitqueue_head(&idev->wait);
atomic_set(&idev->event, 0);
* FDs at the time of unregister and therefore may not be
* freed until they are released.
*/
- ret = request_irq(info->irq, uio_interrupt,
- info->irq_flags, info->name, idev);
+ ret = request_threaded_irq(info->irq, NULL, uio_interrupt,
+ info->irq_flags, info->name, idev);
+
if (ret)
goto err_request_irq;
}
void uio_unregister_device(struct uio_info *info)
{
struct uio_device *idev;
- unsigned long flags;
if (!info || !info->uio_dev)
return;
uio_free_minor(idev);
+ mutex_lock(&idev->info_lock);
uio_dev_del_attributes(idev);
if (info->irq && info->irq != UIO_IRQ_CUSTOM)
free_irq(info->irq, idev);
- spin_lock_irqsave(&idev->info_lock, flags);
idev->info = NULL;
- spin_unlock_irqrestore(&idev->info_lock, flags);
+ mutex_unlock(&idev->info_lock);
device_unregister(&idev->dev);
depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA
select EXTCON
select RESET_CONTROLLER
+ select USB_ULPI_BUS
help
Say Y here if your system has a dual role high speed USB
controller based on ChipIdea silicon IP. It supports:
help
Say Y here to enable host controller functionality of the
ChipIdea driver.
-
-config USB_CHIPIDEA_ULPI
- bool "ChipIdea ULPI PHY support"
- depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA
- help
- Say Y here if you have a ULPI PHY attached to your ChipIdea
- controller.
-
endif
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_USB_CHIPIDEA) += ci_hdrc.o
-ci_hdrc-y := core.o otg.o debug.o
+ci_hdrc-y := core.o otg.o debug.o ulpi.o
ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC) += udc.o
ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST) += host.o
ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o
-ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI) += ulpi.o
# Glue/Bridge layers go here
struct ci_hdrc_platform_data *platdata;
int vbus_active;
-#ifdef CONFIG_USB_CHIPIDEA_ULPI
struct ulpi *ulpi;
struct ulpi_ops ulpi_ops;
-#endif
struct phy *phy;
/* old usb_phy interface */
struct usb_phy *usb_phy;
#endif
}
-#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI)
int ci_ulpi_init(struct ci_hdrc *ci);
void ci_ulpi_exit(struct ci_hdrc *ci);
int ci_ulpi_resume(struct ci_hdrc *ci);
-#else
-static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; }
-static inline void ci_ulpi_exit(struct ci_hdrc *ci) { }
-static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; }
-#endif
u32 hw_read_intr_enable(struct ci_hdrc *ci);
hcd->power_budget = ci->platdata->power_budget;
hcd->tpl_support = ci->platdata->tpl_support;
- if (ci->phy || ci->usb_phy)
+ if (ci->phy || ci->usb_phy) {
hcd->skip_phy_initialization = 1;
+ if (ci->usb_phy)
+ hcd->usb_phy = ci->usb_phy;
+ }
ehci = hcd_to_ehci(hcd);
ehci->caps = ci->hw_bank.cap;
{
int cnt = 100000;
+ if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI)
+ return 0;
+
while (cnt-- > 0) {
if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE))
return 0;
{ USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */
.driver_info = SINGLE_RX_URB,
},
+ { USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */
+ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ },
{ USB_DEVICE(0x22b8, 0x7000), /* Motorola Q Phone */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
},
+ { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
+ .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+ },
{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
.driver_info = CLEAR_HALT_CONDITIONS,
if (!udev || udev->state == USB_STATE_NOTATTACHED) {
/* Tell hub_wq to disconnect the device or
- * check for a new connection
+ * check for a new connection or over current condition.
+ * Based on USB2.0 Spec Section 11.12.5,
+ * C_PORT_OVER_CURRENT could be set while
+ * PORT_OVER_CURRENT is not. So check for any of them.
*/
if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
- (portstatus & USB_PORT_STAT_OVERCURRENT))
+ (portstatus & USB_PORT_STAT_OVERCURRENT) ||
+ (portchange & USB_PORT_STAT_C_OVERCURRENT))
set_bit(port1, hub->change_bits);
} else if (portstatus & USB_PORT_STAT_ENABLE) {
/* Corsair K70 RGB */
{ USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT },
+ /* Corsair Strafe */
+ { USB_DEVICE(0x1b1c, 0x1b15), .driver_info = USB_QUIRK_DELAY_INIT |
+ USB_QUIRK_DELAY_CTRL_MSG },
+
/* Corsair Strafe RGB */
{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT |
USB_QUIRK_DELAY_CTRL_MSG },
* @frame_list_sz: Frame list size
* @desc_gen_cache: Kmem cache for generic descriptors
* @desc_hsisoc_cache: Kmem cache for hs isochronous descriptors
+ * @unaligned_cache: Kmem cache for DMA mode to handle non-aligned buf
*
* These are for peripheral mode:
*
u32 frame_list_sz;
struct kmem_cache *desc_gen_cache;
struct kmem_cache *desc_hsisoc_cache;
+ struct kmem_cache *unaligned_cache;
+#define DWC2_KMEM_UNALIGNED_BUF_SIZE 1024
#endif /* CONFIG_USB_DWC2_HOST || CONFIG_USB_DWC2_DUAL_ROLE */
u32 index;
u32 maxsize = 0;
u32 mask = 0;
+ u8 pid = 0;
maxsize = dwc2_gadget_get_desc_params(hs_ep, &mask);
((len << DEV_DMA_NBYTES_SHIFT) & mask));
if (hs_ep->dir_in) {
- desc->status |= ((hs_ep->mc << DEV_DMA_ISOC_PID_SHIFT) &
+ if (len)
+ pid = DIV_ROUND_UP(len, hs_ep->ep.maxpacket);
+ else
+ pid = 1;
+ desc->status |= ((pid << DEV_DMA_ISOC_PID_SHIFT) &
DEV_DMA_ISOC_PID_MASK) |
((len % hs_ep->ep.maxpacket) ?
DEV_DMA_SHORT : 0) |
struct dwc2_dma_desc *desc;
if (list_empty(&hs_ep->queue)) {
+ hs_ep->target_frame = TARGET_FRAME_INITIAL;
dev_dbg(hsotg->dev, "%s: No requests in queue\n", __func__);
return;
}
*/
tmp = dwc2_hsotg_read_frameno(hsotg);
- dwc2_hsotg_complete_request(hsotg, ep, get_ep_head(ep), 0);
-
if (using_desc_dma(hsotg)) {
if (ep->target_frame == TARGET_FRAME_INITIAL) {
/* Start first ISO Out */
tmp = dwc2_hsotg_read_frameno(hsotg);
if (using_desc_dma(hsotg)) {
- dwc2_hsotg_complete_request(hsotg, hs_ep,
- get_ep_head(hs_ep), 0);
-
hs_ep->target_frame = tmp;
dwc2_gadget_incr_frame_num(hs_ep);
dwc2_gadget_start_isoc_ddma(hs_ep);
for (idx = 1; idx < hsotg->num_of_eps; idx++) {
hs_ep = hsotg->eps_in[idx];
/* Proceed only unmasked ISOC EPs */
- if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+ if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
continue;
epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx));
for (idx = 1; idx < hsotg->num_of_eps; idx++) {
hs_ep = hsotg->eps_out[idx];
/* Proceed only unmasked ISOC EPs */
- if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+ if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
continue;
epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
for (idx = 1; idx < hsotg->num_of_eps; idx++) {
hs_ep = hsotg->eps_out[idx];
/* Proceed only unmasked ISOC EPs */
- if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+ if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
continue;
epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
}
ret = usb_add_gadget_udc(dev, &hsotg->gadget);
- if (ret)
+ if (ret) {
+ dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep,
+ hsotg->ctrl_req);
return ret;
-
+ }
dwc2_hsotg_dump(hsotg);
return 0;
int dwc2_hsotg_remove(struct dwc2_hsotg *hsotg)
{
usb_del_gadget_udc(&hsotg->gadget);
+ dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep, hsotg->ctrl_req);
return 0;
}
}
if (hsotg->params.host_dma) {
- dwc2_writel((u32)chan->xfer_dma,
- hsotg->regs + HCDMA(chan->hc_num));
+ dma_addr_t dma_addr;
+
+ if (chan->align_buf) {
+ if (dbg_hc(chan))
+ dev_vdbg(hsotg->dev, "align_buf\n");
+ dma_addr = chan->align_buf;
+ } else {
+ dma_addr = chan->xfer_dma;
+ }
+ dwc2_writel((u32)dma_addr, hsotg->regs + HCDMA(chan->hc_num));
+
if (dbg_hc(chan))
dev_vdbg(hsotg->dev, "Wrote %08lx to HCDMA(%d)\n",
- (unsigned long)chan->xfer_dma, chan->hc_num);
+ (unsigned long)dma_addr, chan->hc_num);
}
/* Start the split */
}
}
-#define DWC2_USB_DMA_ALIGN 4
+static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg,
+ struct dwc2_qh *qh,
+ struct dwc2_host_chan *chan)
+{
+ if (!hsotg->unaligned_cache ||
+ chan->max_packet > DWC2_KMEM_UNALIGNED_BUF_SIZE)
+ return -ENOMEM;
-struct dma_aligned_buffer {
- void *kmalloc_ptr;
- void *old_xfer_buffer;
- u8 data[0];
-};
+ if (!qh->dw_align_buf) {
+ qh->dw_align_buf = kmem_cache_alloc(hsotg->unaligned_cache,
+ GFP_ATOMIC | GFP_DMA);
+ if (!qh->dw_align_buf)
+ return -ENOMEM;
+ }
+
+ qh->dw_align_buf_dma = dma_map_single(hsotg->dev, qh->dw_align_buf,
+ DWC2_KMEM_UNALIGNED_BUF_SIZE,
+ DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(hsotg->dev, qh->dw_align_buf_dma)) {
+ dev_err(hsotg->dev, "can't map align_buf\n");
+ chan->align_buf = 0;
+ return -EINVAL;
+ }
+
+ chan->align_buf = qh->dw_align_buf_dma;
+ return 0;
+}
+
+#define DWC2_USB_DMA_ALIGN 4
static void dwc2_free_dma_aligned_buffer(struct urb *urb)
{
- struct dma_aligned_buffer *temp;
+ void *stored_xfer_buffer;
+ size_t length;
if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER))
return;
- temp = container_of(urb->transfer_buffer,
- struct dma_aligned_buffer, data);
+ /* Restore urb->transfer_buffer from the end of the allocated area */
+ memcpy(&stored_xfer_buffer, urb->transfer_buffer +
+ urb->transfer_buffer_length, sizeof(urb->transfer_buffer));
- if (usb_urb_dir_in(urb))
- memcpy(temp->old_xfer_buffer, temp->data,
- urb->transfer_buffer_length);
- urb->transfer_buffer = temp->old_xfer_buffer;
- kfree(temp->kmalloc_ptr);
+ if (usb_urb_dir_in(urb)) {
+ if (usb_pipeisoc(urb->pipe))
+ length = urb->transfer_buffer_length;
+ else
+ length = urb->actual_length;
+
+ memcpy(stored_xfer_buffer, urb->transfer_buffer, length);
+ }
+ kfree(urb->transfer_buffer);
+ urb->transfer_buffer = stored_xfer_buffer;
urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER;
}
static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
{
- struct dma_aligned_buffer *temp, *kmalloc_ptr;
+ void *kmalloc_ptr;
size_t kmalloc_size;
if (urb->num_sgs || urb->sg ||
!((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1)))
return 0;
- /* Allocate a buffer with enough padding for alignment */
+ /*
+ * Allocate a buffer with enough padding for original transfer_buffer
+ * pointer. This allocation is guaranteed to be aligned properly for
+ * DMA
+ */
kmalloc_size = urb->transfer_buffer_length +
- sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1;
+ sizeof(urb->transfer_buffer);
kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
if (!kmalloc_ptr)
return -ENOMEM;
- /* Position our struct dma_aligned_buffer such that data is aligned */
- temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1;
- temp->kmalloc_ptr = kmalloc_ptr;
- temp->old_xfer_buffer = urb->transfer_buffer;
+ /*
+ * Position value of original urb->transfer_buffer pointer to the end
+ * of allocation for later referencing
+ */
+ memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+ &urb->transfer_buffer, sizeof(urb->transfer_buffer));
+
if (usb_urb_dir_out(urb))
- memcpy(temp->data, urb->transfer_buffer,
+ memcpy(kmalloc_ptr, urb->transfer_buffer,
urb->transfer_buffer_length);
- urb->transfer_buffer = temp->data;
+ urb->transfer_buffer = kmalloc_ptr;
urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER;
/* Set the transfer attributes */
dwc2_hc_init_xfer(hsotg, chan, qtd);
+ /* For non-dword aligned buffers */
+ if (hsotg->params.host_dma && qh->do_split &&
+ chan->ep_is_in && (chan->xfer_dma & 0x3)) {
+ dev_vdbg(hsotg->dev, "Non-aligned buffer\n");
+ if (dwc2_alloc_split_dma_aligned_buf(hsotg, qh, chan)) {
+ dev_err(hsotg->dev,
+ "Failed to allocate memory to handle non-aligned buffer\n");
+ /* Add channel back to free list */
+ chan->align_buf = 0;
+ chan->multi_count = 0;
+ list_add_tail(&chan->hc_list_entry,
+ &hsotg->free_hc_list);
+ qtd->in_process = 0;
+ qh->channel = NULL;
+ return -ENOMEM;
+ }
+ } else {
+ /*
+ * We assume that DMA is always aligned in non-split
+ * case or split out case. Warn if not.
+ */
+ WARN_ON_ONCE(hsotg->params.host_dma &&
+ (chan->xfer_dma & 0x3));
+ chan->align_buf = 0;
+ }
+
if (chan->ep_type == USB_ENDPOINT_XFER_INT ||
chan->ep_type == USB_ENDPOINT_XFER_ISOC)
/*
}
}
+ if (hsotg->params.host_dma) {
+ /*
+ * Create kmem caches to handle non-aligned buffer
+ * in Buffer DMA mode.
+ */
+ hsotg->unaligned_cache = kmem_cache_create("dwc2-unaligned-dma",
+ DWC2_KMEM_UNALIGNED_BUF_SIZE, 4,
+ SLAB_CACHE_DMA, NULL);
+ if (!hsotg->unaligned_cache)
+ dev_err(hsotg->dev,
+ "unable to create dwc2 unaligned cache\n");
+ }
+
hsotg->otg_port = 1;
hsotg->frame_list = NULL;
hsotg->frame_list_dma = 0;
return 0;
error4:
- kmem_cache_destroy(hsotg->desc_gen_cache);
+ kmem_cache_destroy(hsotg->unaligned_cache);
kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+ kmem_cache_destroy(hsotg->desc_gen_cache);
error3:
dwc2_hcd_release(hsotg);
error2:
usb_remove_hcd(hcd);
hsotg->priv = NULL;
- kmem_cache_destroy(hsotg->desc_gen_cache);
+ kmem_cache_destroy(hsotg->unaligned_cache);
kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+ kmem_cache_destroy(hsotg->desc_gen_cache);
dwc2_hcd_release(hsotg);
usb_put_hcd(hcd);
dwc2_writel(hprt0, hsotg->regs + HPRT0);
/* Wait for the HPRT0.PrtSusp register field to be set */
- if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 300))
+ if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000))
dev_warn(hsotg->dev, "Suspend wasn't generated\n");
/*
return ret;
}
+ dwc2_hcd_rem_wakeup(hsotg);
+
hsotg->hibernated = 0;
hsotg->bus_suspended = 0;
hsotg->lx_state = DWC2_L0;
* (micro)frame
* @xfer_buf: Pointer to current transfer buffer position
* @xfer_dma: DMA address of xfer_buf
+ * @align_buf: In Buffer DMA mode this will be used if xfer_buf is not
+ * DWORD aligned
* @xfer_len: Total number of bytes to transfer
* @xfer_count: Number of bytes transferred so far
* @start_pkt_count: Packet count at start of transfer
u8 *xfer_buf;
dma_addr_t xfer_dma;
+ dma_addr_t align_buf;
u32 xfer_len;
u32 xfer_count;
u16 start_pkt_count;
* speed. Note that this is in "schedule slice" which
* is tightly packed.
* @ntd: Actual number of transfer descriptors in a list
+ * @dw_align_buf: Used instead of original buffer if its physical address
+ * is not dword-aligned
+ * @dw_align_buf_dma: DMA address for dw_align_buf
* @qtd_list: List of QTDs for this QH
* @channel: Host channel currently processing transfers for this QH
* @qh_list_entry: Entry for QH in either the periodic or non-periodic
struct dwc2_hs_transfer_time hs_transfers[DWC2_HS_SCHEDULE_UFRAMES];
u32 ls_start_schedule_slice;
u16 ntd;
+ u8 *dw_align_buf;
+ dma_addr_t dw_align_buf_dma;
struct list_head qtd_list;
struct dwc2_host_chan *channel;
struct list_head qh_list_entry;
frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index];
len = dwc2_get_actual_xfer_length(hsotg, chan, chnum, qtd,
DWC2_HC_XFER_COMPLETE, NULL);
- if (!len) {
+ if (!len && !qtd->isoc_split_offset) {
qtd->complete_split = 0;
- qtd->isoc_split_offset = 0;
return 0;
}
frame_desc->actual_length += len;
+ if (chan->align_buf) {
+ dev_vdbg(hsotg->dev, "non-aligned buffer\n");
+ dma_unmap_single(hsotg->dev, chan->qh->dw_align_buf_dma,
+ DWC2_KMEM_UNALIGNED_BUF_SIZE, DMA_FROM_DEVICE);
+ memcpy(qtd->urb->buf + (chan->xfer_dma - qtd->urb->dma),
+ chan->qh->dw_align_buf, len);
+ }
+
qtd->isoc_split_offset += len;
hctsiz = dwc2_readl(hsotg->regs + HCTSIZ(chnum));
* avoid interrupt storms we'll wait before retrying if we've got
* several NAKs. If we didn't do this we'd retry directly from the
* interrupt handler and could end up quickly getting another
- * interrupt (another NAK), which we'd retry.
+ * interrupt (another NAK), which we'd retry. Note that we do not
+ * delay retries for IN parts of control requests, as those are expected
+ * to complete fairly quickly, and if we delay them we risk confusing
+ * the device and cause it issue STALL.
*
* Note that in DMA mode software only gets involved to re-send NAKed
* transfers for split transactions, so we only need to apply this
qtd->error_count = 0;
qtd->complete_split = 0;
qtd->num_naks++;
- qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY;
+ qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY &&
+ !(chan->ep_type == USB_ENDPOINT_XFER_CONTROL &&
+ chan->ep_is_in);
dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK);
goto handle_nak_done;
}
/* Get the map and adjust if this is a multi_tt hub */
map = qh->dwc_tt->periodic_bitmaps;
if (qh->dwc_tt->usb_tt->multi)
- map += DWC2_ELEMENTS_PER_LS_BITMAP * qh->ttport;
+ map += DWC2_ELEMENTS_PER_LS_BITMAP * (qh->ttport - 1);
return map;
}
if (qh->desc_list)
dwc2_hcd_qh_free_ddma(hsotg, qh);
+ else if (hsotg->unaligned_cache && qh->dw_align_buf)
+ kmem_cache_free(hsotg->unaligned_cache, qh->dw_align_buf);
+
kfree(qh);
}
if (!dwc->clks)
return -ENOMEM;
- dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
dwc->dev = dev;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (IS_ERR(dwc->reset))
return PTR_ERR(dwc->reset);
- ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
- if (ret == -EPROBE_DEFER)
- return ret;
- /*
- * Clocks are optional, but new DT platforms should support all clocks
- * as required by the DT-binding.
- */
- if (ret)
- dwc->num_clks = 0;
+ if (dev->of_node) {
+ dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
+
+ ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
+ if (ret == -EPROBE_DEFER)
+ return ret;
+ /*
+ * Clocks are optional, but new DT platforms should support all
+ * clocks as required by the DT-binding.
+ */
+ if (ret)
+ dwc->num_clks = 0;
+ }
ret = reset_control_deassert(dwc->reset);
if (ret)
reset_control_put(simple->resets);
- pm_runtime_put_sync(dev);
pm_runtime_disable(dev);
+ pm_runtime_put_noidle(dev);
+ pm_runtime_set_suspended(dev);
return 0;
}
#define PCI_DEVICE_ID_INTEL_GLK 0x31aa
#define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee
#define PCI_DEVICE_ID_INTEL_CNPH 0xa36e
+#define PCI_DEVICE_ID_INTEL_ICLLP 0x34ee
#define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
#define PCI_INTEL_BXT_FUNC_PMU_PWR 4
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPLP), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPH), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICLLP), },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
{ } /* Terminating Entry */
};
qcom->dwc3 = of_find_device_by_node(dwc3_np);
if (!qcom->dwc3) {
dev_err(&pdev->dev, "failed to get dwc3 platform device\n");
+ ret = -ENODEV;
goto depopulate;
}
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int dwc3_qcom_pm_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_suspend(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
int ret = 0;
return ret;
}
-static int dwc3_qcom_pm_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_resume(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
int ret;
return ret;
}
-#endif
-#ifdef CONFIG_PM
-static int dwc3_qcom_runtime_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_suspend(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
return dwc3_qcom_suspend(qcom);
}
-static int dwc3_qcom_runtime_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_resume(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
return dwc3_qcom_resume(qcom);
}
-#endif
static const struct dev_pm_ops dwc3_qcom_dev_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(dwc3_qcom_pm_suspend, dwc3_qcom_pm_resume)
ret = dwc3_ep0_start_trans(dep);
} else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) &&
req->request.length && req->request.zero) {
- u32 maxpacket;
ret = usb_gadget_map_request_by_dev(dwc->sysdev,
&req->request, dep->number);
if (ret)
return;
- maxpacket = dep->endpoint.maxpacket;
-
/* prepare normal TRB */
dwc3_ep0_prepare_one_trb(dep, req->request.dma,
req->request.length,
*/
if (w_value && !f->get_alt)
break;
+
+ spin_lock(&cdev->lock);
value = f->set_alt(f, w_index, w_value);
if (value == USB_GADGET_DELAYED_STATUS) {
DBG(cdev,
DBG(cdev, "delayed_status count %d\n",
cdev->delayed_status);
}
+ spin_unlock(&cdev->lock);
break;
case USB_REQ_GET_INTERFACE:
if (ctrl->bRequestType != (USB_DIR_IN|USB_RECIP_INTERFACE))
if (cdev->use_os_string && cdev->os_desc_config &&
(ctrl->bRequestType & USB_TYPE_VENDOR) &&
ctrl->bRequest == cdev->b_vendor_code) {
- struct usb_request *req;
struct usb_configuration *os_desc_cfg;
u8 *buf;
int interface;
struct mm_struct *mm;
struct work_struct work;
+ struct work_struct cancellation_work;
struct usb_ep *ep;
struct usb_request *req;
return 0;
}
+static void ffs_aio_cancel_worker(struct work_struct *work)
+{
+ struct ffs_io_data *io_data = container_of(work, struct ffs_io_data,
+ cancellation_work);
+
+ ENTER();
+
+ usb_ep_dequeue(io_data->ep, io_data->req);
+}
+
static int ffs_aio_cancel(struct kiocb *kiocb)
{
struct ffs_io_data *io_data = kiocb->private;
- struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+ struct ffs_data *ffs = io_data->ffs;
int value;
ENTER();
- spin_lock_irq(&epfile->ffs->eps_lock);
-
- if (likely(io_data && io_data->ep && io_data->req))
- value = usb_ep_dequeue(io_data->ep, io_data->req);
- else
+ if (likely(io_data && io_data->ep && io_data->req)) {
+ INIT_WORK(&io_data->cancellation_work, ffs_aio_cancel_worker);
+ queue_work(ffs->io_completion_wq, &io_data->cancellation_work);
+ value = -EINPROGRESS;
+ } else {
value = -EINVAL;
-
- spin_unlock_irq(&epfile->ffs->eps_lock);
+ }
return value;
}
inode = new_inode(sb);
if (likely(inode)) {
- struct timespec ts = current_time(inode);
+ struct timespec64 ts = current_time(inode);
inode->i_ino = get_next_ino();
inode->i_mode = perms->mode;
__ffs_event_add(ffs, FUNCTIONFS_SETUP);
spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags);
- return USB_GADGET_DELAYED_STATUS;
+ return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
}
static bool ffs_func_req_match(struct usb_function *f,
};
struct cntrl_cur_lay3 {
- __u32 dCUR;
+ __le32 dCUR;
};
struct cntrl_range_lay3 {
- __u16 wNumSubRanges;
- __u32 dMIN;
- __u32 dMAX;
- __u32 dRES;
+ __le16 wNumSubRanges;
+ __le32 dMIN;
+ __le32 dMAX;
+ __le32 dRES;
} __packed;
static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
if (!agdev->out_ep) {
dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
- return ret;
+ return -ENODEV;
}
agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc);
if (!agdev->in_ep) {
dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
- return ret;
+ return -ENODEV;
}
agdev->in_ep_maxpsize = max_t(u16,
memset(&c, 0, sizeof(struct cntrl_cur_lay3));
if (entity_id == USB_IN_CLK_ID)
- c.dCUR = p_srate;
+ c.dCUR = cpu_to_le32(p_srate);
else if (entity_id == USB_OUT_CLK_ID)
- c.dCUR = c_srate;
+ c.dCUR = cpu_to_le32(c_srate);
value = min_t(unsigned, w_length, sizeof c);
memcpy(req->buf, &c, value);
if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
if (entity_id == USB_IN_CLK_ID)
- r.dMIN = p_srate;
+ r.dMIN = cpu_to_le32(p_srate);
else if (entity_id == USB_OUT_CLK_ID)
- r.dMIN = c_srate;
+ r.dMIN = cpu_to_le32(c_srate);
else
return -EOPNOTSUPP;
r.dMAX = r.dMIN;
r.dRES = 0;
- r.wNumSubRanges = 1;
+ r.wNumSubRanges = cpu_to_le16(1);
value = min_t(unsigned, w_length, sizeof r);
memcpy(req->buf, &r, value);
struct uac_rtd_params {
struct snd_uac_chip *uac; /* parent chip */
bool ep_enabled; /* if the ep is enabled */
- /* Size of the ring buffer */
- size_t dma_bytes;
- unsigned char *dma_area;
struct snd_pcm_substream *ss;
void *rbuf;
- size_t period_size;
-
unsigned max_psize; /* MaxPacketSize of endpoint */
struct uac_req *ureq;
static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
{
unsigned pending;
- unsigned long flags;
+ unsigned long flags, flags2;
unsigned int hw_ptr;
- bool update_alsa = false;
int status = req->status;
struct uac_req *ur = req->context;
struct snd_pcm_substream *substream;
+ struct snd_pcm_runtime *runtime;
struct uac_rtd_params *prm = ur->pp;
struct snd_uac_chip *uac = prm->uac;
if (!substream)
goto exit;
+ snd_pcm_stream_lock_irqsave(substream, flags2);
+
+ runtime = substream->runtime;
+ if (!runtime || !snd_pcm_running(substream)) {
+ snd_pcm_stream_unlock_irqrestore(substream, flags2);
+ goto exit;
+ }
+
spin_lock_irqsave(&prm->lock, flags);
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
req->actual = req->length;
}
- pending = prm->hw_ptr % prm->period_size;
- pending += req->actual;
- if (pending >= prm->period_size)
- update_alsa = true;
-
hw_ptr = prm->hw_ptr;
- prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes;
spin_unlock_irqrestore(&prm->lock, flags);
/* Pack USB load in ALSA ring buffer */
- pending = prm->dma_bytes - hw_ptr;
+ pending = runtime->dma_bytes - hw_ptr;
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
if (unlikely(pending < req->actual)) {
- memcpy(req->buf, prm->dma_area + hw_ptr, pending);
- memcpy(req->buf + pending, prm->dma_area,
+ memcpy(req->buf, runtime->dma_area + hw_ptr, pending);
+ memcpy(req->buf + pending, runtime->dma_area,
req->actual - pending);
} else {
- memcpy(req->buf, prm->dma_area + hw_ptr, req->actual);
+ memcpy(req->buf, runtime->dma_area + hw_ptr,
+ req->actual);
}
} else {
if (unlikely(pending < req->actual)) {
- memcpy(prm->dma_area + hw_ptr, req->buf, pending);
- memcpy(prm->dma_area, req->buf + pending,
+ memcpy(runtime->dma_area + hw_ptr, req->buf, pending);
+ memcpy(runtime->dma_area, req->buf + pending,
req->actual - pending);
} else {
- memcpy(prm->dma_area + hw_ptr, req->buf, req->actual);
+ memcpy(runtime->dma_area + hw_ptr, req->buf,
+ req->actual);
}
}
+ spin_lock_irqsave(&prm->lock, flags);
+ /* update hw_ptr after data is copied to memory */
+ prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes;
+ hw_ptr = prm->hw_ptr;
+ spin_unlock_irqrestore(&prm->lock, flags);
+ snd_pcm_stream_unlock_irqrestore(substream, flags2);
+
+ if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual)
+ snd_pcm_period_elapsed(substream);
+
exit:
if (usb_ep_queue(ep, req, GFP_ATOMIC))
dev_err(uac->card->dev, "%d Error!\n", __LINE__);
-
- if (update_alsa)
- snd_pcm_period_elapsed(substream);
}
static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
static int uac_pcm_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *hw_params)
{
- struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
- struct uac_rtd_params *prm;
- int err;
-
- if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
- prm = &uac->p_prm;
- else
- prm = &uac->c_prm;
-
- err = snd_pcm_lib_malloc_pages(substream,
+ return snd_pcm_lib_malloc_pages(substream,
params_buffer_bytes(hw_params));
- if (err >= 0) {
- prm->dma_bytes = substream->runtime->dma_bytes;
- prm->dma_area = substream->runtime->dma_area;
- prm->period_size = params_period_bytes(hw_params);
- }
-
- return err;
}
static int uac_pcm_hw_free(struct snd_pcm_substream *substream)
{
- struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
- struct uac_rtd_params *prm;
-
- if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
- prm = &uac->p_prm;
- else
- prm = &uac->c_prm;
-
- prm->dma_area = NULL;
- prm->dma_bytes = 0;
- prm->period_size = 0;
-
return snd_pcm_lib_free_pages(substream);
}
if (err < 0)
goto snd_fail;
- strcpy(pcm->name, pcm_name);
+ strlcpy(pcm->name, pcm_name, sizeof(pcm->name));
pcm->private_data = uac;
uac->pcm = pcm;
snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops);
snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops);
- strcpy(card->driver, card_name);
- strcpy(card->shortname, card_name);
+ strlcpy(card->driver, card_name, sizeof(card->driver));
+ strlcpy(card->shortname, card_name, sizeof(card->shortname));
sprintf(card->longname, "%s %i", card_name, card->dev->id);
snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
config USB_ASPEED_VHUB
tristate "Aspeed vHub UDC driver"
depends on ARCH_ASPEED || COMPILE_TEST
+ depends on USB_LIBCOMPOSITE
help
USB peripheral controller for the Aspeed AST2500 family
SoCs supporting the "vHub" functionality and USB2.0
/* Check our state, cancel pending requests if needed */
if (ep->ep0.state != ep0_state_token) {
EPDBG(ep, "wrong state\n");
+ ast_vhub_nuke(ep, -EIO);
+
+ /*
+ * Accept the packet regardless, this seems to happen
+ * when stalling a SETUP packet that has an OUT data
+ * phase.
+ */
ast_vhub_nuke(ep, 0);
goto stall;
}
if (chunk && req->req.buf)
memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
+ vhub_dma_workaround(ep->buf);
+
/* Remember chunk size and trigger send */
reg = VHUB_EP0_SET_TX_LEN(chunk);
writel(reg, ep->ep0.ctlstat);
EPVDBG(ep, "rx prime\n");
/* Prime endpoint for receiving data */
- writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+ writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
}
static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
if (!req->req.dma) {
/* For IN transfers, copy data over first */
- if (ep->epn.is_in)
+ if (ep->epn.is_in) {
memcpy(ep->buf, req->req.buf + act, chunk);
+ vhub_dma_workaround(ep->buf);
+ }
writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
- } else
+ } else {
+ if (ep->epn.is_in)
+ vhub_dma_workaround(req->req.buf);
writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+ }
/* Start DMA */
req->active = true;
static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
struct ast_vhub_req *req)
{
+ struct ast_vhub_desc *desc = NULL;
unsigned int act = req->act_count;
unsigned int len = req->req.length;
unsigned int chunk;
/* While we can create descriptors */
while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
- struct ast_vhub_desc *desc;
unsigned int d_num;
/* Grab next free descriptor */
req->act_count = act = act + chunk;
}
+ if (likely(desc))
+ vhub_dma_workaround(desc);
+
/* Tell HW about new descriptors */
writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
#define DDBG(d, fmt, ...) do { } while(0)
#endif
+static inline void vhub_dma_workaround(void *addr)
+{
+ /*
+ * This works around a confirmed HW issue with the Aspeed chip.
+ *
+ * The core uses a different bus to memory than the AHB going to
+ * the USB device controller. Due to the latter having a higher
+ * priority than the core for arbitration on that bus, it's
+ * possible for an MMIO to the device, followed by a DMA by the
+ * device from memory to all be performed and services before
+ * a previous store to memory gets completed.
+ *
+ * This the following scenario can happen:
+ *
+ * - Driver writes to a DMA descriptor (Mbus)
+ * - Driver writes to the MMIO register to start the DMA (AHB)
+ * - The gadget sees the second write and sends a read of the
+ * descriptor to the memory controller (Mbus)
+ * - The gadget hits memory before the descriptor write
+ * causing it to read an obsolete value.
+ *
+ * Thankfully the problem is limited to the USB gadget device, other
+ * masters in the SoC all have a lower priority than the core, thus
+ * ensuring that the store by the core arrives first.
+ *
+ * The workaround consists of using a dummy read of the memory before
+ * doing the MMIO writes. This will ensure that the previous writes
+ * have been "pushed out".
+ */
+ mb();
+ (void)__raw_readl((void __iomem *)addr);
+}
+
/* core.c */
void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
int status);
r8a66597_bset(r8a66597, XCKE, SYSCFG0);
- msleep(3);
+ mdelay(3);
r8a66597_bset(r8a66597, PLLC, SYSCFG0);
- msleep(1);
+ mdelay(1);
r8a66597_bset(r8a66597, SCKE, SYSCFG0);
r8a66597->ep0_req->length = 2;
/* AV: what happens if we get called again before that gets through? */
spin_unlock(&r8a66597->lock);
- r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL);
+ r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC);
spin_lock(&r8a66597->lock);
}
return 0;
}
-static void xhci_do_dbc_stop(struct xhci_hcd *xhci)
+static int xhci_do_dbc_stop(struct xhci_hcd *xhci)
{
struct xhci_dbc *dbc = xhci->dbc;
if (dbc->state == DS_DISABLED)
- return;
+ return -1;
writel(0, &dbc->regs->control);
xhci_dbc_mem_cleanup(xhci);
dbc->state = DS_DISABLED;
+
+ return 0;
}
static int xhci_dbc_start(struct xhci_hcd *xhci)
static void xhci_dbc_stop(struct xhci_hcd *xhci)
{
+ int ret;
unsigned long flags;
struct xhci_dbc *dbc = xhci->dbc;
struct dbc_port *port = &dbc->port;
xhci_dbc_tty_unregister_device(xhci);
spin_lock_irqsave(&dbc->lock, flags);
- xhci_do_dbc_stop(xhci);
+ ret = xhci_do_dbc_stop(xhci);
spin_unlock_irqrestore(&dbc->lock, flags);
- pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
+ if (!ret)
+ pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
}
static void
if (!ep->stream_info)
return NULL;
- if (stream_id > ep->stream_info->num_streams)
+ if (stream_id >= ep->stream_info->num_streams)
return NULL;
return ep->stream_info->stream_rings[stream_id];
}
dev = xhci->devs[slot_id];
- trace_xhci_free_virt_device(dev);
-
xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
if (!dev)
return;
+ trace_xhci_free_virt_device(dev);
+
if (dev->tt_info)
old_active_eps = dev->tt_info->active_eps;
unsigned long mask;
unsigned int port;
bool idle, enable;
- int err;
+ int err = 0;
memset(&rsp, 0, sizeof(rsp));
pm_runtime_disable(&pdev->dev);
usb_put_hcd(tegra->hcd);
disable_xusbc:
- if (!&pdev->dev.pm_domain)
+ if (!pdev->dev.pm_domain)
tegra_powergate_power_off(TEGRA_POWERGATE_XUSBC);
disable_xusba:
- if (!&pdev->dev.pm_domain)
+ if (!pdev->dev.pm_domain)
tegra_powergate_power_off(TEGRA_POWERGATE_XUSBA);
put_padctl:
tegra_xusb_padctl_put(tegra->padctl);
TP_ARGS(ring, trb)
);
+DECLARE_EVENT_CLASS(xhci_log_free_virt_dev,
+ TP_PROTO(struct xhci_virt_device *vdev),
+ TP_ARGS(vdev),
+ TP_STRUCT__entry(
+ __field(void *, vdev)
+ __field(unsigned long long, out_ctx)
+ __field(unsigned long long, in_ctx)
+ __field(u8, fake_port)
+ __field(u8, real_port)
+ __field(u16, current_mel)
+
+ ),
+ TP_fast_assign(
+ __entry->vdev = vdev;
+ __entry->in_ctx = (unsigned long long) vdev->in_ctx->dma;
+ __entry->out_ctx = (unsigned long long) vdev->out_ctx->dma;
+ __entry->fake_port = (u8) vdev->fake_port;
+ __entry->real_port = (u8) vdev->real_port;
+ __entry->current_mel = (u16) vdev->current_mel;
+ ),
+ TP_printk("vdev %p ctx %llx | %llx fake_port %d real_port %d current_mel %d",
+ __entry->vdev, __entry->in_ctx, __entry->out_ctx,
+ __entry->fake_port, __entry->real_port, __entry->current_mel
+ )
+);
+
+DEFINE_EVENT(xhci_log_free_virt_dev, xhci_free_virt_device,
+ TP_PROTO(struct xhci_virt_device *vdev),
+ TP_ARGS(vdev)
+);
+
DECLARE_EVENT_CLASS(xhci_log_virt_dev,
TP_PROTO(struct xhci_virt_device *vdev),
TP_ARGS(vdev),
TP_ARGS(vdev)
);
-DEFINE_EVENT(xhci_log_virt_dev, xhci_free_virt_device,
- TP_PROTO(struct xhci_virt_device *vdev),
- TP_ARGS(vdev)
-);
-
DEFINE_EVENT(xhci_log_virt_dev, xhci_setup_device,
TP_PROTO(struct xhci_virt_device *vdev),
TP_ARGS(vdev)
spin_unlock_irqrestore(&xhci->lock, flags);
}
+static bool xhci_pending_portevent(struct xhci_hcd *xhci)
+{
+ struct xhci_port **ports;
+ int port_index;
+ u32 status;
+ u32 portsc;
+
+ status = readl(&xhci->op_regs->status);
+ if (status & STS_EINT)
+ return true;
+ /*
+ * Checking STS_EINT is not enough as there is a lag between a change
+ * bit being set and the Port Status Change Event that it generated
+ * being written to the Event Ring. See note in xhci 1.1 section 4.19.2.
+ */
+
+ port_index = xhci->usb2_rhub.num_ports;
+ ports = xhci->usb2_rhub.ports;
+ while (port_index--) {
+ portsc = readl(ports[port_index]->addr);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ port_index = xhci->usb3_rhub.num_ports;
+ ports = xhci->usb3_rhub.ports;
+ while (port_index--) {
+ portsc = readl(ports[port_index]->addr);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ return false;
+}
+
/*
* Stop HC (not bus-specific)
*
*/
int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
{
- u32 command, temp = 0, status;
+ u32 command, temp = 0;
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct usb_hcd *secondary_hcd;
int retval = 0;
command = readl(&xhci->op_regs->command);
command |= CMD_CRS;
writel(command, &xhci->op_regs->command);
+ /*
+ * Some controllers take up to 55+ ms to complete the controller
+ * restore so setting the timeout to 100ms. Xhci specification
+ * doesn't mention any timeout value.
+ */
if (xhci_handshake(&xhci->op_regs->status,
- STS_RESTORE, 0, 10 * 1000)) {
+ STS_RESTORE, 0, 100 * 1000)) {
xhci_warn(xhci, "WARN: xHC restore state timeout\n");
spin_unlock_irq(&xhci->lock);
return -ETIMEDOUT;
done:
if (retval == 0) {
/* Resume root hubs only when have pending events. */
- status = readl(&xhci->op_regs->status);
- if (status & STS_EINT) {
+ if (xhci_pending_portevent(xhci)) {
usb_hcd_resume_root_hub(xhci->shared_hcd);
usb_hcd_resume_root_hub(hcd);
}
if (!list_empty(&ep->ring->td_list)) {
dev_err(&udev->dev, "EP not empty, refuse reset\n");
spin_unlock_irqrestore(&xhci->lock, flags);
+ xhci_free_command(xhci, cfg_cmd);
goto cleanup;
}
xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0);
#define PORT_PLC (1 << 22)
/* port configure error change - port failed to configure its link partner */
#define PORT_CEC (1 << 23)
+#define PORT_CHANGE_MASK (PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \
+ PORT_RC | PORT_PLC | PORT_CEC)
+
+
/* Cold Attach Status - xHC can set this bit to report device attached during
* Sx state. Warm port reset should be perfomed to clear this bit and move port
* to connected state.
loff_t *ppos)
{
struct usb_yurex *dev;
- int retval = 0;
- int bytes_read = 0;
+ int len = 0;
char in_buffer[20];
unsigned long flags;
mutex_lock(&dev->io_mutex);
if (!dev->interface) { /* already disconnected */
- retval = -ENODEV;
- goto exit;
+ mutex_unlock(&dev->io_mutex);
+ return -ENODEV;
}
spin_lock_irqsave(&dev->lock, flags);
- bytes_read = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+ len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
spin_unlock_irqrestore(&dev->lock, flags);
-
- if (*ppos < bytes_read) {
- if (copy_to_user(buffer, in_buffer + *ppos, bytes_read - *ppos))
- retval = -EFAULT;
- else {
- retval = bytes_read - *ppos;
- *ppos += bytes_read;
- }
- }
-
-exit:
mutex_unlock(&dev->io_mutex);
- return retval;
+
+ return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
}
static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
if (pdata->init && pdata->init(pdev) != 0)
return -EINVAL;
+#ifdef CONFIG_PPC32
if (pdata->big_endian_mmio) {
_fsl_readl = _fsl_readl_be;
_fsl_writel = _fsl_writel_be;
_fsl_readl = _fsl_readl_le;
_fsl_writel = _fsl_writel_le;
}
+#endif
/* request irq */
p_otg->irq = platform_get_irq(pdev, 0);
/*
* state file in sysfs
*/
-static int show_fsl_usb2_otg_state(struct device *dev,
+static ssize_t show_fsl_usb2_otg_state(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct otg_fsm *fsm = &fsl_otg_dev->fsm;
r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
value, index, buf, bufsize, DEFAULT_TIMEOUT);
- if (r < bufsize) {
+ if (r < (int)bufsize) {
if (r >= 0) {
dev_err(&dev->dev,
"short control message received (%d < %u)\n",
{ USB_DEVICE(0x10C4, 0x8156) }, /* B&G H3000 link cable */
{ USB_DEVICE(0x10C4, 0x815E) }, /* Helicomm IP-Link 1220-DVM */
{ USB_DEVICE(0x10C4, 0x815F) }, /* Timewave HamLinkUSB */
+ { USB_DEVICE(0x10C4, 0x817C) }, /* CESINEL MEDCAL N Power Quality Monitor */
+ { USB_DEVICE(0x10C4, 0x817D) }, /* CESINEL MEDCAL NT Power Quality Monitor */
+ { USB_DEVICE(0x10C4, 0x817E) }, /* CESINEL MEDCAL S Power Quality Monitor */
{ USB_DEVICE(0x10C4, 0x818B) }, /* AVIT Research USB to TTL */
{ USB_DEVICE(0x10C4, 0x819F) }, /* MJS USB Toslink Switcher */
{ USB_DEVICE(0x10C4, 0x81A6) }, /* ThinkOptics WavIt */
{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
{ USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
+ { USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */
+ { USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */
+ { USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */
{ USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */
{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
{ USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */
{ USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */
+ { USB_DEVICE(0x10C4, 0x851E) }, /* CESINEL MEDCAL PT Network Analyzer */
{ USB_DEVICE(0x10C4, 0x85A7) }, /* LifeScan OneTouch Verio IQ */
+ { USB_DEVICE(0x10C4, 0x85B8) }, /* CESINEL ReCon T Energy Logger */
{ USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */
{ USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */
{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
{ USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */
{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+ { USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
+ { USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
{ USB_DEVICE(0x10C4, 0x8962) }, /* Brim Brothers charging dock */
{ USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */
{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+ { USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
+ { USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
+ { USB_DEVICE(0x10C4, 0xEA63) }, /* Silicon Labs Windows Update (CP2101-4/CP2102N) */
{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA71) }, /* Infinity GPS-MIC-1 Radio Monophone */
+ { USB_DEVICE(0x10C4, 0xEA7A) }, /* Silicon Labs Windows Update (CP2105) */
+ { USB_DEVICE(0x10C4, 0xEA7B) }, /* Silicon Labs Windows Update (CP2108) */
{ USB_DEVICE(0x10C4, 0xF001) }, /* Elan Digital Systems USBscope50 */
{ USB_DEVICE(0x10C4, 0xF002) }, /* Elan Digital Systems USBwave12 */
{ USB_DEVICE(0x10C4, 0xF003) }, /* Elan Digital Systems USBpulse100 */
3, /* get pins */
USB_TYPE_VENDOR|USB_RECIP_INTERFACE|USB_DIR_IN,
0, 0, data, 1, 2000);
- if (rc >= 0)
+ if (rc == 1)
*value = *data;
+ else if (rc >= 0)
+ rc = -EIO;
kfree(data);
return rc;
}
dev_dbg(dev, "%s urb buffer size is %d\n", __func__, urb->actual_length);
+ if (urb->actual_length < 1)
+ goto out;
+
dev_dbg(dev, "%s mos7840_port->MsrLsr is %d port %d\n", __func__,
mos7840_port->MsrLsr, mos7840_port->port_num);
data = urb->transfer_buffer;
u64 ts_nsec = local_clock();
unsigned long rem_nsec;
+ mutex_lock(&port->logbuffer_lock);
if (!port->logbuffer[port->logbuffer_head]) {
port->logbuffer[port->logbuffer_head] =
kzalloc(LOG_BUFFER_ENTRY_SIZE, GFP_KERNEL);
- if (!port->logbuffer[port->logbuffer_head])
+ if (!port->logbuffer[port->logbuffer_head]) {
+ mutex_unlock(&port->logbuffer_lock);
return;
+ }
}
vsnprintf(tmpbuffer, sizeof(tmpbuffer), fmt, args);
- mutex_lock(&port->logbuffer_lock);
-
if (tcpm_log_full(port)) {
port->logbuffer_head = max(port->logbuffer_head - 1, 0);
strcpy(tmpbuffer, "overflow");
tcpm_log(port, "Setting voltage/current limit %u mV %u mA", mv, max_ma);
+ port->supply_voltage = mv;
+ port->current_limit = max_ma;
+
if (port->tcpc->set_current_limit)
ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv);
* PPS APDO. Again skip the first sink PDO as this will
* always be 5V 3A.
*/
- for (j = i; j < port->nr_snk_pdo; j++) {
+ for (j = 1; j < port->nr_snk_pdo; j++) {
pdo = port->snk_pdo[j];
switch (pdo_type(pdo)) {
tcpm_set_attached_state(port, false);
port->try_src_count = 0;
port->try_snk_count = 0;
- port->supply_voltage = 0;
- port->current_limit = 0;
port->usb_type = POWER_SUPPLY_USB_TYPE_C;
power_supply_changed(port->psy);
tcpm_port_is_sink(port) &&
time_is_after_jiffies(port->delayed_runtime)) {
tcpm_set_state(port, SNK_DISCOVERY,
- port->delayed_runtime - jiffies);
+ jiffies_to_msecs(port->delayed_runtime -
+ jiffies));
break;
}
tcpm_set_state(port, unattached_state(port), 0);
}
if (con->status.change & UCSI_CONSTAT_CONNECT_CHANGE) {
+ typec_set_pwr_role(con->port, con->status.pwr_dir);
+
+ switch (con->status.partner_type) {
+ case UCSI_CONSTAT_PARTNER_TYPE_UFP:
+ typec_set_data_role(con->port, TYPEC_HOST);
+ break;
+ case UCSI_CONSTAT_PARTNER_TYPE_DFP:
+ typec_set_data_role(con->port, TYPEC_DEVICE);
+ break;
+ default:
+ break;
+ }
+
if (con->status.connected)
ucsi_register_partner(con);
else
return -ENODEV;
}
+ /* This will make sure we can use ioremap_nocache() */
+ status = acpi_release_memory(ACPI_HANDLE(&pdev->dev), res, 1);
+ if (ACPI_FAILURE(status))
+ return -ENOMEM;
+
/*
* NOTE: The memory region for the data structures is used also in an
* operation region, which means ACPI has already reserved it. Therefore
def_bool y if !S390
config VFIO_PCI_IGD
- depends on VFIO_PCI
- def_bool y if X86
+ bool "VFIO PCI extensions for Intel graphics (GVT-d)"
+ depends on VFIO_PCI && X86
+ default y
+ help
+ Support for Intel IGD specific extensions to enable direct
+ assignment to virtual machines. This includes exposing an IGD
+ specific firmware table and read-only copies of the host bridge
+ and LPC bridge config space.
+
+ To enable Intel IGD assignment through vfio-pci, say Y.
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/vgaarb.h>
+#include <linux/nospec.h>
#include "vfio_pci_private.h"
if (info.index >=
VFIO_PCI_NUM_REGIONS + vdev->num_regions)
return -EINVAL;
+ info.index = array_index_nospec(info.index,
+ VFIO_PCI_NUM_REGIONS +
+ vdev->num_regions);
i = info.index - VFIO_PCI_NUM_REGIONS;
}
static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
- unsigned long tce, unsigned long size,
+ unsigned long tce, unsigned long shift,
unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
{
long ret = 0;
struct mm_iommu_table_group_mem_t *mem;
- mem = mm_iommu_lookup(container->mm, tce, size);
+ mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
if (!mem)
return -EINVAL;
- ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+ ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
if (ret)
return -EINVAL;
if (!pua)
return;
- ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
+ ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift,
&hpa, &mem);
if (ret)
pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
entry + i);
ret = tce_iommu_prereg_ua_to_hpa(container,
- tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+ tce, tbl->it_page_shift, &hpa, &mem);
if (ret)
break;
struct page *page[1];
struct vm_area_struct *vma;
struct vm_area_struct *vmas[1];
+ unsigned int flags = 0;
int ret;
+ if (prot & IOMMU_WRITE)
+ flags |= FOLL_WRITE;
+
+ down_read(&mm->mmap_sem);
if (mm == current->mm) {
- ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
- page, vmas);
+ ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
} else {
- unsigned int flags = 0;
-
- if (prot & IOMMU_WRITE)
- flags |= FOLL_WRITE;
-
- down_read(&mm->mmap_sem);
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
vmas, NULL);
/*
ret = -EOPNOTSUPP;
put_page(page[0]);
}
- up_read(&mm->mmap_sem);
}
+ up_read(&mm->mmap_sem);
if (ret == 1) {
*pfn = page_to_pfn(page[0]);
if (ubufs)
vhost_net_ubuf_put_wait_and_free(ubufs);
err_ubufs:
- sockfd_put(sock);
+ if (sock)
+ sockfd_put(sock);
err_vq:
mutex_unlock(&vq->mutex);
err:
d->iotlb = niotlb;
for (i = 0; i < d->nvqs; ++i) {
- mutex_lock(&d->vqs[i]->mutex);
- d->vqs[i]->iotlb = niotlb;
- mutex_unlock(&d->vqs[i]->mutex);
+ struct vhost_virtqueue *vq = d->vqs[i];
+
+ mutex_lock(&vq->mutex);
+ vq->iotlb = niotlb;
+ __vhost_vq_meta_reset(vq);
+ mutex_unlock(&vq->mutex);
}
vhost_umem_clean(oiotlb);
struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
if (!node)
return NULL;
+
+ /* Make sure all padding within the structure is initialized. */
+ memset(&node->msg, 0, sizeof node->msg);
node->vq = vq;
node->msg.type = type;
return node;
config FB_VIA
tristate "VIA UniChrome (Pro) and Chrome9 display support"
- depends on FB && PCI && X86 && GPIOLIB && I2C
+ depends on FB && PCI && GPIOLIB && I2C && (X86 || COMPILE_TEST)
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
config FB_SH_MOBILE_LCDC
tristate "SuperH Mobile LCDC framebuffer support"
depends on FB && (SUPERH || ARCH_RENESAS) && HAVE_CLK
- depends on FB_SH_MOBILE_MERAM || !FB_SH_MOBILE_MERAM
select FB_SYS_FILLRECT
select FB_SYS_COPYAREA
select FB_SYS_IMAGEBLIT
and could also have been called by other names when coupled with
a bridge adapter.
-config FB_AUO_K190X
- tristate "AUO-K190X EPD controller support"
- depends on FB
- select FB_SYS_FILLRECT
- select FB_SYS_COPYAREA
- select FB_SYS_IMAGEBLIT
- select FB_SYS_FOPS
- select FB_DEFERRED_IO
- help
- Provides support for epaper controllers from the K190X series
- of AUO. These controllers can be used to drive epaper displays
- from Sipix.
-
- This option enables the common support, shared by the individual
- controller drivers. You will also have to enable the driver
- for the controller type used in your device.
-
-config FB_AUO_K1900
- tristate "AUO-K1900 EPD controller support"
- depends on FB && FB_AUO_K190X
- help
- This driver implements support for the AUO K1900 epd-controller.
- This controller can drive Sipix epaper displays but can only do
- serial updates, reducing the number of possible frames per second.
-
-config FB_AUO_K1901
- tristate "AUO-K1901 EPD controller support"
- depends on FB && FB_AUO_K190X
- help
- This driver implements support for the AUO K1901 epd-controller.
- This controller can drive Sipix epaper displays and supports
- concurrent updates, making higher frames per second possible.
-
config FB_JZ4740
tristate "JZ4740 LCD framebuffer support"
depends on FB && MACH_JZ4740
source "drivers/video/fbdev/omap2/Kconfig"
source "drivers/video/fbdev/mmp/Kconfig"
-config FB_SH_MOBILE_MERAM
- tristate "SuperH Mobile MERAM read ahead support"
- depends on (SUPERH || ARCH_SHMOBILE)
- select GENERIC_ALLOCATOR
- ---help---
- Enable MERAM support for the SuperH controller.
-
- This will allow for caching of the framebuffer to provide more
- reliable access under heavy main memory bus traffic situations.
- Up to 4 memory channels can be configured, allowing 4 RGB or
- 2 YCbCr framebuffers to be configured.
-
config FB_SSD1307
tristate "Solomon SSD1307 framebuffer support"
depends on FB && I2C
obj-$(CONFIG_FB_MAXINE) += maxinefb.o
obj-$(CONFIG_FB_METRONOME) += metronomefb.o
obj-$(CONFIG_FB_BROADSHEET) += broadsheetfb.o
-obj-$(CONFIG_FB_AUO_K190X) += auo_k190x.o
-obj-$(CONFIG_FB_AUO_K1900) += auo_k1900fb.o
-obj-$(CONFIG_FB_AUO_K1901) += auo_k1901fb.o
obj-$(CONFIG_FB_S1D13XXX) += s1d13xxxfb.o
obj-$(CONFIG_FB_SH7760) += sh7760fb.o
obj-$(CONFIG_FB_IMX) += imxfb.o
obj-$(CONFIG_FB_UDL) += udlfb.o
obj-$(CONFIG_FB_SMSCUFX) += smscufx.o
obj-$(CONFIG_FB_XILINX) += xilinxfb.o
-obj-$(CONFIG_FB_SH_MOBILE_MERAM) += sh_mobile_meram.o
obj-$(CONFIG_FB_SH_MOBILE_LCDC) += sh_mobile_lcdcfb.o
obj-$(CONFIG_FB_OMAP) += omap/
obj-y += omap2/
(void)aty_ld_pll(POWER_MANAGEMENT);
aty_st_le32(BUS_CNTL1, 0x00000010);
aty_st_le32(MEM_POWER_MISC, 0x0c830000);
- mdelay(100);
+ msleep(100);
/* Switch PCI power management to D2 */
pci_set_power_state(pdev, PCI_D2);
* it, we'll restore the dynamic clocks state on wakeup
*/
radeon_pm_disable_dynamic_mode(rinfo);
- mdelay(50);
+ msleep(50);
radeon_pm_save_regs(rinfo, 1);
if (rinfo->is_mobility && !(rinfo->pm_mode & radeon_pm_d2)) {
/* Switch off LVDS interface */
- mdelay(1);
+ usleep_range(1000, 2000);
OUTREG(LVDS_GEN_CNTL, INREG(LVDS_GEN_CNTL) & ~(LVDS_BL_MOD_EN));
- mdelay(1);
+ usleep_range(1000, 2000);
OUTREG(LVDS_GEN_CNTL, INREG(LVDS_GEN_CNTL) & ~(LVDS_EN | LVDS_ON));
OUTREG(LVDS_PLL_CNTL, (INREG(LVDS_PLL_CNTL) & ~30000) | 0x20000);
- mdelay(20);
+ msleep(20);
OUTREG(LVDS_GEN_CNTL, INREG(LVDS_GEN_CNTL) & ~(LVDS_DIGON));
}
pci_disable_device(pdev);
PAGE_ALIGN(fbdev->fb_len),
&fbdev->fb_phys, GFP_KERNEL);
if (!fbdev->fb_mem) {
- print_err("fail to allocate frambuffer (size: %dK))",
+ print_err("fail to allocate framebuffer (size: %dK))",
fbdev->fb_len / 1024);
return -ENOMEM;
}
&fbdev->fb_phys, GFP_KERNEL,
DMA_ATTR_NON_CONSISTENT);
if (!fbdev->fb_mem) {
- print_err("fail to allocate frambuffer (size: %dK))",
+ print_err("fail to allocate framebuffer (size: %dK))",
fbdev->fb_len / 1024);
ret = -ENOMEM;
goto failed;
+++ /dev/null
-/*
- * auok190xfb.c -- FB driver for AUO-K1900 controllers
- *
- * Copyright (C) 2011, 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * based on broadsheetfb.c
- *
- * Copyright (C) 2008, Jaya Kumar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Layout is based on skeletonfb.c by James Simmons and Geert Uytterhoeven.
- *
- * This driver is written to be used with the AUO-K1900 display controller.
- *
- * It is intended to be architecture independent. A board specific driver
- * must be used to perform all the physical IO interactions.
- *
- * The controller supports different update modes:
- * mode0+1 16 step gray (4bit)
- * mode2 4 step gray (2bit) - FIXME: add strange refresh
- * mode3 2 step gray (1bit) - FIXME: add strange refresh
- * mode4 handwriting mode (strange behaviour)
- * mode5 automatic selection of update mode
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/list.h>
-#include <linux/firmware.h>
-#include <linux/gpio.h>
-#include <linux/pm_runtime.h>
-
-#include <video/auo_k190xfb.h>
-
-#include "auo_k190x.h"
-
-/*
- * AUO-K1900 specific commands
- */
-
-#define AUOK1900_CMD_PARTIALDISP 0x1001
-#define AUOK1900_CMD_ROTATION 0x1006
-#define AUOK1900_CMD_LUT_STOP 0x1009
-
-#define AUOK1900_INIT_TEMP_AVERAGE (1 << 13)
-#define AUOK1900_INIT_ROTATE(_x) ((_x & 0x3) << 10)
-#define AUOK1900_INIT_RESOLUTION(_res) ((_res & 0x7) << 2)
-
-static void auok1900_init(struct auok190xfb_par *par)
-{
- struct device *dev = par->info->device;
- struct auok190x_board *board = par->board;
- u16 init_param = 0;
-
- pm_runtime_get_sync(dev);
-
- init_param |= AUOK1900_INIT_TEMP_AVERAGE;
- init_param |= AUOK1900_INIT_ROTATE(par->rotation);
- init_param |= AUOK190X_INIT_INVERSE_WHITE;
- init_param |= AUOK190X_INIT_FORMAT0;
- init_param |= AUOK1900_INIT_RESOLUTION(par->resolution);
- init_param |= AUOK190X_INIT_SHIFT_RIGHT;
-
- auok190x_send_cmdargs(par, AUOK190X_CMD_INIT, 1, &init_param);
-
- /* let the controller finish */
- board->wait_for_rdy(par);
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-}
-
-static void auok1900_update_region(struct auok190xfb_par *par, int mode,
- u16 y1, u16 y2)
-{
- struct device *dev = par->info->device;
- unsigned char *buf = (unsigned char *)par->info->screen_base;
- int xres = par->info->var.xres;
- int line_length = par->info->fix.line_length;
- u16 args[4];
-
- pm_runtime_get_sync(dev);
-
- mutex_lock(&(par->io_lock));
-
- /* y1 and y2 must be a multiple of 2 so drop the lowest bit */
- y1 &= 0xfffe;
- y2 &= 0xfffe;
-
- dev_dbg(dev, "update (x,y,w,h,mode)=(%d,%d,%d,%d,%d)\n",
- 1, y1+1, xres, y2-y1, mode);
-
- /* to FIX handle different partial update modes */
- args[0] = mode | 1;
- args[1] = y1 + 1;
- args[2] = xres;
- args[3] = y2 - y1;
- buf += y1 * line_length;
- auok190x_send_cmdargs_pixels(par, AUOK1900_CMD_PARTIALDISP, 4, args,
- ((y2 - y1) * line_length)/2, (u16 *) buf);
- auok190x_send_command(par, AUOK190X_CMD_DATA_STOP);
-
- par->update_cnt++;
-
- mutex_unlock(&(par->io_lock));
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-}
-
-static void auok1900fb_dpy_update_pages(struct auok190xfb_par *par,
- u16 y1, u16 y2)
-{
- int mode;
-
- if (par->update_mode < 0) {
- mode = AUOK190X_UPDATE_MODE(1);
- par->last_mode = -1;
- } else {
- mode = AUOK190X_UPDATE_MODE(par->update_mode);
- par->last_mode = par->update_mode;
- }
-
- if (par->flash)
- mode |= AUOK190X_UPDATE_NONFLASH;
-
- auok1900_update_region(par, mode, y1, y2);
-}
-
-static void auok1900fb_dpy_update(struct auok190xfb_par *par)
-{
- int mode;
-
- if (par->update_mode < 0) {
- mode = AUOK190X_UPDATE_MODE(0);
- par->last_mode = -1;
- } else {
- mode = AUOK190X_UPDATE_MODE(par->update_mode);
- par->last_mode = par->update_mode;
- }
-
- if (par->flash)
- mode |= AUOK190X_UPDATE_NONFLASH;
-
- auok1900_update_region(par, mode, 0, par->info->var.yres);
- par->update_cnt = 0;
-}
-
-static bool auok1900fb_need_refresh(struct auok190xfb_par *par)
-{
- return (par->update_cnt > 10);
-}
-
-static int auok1900fb_probe(struct platform_device *pdev)
-{
- struct auok190x_init_data init;
- struct auok190x_board *board;
-
- /* pick up board specific routines */
- board = pdev->dev.platform_data;
- if (!board)
- return -EINVAL;
-
- /* fill temporary init struct for common init */
- init.id = "auo_k1900fb";
- init.board = board;
- init.update_partial = auok1900fb_dpy_update_pages;
- init.update_all = auok1900fb_dpy_update;
- init.need_refresh = auok1900fb_need_refresh;
- init.init = auok1900_init;
-
- return auok190x_common_probe(pdev, &init);
-}
-
-static int auok1900fb_remove(struct platform_device *pdev)
-{
- return auok190x_common_remove(pdev);
-}
-
-static struct platform_driver auok1900fb_driver = {
- .probe = auok1900fb_probe,
- .remove = auok1900fb_remove,
- .driver = {
- .name = "auo_k1900fb",
- .pm = &auok190x_pm,
- },
-};
-module_platform_driver(auok1900fb_driver);
-
-MODULE_DESCRIPTION("framebuffer driver for the AUO-K1900 EPD controller");
-MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
-MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * auok190xfb.c -- FB driver for AUO-K1901 controllers
- *
- * Copyright (C) 2011, 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * based on broadsheetfb.c
- *
- * Copyright (C) 2008, Jaya Kumar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Layout is based on skeletonfb.c by James Simmons and Geert Uytterhoeven.
- *
- * This driver is written to be used with the AUO-K1901 display controller.
- *
- * It is intended to be architecture independent. A board specific driver
- * must be used to perform all the physical IO interactions.
- *
- * The controller supports different update modes:
- * mode0+1 16 step gray (4bit)
- * mode2+3 4 step gray (2bit)
- * mode4+5 2 step gray (1bit)
- * - mode4 is described as "without LUT"
- * mode7 automatic selection of update mode
- *
- * The most interesting difference to the K1900 is the ability to do screen
- * updates in an asynchronous fashion. Where the K1900 needs to wait for the
- * current update to complete, the K1901 can process later updates already.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/list.h>
-#include <linux/firmware.h>
-#include <linux/gpio.h>
-#include <linux/pm_runtime.h>
-
-#include <video/auo_k190xfb.h>
-
-#include "auo_k190x.h"
-
-/*
- * AUO-K1901 specific commands
- */
-
-#define AUOK1901_CMD_LUT_INTERFACE 0x0005
-#define AUOK1901_CMD_DMA_START 0x1001
-#define AUOK1901_CMD_CURSOR_START 0x1007
-#define AUOK1901_CMD_CURSOR_STOP AUOK190X_CMD_DATA_STOP
-#define AUOK1901_CMD_DDMA_START 0x1009
-
-#define AUOK1901_INIT_GATE_PULSE_LOW (0 << 14)
-#define AUOK1901_INIT_GATE_PULSE_HIGH (1 << 14)
-#define AUOK1901_INIT_SINGLE_GATE (0 << 13)
-#define AUOK1901_INIT_DOUBLE_GATE (1 << 13)
-
-/* Bits to pixels
- * Mode 15-12 11-8 7-4 3-0
- * format2 2 T 1 T
- * format3 1 T 2 T
- * format4 T 2 T 1
- * format5 T 1 T 2
- *
- * halftone modes:
- * format6 2 2 1 1
- * format7 1 1 2 2
- */
-#define AUOK1901_INIT_FORMAT2 (1 << 7)
-#define AUOK1901_INIT_FORMAT3 ((1 << 7) | (1 << 6))
-#define AUOK1901_INIT_FORMAT4 (1 << 8)
-#define AUOK1901_INIT_FORMAT5 ((1 << 8) | (1 << 6))
-#define AUOK1901_INIT_FORMAT6 ((1 << 8) | (1 << 7))
-#define AUOK1901_INIT_FORMAT7 ((1 << 8) | (1 << 7) | (1 << 6))
-
-/* res[4] to bit 10
- * res[3-0] to bits 5-2
- */
-#define AUOK1901_INIT_RESOLUTION(_res) (((_res & (1 << 4)) << 6) \
- | ((_res & 0xf) << 2))
-
-/*
- * portrait / landscape orientation in AUOK1901_CMD_DMA_START
- */
-#define AUOK1901_DMA_ROTATE90(_rot) ((_rot & 1) << 13)
-
-/*
- * equivalent to 1 << 11, needs the ~ to have same rotation like K1900
- */
-#define AUOK1901_DDMA_ROTATE180(_rot) ((~_rot & 2) << 10)
-
-static void auok1901_init(struct auok190xfb_par *par)
-{
- struct device *dev = par->info->device;
- struct auok190x_board *board = par->board;
- u16 init_param = 0;
-
- pm_runtime_get_sync(dev);
-
- init_param |= AUOK190X_INIT_INVERSE_WHITE;
- init_param |= AUOK190X_INIT_FORMAT0;
- init_param |= AUOK1901_INIT_RESOLUTION(par->resolution);
- init_param |= AUOK190X_INIT_SHIFT_LEFT;
-
- auok190x_send_cmdargs(par, AUOK190X_CMD_INIT, 1, &init_param);
-
- /* let the controller finish */
- board->wait_for_rdy(par);
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-}
-
-static void auok1901_update_region(struct auok190xfb_par *par, int mode,
- u16 y1, u16 y2)
-{
- struct device *dev = par->info->device;
- unsigned char *buf = (unsigned char *)par->info->screen_base;
- int xres = par->info->var.xres;
- int line_length = par->info->fix.line_length;
- u16 args[5];
-
- pm_runtime_get_sync(dev);
-
- mutex_lock(&(par->io_lock));
-
- /* y1 and y2 must be a multiple of 2 so drop the lowest bit */
- y1 &= 0xfffe;
- y2 &= 0xfffe;
-
- dev_dbg(dev, "update (x,y,w,h,mode)=(%d,%d,%d,%d,%d)\n",
- 1, y1+1, xres, y2-y1, mode);
-
- /* K1901: first transfer the region data */
- args[0] = AUOK1901_DMA_ROTATE90(par->rotation) | 1;
- args[1] = y1 + 1;
- args[2] = xres;
- args[3] = y2 - y1;
- buf += y1 * line_length;
- auok190x_send_cmdargs_pixels_nowait(par, AUOK1901_CMD_DMA_START, 4,
- args, ((y2 - y1) * line_length)/2,
- (u16 *) buf);
- auok190x_send_command_nowait(par, AUOK190X_CMD_DATA_STOP);
-
- /* K1901: second tell the controller to update the region with mode */
- args[0] = mode | AUOK1901_DDMA_ROTATE180(par->rotation);
- args[1] = 1;
- args[2] = y1 + 1;
- args[3] = xres;
- args[4] = y2 - y1;
- auok190x_send_cmdargs_nowait(par, AUOK1901_CMD_DDMA_START, 5, args);
-
- par->update_cnt++;
-
- mutex_unlock(&(par->io_lock));
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-}
-
-static void auok1901fb_dpy_update_pages(struct auok190xfb_par *par,
- u16 y1, u16 y2)
-{
- int mode;
-
- if (par->update_mode < 0) {
- mode = AUOK190X_UPDATE_MODE(1);
- par->last_mode = -1;
- } else {
- mode = AUOK190X_UPDATE_MODE(par->update_mode);
- par->last_mode = par->update_mode;
- }
-
- if (par->flash)
- mode |= AUOK190X_UPDATE_NONFLASH;
-
- auok1901_update_region(par, mode, y1, y2);
-}
-
-static void auok1901fb_dpy_update(struct auok190xfb_par *par)
-{
- int mode;
-
- /* When doing full updates, wait for the controller to be ready
- * This will hopefully catch some hangs of the K1901
- */
- par->board->wait_for_rdy(par);
-
- if (par->update_mode < 0) {
- mode = AUOK190X_UPDATE_MODE(0);
- par->last_mode = -1;
- } else {
- mode = AUOK190X_UPDATE_MODE(par->update_mode);
- par->last_mode = par->update_mode;
- }
-
- if (par->flash)
- mode |= AUOK190X_UPDATE_NONFLASH;
-
- auok1901_update_region(par, mode, 0, par->info->var.yres);
- par->update_cnt = 0;
-}
-
-static bool auok1901fb_need_refresh(struct auok190xfb_par *par)
-{
- return (par->update_cnt > 10);
-}
-
-static int auok1901fb_probe(struct platform_device *pdev)
-{
- struct auok190x_init_data init;
- struct auok190x_board *board;
-
- /* pick up board specific routines */
- board = pdev->dev.platform_data;
- if (!board)
- return -EINVAL;
-
- /* fill temporary init struct for common init */
- init.id = "auo_k1901fb";
- init.board = board;
- init.update_partial = auok1901fb_dpy_update_pages;
- init.update_all = auok1901fb_dpy_update;
- init.need_refresh = auok1901fb_need_refresh;
- init.init = auok1901_init;
-
- return auok190x_common_probe(pdev, &init);
-}
-
-static int auok1901fb_remove(struct platform_device *pdev)
-{
- return auok190x_common_remove(pdev);
-}
-
-static struct platform_driver auok1901fb_driver = {
- .probe = auok1901fb_probe,
- .remove = auok1901fb_remove,
- .driver = {
- .name = "auo_k1901fb",
- .pm = &auok190x_pm,
- },
-};
-module_platform_driver(auok1901fb_driver);
-
-MODULE_DESCRIPTION("framebuffer driver for the AUO-K1901 EPD controller");
-MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
-MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * Common code for AUO-K190X framebuffer drivers
- *
- * Copyright (C) 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/sched/mm.h>
-#include <linux/kernel.h>
-#include <linux/gpio.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include <linux/fb.h>
-#include <linux/delay.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/regulator/consumer.h>
-
-#include <video/auo_k190xfb.h>
-
-#include "auo_k190x.h"
-
-struct panel_info {
- int w;
- int h;
-};
-
-/* table of panel specific parameters to be indexed into by the board drivers */
-static struct panel_info panel_table[] = {
- /* standard 6" */
- [AUOK190X_RESOLUTION_800_600] = {
- .w = 800,
- .h = 600,
- },
- /* standard 9" */
- [AUOK190X_RESOLUTION_1024_768] = {
- .w = 1024,
- .h = 768,
- },
- [AUOK190X_RESOLUTION_600_800] = {
- .w = 600,
- .h = 800,
- },
- [AUOK190X_RESOLUTION_768_1024] = {
- .w = 768,
- .h = 1024,
- },
-};
-
-/*
- * private I80 interface to the board driver
- */
-
-static void auok190x_issue_data(struct auok190xfb_par *par, u16 data)
-{
- par->board->set_ctl(par, AUOK190X_I80_WR, 0);
- par->board->set_hdb(par, data);
- par->board->set_ctl(par, AUOK190X_I80_WR, 1);
-}
-
-static void auok190x_issue_cmd(struct auok190xfb_par *par, u16 data)
-{
- par->board->set_ctl(par, AUOK190X_I80_DC, 0);
- auok190x_issue_data(par, data);
- par->board->set_ctl(par, AUOK190X_I80_DC, 1);
-}
-
-/**
- * Conversion of 16bit color to 4bit grayscale
- * does roughly (0.3 * R + 0.6 G + 0.1 B) / 2
- */
-static inline int rgb565_to_gray4(u16 data, struct fb_var_screeninfo *var)
-{
- return ((((data & 0xF800) >> var->red.offset) * 77 +
- ((data & 0x07E0) >> (var->green.offset + 1)) * 151 +
- ((data & 0x1F) >> var->blue.offset) * 28) >> 8 >> 1);
-}
-
-static int auok190x_issue_pixels_rgb565(struct auok190xfb_par *par, int size,
- u16 *data)
-{
- struct fb_var_screeninfo *var = &par->info->var;
- struct device *dev = par->info->device;
- int i;
- u16 tmp;
-
- if (size & 7) {
- dev_err(dev, "issue_pixels: size %d must be a multiple of 8\n",
- size);
- return -EINVAL;
- }
-
- for (i = 0; i < (size >> 2); i++) {
- par->board->set_ctl(par, AUOK190X_I80_WR, 0);
-
- tmp = (rgb565_to_gray4(data[4*i], var) & 0x000F);
- tmp |= (rgb565_to_gray4(data[4*i+1], var) << 4) & 0x00F0;
- tmp |= (rgb565_to_gray4(data[4*i+2], var) << 8) & 0x0F00;
- tmp |= (rgb565_to_gray4(data[4*i+3], var) << 12) & 0xF000;
-
- par->board->set_hdb(par, tmp);
- par->board->set_ctl(par, AUOK190X_I80_WR, 1);
- }
-
- return 0;
-}
-
-static int auok190x_issue_pixels_gray8(struct auok190xfb_par *par, int size,
- u16 *data)
-{
- struct device *dev = par->info->device;
- int i;
- u16 tmp;
-
- if (size & 3) {
- dev_err(dev, "issue_pixels: size %d must be a multiple of 4\n",
- size);
- return -EINVAL;
- }
-
- for (i = 0; i < (size >> 1); i++) {
- par->board->set_ctl(par, AUOK190X_I80_WR, 0);
-
- /* simple reduction of 8bit staticgray to 4bit gray
- * combines 4 * 4bit pixel values into a 16bit value
- */
- tmp = (data[2*i] & 0xF0) >> 4;
- tmp |= (data[2*i] & 0xF000) >> 8;
- tmp |= (data[2*i+1] & 0xF0) << 4;
- tmp |= (data[2*i+1] & 0xF000);
-
- par->board->set_hdb(par, tmp);
- par->board->set_ctl(par, AUOK190X_I80_WR, 1);
- }
-
- return 0;
-}
-
-static int auok190x_issue_pixels(struct auok190xfb_par *par, int size,
- u16 *data)
-{
- struct fb_info *info = par->info;
- struct device *dev = par->info->device;
-
- if (info->var.bits_per_pixel == 8 && info->var.grayscale)
- auok190x_issue_pixels_gray8(par, size, data);
- else if (info->var.bits_per_pixel == 16)
- auok190x_issue_pixels_rgb565(par, size, data);
- else
- dev_err(dev, "unsupported color mode (bits: %d, gray: %d)\n",
- info->var.bits_per_pixel, info->var.grayscale);
-
- return 0;
-}
-
-static u16 auok190x_read_data(struct auok190xfb_par *par)
-{
- u16 data;
-
- par->board->set_ctl(par, AUOK190X_I80_OE, 0);
- data = par->board->get_hdb(par);
- par->board->set_ctl(par, AUOK190X_I80_OE, 1);
-
- return data;
-}
-
-/*
- * Command interface for the controller drivers
- */
-
-void auok190x_send_command_nowait(struct auok190xfb_par *par, u16 data)
-{
- par->board->set_ctl(par, AUOK190X_I80_CS, 0);
- auok190x_issue_cmd(par, data);
- par->board->set_ctl(par, AUOK190X_I80_CS, 1);
-}
-EXPORT_SYMBOL_GPL(auok190x_send_command_nowait);
-
-void auok190x_send_cmdargs_nowait(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv)
-{
- int i;
-
- par->board->set_ctl(par, AUOK190X_I80_CS, 0);
- auok190x_issue_cmd(par, cmd);
-
- for (i = 0; i < argc; i++)
- auok190x_issue_data(par, argv[i]);
- par->board->set_ctl(par, AUOK190X_I80_CS, 1);
-}
-EXPORT_SYMBOL_GPL(auok190x_send_cmdargs_nowait);
-
-int auok190x_send_command(struct auok190xfb_par *par, u16 data)
-{
- int ret;
-
- ret = par->board->wait_for_rdy(par);
- if (ret)
- return ret;
-
- auok190x_send_command_nowait(par, data);
- return 0;
-}
-EXPORT_SYMBOL_GPL(auok190x_send_command);
-
-int auok190x_send_cmdargs(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv)
-{
- int ret;
-
- ret = par->board->wait_for_rdy(par);
- if (ret)
- return ret;
-
- auok190x_send_cmdargs_nowait(par, cmd, argc, argv);
- return 0;
-}
-EXPORT_SYMBOL_GPL(auok190x_send_cmdargs);
-
-int auok190x_read_cmdargs(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv)
-{
- int i, ret;
-
- ret = par->board->wait_for_rdy(par);
- if (ret)
- return ret;
-
- par->board->set_ctl(par, AUOK190X_I80_CS, 0);
- auok190x_issue_cmd(par, cmd);
-
- for (i = 0; i < argc; i++)
- argv[i] = auok190x_read_data(par);
- par->board->set_ctl(par, AUOK190X_I80_CS, 1);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(auok190x_read_cmdargs);
-
-void auok190x_send_cmdargs_pixels_nowait(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv, int size, u16 *data)
-{
- int i;
-
- par->board->set_ctl(par, AUOK190X_I80_CS, 0);
-
- auok190x_issue_cmd(par, cmd);
-
- for (i = 0; i < argc; i++)
- auok190x_issue_data(par, argv[i]);
-
- auok190x_issue_pixels(par, size, data);
-
- par->board->set_ctl(par, AUOK190X_I80_CS, 1);
-}
-EXPORT_SYMBOL_GPL(auok190x_send_cmdargs_pixels_nowait);
-
-int auok190x_send_cmdargs_pixels(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv, int size, u16 *data)
-{
- int ret;
-
- ret = par->board->wait_for_rdy(par);
- if (ret)
- return ret;
-
- auok190x_send_cmdargs_pixels_nowait(par, cmd, argc, argv, size, data);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(auok190x_send_cmdargs_pixels);
-
-/*
- * fbdefio callbacks - common on both controllers.
- */
-
-static void auok190xfb_dpy_first_io(struct fb_info *info)
-{
- /* tell runtime-pm that we wish to use the device in a short time */
- pm_runtime_get(info->device);
-}
-
-/* this is called back from the deferred io workqueue */
-static void auok190xfb_dpy_deferred_io(struct fb_info *info,
- struct list_head *pagelist)
-{
- struct fb_deferred_io *fbdefio = info->fbdefio;
- struct auok190xfb_par *par = info->par;
- u16 line_length = info->fix.line_length;
- u16 yres = info->var.yres;
- u16 y1 = 0, h = 0;
- int prev_index = -1;
- struct page *cur;
- int h_inc;
- int threshold;
-
- if (!list_empty(pagelist))
- /* the device resume should've been requested through first_io,
- * if the resume did not finish until now, wait for it.
- */
- pm_runtime_barrier(info->device);
- else
- /* We reached this via the fsync or some other way.
- * In either case the first_io function did not run,
- * so we runtime_resume the device here synchronously.
- */
- pm_runtime_get_sync(info->device);
-
- /* Do a full screen update every n updates to prevent
- * excessive darkening of the Sipix display.
- * If we do this, there is no need to walk the pages.
- */
- if (par->need_refresh(par)) {
- par->update_all(par);
- goto out;
- }
-
- /* height increment is fixed per page */
- h_inc = DIV_ROUND_UP(PAGE_SIZE , line_length);
-
- /* calculate number of pages from pixel height */
- threshold = par->consecutive_threshold / h_inc;
- if (threshold < 1)
- threshold = 1;
-
- /* walk the written page list and swizzle the data */
- list_for_each_entry(cur, &fbdefio->pagelist, lru) {
- if (prev_index < 0) {
- /* just starting so assign first page */
- y1 = (cur->index << PAGE_SHIFT) / line_length;
- h = h_inc;
- } else if ((cur->index - prev_index) <= threshold) {
- /* page is within our threshold for single updates */
- h += h_inc * (cur->index - prev_index);
- } else {
- /* page not consecutive, issue previous update first */
- par->update_partial(par, y1, y1 + h);
-
- /* start over with our non consecutive page */
- y1 = (cur->index << PAGE_SHIFT) / line_length;
- h = h_inc;
- }
- prev_index = cur->index;
- }
-
- /* if we still have any pages to update we do so now */
- if (h >= yres)
- /* its a full screen update, just do it */
- par->update_all(par);
- else
- par->update_partial(par, y1, min((u16) (y1 + h), yres));
-
-out:
- pm_runtime_mark_last_busy(info->device);
- pm_runtime_put_autosuspend(info->device);
-}
-
-/*
- * framebuffer operations
- */
-
-/*
- * this is the slow path from userspace. they can seek and write to
- * the fb. it's inefficient to do anything less than a full screen draw
- */
-static ssize_t auok190xfb_write(struct fb_info *info, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct auok190xfb_par *par = info->par;
- unsigned long p = *ppos;
- void *dst;
- int err = 0;
- unsigned long total_size;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return -EPERM;
-
- total_size = info->fix.smem_len;
-
- if (p > total_size)
- return -EFBIG;
-
- if (count > total_size) {
- err = -EFBIG;
- count = total_size;
- }
-
- if (count + p > total_size) {
- if (!err)
- err = -ENOSPC;
-
- count = total_size - p;
- }
-
- dst = (void *)(info->screen_base + p);
-
- if (copy_from_user(dst, buf, count))
- err = -EFAULT;
-
- if (!err)
- *ppos += count;
-
- par->update_all(par);
-
- return (err) ? err : count;
-}
-
-static void auok190xfb_fillrect(struct fb_info *info,
- const struct fb_fillrect *rect)
-{
- struct auok190xfb_par *par = info->par;
-
- sys_fillrect(info, rect);
-
- par->update_all(par);
-}
-
-static void auok190xfb_copyarea(struct fb_info *info,
- const struct fb_copyarea *area)
-{
- struct auok190xfb_par *par = info->par;
-
- sys_copyarea(info, area);
-
- par->update_all(par);
-}
-
-static void auok190xfb_imageblit(struct fb_info *info,
- const struct fb_image *image)
-{
- struct auok190xfb_par *par = info->par;
-
- sys_imageblit(info, image);
-
- par->update_all(par);
-}
-
-static int auok190xfb_check_var(struct fb_var_screeninfo *var,
- struct fb_info *info)
-{
- struct device *dev = info->device;
- struct auok190xfb_par *par = info->par;
- struct panel_info *panel = &panel_table[par->resolution];
- int size;
-
- /*
- * Color depth
- */
-
- if (var->bits_per_pixel == 8 && var->grayscale == 1) {
- /*
- * For 8-bit grayscale, R, G, and B offset are equal.
- */
- var->red.length = 8;
- var->red.offset = 0;
- var->red.msb_right = 0;
-
- var->green.length = 8;
- var->green.offset = 0;
- var->green.msb_right = 0;
-
- var->blue.length = 8;
- var->blue.offset = 0;
- var->blue.msb_right = 0;
-
- var->transp.length = 0;
- var->transp.offset = 0;
- var->transp.msb_right = 0;
- } else if (var->bits_per_pixel == 16) {
- var->red.length = 5;
- var->red.offset = 11;
- var->red.msb_right = 0;
-
- var->green.length = 6;
- var->green.offset = 5;
- var->green.msb_right = 0;
-
- var->blue.length = 5;
- var->blue.offset = 0;
- var->blue.msb_right = 0;
-
- var->transp.length = 0;
- var->transp.offset = 0;
- var->transp.msb_right = 0;
- } else {
- dev_warn(dev, "unsupported color mode (bits: %d, grayscale: %d)\n",
- info->var.bits_per_pixel, info->var.grayscale);
- return -EINVAL;
- }
-
- /*
- * Dimensions
- */
-
- switch (var->rotate) {
- case FB_ROTATE_UR:
- case FB_ROTATE_UD:
- var->xres = panel->w;
- var->yres = panel->h;
- break;
- case FB_ROTATE_CW:
- case FB_ROTATE_CCW:
- var->xres = panel->h;
- var->yres = panel->w;
- break;
- default:
- dev_dbg(dev, "Invalid rotation request\n");
- return -EINVAL;
- }
-
- var->xres_virtual = var->xres;
- var->yres_virtual = var->yres;
-
- /*
- * Memory limit
- */
-
- size = var->xres_virtual * var->yres_virtual * var->bits_per_pixel / 8;
- if (size > info->fix.smem_len) {
- dev_err(dev, "Memory limit exceeded, requested %dK\n",
- size >> 10);
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static int auok190xfb_set_fix(struct fb_info *info)
-{
- struct fb_fix_screeninfo *fix = &info->fix;
- struct fb_var_screeninfo *var = &info->var;
-
- fix->line_length = var->xres_virtual * var->bits_per_pixel / 8;
-
- fix->type = FB_TYPE_PACKED_PIXELS;
- fix->accel = FB_ACCEL_NONE;
- fix->visual = (var->grayscale) ? FB_VISUAL_STATIC_PSEUDOCOLOR
- : FB_VISUAL_TRUECOLOR;
- fix->xpanstep = 0;
- fix->ypanstep = 0;
- fix->ywrapstep = 0;
-
- return 0;
-}
-
-static int auok190xfb_set_par(struct fb_info *info)
-{
- struct auok190xfb_par *par = info->par;
-
- par->rotation = info->var.rotate;
- auok190xfb_set_fix(info);
-
- /* reinit the controller to honor the rotation */
- par->init(par);
-
- /* wait for init to complete */
- par->board->wait_for_rdy(par);
-
- return 0;
-}
-
-static struct fb_ops auok190xfb_ops = {
- .owner = THIS_MODULE,
- .fb_read = fb_sys_read,
- .fb_write = auok190xfb_write,
- .fb_fillrect = auok190xfb_fillrect,
- .fb_copyarea = auok190xfb_copyarea,
- .fb_imageblit = auok190xfb_imageblit,
- .fb_check_var = auok190xfb_check_var,
- .fb_set_par = auok190xfb_set_par,
-};
-
-/*
- * Controller-functions common to both K1900 and K1901
- */
-
-static int auok190x_read_temperature(struct auok190xfb_par *par)
-{
- struct device *dev = par->info->device;
- u16 data[4];
- int temp;
-
- pm_runtime_get_sync(dev);
-
- mutex_lock(&(par->io_lock));
-
- auok190x_read_cmdargs(par, AUOK190X_CMD_READ_VERSION, 4, data);
-
- mutex_unlock(&(par->io_lock));
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-
- /* sanitize and split of half-degrees for now */
- temp = ((data[0] & AUOK190X_VERSION_TEMP_MASK) >> 1);
-
- /* handle positive and negative temperatures */
- if (temp >= 201)
- return (255 - temp + 1) * (-1);
- else
- return temp;
-}
-
-static void auok190x_identify(struct auok190xfb_par *par)
-{
- struct device *dev = par->info->device;
- u16 data[4];
-
- pm_runtime_get_sync(dev);
-
- mutex_lock(&(par->io_lock));
-
- auok190x_read_cmdargs(par, AUOK190X_CMD_READ_VERSION, 4, data);
-
- mutex_unlock(&(par->io_lock));
-
- par->epd_type = data[1] & AUOK190X_VERSION_TEMP_MASK;
-
- par->panel_size_int = AUOK190X_VERSION_SIZE_INT(data[2]);
- par->panel_size_float = AUOK190X_VERSION_SIZE_FLOAT(data[2]);
- par->panel_model = AUOK190X_VERSION_MODEL(data[2]);
-
- par->tcon_version = AUOK190X_VERSION_TCON(data[3]);
- par->lut_version = AUOK190X_VERSION_LUT(data[3]);
-
- dev_dbg(dev, "panel %d.%din, model 0x%x, EPD 0x%x TCON-rev 0x%x, LUT-rev 0x%x",
- par->panel_size_int, par->panel_size_float, par->panel_model,
- par->epd_type, par->tcon_version, par->lut_version);
-
- pm_runtime_mark_last_busy(dev);
- pm_runtime_put_autosuspend(dev);
-}
-
-/*
- * Sysfs functions
- */
-
-static ssize_t update_mode_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct auok190xfb_par *par = info->par;
-
- return sprintf(buf, "%d\n", par->update_mode);
-}
-
-static ssize_t update_mode_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct auok190xfb_par *par = info->par;
- int mode, ret;
-
- ret = kstrtoint(buf, 10, &mode);
- if (ret)
- return ret;
-
- par->update_mode = mode;
-
- /* if we enter a better mode, do a full update */
- if (par->last_mode > 1 && mode < par->last_mode)
- par->update_all(par);
-
- return count;
-}
-
-static ssize_t flash_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct auok190xfb_par *par = info->par;
-
- return sprintf(buf, "%d\n", par->flash);
-}
-
-static ssize_t flash_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct auok190xfb_par *par = info->par;
- int flash, ret;
-
- ret = kstrtoint(buf, 10, &flash);
- if (ret)
- return ret;
-
- if (flash > 0)
- par->flash = 1;
- else
- par->flash = 0;
-
- return count;
-}
-
-static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct auok190xfb_par *par = info->par;
- int temp;
-
- temp = auok190x_read_temperature(par);
- return sprintf(buf, "%d\n", temp);
-}
-
-static DEVICE_ATTR_RW(update_mode);
-static DEVICE_ATTR_RW(flash);
-static DEVICE_ATTR(temp, 0644, temp_show, NULL);
-
-static struct attribute *auok190x_attributes[] = {
- &dev_attr_update_mode.attr,
- &dev_attr_flash.attr,
- &dev_attr_temp.attr,
- NULL
-};
-
-static const struct attribute_group auok190x_attr_group = {
- .attrs = auok190x_attributes,
-};
-
-static int auok190x_power(struct auok190xfb_par *par, bool on)
-{
- struct auok190x_board *board = par->board;
- int ret;
-
- if (on) {
- /* We should maintain POWER up for at least 80ms before set
- * RST_N and SLP_N to high (TCON spec 20100803_v35 p59)
- */
- ret = regulator_enable(par->regulator);
- if (ret)
- return ret;
-
- msleep(200);
- gpio_set_value(board->gpio_nrst, 1);
- gpio_set_value(board->gpio_nsleep, 1);
- msleep(200);
- } else {
- regulator_disable(par->regulator);
- gpio_set_value(board->gpio_nrst, 0);
- gpio_set_value(board->gpio_nsleep, 0);
- }
-
- return 0;
-}
-
-/*
- * Recovery - powercycle the controller
- */
-
-static void auok190x_recover(struct auok190xfb_par *par)
-{
- struct device *dev = par->info->device;
-
- auok190x_power(par, 0);
- msleep(100);
- auok190x_power(par, 1);
-
- /* after powercycling the device, it's always active */
- pm_runtime_set_active(dev);
- par->standby = 0;
-
- par->init(par);
-
- /* wait for init to complete */
- par->board->wait_for_rdy(par);
-}
-
-/*
- * Power-management
- */
-static int __maybe_unused auok190x_runtime_suspend(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct fb_info *info = platform_get_drvdata(pdev);
- struct auok190xfb_par *par = info->par;
- struct auok190x_board *board = par->board;
- u16 standby_param;
-
- /* take and keep the lock until we are resumed, as the controller
- * will never reach the non-busy state when in standby mode
- */
- mutex_lock(&(par->io_lock));
-
- if (par->standby) {
- dev_warn(dev, "already in standby, runtime-pm pairing mismatch\n");
- mutex_unlock(&(par->io_lock));
- return 0;
- }
-
- /* according to runtime_pm.txt runtime_suspend only means, that the
- * device will not process data and will not communicate with the CPU
- * As we hold the lock, this stays true even without standby
- */
- if (board->quirks & AUOK190X_QUIRK_STANDBYBROKEN) {
- dev_dbg(dev, "runtime suspend without standby\n");
- goto finish;
- } else if (board->quirks & AUOK190X_QUIRK_STANDBYPARAM) {
- /* for some TCON versions STANDBY expects a parameter (0) but
- * it seems the real tcon version has to be determined yet.
- */
- dev_dbg(dev, "runtime suspend with additional empty param\n");
- standby_param = 0;
- auok190x_send_cmdargs(par, AUOK190X_CMD_STANDBY, 1,
- &standby_param);
- } else {
- dev_dbg(dev, "runtime suspend without param\n");
- auok190x_send_command(par, AUOK190X_CMD_STANDBY);
- }
-
- msleep(64);
-
-finish:
- par->standby = 1;
-
- return 0;
-}
-
-static int __maybe_unused auok190x_runtime_resume(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct fb_info *info = platform_get_drvdata(pdev);
- struct auok190xfb_par *par = info->par;
- struct auok190x_board *board = par->board;
-
- if (!par->standby) {
- dev_warn(dev, "not in standby, runtime-pm pairing mismatch\n");
- return 0;
- }
-
- if (board->quirks & AUOK190X_QUIRK_STANDBYBROKEN) {
- dev_dbg(dev, "runtime resume without standby\n");
- } else {
- /* when in standby, controller is always busy
- * and only accepts the wakeup command
- */
- dev_dbg(dev, "runtime resume from standby\n");
- auok190x_send_command_nowait(par, AUOK190X_CMD_WAKEUP);
-
- msleep(160);
-
- /* wait for the controller to be ready and release the lock */
- board->wait_for_rdy(par);
- }
-
- par->standby = 0;
-
- mutex_unlock(&(par->io_lock));
-
- return 0;
-}
-
-static int __maybe_unused auok190x_suspend(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct fb_info *info = platform_get_drvdata(pdev);
- struct auok190xfb_par *par = info->par;
- struct auok190x_board *board = par->board;
- int ret;
-
- dev_dbg(dev, "suspend\n");
- if (board->quirks & AUOK190X_QUIRK_STANDBYBROKEN) {
- /* suspend via powering off the ic */
- dev_dbg(dev, "suspend with broken standby\n");
-
- auok190x_power(par, 0);
- } else {
- dev_dbg(dev, "suspend using sleep\n");
-
- /* the sleep state can only be entered from the standby state.
- * pm_runtime_get_noresume gets called before the suspend call.
- * So the devices usage count is >0 but it is not necessarily
- * active.
- */
- if (!pm_runtime_status_suspended(dev)) {
- ret = auok190x_runtime_suspend(dev);
- if (ret < 0) {
- dev_err(dev, "auok190x_runtime_suspend failed with %d\n",
- ret);
- return ret;
- }
- par->manual_standby = 1;
- }
-
- gpio_direction_output(board->gpio_nsleep, 0);
- }
-
- msleep(100);
-
- return 0;
-}
-
-static int __maybe_unused auok190x_resume(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct fb_info *info = platform_get_drvdata(pdev);
- struct auok190xfb_par *par = info->par;
- struct auok190x_board *board = par->board;
-
- dev_dbg(dev, "resume\n");
- if (board->quirks & AUOK190X_QUIRK_STANDBYBROKEN) {
- dev_dbg(dev, "resume with broken standby\n");
-
- auok190x_power(par, 1);
-
- par->init(par);
- } else {
- dev_dbg(dev, "resume from sleep\n");
-
- /* device should be in runtime suspend when we were suspended
- * and pm_runtime_put_sync gets called after this function.
- * So there is no need to touch the standby mode here at all.
- */
- gpio_direction_output(board->gpio_nsleep, 1);
- msleep(100);
-
- /* an additional init call seems to be necessary after sleep */
- auok190x_runtime_resume(dev);
- par->init(par);
-
- /* if we were runtime-suspended before, suspend again*/
- if (!par->manual_standby)
- auok190x_runtime_suspend(dev);
- else
- par->manual_standby = 0;
- }
-
- return 0;
-}
-
-const struct dev_pm_ops auok190x_pm = {
- SET_RUNTIME_PM_OPS(auok190x_runtime_suspend, auok190x_runtime_resume,
- NULL)
- SET_SYSTEM_SLEEP_PM_OPS(auok190x_suspend, auok190x_resume)
-};
-EXPORT_SYMBOL_GPL(auok190x_pm);
-
-/*
- * Common probe and remove code
- */
-
-int auok190x_common_probe(struct platform_device *pdev,
- struct auok190x_init_data *init)
-{
- struct auok190x_board *board = init->board;
- struct auok190xfb_par *par;
- struct fb_info *info;
- struct panel_info *panel;
- int videomemorysize, ret;
- unsigned char *videomemory;
-
- /* check board contents */
- if (!board->init || !board->cleanup || !board->wait_for_rdy
- || !board->set_ctl || !board->set_hdb || !board->get_hdb
- || !board->setup_irq)
- return -EINVAL;
-
- info = framebuffer_alloc(sizeof(struct auok190xfb_par), &pdev->dev);
- if (!info)
- return -ENOMEM;
-
- par = info->par;
- par->info = info;
- par->board = board;
- par->recover = auok190x_recover;
- par->update_partial = init->update_partial;
- par->update_all = init->update_all;
- par->need_refresh = init->need_refresh;
- par->init = init->init;
-
- /* init update modes */
- par->update_cnt = 0;
- par->update_mode = -1;
- par->last_mode = -1;
- par->flash = 0;
-
- par->regulator = regulator_get(info->device, "vdd");
- if (IS_ERR(par->regulator)) {
- ret = PTR_ERR(par->regulator);
- dev_err(info->device, "Failed to get regulator: %d\n", ret);
- goto err_reg;
- }
-
- ret = board->init(par);
- if (ret) {
- dev_err(info->device, "board init failed, %d\n", ret);
- goto err_board;
- }
-
- ret = gpio_request(board->gpio_nsleep, "AUOK190x sleep");
- if (ret) {
- dev_err(info->device, "could not request sleep gpio, %d\n",
- ret);
- goto err_gpio1;
- }
-
- ret = gpio_direction_output(board->gpio_nsleep, 0);
- if (ret) {
- dev_err(info->device, "could not set sleep gpio, %d\n", ret);
- goto err_gpio2;
- }
-
- ret = gpio_request(board->gpio_nrst, "AUOK190x reset");
- if (ret) {
- dev_err(info->device, "could not request reset gpio, %d\n",
- ret);
- goto err_gpio2;
- }
-
- ret = gpio_direction_output(board->gpio_nrst, 0);
- if (ret) {
- dev_err(info->device, "could not set reset gpio, %d\n", ret);
- goto err_gpio3;
- }
-
- ret = auok190x_power(par, 1);
- if (ret) {
- dev_err(info->device, "could not power on the device, %d\n",
- ret);
- goto err_gpio3;
- }
-
- mutex_init(&par->io_lock);
-
- init_waitqueue_head(&par->waitq);
-
- ret = par->board->setup_irq(par->info);
- if (ret) {
- dev_err(info->device, "could not setup ready-irq, %d\n", ret);
- goto err_irq;
- }
-
- /* wait for init to complete */
- par->board->wait_for_rdy(par);
-
- /*
- * From here on the controller can talk to us
- */
-
- /* initialise fix, var, resolution and rotation */
-
- strlcpy(info->fix.id, init->id, 16);
- info->var.bits_per_pixel = 8;
- info->var.grayscale = 1;
-
- panel = &panel_table[board->resolution];
-
- par->resolution = board->resolution;
- par->rotation = 0;
-
- /* videomemory handling */
-
- videomemorysize = roundup((panel->w * panel->h) * 2, PAGE_SIZE);
- videomemory = vzalloc(videomemorysize);
- if (!videomemory) {
- ret = -ENOMEM;
- goto err_irq;
- }
-
- info->screen_base = (char *)videomemory;
- info->fix.smem_len = videomemorysize;
-
- info->flags = FBINFO_FLAG_DEFAULT | FBINFO_VIRTFB;
- info->fbops = &auok190xfb_ops;
-
- ret = auok190xfb_check_var(&info->var, info);
- if (ret)
- goto err_defio;
-
- auok190xfb_set_fix(info);
-
- /* deferred io init */
-
- info->fbdefio = devm_kzalloc(info->device,
- sizeof(struct fb_deferred_io),
- GFP_KERNEL);
- if (!info->fbdefio) {
- dev_err(info->device, "Failed to allocate memory\n");
- ret = -ENOMEM;
- goto err_defio;
- }
-
- dev_dbg(info->device, "targeting %d frames per second\n", board->fps);
- info->fbdefio->delay = HZ / board->fps;
- info->fbdefio->first_io = auok190xfb_dpy_first_io,
- info->fbdefio->deferred_io = auok190xfb_dpy_deferred_io,
- fb_deferred_io_init(info);
-
- /* color map */
-
- ret = fb_alloc_cmap(&info->cmap, 256, 0);
- if (ret < 0) {
- dev_err(info->device, "Failed to allocate colormap\n");
- goto err_cmap;
- }
-
- /* controller init */
-
- par->consecutive_threshold = 100;
- par->init(par);
- auok190x_identify(par);
-
- platform_set_drvdata(pdev, info);
-
- ret = register_framebuffer(info);
- if (ret < 0)
- goto err_regfb;
-
- ret = sysfs_create_group(&info->device->kobj, &auok190x_attr_group);
- if (ret)
- goto err_sysfs;
-
- dev_info(info->device, "fb%d: %dx%d using %dK of video memory\n",
- info->node, info->var.xres, info->var.yres,
- videomemorysize >> 10);
-
- /* increase autosuspend_delay when we use alternative methods
- * for runtime_pm
- */
- par->autosuspend_delay = (board->quirks & AUOK190X_QUIRK_STANDBYBROKEN)
- ? 1000 : 200;
-
- pm_runtime_set_active(info->device);
- pm_runtime_enable(info->device);
- pm_runtime_set_autosuspend_delay(info->device, par->autosuspend_delay);
- pm_runtime_use_autosuspend(info->device);
-
- return 0;
-
-err_sysfs:
- unregister_framebuffer(info);
-err_regfb:
- fb_dealloc_cmap(&info->cmap);
-err_cmap:
- fb_deferred_io_cleanup(info);
-err_defio:
- vfree((void *)info->screen_base);
-err_irq:
- auok190x_power(par, 0);
-err_gpio3:
- gpio_free(board->gpio_nrst);
-err_gpio2:
- gpio_free(board->gpio_nsleep);
-err_gpio1:
- board->cleanup(par);
-err_board:
- regulator_put(par->regulator);
-err_reg:
- framebuffer_release(info);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(auok190x_common_probe);
-
-int auok190x_common_remove(struct platform_device *pdev)
-{
- struct fb_info *info = platform_get_drvdata(pdev);
- struct auok190xfb_par *par = info->par;
- struct auok190x_board *board = par->board;
-
- pm_runtime_disable(info->device);
-
- sysfs_remove_group(&info->device->kobj, &auok190x_attr_group);
-
- unregister_framebuffer(info);
-
- fb_dealloc_cmap(&info->cmap);
-
- fb_deferred_io_cleanup(info);
-
- vfree((void *)info->screen_base);
-
- auok190x_power(par, 0);
-
- gpio_free(board->gpio_nrst);
- gpio_free(board->gpio_nsleep);
-
- board->cleanup(par);
-
- regulator_put(par->regulator);
-
- framebuffer_release(info);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(auok190x_common_remove);
-
-MODULE_DESCRIPTION("Common code for AUO-K190X controllers");
-MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
-MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * Private common definitions for AUO-K190X framebuffer drivers
- *
- * Copyright (C) 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * I80 interface specific defines
- */
-
-#define AUOK190X_I80_CS 0x01
-#define AUOK190X_I80_DC 0x02
-#define AUOK190X_I80_WR 0x03
-#define AUOK190X_I80_OE 0x04
-
-/*
- * AUOK190x commands, common to both controllers
- */
-
-#define AUOK190X_CMD_INIT 0x0000
-#define AUOK190X_CMD_STANDBY 0x0001
-#define AUOK190X_CMD_WAKEUP 0x0002
-#define AUOK190X_CMD_TCON_RESET 0x0003
-#define AUOK190X_CMD_DATA_STOP 0x1002
-#define AUOK190X_CMD_LUT_START 0x1003
-#define AUOK190X_CMD_DISP_REFRESH 0x1004
-#define AUOK190X_CMD_DISP_RESET 0x1005
-#define AUOK190X_CMD_PRE_DISPLAY_START 0x100D
-#define AUOK190X_CMD_PRE_DISPLAY_STOP 0x100F
-#define AUOK190X_CMD_FLASH_W 0x2000
-#define AUOK190X_CMD_FLASH_E 0x2001
-#define AUOK190X_CMD_FLASH_STS 0x2002
-#define AUOK190X_CMD_FRAMERATE 0x3000
-#define AUOK190X_CMD_READ_VERSION 0x4000
-#define AUOK190X_CMD_READ_STATUS 0x4001
-#define AUOK190X_CMD_READ_LUT 0x4003
-#define AUOK190X_CMD_DRIVERTIMING 0x5000
-#define AUOK190X_CMD_LBALANCE 0x5001
-#define AUOK190X_CMD_AGINGMODE 0x6000
-#define AUOK190X_CMD_AGINGEXIT 0x6001
-
-/*
- * Common settings for AUOK190X_CMD_INIT
- */
-
-#define AUOK190X_INIT_DATA_FILTER (0 << 12)
-#define AUOK190X_INIT_DATA_BYPASS (1 << 12)
-#define AUOK190X_INIT_INVERSE_WHITE (0 << 9)
-#define AUOK190X_INIT_INVERSE_BLACK (1 << 9)
-#define AUOK190X_INIT_SCAN_DOWN (0 << 1)
-#define AUOK190X_INIT_SCAN_UP (1 << 1)
-#define AUOK190X_INIT_SHIFT_LEFT (0 << 0)
-#define AUOK190X_INIT_SHIFT_RIGHT (1 << 0)
-
-/* Common bits to pixels
- * Mode 15-12 11-8 7-4 3-0
- * format0 4 3 2 1
- * format1 3 4 1 2
- */
-
-#define AUOK190X_INIT_FORMAT0 0
-#define AUOK190X_INIT_FORMAT1 (1 << 6)
-
-/*
- * settings for AUOK190X_CMD_RESET
- */
-
-#define AUOK190X_RESET_TCON (0 << 0)
-#define AUOK190X_RESET_NORMAL (1 << 0)
-#define AUOK190X_RESET_PON (1 << 1)
-
-/*
- * AUOK190X_CMD_VERSION
- */
-
-#define AUOK190X_VERSION_TEMP_MASK (0x1ff)
-#define AUOK190X_VERSION_EPD_MASK (0xff)
-#define AUOK190X_VERSION_SIZE_INT(_val) ((_val & 0xfc00) >> 10)
-#define AUOK190X_VERSION_SIZE_FLOAT(_val) ((_val & 0x3c0) >> 6)
-#define AUOK190X_VERSION_MODEL(_val) (_val & 0x3f)
-#define AUOK190X_VERSION_LUT(_val) (_val & 0xff)
-#define AUOK190X_VERSION_TCON(_val) ((_val & 0xff00) >> 8)
-
-/*
- * update modes for CMD_PARTIALDISP on K1900 and CMD_DDMA on K1901
- */
-
-#define AUOK190X_UPDATE_MODE(_res) ((_res & 0x7) << 12)
-#define AUOK190X_UPDATE_NONFLASH (1 << 15)
-
-/*
- * track panel specific parameters for common init
- */
-
-struct auok190x_init_data {
- char *id;
- struct auok190x_board *board;
-
- void (*update_partial)(struct auok190xfb_par *par, u16 y1, u16 y2);
- void (*update_all)(struct auok190xfb_par *par);
- bool (*need_refresh)(struct auok190xfb_par *par);
- void (*init)(struct auok190xfb_par *par);
-};
-
-
-extern void auok190x_send_command_nowait(struct auok190xfb_par *par, u16 data);
-extern int auok190x_send_command(struct auok190xfb_par *par, u16 data);
-extern void auok190x_send_cmdargs_nowait(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv);
-extern int auok190x_send_cmdargs(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv);
-extern void auok190x_send_cmdargs_pixels_nowait(struct auok190xfb_par *par,
- u16 cmd, int argc, u16 *argv,
- int size, u16 *data);
-extern int auok190x_send_cmdargs_pixels(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv, int size,
- u16 *data);
-extern int auok190x_read_cmdargs(struct auok190xfb_par *par, u16 cmd,
- int argc, u16 *argv);
-
-extern int auok190x_common_probe(struct platform_device *pdev,
- struct auok190x_init_data *init);
-extern int auok190x_common_remove(struct platform_device *pdev);
-
-extern const struct dev_pm_ops auok190x_pm;
}
/* this is to find and return the vmalloc-ed fb pages */
-static int fb_deferred_io_fault(struct vm_fault *vmf)
+static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf)
{
unsigned long offset;
struct page *page;
EXPORT_SYMBOL_GPL(fb_deferred_io_fsync);
/* vm_ops->page_mkwrite handler */
-static int fb_deferred_io_mkwrite(struct vm_fault *vmf)
+static vm_fault_t fb_deferred_io_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct fb_info *info = vmf->vma->vm_private_data;
#include <drm/drm_connector.h> /* For DRM_MODE_PANEL_ORIENTATION_* */
static bool request_mem_succeeded = false;
-static bool nowc = false;
+static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
static struct fb_var_screeninfo efifb_defined = {
.activate = FB_ACTIVATE_NOW,
static void efifb_destroy(struct fb_info *info)
{
- if (info->screen_base)
- iounmap(info->screen_base);
+ if (info->screen_base) {
+ if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+ iounmap(info->screen_base);
+ else
+ memunmap(info->screen_base);
+ }
if (request_mem_succeeded)
release_mem_region(info->apertures->ranges[0].base,
info->apertures->ranges[0].size);
else if (!strncmp(this_opt, "width:", 6))
screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
else if (!strcmp(this_opt, "nowc"))
- nowc = true;
+ mem_flags &= ~EFI_MEMORY_WC;
}
}
unsigned int size_remap;
unsigned int size_total;
char *option = NULL;
+ efi_memory_desc_t md;
if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
return -ENODEV;
info->apertures->ranges[0].base = efifb_fix.smem_start;
info->apertures->ranges[0].size = size_remap;
- if (nowc)
- info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
- else
- info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
+ if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+ if ((efifb_fix.smem_start + efifb_fix.smem_len) >
+ (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
+ pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
+ efifb_fix.smem_start);
+ err = -EIO;
+ goto err_release_fb;
+ }
+ /*
+ * If the UEFI memory map covers the efifb region, we may only
+ * remap it using the attributes the memory map prescribes.
+ */
+ mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB;
+ mem_flags &= md.attribute;
+ }
+ if (mem_flags & EFI_MEMORY_WC)
+ info->screen_base = ioremap_wc(efifb_fix.smem_start,
+ efifb_fix.smem_len);
+ else if (mem_flags & EFI_MEMORY_UC)
+ info->screen_base = ioremap(efifb_fix.smem_start,
+ efifb_fix.smem_len);
+ else if (mem_flags & EFI_MEMORY_WT)
+ info->screen_base = memremap(efifb_fix.smem_start,
+ efifb_fix.smem_len, MEMREMAP_WT);
+ else if (mem_flags & EFI_MEMORY_WB)
+ info->screen_base = memremap(efifb_fix.smem_start,
+ efifb_fix.smem_len, MEMREMAP_WB);
if (!info->screen_base) {
- pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+ pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n",
efifb_fix.smem_len, efifb_fix.smem_start);
err = -EIO;
goto err_release_fb;
err_groups:
sysfs_remove_groups(&dev->dev.kobj, efifb_groups);
err_unmap:
- iounmap(info->screen_base);
+ if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+ iounmap(info->screen_base);
+ else
+ memunmap(info->screen_base);
err_release_fb:
framebuffer_release(info);
err_release_mem:
/* put videomode list to info structure */
videomodes = kcalloc(videomode_num, sizeof(struct fb_videomode),
GFP_KERNEL);
- if (!videomodes) {
- dev_err(fbi->dev, "can't malloc video modes\n");
+ if (!videomodes)
return -ENOMEM;
- }
+
for (i = 0; i < videomode_num; i++)
mmpmode_to_fbmode(&videomodes[i], &mmp_modes[i]);
fb_videomode_to_modelist(videomodes, videomode_num, &info->modelist);
dev_info(ctrl->dev, "%s: %s\n", __func__, config->name);
/* init driver data */
- path_info = kzalloc(sizeof(struct mmp_path_info), GFP_KERNEL);
- if (!path_info) {
- dev_err(ctrl->dev, "%s: unable to alloc path_info for %s\n",
- __func__, config->name);
+ path_info = kzalloc(sizeof(*path_info), GFP_KERNEL);
+ if (!path_info)
return 0;
- }
+
path_info->name = config->name;
path_info->id = path_plat->id;
path_info->dev = ctrl->dev;
"(default=0)");
module_param(noscale, int, 0);
MODULE_PARM_DESC(noscale,
- "Disables screen scaleing. (0 or 1=disable) "
+ "Disables screen scaling. (0 or 1=disable) "
"(default=0, do scaling)");
module_param(paneltweak, int, 0);
MODULE_PARM_DESC(paneltweak,
};
module_platform_driver(ams_delta_panel_driver);
+
+MODULE_AUTHOR("Jonathan McDowell <noodles@earth.li>");
+MODULE_DESCRIPTION("LCD panel support for the Amstrad E3 (Delta) videophone");
+MODULE_LICENSE("GPL");
};
module_platform_driver(h3_panel_driver);
+
+MODULE_AUTHOR("Imre Deak");
+MODULE_DESCRIPTION("LCD panel support for the TI OMAP H3 board");
+MODULE_LICENSE("GPL");
};
module_platform_driver(htcherald_panel_driver);
+
+MODULE_AUTHOR("Cory Maccarrone");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LCD panel support for the HTC Herald");
};
module_platform_driver(innovator1510_panel_driver);
+
+MODULE_AUTHOR("Imre Deak");
+MODULE_DESCRIPTION("LCD panel support for the TI OMAP1510 Innovator board");
+MODULE_LICENSE("GPL");
};
module_platform_driver(innovator1610_panel_driver);
+
+MODULE_AUTHOR("Imre Deak");
+MODULE_DESCRIPTION("LCD panel support for the TI OMAP1610 Innovator board");
+MODULE_LICENSE("GPL");
};
module_platform_driver(osk_panel_driver);
+
+MODULE_AUTHOR("Imre Deak");
+MODULE_DESCRIPTION("LCD panel support for the TI OMAP OSK board");
+MODULE_LICENSE("GPL");
};
module_platform_driver(palmte_panel_driver);
+
+MODULE_AUTHOR("Romain Goyet <r.goyet@gmail.com>, Laurent Gonzalez <palmte.linux@free.fr>");
+MODULE_DESCRIPTION("LCD panel support for the Palm Tungsten E");
+MODULE_LICENSE("GPL");
};
module_platform_driver(palmtt_panel_driver);
+
+MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("LCD panel support for Palm Tungsten|T");
+MODULE_LICENSE("GPL");
};
module_platform_driver(palmz71_panel_driver);
+
+MODULE_AUTHOR("Romain Goyet, Laurent Gonzalez, Marek Vasut");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LCD panel support for the Palm Zire71");
goto cleanup;
}
- fbdev = kzalloc(sizeof(struct omapfb_device), GFP_KERNEL);
+ fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL);
if (fbdev == NULL) {
dev_err(&pdev->dev,
"unable to allocate memory for device info\n");
tristate "OMAP2+ frame buffer support"
depends on FB
depends on DRM_OMAP = n
+ depends on GPIOLIB
select FB_OMAP2_DSS
select OMAP2_VRFB if ARCH_OMAP2 || ARCH_OMAP3
static ssize_t dsicm_num_errors_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
struct omap_dss_device *in = ddata->in;
u8 errors = 0;
int r;
static ssize_t dsicm_hw_revision_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
struct omap_dss_device *in = ddata->in;
u8 id1, id2, id3;
int r;
struct device_attribute *attr,
const char *buf, size_t count)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
struct omap_dss_device *in = ddata->in;
unsigned long t;
int r;
struct device_attribute *attr,
char *buf)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
unsigned t;
mutex_lock(&ddata->lock);
struct device_attribute *attr,
const char *buf, size_t count)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
struct omap_dss_device *in = ddata->in;
unsigned long t;
int r;
struct device_attribute *attr,
char *buf)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct panel_drv_data *ddata = platform_get_drvdata(pdev);
+ struct panel_drv_data *ddata = dev_get_drvdata(dev);
unsigned t;
mutex_lock(&ddata->lock);
if (ret)
s = "color-tft";
- for (i = 0; lcd_types[i]; i++)
- if (!strcmp(s, lcd_types[i]))
- break;
- if (!i || !lcd_types[i]) {
+ i = match_string(lcd_types, -1, s);
+ if (i < 0) {
dev_err(dev, "lcd-type %s is unknown\n", s);
- return -EINVAL;
+ return i;
}
info->lcd_conn |= LCD_CONN_TYPE(i);
info->lcd_conn |= LCD_CONN_WIDTH(bus_width);
vga_out8(0x3d4, 0x66, par);
cr66 = vga_in8(0x3d5, par);
vga_out8(0x3d5, cr66 | 0x02, par);
- mdelay(10);
+ usleep_range(10000, 11000);
vga_out8(0x3d4, 0x66, par);
vga_out8(0x3d5, cr66 & ~0x02, par); /* clear reset flag */
- mdelay(10);
+ usleep_range(10000, 11000);
/*
vga_out8(0x3d4, 0x3f, par);
cr3f = vga_in8(0x3d5, par);
vga_out8(0x3d5, cr3f | 0x08, par);
- mdelay(10);
+ usleep_range(10000, 11000);
vga_out8(0x3d4, 0x3f, par);
vga_out8(0x3d5, cr3f & ~0x08, par); /* clear reset flags */
- mdelay(10);
+ usleep_range(10000, 11000);
/* Savage ramdac speeds */
par->numClocks = 4;
#include <linux/vmalloc.h>
#include <video/sh_mobile_lcdc.h>
-#include <video/sh_mobile_meram.h>
#include "sh_mobile_lcdcfb.h"
struct notifier_block notifier;
int started;
int forced_fourcc; /* 2 channel LCDC must share fourcc setting */
- struct sh_mobile_meram_info *meram_dev;
};
/* -----------------------------------------------------------------------------
if (priv->dot_clk)
clk_prepare_enable(priv->dot_clk);
pm_runtime_get_sync(priv->dev);
- if (priv->meram_dev && priv->meram_dev->pdev)
- pm_runtime_get_sync(&priv->meram_dev->pdev->dev);
}
}
static void sh_mobile_lcdc_clk_off(struct sh_mobile_lcdc_priv *priv)
{
if (atomic_sub_return(1, &priv->hw_usecnt) == -1) {
- if (priv->meram_dev && priv->meram_dev->pdev)
- pm_runtime_put_sync(&priv->meram_dev->pdev->dev);
pm_runtime_put(priv->dev);
if (priv->dot_clk)
clk_disable_unprepare(priv->dot_clk);
static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
{
- struct sh_mobile_meram_info *mdev = priv->meram_dev;
struct sh_mobile_lcdc_chan *ch;
unsigned long tmp;
int ret;
/* Compute frame buffer base address and pitch for each channel. */
for (k = 0; k < ARRAY_SIZE(priv->ch); k++) {
- int pixelformat;
- void *cache;
-
ch = &priv->ch[k];
if (!ch->enabled)
continue;
ch->base_addr_c = ch->dma_handle
+ ch->xres_virtual * ch->yres_virtual;
ch->line_size = ch->pitch;
-
- /* Enable MERAM if possible. */
- if (mdev == NULL || ch->cfg->meram_cfg == NULL)
- continue;
-
- /* Free the allocated MERAM cache. */
- if (ch->cache) {
- sh_mobile_meram_cache_free(mdev, ch->cache);
- ch->cache = NULL;
- }
-
- switch (ch->format->fourcc) {
- case V4L2_PIX_FMT_NV12:
- case V4L2_PIX_FMT_NV21:
- case V4L2_PIX_FMT_NV16:
- case V4L2_PIX_FMT_NV61:
- pixelformat = SH_MOBILE_MERAM_PF_NV;
- break;
- case V4L2_PIX_FMT_NV24:
- case V4L2_PIX_FMT_NV42:
- pixelformat = SH_MOBILE_MERAM_PF_NV24;
- break;
- case V4L2_PIX_FMT_RGB565:
- case V4L2_PIX_FMT_BGR24:
- case V4L2_PIX_FMT_BGR32:
- default:
- pixelformat = SH_MOBILE_MERAM_PF_RGB;
- break;
- }
-
- cache = sh_mobile_meram_cache_alloc(mdev, ch->cfg->meram_cfg,
- ch->pitch, ch->yres, pixelformat,
- &ch->line_size);
- if (!IS_ERR(cache)) {
- sh_mobile_meram_cache_update(mdev, cache,
- ch->base_addr_y, ch->base_addr_c,
- &ch->base_addr_y, &ch->base_addr_c);
- ch->cache = cache;
- }
}
for (k = 0; k < ARRAY_SIZE(priv->overlays); ++k) {
}
sh_mobile_lcdc_display_off(ch);
-
- /* Free the MERAM cache. */
- if (ch->cache) {
- sh_mobile_meram_cache_free(priv->meram_dev, ch->cache);
- ch->cache = NULL;
- }
-
}
/* stop the lcdc */
base_addr_c = ch->dma_handle + ch->xres_virtual * ch->yres_virtual
+ c_offset;
- if (ch->cache)
- sh_mobile_meram_cache_update(priv->meram_dev, ch->cache,
- base_addr_y, base_addr_c,
- &base_addr_y, &base_addr_c);
-
ch->base_addr_y = base_addr_y;
ch->base_addr_c = base_addr_c;
ch->pan_y_offset = y_offset;
if (info->fbdefio) {
ch->sglist = vmalloc(sizeof(struct scatterlist) *
ch->fb_size >> PAGE_SHIFT);
- if (!ch->sglist) {
- dev_err(ch->lcdc->dev, "cannot allocate sglist\n");
+ if (!ch->sglist)
return -ENOMEM;
- }
}
info->bl_dev = ch->bl;
static int sh_mobile_lcdc_runtime_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct sh_mobile_lcdc_priv *priv = platform_get_drvdata(pdev);
+ struct sh_mobile_lcdc_priv *priv = dev_get_drvdata(dev);
/* turn off LCDC hardware */
lcdc_write(priv, _LDCNT1R, 0);
static int sh_mobile_lcdc_runtime_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct sh_mobile_lcdc_priv *priv = platform_get_drvdata(pdev);
+ struct sh_mobile_lcdc_priv *priv = dev_get_drvdata(dev);
__sh_mobile_lcdc_start(priv);
}
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (!priv) {
- dev_err(&pdev->dev, "cannot allocate device data\n");
+ if (!priv)
return -ENOMEM;
- }
priv->dev = &pdev->dev;
- priv->meram_dev = pdata->meram_dev;
+
for (i = 0; i < ARRAY_SIZE(priv->ch); i++)
mutex_init(&priv->ch[i].open_lock);
platform_set_drvdata(pdev, priv);
unsigned long *reg_offs;
unsigned long ldmt1r_value;
unsigned long enabled; /* ME and SE in LDCNT2R */
- void *cache;
struct mutex open_lock; /* protects the use counter */
int use_count;
+++ /dev/null
-/*
- * SuperH Mobile MERAM Driver for SuperH Mobile LCDC Driver
- *
- * Copyright (c) 2011 Damian Hobson-Garcia <dhobsong@igel.co.jp>
- * Takanari Hayama <taki@igel.co.jp>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/genalloc.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include <linux/slab.h>
-
-#include <video/sh_mobile_meram.h>
-
-/* -----------------------------------------------------------------------------
- * MERAM registers
- */
-
-#define MEVCR1 0x4
-#define MEVCR1_RST (1 << 31)
-#define MEVCR1_WD (1 << 30)
-#define MEVCR1_AMD1 (1 << 29)
-#define MEVCR1_AMD0 (1 << 28)
-#define MEQSEL1 0x40
-#define MEQSEL2 0x44
-
-#define MExxCTL 0x400
-#define MExxCTL_BV (1 << 31)
-#define MExxCTL_BSZ_SHIFT 28
-#define MExxCTL_MSAR_MASK (0x7ff << MExxCTL_MSAR_SHIFT)
-#define MExxCTL_MSAR_SHIFT 16
-#define MExxCTL_NXT_MASK (0x1f << MExxCTL_NXT_SHIFT)
-#define MExxCTL_NXT_SHIFT 11
-#define MExxCTL_WD1 (1 << 10)
-#define MExxCTL_WD0 (1 << 9)
-#define MExxCTL_WS (1 << 8)
-#define MExxCTL_CB (1 << 7)
-#define MExxCTL_WBF (1 << 6)
-#define MExxCTL_WF (1 << 5)
-#define MExxCTL_RF (1 << 4)
-#define MExxCTL_CM (1 << 3)
-#define MExxCTL_MD_READ (1 << 0)
-#define MExxCTL_MD_WRITE (2 << 0)
-#define MExxCTL_MD_ICB_WB (3 << 0)
-#define MExxCTL_MD_ICB (4 << 0)
-#define MExxCTL_MD_FB (7 << 0)
-#define MExxCTL_MD_MASK (7 << 0)
-#define MExxBSIZE 0x404
-#define MExxBSIZE_RCNT_SHIFT 28
-#define MExxBSIZE_YSZM1_SHIFT 16
-#define MExxBSIZE_XSZM1_SHIFT 0
-#define MExxMNCF 0x408
-#define MExxMNCF_KWBNM_SHIFT 28
-#define MExxMNCF_KRBNM_SHIFT 24
-#define MExxMNCF_BNM_SHIFT 16
-#define MExxMNCF_XBV (1 << 15)
-#define MExxMNCF_CPL_YCBCR444 (1 << 12)
-#define MExxMNCF_CPL_YCBCR420 (2 << 12)
-#define MExxMNCF_CPL_YCBCR422 (3 << 12)
-#define MExxMNCF_CPL_MSK (3 << 12)
-#define MExxMNCF_BL (1 << 2)
-#define MExxMNCF_LNM_SHIFT 0
-#define MExxSARA 0x410
-#define MExxSARB 0x414
-#define MExxSBSIZE 0x418
-#define MExxSBSIZE_HDV (1 << 31)
-#define MExxSBSIZE_HSZ16 (0 << 28)
-#define MExxSBSIZE_HSZ32 (1 << 28)
-#define MExxSBSIZE_HSZ64 (2 << 28)
-#define MExxSBSIZE_HSZ128 (3 << 28)
-#define MExxSBSIZE_SBSIZZ_SHIFT 0
-
-#define MERAM_MExxCTL_VAL(next, addr) \
- ((((next) << MExxCTL_NXT_SHIFT) & MExxCTL_NXT_MASK) | \
- (((addr) << MExxCTL_MSAR_SHIFT) & MExxCTL_MSAR_MASK))
-#define MERAM_MExxBSIZE_VAL(rcnt, yszm1, xszm1) \
- (((rcnt) << MExxBSIZE_RCNT_SHIFT) | \
- ((yszm1) << MExxBSIZE_YSZM1_SHIFT) | \
- ((xszm1) << MExxBSIZE_XSZM1_SHIFT))
-
-static const unsigned long common_regs[] = {
- MEVCR1,
- MEQSEL1,
- MEQSEL2,
-};
-#define MERAM_REGS_SIZE ARRAY_SIZE(common_regs)
-
-static const unsigned long icb_regs[] = {
- MExxCTL,
- MExxBSIZE,
- MExxMNCF,
- MExxSARA,
- MExxSARB,
- MExxSBSIZE,
-};
-#define ICB_REGS_SIZE ARRAY_SIZE(icb_regs)
-
-/*
- * sh_mobile_meram_icb - MERAM ICB information
- * @regs: Registers cache
- * @index: ICB index
- * @offset: MERAM block offset
- * @size: MERAM block size in KiB
- * @cache_unit: Bytes to cache per ICB
- * @pixelformat: Video pixel format of the data stored in the ICB
- * @current_reg: Which of Start Address Register A (0) or B (1) is in use
- */
-struct sh_mobile_meram_icb {
- unsigned long regs[ICB_REGS_SIZE];
- unsigned int index;
- unsigned long offset;
- unsigned int size;
-
- unsigned int cache_unit;
- unsigned int pixelformat;
- unsigned int current_reg;
-};
-
-#define MERAM_ICB_NUM 32
-
-struct sh_mobile_meram_fb_plane {
- struct sh_mobile_meram_icb *marker;
- struct sh_mobile_meram_icb *cache;
-};
-
-struct sh_mobile_meram_fb_cache {
- unsigned int nplanes;
- struct sh_mobile_meram_fb_plane planes[2];
-};
-
-/*
- * sh_mobile_meram_priv - MERAM device
- * @base: Registers base address
- * @meram: MERAM physical address
- * @regs: Registers cache
- * @lock: Protects used_icb and icbs
- * @used_icb: Bitmask of used ICBs
- * @icbs: ICBs
- * @pool: Allocation pool to manage the MERAM
- */
-struct sh_mobile_meram_priv {
- void __iomem *base;
- unsigned long meram;
- unsigned long regs[MERAM_REGS_SIZE];
-
- struct mutex lock;
- unsigned long used_icb;
- struct sh_mobile_meram_icb icbs[MERAM_ICB_NUM];
-
- struct gen_pool *pool;
-};
-
-/* settings */
-#define MERAM_GRANULARITY 1024
-#define MERAM_SEC_LINE 15
-#define MERAM_LINE_WIDTH 2048
-
-/* -----------------------------------------------------------------------------
- * Registers access
- */
-
-#define MERAM_ICB_OFFSET(base, idx, off) ((base) + (off) + (idx) * 0x20)
-
-static inline void meram_write_icb(void __iomem *base, unsigned int idx,
- unsigned int off, unsigned long val)
-{
- iowrite32(val, MERAM_ICB_OFFSET(base, idx, off));
-}
-
-static inline unsigned long meram_read_icb(void __iomem *base, unsigned int idx,
- unsigned int off)
-{
- return ioread32(MERAM_ICB_OFFSET(base, idx, off));
-}
-
-static inline void meram_write_reg(void __iomem *base, unsigned int off,
- unsigned long val)
-{
- iowrite32(val, base + off);
-}
-
-static inline unsigned long meram_read_reg(void __iomem *base, unsigned int off)
-{
- return ioread32(base + off);
-}
-
-/* -----------------------------------------------------------------------------
- * MERAM allocation and free
- */
-
-static unsigned long meram_alloc(struct sh_mobile_meram_priv *priv, size_t size)
-{
- return gen_pool_alloc(priv->pool, size);
-}
-
-static void meram_free(struct sh_mobile_meram_priv *priv, unsigned long mem,
- size_t size)
-{
- gen_pool_free(priv->pool, mem, size);
-}
-
-/* -----------------------------------------------------------------------------
- * LCDC cache planes allocation, init, cleanup and free
- */
-
-/* Allocate ICBs and MERAM for a plane. */
-static int meram_plane_alloc(struct sh_mobile_meram_priv *priv,
- struct sh_mobile_meram_fb_plane *plane,
- size_t size)
-{
- unsigned long mem;
- unsigned long idx;
-
- idx = find_first_zero_bit(&priv->used_icb, 28);
- if (idx == 28)
- return -ENOMEM;
- plane->cache = &priv->icbs[idx];
-
- idx = find_next_zero_bit(&priv->used_icb, 32, 28);
- if (idx == 32)
- return -ENOMEM;
- plane->marker = &priv->icbs[idx];
-
- mem = meram_alloc(priv, size * 1024);
- if (mem == 0)
- return -ENOMEM;
-
- __set_bit(plane->marker->index, &priv->used_icb);
- __set_bit(plane->cache->index, &priv->used_icb);
-
- plane->marker->offset = mem - priv->meram;
- plane->marker->size = size;
-
- return 0;
-}
-
-/* Free ICBs and MERAM for a plane. */
-static void meram_plane_free(struct sh_mobile_meram_priv *priv,
- struct sh_mobile_meram_fb_plane *plane)
-{
- meram_free(priv, priv->meram + plane->marker->offset,
- plane->marker->size * 1024);
-
- __clear_bit(plane->marker->index, &priv->used_icb);
- __clear_bit(plane->cache->index, &priv->used_icb);
-}
-
-/* Is this a YCbCr(NV12, NV16 or NV24) colorspace? */
-static int is_nvcolor(int cspace)
-{
- if (cspace == SH_MOBILE_MERAM_PF_NV ||
- cspace == SH_MOBILE_MERAM_PF_NV24)
- return 1;
- return 0;
-}
-
-/* Set the next address to fetch. */
-static void meram_set_next_addr(struct sh_mobile_meram_priv *priv,
- struct sh_mobile_meram_fb_cache *cache,
- unsigned long base_addr_y,
- unsigned long base_addr_c)
-{
- struct sh_mobile_meram_icb *icb = cache->planes[0].marker;
- unsigned long target;
-
- icb->current_reg ^= 1;
- target = icb->current_reg ? MExxSARB : MExxSARA;
-
- /* set the next address to fetch */
- meram_write_icb(priv->base, cache->planes[0].cache->index, target,
- base_addr_y);
- meram_write_icb(priv->base, cache->planes[0].marker->index, target,
- base_addr_y + cache->planes[0].marker->cache_unit);
-
- if (cache->nplanes == 2) {
- meram_write_icb(priv->base, cache->planes[1].cache->index,
- target, base_addr_c);
- meram_write_icb(priv->base, cache->planes[1].marker->index,
- target, base_addr_c +
- cache->planes[1].marker->cache_unit);
- }
-}
-
-/* Get the next ICB address. */
-static void
-meram_get_next_icb_addr(struct sh_mobile_meram_info *pdata,
- struct sh_mobile_meram_fb_cache *cache,
- unsigned long *icb_addr_y, unsigned long *icb_addr_c)
-{
- struct sh_mobile_meram_icb *icb = cache->planes[0].marker;
- unsigned long icb_offset;
-
- if (pdata->addr_mode == SH_MOBILE_MERAM_MODE0)
- icb_offset = 0x80000000 | (icb->current_reg << 29);
- else
- icb_offset = 0xc0000000 | (icb->current_reg << 23);
-
- *icb_addr_y = icb_offset | (cache->planes[0].marker->index << 24);
- if (cache->nplanes == 2)
- *icb_addr_c = icb_offset
- | (cache->planes[1].marker->index << 24);
-}
-
-#define MERAM_CALC_BYTECOUNT(x, y) \
- (((x) * (y) + (MERAM_LINE_WIDTH - 1)) & ~(MERAM_LINE_WIDTH - 1))
-
-/* Initialize MERAM. */
-static int meram_plane_init(struct sh_mobile_meram_priv *priv,
- struct sh_mobile_meram_fb_plane *plane,
- unsigned int xres, unsigned int yres,
- unsigned int *out_pitch)
-{
- struct sh_mobile_meram_icb *marker = plane->marker;
- unsigned long total_byte_count = MERAM_CALC_BYTECOUNT(xres, yres);
- unsigned long bnm;
- unsigned int lcdc_pitch;
- unsigned int xpitch;
- unsigned int line_cnt;
- unsigned int save_lines;
-
- /* adjust pitch to 1024, 2048, 4096 or 8192 */
- lcdc_pitch = (xres - 1) | 1023;
- lcdc_pitch = lcdc_pitch | (lcdc_pitch >> 1);
- lcdc_pitch = lcdc_pitch | (lcdc_pitch >> 2);
- lcdc_pitch += 1;
-
- /* derive settings */
- if (lcdc_pitch == 8192 && yres >= 1024) {
- lcdc_pitch = xpitch = MERAM_LINE_WIDTH;
- line_cnt = total_byte_count >> 11;
- *out_pitch = xres;
- save_lines = plane->marker->size / 16 / MERAM_SEC_LINE;
- save_lines *= MERAM_SEC_LINE;
- } else {
- xpitch = xres;
- line_cnt = yres;
- *out_pitch = lcdc_pitch;
- save_lines = plane->marker->size / (lcdc_pitch >> 10) / 2;
- save_lines &= 0xff;
- }
- bnm = (save_lines - 1) << 16;
-
- /* TODO: we better to check if we have enough MERAM buffer size */
-
- /* set up ICB */
- meram_write_icb(priv->base, plane->cache->index, MExxBSIZE,
- MERAM_MExxBSIZE_VAL(0x0, line_cnt - 1, xpitch - 1));
- meram_write_icb(priv->base, plane->marker->index, MExxBSIZE,
- MERAM_MExxBSIZE_VAL(0xf, line_cnt - 1, xpitch - 1));
-
- meram_write_icb(priv->base, plane->cache->index, MExxMNCF, bnm);
- meram_write_icb(priv->base, plane->marker->index, MExxMNCF, bnm);
-
- meram_write_icb(priv->base, plane->cache->index, MExxSBSIZE, xpitch);
- meram_write_icb(priv->base, plane->marker->index, MExxSBSIZE, xpitch);
-
- /* save a cache unit size */
- plane->cache->cache_unit = xres * save_lines;
- plane->marker->cache_unit = xres * save_lines;
-
- /*
- * Set MERAM for framebuffer
- *
- * we also chain the cache_icb and the marker_icb.
- * we also split the allocated MERAM buffer between two ICBs.
- */
- meram_write_icb(priv->base, plane->cache->index, MExxCTL,
- MERAM_MExxCTL_VAL(plane->marker->index, marker->offset)
- | MExxCTL_WD1 | MExxCTL_WD0 | MExxCTL_WS | MExxCTL_CM |
- MExxCTL_MD_FB);
- meram_write_icb(priv->base, plane->marker->index, MExxCTL,
- MERAM_MExxCTL_VAL(plane->cache->index, marker->offset +
- plane->marker->size / 2) |
- MExxCTL_WD1 | MExxCTL_WD0 | MExxCTL_WS | MExxCTL_CM |
- MExxCTL_MD_FB);
-
- return 0;
-}
-
-static void meram_plane_cleanup(struct sh_mobile_meram_priv *priv,
- struct sh_mobile_meram_fb_plane *plane)
-{
- /* disable ICB */
- meram_write_icb(priv->base, plane->cache->index, MExxCTL,
- MExxCTL_WBF | MExxCTL_WF | MExxCTL_RF);
- meram_write_icb(priv->base, plane->marker->index, MExxCTL,
- MExxCTL_WBF | MExxCTL_WF | MExxCTL_RF);
-
- plane->cache->cache_unit = 0;
- plane->marker->cache_unit = 0;
-}
-
-/* -----------------------------------------------------------------------------
- * MERAM operations
- */
-
-unsigned long sh_mobile_meram_alloc(struct sh_mobile_meram_info *pdata,
- size_t size)
-{
- struct sh_mobile_meram_priv *priv = pdata->priv;
-
- return meram_alloc(priv, size);
-}
-EXPORT_SYMBOL_GPL(sh_mobile_meram_alloc);
-
-void sh_mobile_meram_free(struct sh_mobile_meram_info *pdata, unsigned long mem,
- size_t size)
-{
- struct sh_mobile_meram_priv *priv = pdata->priv;
-
- meram_free(priv, mem, size);
-}
-EXPORT_SYMBOL_GPL(sh_mobile_meram_free);
-
-/* Allocate memory for the ICBs and mark them as used. */
-static struct sh_mobile_meram_fb_cache *
-meram_cache_alloc(struct sh_mobile_meram_priv *priv,
- const struct sh_mobile_meram_cfg *cfg,
- int pixelformat)
-{
- unsigned int nplanes = is_nvcolor(pixelformat) ? 2 : 1;
- struct sh_mobile_meram_fb_cache *cache;
- int ret;
-
- cache = kzalloc(sizeof(*cache), GFP_KERNEL);
- if (cache == NULL)
- return ERR_PTR(-ENOMEM);
-
- cache->nplanes = nplanes;
-
- ret = meram_plane_alloc(priv, &cache->planes[0],
- cfg->icb[0].meram_size);
- if (ret < 0)
- goto error;
-
- cache->planes[0].marker->current_reg = 1;
- cache->planes[0].marker->pixelformat = pixelformat;
-
- if (cache->nplanes == 1)
- return cache;
-
- ret = meram_plane_alloc(priv, &cache->planes[1],
- cfg->icb[1].meram_size);
- if (ret < 0) {
- meram_plane_free(priv, &cache->planes[0]);
- goto error;
- }
-
- return cache;
-
-error:
- kfree(cache);
- return ERR_PTR(-ENOMEM);
-}
-
-void *sh_mobile_meram_cache_alloc(struct sh_mobile_meram_info *pdata,
- const struct sh_mobile_meram_cfg *cfg,
- unsigned int xres, unsigned int yres,
- unsigned int pixelformat, unsigned int *pitch)
-{
- struct sh_mobile_meram_fb_cache *cache;
- struct sh_mobile_meram_priv *priv = pdata->priv;
- struct platform_device *pdev = pdata->pdev;
- unsigned int nplanes = is_nvcolor(pixelformat) ? 2 : 1;
- unsigned int out_pitch;
-
- if (priv == NULL)
- return ERR_PTR(-ENODEV);
-
- if (pixelformat != SH_MOBILE_MERAM_PF_NV &&
- pixelformat != SH_MOBILE_MERAM_PF_NV24 &&
- pixelformat != SH_MOBILE_MERAM_PF_RGB)
- return ERR_PTR(-EINVAL);
-
- dev_dbg(&pdev->dev, "registering %dx%d (%s)", xres, yres,
- !pixelformat ? "yuv" : "rgb");
-
- /* we can't handle wider than 8192px */
- if (xres > 8192) {
- dev_err(&pdev->dev, "width exceeding the limit (> 8192).");
- return ERR_PTR(-EINVAL);
- }
-
- if (cfg->icb[0].meram_size == 0)
- return ERR_PTR(-EINVAL);
-
- if (nplanes == 2 && cfg->icb[1].meram_size == 0)
- return ERR_PTR(-EINVAL);
-
- mutex_lock(&priv->lock);
-
- /* We now register the ICBs and allocate the MERAM regions. */
- cache = meram_cache_alloc(priv, cfg, pixelformat);
- if (IS_ERR(cache)) {
- dev_err(&pdev->dev, "MERAM allocation failed (%ld).",
- PTR_ERR(cache));
- goto err;
- }
-
- /* initialize MERAM */
- meram_plane_init(priv, &cache->planes[0], xres, yres, &out_pitch);
- *pitch = out_pitch;
- if (pixelformat == SH_MOBILE_MERAM_PF_NV)
- meram_plane_init(priv, &cache->planes[1],
- xres, (yres + 1) / 2, &out_pitch);
- else if (pixelformat == SH_MOBILE_MERAM_PF_NV24)
- meram_plane_init(priv, &cache->planes[1],
- 2 * xres, (yres + 1) / 2, &out_pitch);
-
-err:
- mutex_unlock(&priv->lock);
- return cache;
-}
-EXPORT_SYMBOL_GPL(sh_mobile_meram_cache_alloc);
-
-void
-sh_mobile_meram_cache_free(struct sh_mobile_meram_info *pdata, void *data)
-{
- struct sh_mobile_meram_fb_cache *cache = data;
- struct sh_mobile_meram_priv *priv = pdata->priv;
-
- mutex_lock(&priv->lock);
-
- /* Cleanup and free. */
- meram_plane_cleanup(priv, &cache->planes[0]);
- meram_plane_free(priv, &cache->planes[0]);
-
- if (cache->nplanes == 2) {
- meram_plane_cleanup(priv, &cache->planes[1]);
- meram_plane_free(priv, &cache->planes[1]);
- }
-
- kfree(cache);
-
- mutex_unlock(&priv->lock);
-}
-EXPORT_SYMBOL_GPL(sh_mobile_meram_cache_free);
-
-void
-sh_mobile_meram_cache_update(struct sh_mobile_meram_info *pdata, void *data,
- unsigned long base_addr_y,
- unsigned long base_addr_c,
- unsigned long *icb_addr_y,
- unsigned long *icb_addr_c)
-{
- struct sh_mobile_meram_fb_cache *cache = data;
- struct sh_mobile_meram_priv *priv = pdata->priv;
-
- mutex_lock(&priv->lock);
-
- meram_set_next_addr(priv, cache, base_addr_y, base_addr_c);
- meram_get_next_icb_addr(pdata, cache, icb_addr_y, icb_addr_c);
-
- mutex_unlock(&priv->lock);
-}
-EXPORT_SYMBOL_GPL(sh_mobile_meram_cache_update);
-
-/* -----------------------------------------------------------------------------
- * Power management
- */
-
-#ifdef CONFIG_PM
-static int sh_mobile_meram_suspend(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct sh_mobile_meram_priv *priv = platform_get_drvdata(pdev);
- unsigned int i, j;
-
- for (i = 0; i < MERAM_REGS_SIZE; i++)
- priv->regs[i] = meram_read_reg(priv->base, common_regs[i]);
-
- for (i = 0; i < 32; i++) {
- if (!test_bit(i, &priv->used_icb))
- continue;
- for (j = 0; j < ICB_REGS_SIZE; j++) {
- priv->icbs[i].regs[j] =
- meram_read_icb(priv->base, i, icb_regs[j]);
- /* Reset ICB on resume */
- if (icb_regs[j] == MExxCTL)
- priv->icbs[i].regs[j] |=
- MExxCTL_WBF | MExxCTL_WF | MExxCTL_RF;
- }
- }
- return 0;
-}
-
-static int sh_mobile_meram_resume(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct sh_mobile_meram_priv *priv = platform_get_drvdata(pdev);
- unsigned int i, j;
-
- for (i = 0; i < 32; i++) {
- if (!test_bit(i, &priv->used_icb))
- continue;
- for (j = 0; j < ICB_REGS_SIZE; j++)
- meram_write_icb(priv->base, i, icb_regs[j],
- priv->icbs[i].regs[j]);
- }
-
- for (i = 0; i < MERAM_REGS_SIZE; i++)
- meram_write_reg(priv->base, common_regs[i], priv->regs[i]);
- return 0;
-}
-#endif /* CONFIG_PM */
-
-static UNIVERSAL_DEV_PM_OPS(sh_mobile_meram_dev_pm_ops,
- sh_mobile_meram_suspend,
- sh_mobile_meram_resume, NULL);
-
-/* -----------------------------------------------------------------------------
- * Probe/remove and driver init/exit
- */
-
-static int sh_mobile_meram_probe(struct platform_device *pdev)
-{
- struct sh_mobile_meram_priv *priv;
- struct sh_mobile_meram_info *pdata = pdev->dev.platform_data;
- struct resource *regs;
- struct resource *meram;
- unsigned int i;
- int error;
-
- if (!pdata) {
- dev_err(&pdev->dev, "no platform data defined\n");
- return -EINVAL;
- }
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- meram = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (regs == NULL || meram == NULL) {
- dev_err(&pdev->dev, "cannot get platform resources\n");
- return -ENOENT;
- }
-
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (!priv) {
- dev_err(&pdev->dev, "cannot allocate device data\n");
- return -ENOMEM;
- }
-
- /* Initialize private data. */
- mutex_init(&priv->lock);
- priv->used_icb = pdata->reserved_icbs;
-
- for (i = 0; i < MERAM_ICB_NUM; ++i)
- priv->icbs[i].index = i;
-
- pdata->priv = priv;
- pdata->pdev = pdev;
-
- /* Request memory regions and remap the registers. */
- if (!request_mem_region(regs->start, resource_size(regs), pdev->name)) {
- dev_err(&pdev->dev, "MERAM registers region already claimed\n");
- error = -EBUSY;
- goto err_req_regs;
- }
-
- if (!request_mem_region(meram->start, resource_size(meram),
- pdev->name)) {
- dev_err(&pdev->dev, "MERAM memory region already claimed\n");
- error = -EBUSY;
- goto err_req_meram;
- }
-
- priv->base = ioremap_nocache(regs->start, resource_size(regs));
- if (!priv->base) {
- dev_err(&pdev->dev, "ioremap failed\n");
- error = -EFAULT;
- goto err_ioremap;
- }
-
- priv->meram = meram->start;
-
- /* Create and initialize the MERAM memory pool. */
- priv->pool = gen_pool_create(ilog2(MERAM_GRANULARITY), -1);
- if (priv->pool == NULL) {
- error = -ENOMEM;
- goto err_genpool;
- }
-
- error = gen_pool_add(priv->pool, meram->start, resource_size(meram),
- -1);
- if (error < 0)
- goto err_genpool;
-
- /* initialize ICB addressing mode */
- if (pdata->addr_mode == SH_MOBILE_MERAM_MODE1)
- meram_write_reg(priv->base, MEVCR1, MEVCR1_AMD1);
-
- platform_set_drvdata(pdev, priv);
- pm_runtime_enable(&pdev->dev);
-
- dev_info(&pdev->dev, "sh_mobile_meram initialized.");
-
- return 0;
-
-err_genpool:
- if (priv->pool)
- gen_pool_destroy(priv->pool);
- iounmap(priv->base);
-err_ioremap:
- release_mem_region(meram->start, resource_size(meram));
-err_req_meram:
- release_mem_region(regs->start, resource_size(regs));
-err_req_regs:
- mutex_destroy(&priv->lock);
- kfree(priv);
-
- return error;
-}
-
-
-static int sh_mobile_meram_remove(struct platform_device *pdev)
-{
- struct sh_mobile_meram_priv *priv = platform_get_drvdata(pdev);
- struct resource *regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- struct resource *meram = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-
- pm_runtime_disable(&pdev->dev);
-
- gen_pool_destroy(priv->pool);
-
- iounmap(priv->base);
- release_mem_region(meram->start, resource_size(meram));
- release_mem_region(regs->start, resource_size(regs));
-
- mutex_destroy(&priv->lock);
-
- kfree(priv);
-
- return 0;
-}
-
-static struct platform_driver sh_mobile_meram_driver = {
- .driver = {
- .name = "sh_mobile_meram",
- .pm = &sh_mobile_meram_dev_pm_ops,
- },
- .probe = sh_mobile_meram_probe,
- .remove = sh_mobile_meram_remove,
-};
-
-module_platform_driver(sh_mobile_meram_driver);
-
-MODULE_DESCRIPTION("SuperH Mobile MERAM driver");
-MODULE_AUTHOR("Damian Hobson-Garcia / Takanari Hayama");
-MODULE_LICENSE("GPL v2");
* @dev: PCI device
* @msg: the suspend event code.
*
- * See Documentation/power/admin-guide/devices.rst for more information
+ * See Documentation/driver-api/pm/devices.rst for more information
*/
static int xxxfb_suspend(struct pci_dev *dev, pm_message_t msg)
{
* xxxfb_resume - Optional but recommended function. Resume the device.
* @dev: PCI device
*
- * See Documentation/power/admin-guide/devices.rst for more information
+ * See Documentation/driver-api/pm/devices.rst for more information
*/
static int xxxfb_resume(struct pci_dev *dev)
{
* @dev: platform device
* @msg: the suspend event code.
*
- * See Documentation/power/admin-guide/devices.rst for more information
+ * See Documentation/driver-api/pm/devices.rst for more information
*/
static int xxxfb_suspend(struct platform_device *dev, pm_message_t msg)
{
* xxxfb_resume - Optional but recommended function. Resume the device.
* @dev: platform device
*
- * See Documentation/power/admin-guide/devices.rst for more information
+ * See Documentation/driver-api/pm/devices.rst for more information
*/
static int xxxfb_resume(struct platform_dev *dev)
{
int ret;
/* allocate our framebuffers */
-
- info = kzalloc(sizeof(struct sm501fb_info), GFP_KERNEL);
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
dev_err(dev, "failed to allocate state\n");
return -ENOMEM;
#include <linux/console.h>
#include <linux/timer.h>
+#ifdef CONFIG_X86
+#include <asm/olpc.h>
+#else
+#define machine_is_olpc(x) 0
+#endif
+
#include "debug.h"
#include "viafbdev.h"
*/
#include <linux/via-core.h>
-#include <asm/olpc.h>
#include "global.h"
#include "via_clock.h"
#include <linux/platform_device.h>
#include <linux/list.h>
#include <linux/pm.h>
-#include <asm/olpc.h>
/*
* The default port config.
#include <linux/kernel.h>
#include <linux/via-core.h>
-#include <asm/olpc.h>
+
#include "via_clock.h"
#include "global.h"
#include "debug.h"
#include <linux/stat.h>
#include <linux/via-core.h>
#include <linux/via_i2c.h>
-#include <asm/olpc.h>
#define _MASTER_FILE
#include "global.h"
tell_host(vb, vb->inflate_vq);
/* balloon's page migration 2nd step -- deflate "page" */
+ spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
balloon_page_delete(page);
+ spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
set_page_pfns(vb, vb->pfns, page);
tell_host(vb, vb->deflate_vq);
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
struct device *dev = get_device(&vp_dev->vdev.dev);
+ pci_disable_sriov(pci_dev);
+
unregister_virtio_device(&vp_dev->vdev);
if (vp_dev->ioaddr)
put_device(dev);
}
+static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs)
+{
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+ struct virtio_device *vdev = &vp_dev->vdev;
+ int ret;
+
+ if (!(vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_DRIVER_OK))
+ return -EBUSY;
+
+ if (!__virtio_test_bit(vdev, VIRTIO_F_SR_IOV))
+ return -EINVAL;
+
+ if (pci_vfs_assigned(pci_dev))
+ return -EPERM;
+
+ if (num_vfs == 0) {
+ pci_disable_sriov(pci_dev);
+ return 0;
+ }
+
+ ret = pci_enable_sriov(pci_dev, num_vfs);
+ if (ret < 0)
+ return ret;
+
+ return num_vfs;
+}
+
static struct pci_driver virtio_pci_driver = {
.name = "virtio-pci",
.id_table = virtio_pci_id_table,
#ifdef CONFIG_PM_SLEEP
.driver.pm = &virtio_pci_pm_ops,
#endif
+ .sriov_configure = virtio_pci_sriov_configure,
};
module_pci_driver(virtio_pci_driver);
return features;
}
+static void vp_transport_features(struct virtio_device *vdev, u64 features)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct pci_dev *pci_dev = vp_dev->pci_dev;
+
+ if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
+ pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
+ __virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
+}
+
/* virtio config->finalize_features() implementation */
static int vp_finalize_features(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ u64 features = vdev->features;
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
+ /* Give virtio_pci a chance to accept features. */
+ vp_transport_features(vdev, features);
+
if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
dev_err(&vdev->dev, "virtio: device uses modern interface "
"but does not have VIRTIO_F_VERSION_1\n");
xen-evtchn-y := evtchn.o
xen-gntdev-y := gntdev.o
xen-gntalloc-y := gntalloc.o
-xen-privcmd-y := privcmd.o
+xen-privcmd-y := privcmd.o privcmd-buf.o
xen_irq_info_cleanup(info);
}
- BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
-
xen_free_irq(irq);
}
return 0;
}
-EXPORT_SYMBOL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
/**
* gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
}
free_xenballooned_pages(nr_pages, pages);
}
-EXPORT_SYMBOL(gnttab_free_pages);
+EXPORT_SYMBOL_GPL(gnttab_free_pages);
/* Handling of paged out grant targets (GNTST_eagain) */
#define MAX_DELAY 256
return;
}
- if (sysrq_key != '\0')
- xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+ if (sysrq_key != '\0') {
+ err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+ if (err) {
+ pr_err("%s: Error %d writing sysrq in control/sysrq\n",
+ __func__, err);
+ xenbus_transaction_end(xbt, 1);
+ return;
+ }
+ }
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN)
continue;
snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
shutdown_handlers[idx].command);
- xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+ err = xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+ if (err) {
+ pr_err("%s: Error %d writing %s\n", __func__,
+ err, node);
+ return err;
+ }
}
return 0;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/******************************************************************************
+ * privcmd-buf.c
+ *
+ * Mmap of hypercall buffers.
+ *
+ * Copyright (c) 2018 Juergen Gross
+ */
+
+#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "privcmd.h"
+
+MODULE_LICENSE("GPL");
+
+static unsigned int limit = 64;
+module_param(limit, uint, 0644);
+MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by "
+ "the privcmd-buf device per open file");
+
+struct privcmd_buf_private {
+ struct mutex lock;
+ struct list_head list;
+ unsigned int allocated;
+};
+
+struct privcmd_buf_vma_private {
+ struct privcmd_buf_private *file_priv;
+ struct list_head list;
+ unsigned int users;
+ unsigned int n_pages;
+ struct page *pages[];
+};
+
+static int privcmd_buf_open(struct inode *ino, struct file *file)
+{
+ struct privcmd_buf_private *file_priv;
+
+ file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
+ if (!file_priv)
+ return -ENOMEM;
+
+ mutex_init(&file_priv->lock);
+ INIT_LIST_HEAD(&file_priv->list);
+
+ file->private_data = file_priv;
+
+ return 0;
+}
+
+static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv)
+{
+ unsigned int i;
+
+ vma_priv->file_priv->allocated -= vma_priv->n_pages;
+
+ list_del(&vma_priv->list);
+
+ for (i = 0; i < vma_priv->n_pages; i++)
+ if (vma_priv->pages[i])
+ __free_page(vma_priv->pages[i]);
+
+ kfree(vma_priv);
+}
+
+static int privcmd_buf_release(struct inode *ino, struct file *file)
+{
+ struct privcmd_buf_private *file_priv = file->private_data;
+ struct privcmd_buf_vma_private *vma_priv;
+
+ mutex_lock(&file_priv->lock);
+
+ while (!list_empty(&file_priv->list)) {
+ vma_priv = list_first_entry(&file_priv->list,
+ struct privcmd_buf_vma_private,
+ list);
+ privcmd_buf_vmapriv_free(vma_priv);
+ }
+
+ mutex_unlock(&file_priv->lock);
+
+ kfree(file_priv);
+
+ return 0;
+}
+
+static void privcmd_buf_vma_open(struct vm_area_struct *vma)
+{
+ struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+
+ if (!vma_priv)
+ return;
+
+ mutex_lock(&vma_priv->file_priv->lock);
+ vma_priv->users++;
+ mutex_unlock(&vma_priv->file_priv->lock);
+}
+
+static void privcmd_buf_vma_close(struct vm_area_struct *vma)
+{
+ struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+ struct privcmd_buf_private *file_priv;
+
+ if (!vma_priv)
+ return;
+
+ file_priv = vma_priv->file_priv;
+
+ mutex_lock(&file_priv->lock);
+
+ vma_priv->users--;
+ if (!vma_priv->users)
+ privcmd_buf_vmapriv_free(vma_priv);
+
+ mutex_unlock(&file_priv->lock);
+}
+
+static vm_fault_t privcmd_buf_vma_fault(struct vm_fault *vmf)
+{
+ pr_debug("fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+ vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end,
+ vmf->pgoff, (void *)vmf->address);
+
+ return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_operations_struct privcmd_buf_vm_ops = {
+ .open = privcmd_buf_vma_open,
+ .close = privcmd_buf_vma_close,
+ .fault = privcmd_buf_vma_fault,
+};
+
+static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct privcmd_buf_private *file_priv = file->private_data;
+ struct privcmd_buf_vma_private *vma_priv;
+ unsigned long count = vma_pages(vma);
+ unsigned int i;
+ int ret = 0;
+
+ if (!(vma->vm_flags & VM_SHARED) || count > limit ||
+ file_priv->allocated + count > limit)
+ return -EINVAL;
+
+ vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
+ GFP_KERNEL);
+ if (!vma_priv)
+ return -ENOMEM;
+
+ vma_priv->n_pages = count;
+ count = 0;
+ for (i = 0; i < vma_priv->n_pages; i++) {
+ vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!vma_priv->pages[i])
+ break;
+ count++;
+ }
+
+ mutex_lock(&file_priv->lock);
+
+ file_priv->allocated += count;
+
+ vma_priv->file_priv = file_priv;
+ vma_priv->users = 1;
+
+ vma->vm_flags |= VM_IO | VM_DONTEXPAND;
+ vma->vm_ops = &privcmd_buf_vm_ops;
+ vma->vm_private_data = vma_priv;
+
+ list_add(&vma_priv->list, &file_priv->list);
+
+ if (vma_priv->n_pages != count)
+ ret = -ENOMEM;
+ else
+ for (i = 0; i < vma_priv->n_pages; i++) {
+ ret = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE,
+ vma_priv->pages[i]);
+ if (ret)
+ break;
+ }
+
+ if (ret)
+ privcmd_buf_vmapriv_free(vma_priv);
+
+ mutex_unlock(&file_priv->lock);
+
+ return ret;
+}
+
+const struct file_operations xen_privcmdbuf_fops = {
+ .owner = THIS_MODULE,
+ .open = privcmd_buf_open,
+ .release = privcmd_buf_release,
+ .mmap = privcmd_buf_mmap,
+};
+EXPORT_SYMBOL_GPL(xen_privcmdbuf_fops);
+
+struct miscdevice xen_privcmdbuf_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "xen/hypercall",
+ .fops = &xen_privcmdbuf_fops,
+};
pr_err("Could not register Xen privcmd device\n");
return err;
}
+
+ err = misc_register(&xen_privcmdbuf_dev);
+ if (err != 0) {
+ pr_err("Could not register Xen hypercall-buf device\n");
+ misc_deregister(&privcmd_dev);
+ return err;
+ }
+
return 0;
}
static void __exit privcmd_exit(void)
{
misc_deregister(&privcmd_dev);
+ misc_deregister(&xen_privcmdbuf_dev);
}
module_init(privcmd_init);
#include <linux/fs.h>
extern const struct file_operations xen_privcmd_fops;
+extern const struct file_operations xen_privcmdbuf_fops;
+
+extern struct miscdevice xen_privcmdbuf_dev;
{
struct v2p_entry *entry;
unsigned long flags;
+ int err;
if (try) {
spin_lock_irqsave(&info->v2p_lock, flags);
scsiback_del_translation_entry(info, vir);
}
} else if (!try) {
- xenbus_printf(XBT_NIL, info->dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, info->dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
}
}
snprintf(str, sizeof(str), "vscsi-devs/%s/p-dev", ent);
val = xenbus_read(XBT_NIL, dev->nodename, str, NULL);
if (IS_ERR(val)) {
- xenbus_printf(XBT_NIL, dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
return;
}
strlcpy(phy, val, VSCSI_NAMELEN);
err = xenbus_scanf(XBT_NIL, dev->nodename, str, "%u:%u:%u:%u",
&vir.hst, &vir.chn, &vir.tgt, &vir.lun);
if (XENBUS_EXIST_ERR(err)) {
- xenbus_printf(XBT_NIL, dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
return;
}
static int
v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t mode,
- int *opened)
+ struct file *file, unsigned flags, umode_t mode)
{
int err;
u32 perm;
v9inode->writeback_fid = (void *) inode_fid;
}
mutex_unlock(&v9inode->v_mutex);
- err = finish_open(file, dentry, generic_file_open, opened);
+ err = finish_open(file, dentry, generic_file_open);
if (err)
goto error;
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(d_inode(dentry), file);
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
out:
dput(res);
return err;
static int
v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t omode,
- int *opened)
+ struct file *file, unsigned flags, umode_t omode)
{
int err = 0;
kgid_t gid;
}
mutex_unlock(&v9inode->v_mutex);
/* Since we are opening a file, assign the open fid to the file */
- err = finish_open(file, dentry, generic_file_open, opened);
+ err = finish_open(file, dentry, generic_file_open);
if (err)
goto err_clunk_old_fid;
file->private_data = ofid;
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(inode, file);
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
out:
v9fs_put_acl(dacl, pacl);
dput(res);
will automatically feed it to the correct interpreter.
You can do other nice things, too. Read the file
- <file:Documentation/binfmt_misc.txt> to learn how to use this
+ <file:Documentation/admin-guide/binfmt-misc.rst> to learn how to use this
feature, <file:Documentation/admin-guide/java.rst> for information about how
to include Java support. and <file:Documentation/admin-guide/mono.rst> for
information about how to include Mono-based .NET support.
return;
cur_time:
- *tv = current_time(inode);
+ *tv = timespec64_to_timespec(current_time(inode));
return;
too_early:
struct inode *
adfs_iget(struct super_block *sb, struct object_info *obj)
{
+ struct timespec ts;
struct inode *inode;
inode = new_inode(sb);
ADFS_I(inode)->stamped = ((obj->loadaddr & 0xfff00000) == 0xfff00000);
inode->i_mode = adfs_atts2mode(sb, inode);
- adfs_adfs2unix_time(&inode->i_mtime, inode);
+ ts = timespec64_to_timespec(inode->i_mtime);
+ adfs_adfs2unix_time(&ts, inode);
+ inode->i_mtime = timespec_to_timespec64(ts);
inode->i_atime = inode->i_mtime;
inode->i_ctime = inode->i_mtime;
ADFS_I(inode)->mmu_private = inode->i_size;
}
- insert_inode_hash(inode);
+ inode_fake_hash(inode);
out:
return inode;
static const struct super_operations adfs_sops = {
.alloc_inode = adfs_alloc_inode,
.destroy_inode = adfs_destroy_inode,
+ .drop_inode = generic_delete_inode,
.write_inode = adfs_write_inode,
.put_super = adfs_put_super,
.statfs = adfs_statfs,
afs-cache-$(CONFIG_AFS_FSCACHE) := cache.o
-kafs-objs := \
+kafs-y := \
$(afs-cache-y) \
addr_list.o \
callback.o \
main.o \
misc.o \
mntpt.o \
- proc.o \
rotate.o \
rxrpc.o \
security.o \
write.o \
xattr.o
+kafs-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_AFS_FS) := kafs.o
_enter("%s", cell->name);
ret = dns_query("afsdb", cell->name, cell->name_len,
- "ipv4", &vllist, _expiry);
+ "", &vllist, _expiry);
if (ret < 0)
return ERR_PTR(ret);
#include <linux/sched.h>
#include "internal.h"
+/*
+ * Create volume and callback interests on a server.
+ */
+static struct afs_cb_interest *afs_create_interest(struct afs_server *server,
+ struct afs_vnode *vnode)
+{
+ struct afs_vol_interest *new_vi, *vi;
+ struct afs_cb_interest *new;
+ struct hlist_node **pp;
+
+ new_vi = kzalloc(sizeof(struct afs_vol_interest), GFP_KERNEL);
+ if (!new_vi)
+ return NULL;
+
+ new = kzalloc(sizeof(struct afs_cb_interest), GFP_KERNEL);
+ if (!new) {
+ kfree(new_vi);
+ return NULL;
+ }
+
+ new_vi->usage = 1;
+ new_vi->vid = vnode->volume->vid;
+ INIT_HLIST_NODE(&new_vi->srv_link);
+ INIT_HLIST_HEAD(&new_vi->cb_interests);
+
+ refcount_set(&new->usage, 1);
+ new->sb = vnode->vfs_inode.i_sb;
+ new->vid = vnode->volume->vid;
+ new->server = afs_get_server(server);
+ INIT_HLIST_NODE(&new->cb_vlink);
+
+ write_lock(&server->cb_break_lock);
+
+ for (pp = &server->cb_volumes.first; *pp; pp = &(*pp)->next) {
+ vi = hlist_entry(*pp, struct afs_vol_interest, srv_link);
+ if (vi->vid < new_vi->vid)
+ continue;
+ if (vi->vid > new_vi->vid)
+ break;
+ vi->usage++;
+ goto found_vi;
+ }
+
+ new_vi->srv_link.pprev = pp;
+ new_vi->srv_link.next = *pp;
+ if (*pp)
+ (*pp)->pprev = &new_vi->srv_link.next;
+ *pp = &new_vi->srv_link;
+ vi = new_vi;
+ new_vi = NULL;
+found_vi:
+
+ new->vol_interest = vi;
+ hlist_add_head(&new->cb_vlink, &vi->cb_interests);
+
+ write_unlock(&server->cb_break_lock);
+ kfree(new_vi);
+ return new;
+}
+
/*
* Set up an interest-in-callbacks record for a volume on a server and
* register it with the server.
}
if (!cbi) {
- new = kzalloc(sizeof(struct afs_cb_interest), GFP_KERNEL);
+ new = afs_create_interest(server, vnode);
if (!new)
return -ENOMEM;
- refcount_set(&new->usage, 1);
- new->sb = vnode->vfs_inode.i_sb;
- new->vid = vnode->volume->vid;
- new->server = afs_get_server(server);
- INIT_LIST_HEAD(&new->cb_link);
-
- write_lock(&server->cb_break_lock);
- list_add_tail(&new->cb_link, &server->cb_interests);
- write_unlock(&server->cb_break_lock);
-
write_lock(&slist->lock);
if (!entry->cb_interest) {
entry->cb_interest = afs_get_cb_interest(new);
*/
void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi)
{
+ struct afs_vol_interest *vi;
+
if (cbi && refcount_dec_and_test(&cbi->usage)) {
- if (!list_empty(&cbi->cb_link)) {
+ if (!hlist_unhashed(&cbi->cb_vlink)) {
write_lock(&cbi->server->cb_break_lock);
- list_del_init(&cbi->cb_link);
+
+ hlist_del_init(&cbi->cb_vlink);
+ vi = cbi->vol_interest;
+ cbi->vol_interest = NULL;
+ if (--vi->usage == 0)
+ hlist_del(&vi->srv_link);
+ else
+ vi = NULL;
+
write_unlock(&cbi->server->cb_break_lock);
+ kfree(vi);
afs_put_server(net, cbi->server);
}
kfree(cbi);
static void afs_break_one_callback(struct afs_server *server,
struct afs_fid *fid)
{
+ struct afs_vol_interest *vi;
struct afs_cb_interest *cbi;
struct afs_iget_data data;
struct afs_vnode *vnode;
struct inode *inode;
read_lock(&server->cb_break_lock);
+ hlist_for_each_entry(vi, &server->cb_volumes, srv_link) {
+ if (vi->vid < fid->vid)
+ continue;
+ if (vi->vid > fid->vid) {
+ vi = NULL;
+ break;
+ }
+ //atomic_inc(&vi->usage);
+ break;
+ }
+
+ /* TODO: Find all matching volumes if we couldn't match the server and
+ * break them anyway.
+ */
+ if (!vi)
+ goto out;
/* Step through all interested superblocks. There may be more than one
* because of cell aliasing.
*/
- list_for_each_entry(cbi, &server->cb_interests, cb_link) {
- if (cbi->vid != fid->vid)
- continue;
-
+ hlist_for_each_entry(cbi, &vi->cb_interests, cb_vlink) {
if (fid->vnode == 0 && fid->unique == 0) {
/* The callback break applies to an entire volume. */
struct afs_super_info *as = AFS_FS_S(cbi->sb);
}
}
+out:
read_unlock(&server->cb_break_lock);
}
#include <linux/dns_resolver.h>
#include <linux/sched.h>
#include <linux/inet.h>
+#include <linux/namei.h>
#include <keys/rxrpc-type.h>
#include "internal.h"
/* install the new cell */
write_seqlock(&net->cells_lock);
- old_root = net->ws_cell;
- net->ws_cell = new_root;
+ old_root = rcu_access_pointer(net->ws_cell);
+ rcu_assign_pointer(net->ws_cell, new_root);
write_sequnlock(&net->cells_lock);
afs_put_cell(net, old_root);
NULL, 0,
cell, 0, true);
#endif
- ret = afs_proc_cell_setup(net, cell);
+ ret = afs_proc_cell_setup(cell);
if (ret < 0)
return ret;
- spin_lock(&net->proc_cells_lock);
+
+ mutex_lock(&net->proc_cells_lock);
list_add_tail(&cell->proc_link, &net->proc_cells);
- spin_unlock(&net->proc_cells_lock);
+ afs_dynroot_mkdir(net, cell);
+ mutex_unlock(&net->proc_cells_lock);
return 0;
}
{
_enter("%s", cell->name);
- afs_proc_cell_remove(net, cell);
+ afs_proc_cell_remove(cell);
- spin_lock(&net->proc_cells_lock);
+ mutex_lock(&net->proc_cells_lock);
list_del_init(&cell->proc_link);
- spin_unlock(&net->proc_cells_lock);
+ afs_dynroot_rmdir(net, cell);
+ mutex_unlock(&net->proc_cells_lock);
#ifdef CONFIG_AFS_FSCACHE
fscache_relinquish_cookie(cell->cache, NULL, false);
_enter("");
write_seqlock(&net->cells_lock);
- ws = net->ws_cell;
- net->ws_cell = NULL;
+ ws = rcu_access_pointer(net->ws_cell);
+ RCU_INIT_POINTER(net->ws_cell, NULL);
write_sequnlock(&net->cells_lock);
afs_put_cell(net, ws);
nifs = 0;
ifs = kcalloc(32, sizeof(*ifs), GFP_KERNEL);
if (ifs) {
- nifs = afs_get_ipv4_interfaces(ifs, 32, false);
+ nifs = afs_get_ipv4_interfaces(call->net, ifs, 32, false);
if (nifs < 0) {
kfree(ifs);
ifs = NULL;
{
struct afs_vnode *dvnode = AFS_FS_I(dir);
struct inode *inode;
+ struct dentry *d;
struct key *key;
int ret;
afs_stat_v(dvnode, n_lookup);
inode = afs_do_lookup(dir, dentry, key);
- if (IS_ERR(inode)) {
- ret = PTR_ERR(inode);
- if (ret == -ENOENT) {
- inode = afs_try_auto_mntpt(dentry, dir);
- if (!IS_ERR(inode)) {
- key_put(key);
- goto success;
- }
-
- ret = PTR_ERR(inode);
- }
-
- key_put(key);
- if (ret == -ENOENT) {
- d_add(dentry, NULL);
- _leave(" = NULL [negative]");
- return NULL;
- }
- _leave(" = %d [do]", ret);
- return ERR_PTR(ret);
- }
- dentry->d_fsdata = (void *)(unsigned long)dvnode->status.data_version;
-
- /* instantiate the dentry */
key_put(key);
- if (IS_ERR(inode)) {
- _leave(" = %ld", PTR_ERR(inode));
- return ERR_CAST(inode);
+ if (inode == ERR_PTR(-ENOENT)) {
+ inode = afs_try_auto_mntpt(dentry, dir);
+ } else {
+ dentry->d_fsdata =
+ (void *)(unsigned long)dvnode->status.data_version;
}
-
-success:
- d_add(dentry, inode);
- _leave(" = 0 { ino=%lu v=%u }",
- d_inode(dentry)->i_ino,
- d_inode(dentry)->i_generation);
-
- return NULL;
+ d = d_splice_alias(inode, dentry);
+ if (!IS_ERR_OR_NULL(d))
+ d->d_fsdata = dentry->d_fsdata;
+ return d;
}
/*
-/* dir.c: AFS dynamic root handling
+/* AFS dynamic root handling
*
* Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
return 0;
}
- ret = dns_query("afsdb", name, len, "ipv4", NULL, NULL);
+ ret = dns_query("afsdb", name, len, "", NULL, NULL);
if (ret == -ENODATA)
ret = -EDESTADDRREQ;
return ret;
out:
_leave("= %d", ret);
- return ERR_PTR(ret);
+ return ret == -ENOENT ? NULL : ERR_PTR(ret);
}
/*
static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
- struct afs_vnode *vnode;
- struct inode *inode;
- int ret;
-
- vnode = AFS_FS_I(dir);
-
_enter("%pd", dentry);
ASSERTCMP(d_inode(dentry), ==, NULL);
memcmp(dentry->d_name.name, "@cell", 5) == 0)
return afs_lookup_atcell(dentry);
- inode = afs_try_auto_mntpt(dentry, dir);
- if (IS_ERR(inode)) {
- ret = PTR_ERR(inode);
- if (ret == -ENOENT) {
- d_add(dentry, NULL);
- _leave(" = NULL [negative]");
- return NULL;
- }
- _leave(" = %d [do]", ret);
- return ERR_PTR(ret);
- }
-
- d_add(dentry, inode);
- _leave(" = 0 { ino=%lu v=%u }",
- d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
- return NULL;
+ return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry);
}
const struct inode_operations afs_dynroot_inode_operations = {
.d_release = afs_d_release,
.d_automount = afs_d_automount,
};
+
+/*
+ * Create a manually added cell mount directory.
+ * - The caller must hold net->proc_cells_lock
+ */
+int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell)
+{
+ struct super_block *sb = net->dynroot_sb;
+ struct dentry *root, *subdir;
+ int ret;
+
+ if (!sb || atomic_read(&sb->s_active) == 0)
+ return 0;
+
+ /* Let the ->lookup op do the creation */
+ root = sb->s_root;
+ inode_lock(root->d_inode);
+ subdir = lookup_one_len(cell->name, root, cell->name_len);
+ if (IS_ERR(subdir)) {
+ ret = PTR_ERR(subdir);
+ goto unlock;
+ }
+
+ /* Note that we're retaining an extra ref on the dentry */
+ subdir->d_fsdata = (void *)1UL;
+ ret = 0;
+unlock:
+ inode_unlock(root->d_inode);
+ return ret;
+}
+
+/*
+ * Remove a manually added cell mount directory.
+ * - The caller must hold net->proc_cells_lock
+ */
+void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell)
+{
+ struct super_block *sb = net->dynroot_sb;
+ struct dentry *root, *subdir;
+
+ if (!sb || atomic_read(&sb->s_active) == 0)
+ return;
+
+ root = sb->s_root;
+ inode_lock(root->d_inode);
+
+ /* Don't want to trigger a lookup call, which will re-add the cell */
+ subdir = try_lookup_one_len(cell->name, root, cell->name_len);
+ if (IS_ERR_OR_NULL(subdir)) {
+ _debug("lookup %ld", PTR_ERR(subdir));
+ goto no_dentry;
+ }
+
+ _debug("rmdir %pd %u", subdir, d_count(subdir));
+
+ if (subdir->d_fsdata) {
+ _debug("unpin %u", d_count(subdir));
+ subdir->d_fsdata = NULL;
+ dput(subdir);
+ }
+ dput(subdir);
+no_dentry:
+ inode_unlock(root->d_inode);
+ _leave("");
+}
+
+/*
+ * Populate a newly created dynamic root with cell names.
+ */
+int afs_dynroot_populate(struct super_block *sb)
+{
+ struct afs_cell *cell;
+ struct afs_net *net = afs_sb2net(sb);
+ int ret;
+
+ if (mutex_lock_interruptible(&net->proc_cells_lock) < 0)
+ return -ERESTARTSYS;
+
+ net->dynroot_sb = sb;
+ list_for_each_entry(cell, &net->proc_cells, proc_link) {
+ ret = afs_dynroot_mkdir(net, cell);
+ if (ret < 0)
+ goto error;
+ }
+
+ ret = 0;
+out:
+ mutex_unlock(&net->proc_cells_lock);
+ return ret;
+
+error:
+ net->dynroot_sb = NULL;
+ goto out;
+}
+
+/*
+ * When a dynamic root that's in the process of being destroyed, depopulate it
+ * of pinned directories.
+ */
+void afs_dynroot_depopulate(struct super_block *sb)
+{
+ struct afs_net *net = afs_sb2net(sb);
+ struct dentry *root = sb->s_root, *subdir, *tmp;
+
+ /* Prevent more subdirs from being created */
+ mutex_lock(&net->proc_cells_lock);
+ if (net->dynroot_sb == sb)
+ net->dynroot_sb = NULL;
+ mutex_unlock(&net->proc_cells_lock);
+
+ inode_lock(root->d_inode);
+
+ /* Remove all the pins for dirs created for manually added cells */
+ list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) {
+ if (subdir->d_fsdata) {
+ subdir->d_fsdata = NULL;
+ dput(subdir);
+ }
+ }
+
+ inode_unlock(root->d_inode);
+}
const afs_dataversion_t *expected_version,
u8 flags)
{
- struct timespec t;
+ struct timespec64 t;
umode_t mode;
t.tv_sec = status->mtime_client;
u64 data_version, size;
u32 type, abort_code;
u8 flags = 0;
- int ret;
-
- if (vnode)
- write_seqlock(&vnode->cb_lock);
abort_code = ntohl(xdr->abort_code);
* case.
*/
status->abort_code = abort_code;
- ret = 0;
- goto out;
+ return 0;
}
pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
if (abort_code != 0 && inline_error) {
status->abort_code = abort_code;
- ret = 0;
- goto out;
+ return 0;
}
type = ntohl(xdr->type);
flags);
}
- ret = 0;
-
-out:
- if (vnode)
- write_sequnlock(&vnode->cb_lock);
- return ret;
+ return 0;
bad:
xdr_dump_bad(*_bp);
- ret = afs_protocol_error(call, -EBADMSG);
- goto out;
+ return afs_protocol_error(call, -EBADMSG);
+}
+
+/*
+ * Decode the file status. We need to lock the target vnode if we're going to
+ * update its status so that stat() sees the attributes update atomically.
+ */
+static int afs_decode_status(struct afs_call *call,
+ const __be32 **_bp,
+ struct afs_file_status *status,
+ struct afs_vnode *vnode,
+ const afs_dataversion_t *expected_version,
+ struct afs_read *read_req)
+{
+ int ret;
+
+ if (!vnode)
+ return xdr_decode_AFSFetchStatus(call, _bp, status, vnode,
+ expected_version, read_req);
+
+ write_seqlock(&vnode->cb_lock);
+ ret = xdr_decode_AFSFetchStatus(call, _bp, status, vnode,
+ expected_version, read_req);
+ write_sequnlock(&vnode->cb_lock);
+ return ret;
}
/*
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
xdr_decode_AFSCallBack(call, vnode, &bp);
if (call->reply[1])
return ret;
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &vnode->status.data_version, req) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode,
+ &vnode->status.data_version, req) < 0)
return afs_protocol_error(call, -EBADMSG);
xdr_decode_AFSCallBack(call, vnode, &bp);
if (call->reply[1])
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
xdr_decode_AFSFid(&bp, call->reply[1]);
- if (xdr_decode_AFSFetchStatus(call, &bp, call->reply[2], NULL, NULL, NULL) < 0 ||
- xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL) < 0 ||
+ afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
xdr_decode_AFSCallBack_raw(&bp, call->reply[3]);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode, NULL, NULL) < 0 ||
- xdr_decode_AFSFetchStatus(call, &bp, &dvnode->status, dvnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL) < 0 ||
+ afs_decode_status(call, &bp, &dvnode->status, dvnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
xdr_decode_AFSFid(&bp, call->reply[1]);
- if (xdr_decode_AFSFetchStatus(call, &bp, call->reply[2], NULL, NULL, NULL) ||
- xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL) ||
+ afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &orig_dvnode->status, orig_dvnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
if (new_dvnode != orig_dvnode &&
- xdr_decode_AFSFetchStatus(call, &bp, &new_dvnode->status, new_dvnode,
- &call->expected_version_2, NULL) < 0)
+ afs_decode_status(call, &bp, &new_dvnode->status, new_dvnode,
+ &call->expected_version_2, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- if (xdr_decode_AFSFetchStatus(call, &bp, &vnode->status, vnode,
- &call->expected_version, NULL) < 0)
+ if (afs_decode_status(call, &bp, &vnode->status, vnode,
+ &call->expected_version, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
/* xdr_decode_AFSVolSync(&bp, call->reply[X]); */
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- xdr_decode_AFSFetchStatus(call, &bp, status, vnode,
- &call->expected_version, NULL);
+ afs_decode_status(call, &bp, status, vnode,
+ &call->expected_version, NULL);
callback[call->count].version = ntohl(bp[0]);
callback[call->count].expiry = ntohl(bp[1]);
callback[call->count].type = ntohl(bp[2]);
bp = call->buffer;
statuses = call->reply[1];
- if (xdr_decode_AFSFetchStatus(call, &bp, &statuses[call->count],
- call->count == 0 ? vnode : NULL,
- NULL, NULL) < 0)
+ if (afs_decode_status(call, &bp, &statuses[call->count],
+ call->count == 0 ? vnode : NULL,
+ NULL, NULL) < 0)
return afs_protocol_error(call, -EBADMSG);
call->count++;
#include <linux/backing-dev.h>
#include <linux/uuid.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "afs.h"
afs_voltype_t type; /* type of volume requested */
int volnamesz; /* size of volume name */
const char *volname; /* name of volume to mount */
- struct afs_net *net; /* Network namespace in effect */
+ struct net *net_ns; /* Network namespace in effect */
+ struct afs_net *net; /* the AFS net namespace stuff */
struct afs_cell *cell; /* cell in which to find volume */
struct afs_volume *volume; /* volume record */
struct key *key; /* key to use for secure mounting */
* - there's one superblock per volume
*/
struct afs_super_info {
- struct afs_net *net; /* Network namespace */
+ struct net *net_ns; /* Network namespace */
struct afs_cell *cell; /* The cell in which the volume resides */
struct afs_volume *volume; /* volume record */
bool dyn_root; /* True if dynamic root */
char *subs[AFS_NR_SYSNAME];
refcount_t usage;
unsigned short nr;
- short error;
char blank[1];
};
* AFS network namespace record.
*/
struct afs_net {
+ struct net *net; /* Backpointer to the owning net namespace */
struct afs_uuid uuid;
bool live; /* F if this namespace is being removed */
/* Cell database */
struct rb_root cells;
- struct afs_cell *ws_cell;
+ struct afs_cell __rcu *ws_cell;
struct work_struct cells_manager;
struct timer_list cells_timer;
atomic_t cells_outstanding;
seqlock_t cells_lock;
- spinlock_t proc_cells_lock;
+ struct mutex proc_cells_lock;
struct list_head proc_cells;
/* Known servers. Theoretically each fileserver can only be in one
struct mutex lock_manager_mutex;
/* Misc */
+ struct super_block *dynroot_sb; /* Dynamic root mount superblock */
struct proc_dir_entry *proc_afs; /* /proc/net/afs directory */
struct afs_sysnames *sysnames;
rwlock_t sysnames_lock;
};
extern const char afs_init_sysname[];
-extern struct afs_net __afs_net;// Dummy AFS network namespace; TODO: replace with real netns
enum afs_cell_state {
AFS_CELL_UNSET,
rwlock_t fs_lock; /* access lock */
/* callback promise management */
- struct list_head cb_interests; /* List of superblocks using this server */
+ struct hlist_head cb_volumes; /* List of volume interests on this server */
unsigned cb_s_break; /* Break-everything counter. */
rwlock_t cb_break_lock; /* Volume finding lock */
};
+/*
+ * Volume collation in the server's callback interest list.
+ */
+struct afs_vol_interest {
+ struct hlist_node srv_link; /* Link in server->cb_volumes */
+ struct hlist_head cb_interests; /* List of callback interests on the server */
+ afs_volid_t vid; /* Volume ID to match */
+ unsigned int usage;
+};
+
/*
* Interest by a superblock on a server.
*/
struct afs_cb_interest {
- struct list_head cb_link; /* Link in server->cb_interests */
+ struct hlist_node cb_vlink; /* Link in vol_interest->cb_interests */
+ struct afs_vol_interest *vol_interest;
struct afs_server *server; /* Server on which this interest resides */
struct super_block *sb; /* Superblock on which inodes reside */
afs_volid_t vid; /* Volume ID to match */
extern const struct dentry_operations afs_dynroot_dentry_operations;
extern struct inode *afs_try_auto_mntpt(struct dentry *, struct inode *);
+extern int afs_dynroot_mkdir(struct afs_net *, struct afs_cell *);
+extern void afs_dynroot_rmdir(struct afs_net *, struct afs_cell *);
+extern int afs_dynroot_populate(struct super_block *);
+extern void afs_dynroot_depopulate(struct super_block *);
/*
* file.c
* main.c
*/
extern struct workqueue_struct *afs_wq;
+extern int afs_net_id;
-static inline struct afs_net *afs_d2net(struct dentry *dentry)
+static inline struct afs_net *afs_net(struct net *net)
{
- return &__afs_net;
+ return net_generic(net, afs_net_id);
}
-static inline struct afs_net *afs_i2net(struct inode *inode)
+static inline struct afs_net *afs_sb2net(struct super_block *sb)
{
- return &__afs_net;
+ return afs_net(AFS_FS_S(sb)->net_ns);
}
-static inline struct afs_net *afs_v2net(struct afs_vnode *vnode)
+static inline struct afs_net *afs_d2net(struct dentry *dentry)
{
- return &__afs_net;
+ return afs_sb2net(dentry->d_sb);
}
-static inline struct afs_net *afs_sock2net(struct sock *sk)
+static inline struct afs_net *afs_i2net(struct inode *inode)
{
- return &__afs_net;
+ return afs_sb2net(inode->i_sb);
}
-static inline struct afs_net *afs_get_net(struct afs_net *net)
+static inline struct afs_net *afs_v2net(struct afs_vnode *vnode)
{
- return net;
+ return afs_i2net(&vnode->vfs_inode);
}
-static inline void afs_put_net(struct afs_net *net)
+static inline struct afs_net *afs_sock2net(struct sock *sk)
{
+ return net_generic(sock_net(sk), afs_net_id);
}
static inline void __afs_stat(atomic_t *s)
/*
* netdevices.c
*/
-extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool);
+extern int afs_get_ipv4_interfaces(struct afs_net *, struct afs_interface *,
+ size_t, bool);
/*
* proc.c
*/
+#ifdef CONFIG_PROC_FS
extern int __net_init afs_proc_init(struct afs_net *);
extern void __net_exit afs_proc_cleanup(struct afs_net *);
-extern int afs_proc_cell_setup(struct afs_net *, struct afs_cell *);
-extern void afs_proc_cell_remove(struct afs_net *, struct afs_cell *);
+extern int afs_proc_cell_setup(struct afs_cell *);
+extern void afs_proc_cell_remove(struct afs_cell *);
extern void afs_put_sysnames(struct afs_sysnames *);
+#else
+static inline int afs_proc_init(struct afs_net *net) { return 0; }
+static inline void afs_proc_cleanup(struct afs_net *net) {}
+static inline int afs_proc_cell_setup(struct afs_cell *cell) { return 0; }
+static inline void afs_proc_cell_remove(struct afs_cell *cell) {}
+static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {}
+#endif
/*
* rotate.c
* super.c
*/
extern int __init afs_fs_init(void);
-extern void __exit afs_fs_exit(void);
+extern void afs_fs_exit(void);
/*
* vlclient.c
#include <linux/completion.h>
#include <linux/sched.h>
#include <linux/random.h>
+#include <linux/proc_fs.h>
#define CREATE_TRACE_POINTS
#include "internal.h"
MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list");
struct workqueue_struct *afs_wq;
-struct afs_net __afs_net;
+static struct proc_dir_entry *afs_proc_symlink;
#if defined(CONFIG_ALPHA)
const char afs_init_sysname[] = "alpha_linux26";
/*
* Initialise an AFS network namespace record.
*/
-static int __net_init afs_net_init(struct afs_net *net)
+static int __net_init afs_net_init(struct net *net_ns)
{
struct afs_sysnames *sysnames;
+ struct afs_net *net = afs_net(net_ns);
int ret;
+ net->net = net_ns;
net->live = true;
generate_random_uuid((unsigned char *)&net->uuid);
INIT_WORK(&net->cells_manager, afs_manage_cells);
timer_setup(&net->cells_timer, afs_cells_timer, 0);
- spin_lock_init(&net->proc_cells_lock);
+ mutex_init(&net->proc_cells_lock);
INIT_LIST_HEAD(&net->proc_cells);
seqlock_init(&net->fs_lock);
/*
* Clean up and destroy an AFS network namespace record.
*/
-static void __net_exit afs_net_exit(struct afs_net *net)
+static void __net_exit afs_net_exit(struct net *net_ns)
{
+ struct afs_net *net = afs_net(net_ns);
+
net->live = false;
afs_cell_purge(net);
afs_purge_servers(net);
afs_put_sysnames(net->sysnames);
}
+static struct pernet_operations afs_net_ops = {
+ .init = afs_net_init,
+ .exit = afs_net_exit,
+ .id = &afs_net_id,
+ .size = sizeof(struct afs_net),
+};
+
/*
* initialise the AFS client FS module
*/
goto error_cache;
#endif
- ret = afs_net_init(&__afs_net);
+ ret = register_pernet_subsys(&afs_net_ops);
if (ret < 0)
goto error_net;
if (ret < 0)
goto error_fs;
+ afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs");
+ if (IS_ERR(afs_proc_symlink)) {
+ ret = PTR_ERR(afs_proc_symlink);
+ goto error_proc;
+ }
+
return ret;
+error_proc:
+ afs_fs_exit();
error_fs:
- afs_net_exit(&__afs_net);
+ unregister_pernet_subsys(&afs_net_ops);
error_net:
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
{
printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 unregistering.\n");
+ proc_remove(afs_proc_symlink);
afs_fs_exit();
- afs_net_exit(&__afs_net);
+ unregister_pernet_subsys(&afs_net_ops);
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
#endif
* - maxbufs must be at least 1
* - returns the number of interface records in the buffer
*/
-int afs_get_ipv4_interfaces(struct afs_interface *bufs, size_t maxbufs,
- bool wantloopback)
+int afs_get_ipv4_interfaces(struct afs_net *net, struct afs_interface *bufs,
+ size_t maxbufs, bool wantloopback)
{
struct net_device *dev;
struct in_device *idev;
ASSERT(maxbufs > 0);
rtnl_lock();
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net->net, dev) {
if (dev->type == ARPHRD_LOOPBACK && !wantloopback)
continue;
idev = __in_dev_get_rtnl(dev);
#include <linux/uaccess.h>
#include "internal.h"
-static inline struct afs_net *afs_proc2net(struct file *f)
+static inline struct afs_net *afs_seq2net(struct seq_file *m)
{
- return &__afs_net;
+ return afs_net(seq_file_net(m));
}
-static inline struct afs_net *afs_seq2net(struct seq_file *m)
+static inline struct afs_net *afs_seq2net_single(struct seq_file *m)
{
- return &__afs_net; // TODO: use seq_file_net(m)
+ return afs_net(seq_file_single_net(m));
}
-static int afs_proc_cells_open(struct inode *inode, struct file *file);
-static void *afs_proc_cells_start(struct seq_file *p, loff_t *pos);
-static void *afs_proc_cells_next(struct seq_file *p, void *v, loff_t *pos);
-static void afs_proc_cells_stop(struct seq_file *p, void *v);
-static int afs_proc_cells_show(struct seq_file *m, void *v);
-static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf,
- size_t size, loff_t *_pos);
-
-static const struct seq_operations afs_proc_cells_ops = {
- .start = afs_proc_cells_start,
- .next = afs_proc_cells_next,
- .stop = afs_proc_cells_stop,
- .show = afs_proc_cells_show,
-};
-
-static const struct file_operations afs_proc_cells_fops = {
- .open = afs_proc_cells_open,
- .read = seq_read,
- .write = afs_proc_cells_write,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static ssize_t afs_proc_rootcell_read(struct file *file, char __user *buf,
- size_t size, loff_t *_pos);
-static ssize_t afs_proc_rootcell_write(struct file *file,
- const char __user *buf,
- size_t size, loff_t *_pos);
-
-static const struct file_operations afs_proc_rootcell_fops = {
- .read = afs_proc_rootcell_read,
- .write = afs_proc_rootcell_write,
- .llseek = no_llseek,
-};
-
-static void *afs_proc_cell_volumes_start(struct seq_file *p, loff_t *pos);
-static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
- loff_t *pos);
-static void afs_proc_cell_volumes_stop(struct seq_file *p, void *v);
-static int afs_proc_cell_volumes_show(struct seq_file *m, void *v);
-
-static const struct seq_operations afs_proc_cell_volumes_ops = {
- .start = afs_proc_cell_volumes_start,
- .next = afs_proc_cell_volumes_next,
- .stop = afs_proc_cell_volumes_stop,
- .show = afs_proc_cell_volumes_show,
-};
-
-static void *afs_proc_cell_vlservers_start(struct seq_file *p, loff_t *pos);
-static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
- loff_t *pos);
-static void afs_proc_cell_vlservers_stop(struct seq_file *p, void *v);
-static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v);
-
-static const struct seq_operations afs_proc_cell_vlservers_ops = {
- .start = afs_proc_cell_vlservers_start,
- .next = afs_proc_cell_vlservers_next,
- .stop = afs_proc_cell_vlservers_stop,
- .show = afs_proc_cell_vlservers_show,
-};
-
-static void *afs_proc_servers_start(struct seq_file *p, loff_t *pos);
-static void *afs_proc_servers_next(struct seq_file *p, void *v,
- loff_t *pos);
-static void afs_proc_servers_stop(struct seq_file *p, void *v);
-static int afs_proc_servers_show(struct seq_file *m, void *v);
-
-static const struct seq_operations afs_proc_servers_ops = {
- .start = afs_proc_servers_start,
- .next = afs_proc_servers_next,
- .stop = afs_proc_servers_stop,
- .show = afs_proc_servers_show,
-};
-
-static int afs_proc_sysname_open(struct inode *inode, struct file *file);
-static int afs_proc_sysname_release(struct inode *inode, struct file *file);
-static void *afs_proc_sysname_start(struct seq_file *p, loff_t *pos);
-static void *afs_proc_sysname_next(struct seq_file *p, void *v,
- loff_t *pos);
-static void afs_proc_sysname_stop(struct seq_file *p, void *v);
-static int afs_proc_sysname_show(struct seq_file *m, void *v);
-static ssize_t afs_proc_sysname_write(struct file *file,
- const char __user *buf,
- size_t size, loff_t *_pos);
-
-static const struct seq_operations afs_proc_sysname_ops = {
- .start = afs_proc_sysname_start,
- .next = afs_proc_sysname_next,
- .stop = afs_proc_sysname_stop,
- .show = afs_proc_sysname_show,
-};
-
-static const struct file_operations afs_proc_sysname_fops = {
- .open = afs_proc_sysname_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = afs_proc_sysname_release,
- .write = afs_proc_sysname_write,
-};
-
-static int afs_proc_stats_show(struct seq_file *m, void *v);
-
/*
- * initialise the /proc/fs/afs/ directory
+ * Display the list of cells known to the namespace.
*/
-int afs_proc_init(struct afs_net *net)
+static int afs_proc_cells_show(struct seq_file *m, void *v)
{
- _enter("");
-
- net->proc_afs = proc_mkdir("fs/afs", NULL);
- if (!net->proc_afs)
- goto error_dir;
+ struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link);
+ struct afs_net *net = afs_seq2net(m);
- if (!proc_create("cells", 0644, net->proc_afs, &afs_proc_cells_fops) ||
- !proc_create("rootcell", 0644, net->proc_afs, &afs_proc_rootcell_fops) ||
- !proc_create_seq("servers", 0644, net->proc_afs, &afs_proc_servers_ops) ||
- !proc_create_single("stats", 0644, net->proc_afs, afs_proc_stats_show) ||
- !proc_create("sysname", 0644, net->proc_afs, &afs_proc_sysname_fops))
- goto error_tree;
+ if (v == &net->proc_cells) {
+ /* display header on line 1 */
+ seq_puts(m, "USE NAME\n");
+ return 0;
+ }
- _leave(" = 0");
+ /* display one cell per line on subsequent lines */
+ seq_printf(m, "%3u %s\n", atomic_read(&cell->usage), cell->name);
return 0;
-
-error_tree:
- proc_remove(net->proc_afs);
-error_dir:
- _leave(" = -ENOMEM");
- return -ENOMEM;
-}
-
-/*
- * clean up the /proc/fs/afs/ directory
- */
-void afs_proc_cleanup(struct afs_net *net)
-{
- proc_remove(net->proc_afs);
- net->proc_afs = NULL;
-}
-
-/*
- * open "/proc/fs/afs/cells" which provides a summary of extant cells
- */
-static int afs_proc_cells_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &afs_proc_cells_ops);
}
-/*
- * set up the iterator to start reading from the cells list and return the
- * first item
- */
static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos)
__acquires(rcu)
{
- struct afs_net *net = afs_seq2net(m);
-
rcu_read_lock();
- return seq_list_start_head(&net->proc_cells, *_pos);
+ return seq_list_start_head(&afs_seq2net(m)->proc_cells, *_pos);
}
-/*
- * move to next cell in cells list
- */
static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct afs_net *net = afs_seq2net(m);
-
- return seq_list_next(v, &net->proc_cells, pos);
+ return seq_list_next(v, &afs_seq2net(m)->proc_cells, pos);
}
-/*
- * clean up after reading from the cells list
- */
static void afs_proc_cells_stop(struct seq_file *m, void *v)
__releases(rcu)
{
rcu_read_unlock();
}
-/*
- * display a header line followed by a load of cell lines
- */
-static int afs_proc_cells_show(struct seq_file *m, void *v)
-{
- struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link);
- struct afs_net *net = afs_seq2net(m);
-
- if (v == &net->proc_cells) {
- /* display header on line 1 */
- seq_puts(m, "USE NAME\n");
- return 0;
- }
-
- /* display one cell per line on subsequent lines */
- seq_printf(m, "%3u %s\n", atomic_read(&cell->usage), cell->name);
- return 0;
-}
+static const struct seq_operations afs_proc_cells_ops = {
+ .start = afs_proc_cells_start,
+ .next = afs_proc_cells_next,
+ .stop = afs_proc_cells_stop,
+ .show = afs_proc_cells_show,
+};
/*
* handle writes to /proc/fs/afs/cells
* - to add cells: echo "add <cellname> <IP>[:<IP>][:<IP>]"
*/
-static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf,
- size_t size, loff_t *_pos)
+static int afs_proc_cells_write(struct file *file, char *buf, size_t size)
{
- struct afs_net *net = afs_proc2net(file);
- char *kbuf, *name, *args;
+ struct seq_file *m = file->private_data;
+ struct afs_net *net = afs_seq2net(m);
+ char *name, *args;
int ret;
- /* start by dragging the command into memory */
- if (size <= 1 || size >= PAGE_SIZE)
- return -EINVAL;
-
- kbuf = memdup_user_nul(buf, size);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
-
/* trim to first NL */
- name = memchr(kbuf, '\n', size);
+ name = memchr(buf, '\n', size);
if (name)
*name = 0;
/* split into command, name and argslist */
- name = strchr(kbuf, ' ');
+ name = strchr(buf, ' ');
if (!name)
goto inval;
do {
goto inval;
/* determine command to perform */
- _debug("cmd=%s name=%s args=%s", kbuf, name, args);
+ _debug("cmd=%s name=%s args=%s", buf, name, args);
- if (strcmp(kbuf, "add") == 0) {
+ if (strcmp(buf, "add") == 0) {
struct afs_cell *cell;
cell = afs_lookup_cell(net, name, strlen(name), args, true);
goto inval;
}
- ret = size;
+ ret = 0;
done:
- kfree(kbuf);
_leave(" = %d", ret);
return ret;
goto done;
}
-static ssize_t afs_proc_rootcell_read(struct file *file, char __user *buf,
- size_t size, loff_t *_pos)
+/*
+ * Display the name of the current workstation cell.
+ */
+static int afs_proc_rootcell_show(struct seq_file *m, void *v)
{
struct afs_cell *cell;
- struct afs_net *net = afs_proc2net(file);
- unsigned int seq = 0;
- char name[AFS_MAXCELLNAME + 1];
- int len;
-
- if (*_pos > 0)
- return 0;
- if (!net->ws_cell)
- return 0;
-
- rcu_read_lock();
- do {
- read_seqbegin_or_lock(&net->cells_lock, &seq);
- len = 0;
- cell = rcu_dereference_raw(net->ws_cell);
- if (cell) {
- len = cell->name_len;
- memcpy(name, cell->name, len);
- }
- } while (need_seqretry(&net->cells_lock, seq));
- done_seqretry(&net->cells_lock, seq);
- rcu_read_unlock();
-
- if (!len)
- return 0;
-
- name[len++] = '\n';
- if (len > size)
- len = size;
- if (copy_to_user(buf, name, len) != 0)
- return -EFAULT;
- *_pos = 1;
- return len;
+ struct afs_net *net;
+
+ net = afs_seq2net_single(m);
+ if (rcu_access_pointer(net->ws_cell)) {
+ rcu_read_lock();
+ cell = rcu_dereference(net->ws_cell);
+ if (cell)
+ seq_printf(m, "%s\n", cell->name);
+ rcu_read_unlock();
+ }
+ return 0;
}
/*
- * handle writes to /proc/fs/afs/rootcell
- * - to initialize rootcell: echo "cell.name:192.168.231.14"
+ * Set the current workstation cell and optionally supply its list of volume
+ * location servers.
+ *
+ * echo "cell.name:192.168.231.14" >/proc/fs/afs/rootcell
*/
-static ssize_t afs_proc_rootcell_write(struct file *file,
- const char __user *buf,
- size_t size, loff_t *_pos)
+static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size)
{
- struct afs_net *net = afs_proc2net(file);
- char *kbuf, *s;
+ struct seq_file *m = file->private_data;
+ struct afs_net *net = afs_seq2net_single(m);
+ char *s;
int ret;
- /* start by dragging the command into memory */
- if (size <= 1 || size >= PAGE_SIZE)
- return -EINVAL;
-
- kbuf = memdup_user_nul(buf, size);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
-
ret = -EINVAL;
- if (kbuf[0] == '.')
+ if (buf[0] == '.')
goto out;
- if (memchr(kbuf, '/', size))
+ if (memchr(buf, '/', size))
goto out;
/* trim to first NL */
- s = memchr(kbuf, '\n', size);
+ s = memchr(buf, '\n', size);
if (s)
*s = 0;
/* determine command to perform */
- _debug("rootcell=%s", kbuf);
+ _debug("rootcell=%s", buf);
- ret = afs_cell_init(net, kbuf);
- if (ret >= 0)
- ret = size; /* consume everything, always */
+ ret = afs_cell_init(net, buf);
out:
- kfree(kbuf);
_leave(" = %d", ret);
return ret;
}
+static const char afs_vol_types[3][3] = {
+ [AFSVL_RWVOL] = "RW",
+ [AFSVL_ROVOL] = "RO",
+ [AFSVL_BACKVOL] = "BK",
+};
+
/*
- * initialise /proc/fs/afs/<cell>/
+ * Display the list of volumes known to a cell.
*/
-int afs_proc_cell_setup(struct afs_net *net, struct afs_cell *cell)
+static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
{
- struct proc_dir_entry *dir;
-
- _enter("%p{%s},%p", cell, cell->name, net->proc_afs);
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
+ struct afs_volume *vol = list_entry(v, struct afs_volume, proc_link);
- dir = proc_mkdir(cell->name, net->proc_afs);
- if (!dir)
- goto error_dir;
+ /* Display header on line 1 */
+ if (v == &cell->proc_volumes) {
+ seq_puts(m, "USE VID TY\n");
+ return 0;
+ }
- if (!proc_create_seq_data("vlservers", 0, dir,
- &afs_proc_cell_vlservers_ops, cell))
- goto error_tree;
- if (!proc_create_seq_data("volumes", 0, dir, &afs_proc_cell_volumes_ops,
- cell))
- goto error_tree;
+ seq_printf(m, "%3d %08x %s\n",
+ atomic_read(&vol->usage), vol->vid,
+ afs_vol_types[vol->type]);
- _leave(" = 0");
return 0;
-
-error_tree:
- remove_proc_subtree(cell->name, net->proc_afs);
-error_dir:
- _leave(" = -ENOMEM");
- return -ENOMEM;
}
-/*
- * remove /proc/fs/afs/<cell>/
- */
-void afs_proc_cell_remove(struct afs_net *net, struct afs_cell *cell)
-{
- _enter("");
-
- remove_proc_subtree(cell->name, net->proc_afs);
-
- _leave("");
-}
-
-/*
- * set up the iterator to start reading from the cells list and return the
- * first item
- */
static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
__acquires(cell->proc_lock)
{
struct afs_cell *cell = PDE_DATA(file_inode(m->file));
- _enter("cell=%p pos=%Ld", cell, *_pos);
-
read_lock(&cell->proc_lock);
return seq_list_start_head(&cell->proc_volumes, *_pos);
}
-/*
- * move to next cell in cells list
- */
-static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
+static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v,
loff_t *_pos)
{
- struct afs_cell *cell = PDE_DATA(file_inode(p->file));
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
- _enter("cell=%p pos=%Ld", cell, *_pos);
return seq_list_next(v, &cell->proc_volumes, _pos);
}
-/*
- * clean up after reading from the cells list
- */
-static void afs_proc_cell_volumes_stop(struct seq_file *p, void *v)
+static void afs_proc_cell_volumes_stop(struct seq_file *m, void *v)
__releases(cell->proc_lock)
{
- struct afs_cell *cell = PDE_DATA(file_inode(p->file));
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
read_unlock(&cell->proc_lock);
}
-static const char afs_vol_types[3][3] = {
- [AFSVL_RWVOL] = "RW",
- [AFSVL_ROVOL] = "RO",
- [AFSVL_BACKVOL] = "BK",
+static const struct seq_operations afs_proc_cell_volumes_ops = {
+ .start = afs_proc_cell_volumes_start,
+ .next = afs_proc_cell_volumes_next,
+ .stop = afs_proc_cell_volumes_stop,
+ .show = afs_proc_cell_volumes_show,
};
/*
- * display a header line followed by a load of volume lines
+ * Display the list of Volume Location servers we're using for a cell.
*/
-static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
+static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
{
- struct afs_cell *cell = PDE_DATA(file_inode(m->file));
- struct afs_volume *vol = list_entry(v, struct afs_volume, proc_link);
+ struct sockaddr_rxrpc *addr = v;
- /* Display header on line 1 */
- if (v == &cell->proc_volumes) {
- seq_puts(m, "USE VID TY\n");
+ /* display header on line 1 */
+ if (v == (void *)1) {
+ seq_puts(m, "ADDRESS\n");
return 0;
}
- seq_printf(m, "%3d %08x %s\n",
- atomic_read(&vol->usage), vol->vid,
- afs_vol_types[vol->type]);
-
+ /* display one cell per line on subsequent lines */
+ seq_printf(m, "%pISp\n", &addr->transport);
return 0;
}
-/*
- * set up the iterator to start reading from the cells list and return the
- * first item
- */
static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
__acquires(rcu)
{
return alist->addrs + pos;
}
-/*
- * move to next cell in cells list
- */
-static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
+static void *afs_proc_cell_vlservers_next(struct seq_file *m, void *v,
loff_t *_pos)
{
struct afs_addr_list *alist;
- struct afs_cell *cell = PDE_DATA(file_inode(p->file));
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
loff_t pos;
alist = rcu_dereference(cell->vl_addrs);
return alist->addrs + pos;
}
-/*
- * clean up after reading from the cells list
- */
-static void afs_proc_cell_vlservers_stop(struct seq_file *p, void *v)
+static void afs_proc_cell_vlservers_stop(struct seq_file *m, void *v)
__releases(rcu)
{
rcu_read_unlock();
}
+static const struct seq_operations afs_proc_cell_vlservers_ops = {
+ .start = afs_proc_cell_vlservers_start,
+ .next = afs_proc_cell_vlservers_next,
+ .stop = afs_proc_cell_vlservers_stop,
+ .show = afs_proc_cell_vlservers_show,
+};
+
/*
- * display a header line followed by a load of volume lines
+ * Display the list of fileservers we're using within a namespace.
*/
-static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
+static int afs_proc_servers_show(struct seq_file *m, void *v)
{
- struct sockaddr_rxrpc *addr = v;
+ struct afs_server *server;
+ struct afs_addr_list *alist;
+ int i;
- /* display header on line 1 */
- if (v == (void *)1) {
- seq_puts(m, "ADDRESS\n");
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(m, "UUID USE ADDR\n");
return 0;
}
- /* display one cell per line on subsequent lines */
- seq_printf(m, "%pISp\n", &addr->transport);
+ server = list_entry(v, struct afs_server, proc_link);
+ alist = rcu_dereference(server->addresses);
+ seq_printf(m, "%pU %3d %pISpc%s\n",
+ &server->uuid,
+ atomic_read(&server->usage),
+ &alist->addrs[0].transport,
+ alist->index == 0 ? "*" : "");
+ for (i = 1; i < alist->nr_addrs; i++)
+ seq_printf(m, " %pISpc%s\n",
+ &alist->addrs[i].transport,
+ alist->index == i ? "*" : "");
return 0;
}
-/*
- * Set up the iterator to start reading from the server list and return the
- * first item.
- */
static void *afs_proc_servers_start(struct seq_file *m, loff_t *_pos)
__acquires(rcu)
{
- struct afs_net *net = afs_seq2net(m);
-
rcu_read_lock();
- return seq_hlist_start_head_rcu(&net->fs_proc, *_pos);
+ return seq_hlist_start_head_rcu(&afs_seq2net(m)->fs_proc, *_pos);
}
-/*
- * move to next cell in cells list
- */
static void *afs_proc_servers_next(struct seq_file *m, void *v, loff_t *_pos)
{
- struct afs_net *net = afs_seq2net(m);
-
- return seq_hlist_next_rcu(v, &net->fs_proc, _pos);
+ return seq_hlist_next_rcu(v, &afs_seq2net(m)->fs_proc, _pos);
}
-/*
- * clean up after reading from the cells list
- */
-static void afs_proc_servers_stop(struct seq_file *p, void *v)
+static void afs_proc_servers_stop(struct seq_file *m, void *v)
__releases(rcu)
{
rcu_read_unlock();
}
+static const struct seq_operations afs_proc_servers_ops = {
+ .start = afs_proc_servers_start,
+ .next = afs_proc_servers_next,
+ .stop = afs_proc_servers_stop,
+ .show = afs_proc_servers_show,
+};
+
/*
- * display a header line followed by a load of volume lines
+ * Display the list of strings that may be substituted for the @sys pathname
+ * macro.
*/
-static int afs_proc_servers_show(struct seq_file *m, void *v)
+static int afs_proc_sysname_show(struct seq_file *m, void *v)
{
- struct afs_server *server;
- struct afs_addr_list *alist;
-
- if (v == SEQ_START_TOKEN) {
- seq_puts(m, "UUID USE ADDR\n");
- return 0;
- }
+ struct afs_net *net = afs_seq2net(m);
+ struct afs_sysnames *sysnames = net->sysnames;
+ unsigned int i = (unsigned long)v - 1;
- server = list_entry(v, struct afs_server, proc_link);
- alist = rcu_dereference(server->addresses);
- seq_printf(m, "%pU %3d %pISp\n",
- &server->uuid,
- atomic_read(&server->usage),
- &alist->addrs[alist->index].transport);
+ if (i < sysnames->nr)
+ seq_printf(m, "%s\n", sysnames->subs[i]);
return 0;
}
-void afs_put_sysnames(struct afs_sysnames *sysnames)
+static void *afs_proc_sysname_start(struct seq_file *m, loff_t *pos)
+ __acquires(&net->sysnames_lock)
{
- int i;
+ struct afs_net *net = afs_seq2net(m);
+ struct afs_sysnames *names;
- if (sysnames && refcount_dec_and_test(&sysnames->usage)) {
- for (i = 0; i < sysnames->nr; i++)
- if (sysnames->subs[i] != afs_init_sysname &&
- sysnames->subs[i] != sysnames->blank)
- kfree(sysnames->subs[i]);
- }
+ read_lock(&net->sysnames_lock);
+
+ names = net->sysnames;
+ if (*pos >= names->nr)
+ return NULL;
+ return (void *)(unsigned long)(*pos + 1);
}
-/*
- * Handle opening of /proc/fs/afs/sysname. If it is opened for writing, we
- * assume the caller wants to change the substitution list and we allocate a
- * buffer to hold the list.
- */
-static int afs_proc_sysname_open(struct inode *inode, struct file *file)
+static void *afs_proc_sysname_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct afs_sysnames *sysnames;
- struct seq_file *m;
- int ret;
-
- ret = seq_open(file, &afs_proc_sysname_ops);
- if (ret < 0)
- return ret;
+ struct afs_net *net = afs_seq2net(m);
+ struct afs_sysnames *names = net->sysnames;
- if (file->f_mode & FMODE_WRITE) {
- sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL);
- if (!sysnames) {
- seq_release(inode, file);
- return -ENOMEM;
- }
+ *pos += 1;
+ if (*pos >= names->nr)
+ return NULL;
+ return (void *)(unsigned long)(*pos + 1);
+}
- refcount_set(&sysnames->usage, 1);
- m = file->private_data;
- m->private = sysnames;
- }
+static void afs_proc_sysname_stop(struct seq_file *m, void *v)
+ __releases(&net->sysnames_lock)
+{
+ struct afs_net *net = afs_seq2net(m);
- return 0;
+ read_unlock(&net->sysnames_lock);
}
+static const struct seq_operations afs_proc_sysname_ops = {
+ .start = afs_proc_sysname_start,
+ .next = afs_proc_sysname_next,
+ .stop = afs_proc_sysname_stop,
+ .show = afs_proc_sysname_show,
+};
+
/*
- * Handle writes to /proc/fs/afs/sysname to set the @sys substitution.
+ * Allow the @sys substitution to be configured.
*/
-static ssize_t afs_proc_sysname_write(struct file *file,
- const char __user *buf,
- size_t size, loff_t *_pos)
+static int afs_proc_sysname_write(struct file *file, char *buf, size_t size)
{
- struct afs_sysnames *sysnames;
+ struct afs_sysnames *sysnames, *kill;
struct seq_file *m = file->private_data;
- char *kbuf = NULL, *s, *p, *sub;
+ struct afs_net *net = afs_seq2net(m);
+ char *s, *p, *sub;
int ret, len;
- sysnames = m->private;
+ sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL);
if (!sysnames)
- return -EINVAL;
- if (sysnames->error)
- return sysnames->error;
-
- if (size >= PAGE_SIZE - 1) {
- sysnames->error = -EINVAL;
- return -EINVAL;
- }
- if (size == 0)
- return 0;
-
- kbuf = memdup_user_nul(buf, size);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
-
- inode_lock(file_inode(file));
+ return -ENOMEM;
+ refcount_set(&sysnames->usage, 1);
+ kill = sysnames;
- p = kbuf;
+ p = buf;
while ((s = strsep(&p, " \t\n"))) {
len = strlen(s);
if (len == 0)
sysnames->nr++;
}
- ret = size; /* consume everything, always */
+ if (sysnames->nr == 0) {
+ sysnames->subs[0] = sysnames->blank;
+ sysnames->nr++;
+ }
+
+ write_lock(&net->sysnames_lock);
+ kill = net->sysnames;
+ net->sysnames = sysnames;
+ write_unlock(&net->sysnames_lock);
+ ret = 0;
out:
- inode_unlock(file_inode(file));
- kfree(kbuf);
+ afs_put_sysnames(kill);
return ret;
invalid:
ret = -EINVAL;
error:
- sysnames->error = ret;
goto out;
}
-static int afs_proc_sysname_release(struct inode *inode, struct file *file)
+void afs_put_sysnames(struct afs_sysnames *sysnames)
{
- struct afs_sysnames *sysnames, *kill = NULL;
- struct seq_file *m = file->private_data;
- struct afs_net *net = afs_seq2net(m);
+ int i;
- sysnames = m->private;
- if (sysnames) {
- if (!sysnames->error) {
- kill = sysnames;
- if (sysnames->nr == 0) {
- sysnames->subs[0] = sysnames->blank;
- sysnames->nr++;
- }
- write_lock(&net->sysnames_lock);
- kill = net->sysnames;
- net->sysnames = sysnames;
- write_unlock(&net->sysnames_lock);
- }
- afs_put_sysnames(kill);
+ if (sysnames && refcount_dec_and_test(&sysnames->usage)) {
+ for (i = 0; i < sysnames->nr; i++)
+ if (sysnames->subs[i] != afs_init_sysname &&
+ sysnames->subs[i] != sysnames->blank)
+ kfree(sysnames->subs[i]);
}
-
- return seq_release(inode, file);
-}
-
-static void *afs_proc_sysname_start(struct seq_file *m, loff_t *pos)
- __acquires(&net->sysnames_lock)
-{
- struct afs_net *net = afs_seq2net(m);
- struct afs_sysnames *names = net->sysnames;
-
- read_lock(&net->sysnames_lock);
-
- if (*pos >= names->nr)
- return NULL;
- return (void *)(unsigned long)(*pos + 1);
-}
-
-static void *afs_proc_sysname_next(struct seq_file *m, void *v, loff_t *pos)
-{
- struct afs_net *net = afs_seq2net(m);
- struct afs_sysnames *names = net->sysnames;
-
- *pos += 1;
- if (*pos >= names->nr)
- return NULL;
- return (void *)(unsigned long)(*pos + 1);
-}
-
-static void afs_proc_sysname_stop(struct seq_file *m, void *v)
- __releases(&net->sysnames_lock)
-{
- struct afs_net *net = afs_seq2net(m);
-
- read_unlock(&net->sysnames_lock);
-}
-
-static int afs_proc_sysname_show(struct seq_file *m, void *v)
-{
- struct afs_net *net = afs_seq2net(m);
- struct afs_sysnames *sysnames = net->sysnames;
- unsigned int i = (unsigned long)v - 1;
-
- if (i < sysnames->nr)
- seq_printf(m, "%s\n", sysnames->subs[i]);
- return 0;
}
/*
*/
static int afs_proc_stats_show(struct seq_file *m, void *v)
{
- struct afs_net *net = afs_seq2net(m);
+ struct afs_net *net = afs_seq2net_single(m);
seq_puts(m, "kAFS statistics\n");
atomic_long_read(&net->n_store_bytes));
return 0;
}
+
+/*
+ * initialise /proc/fs/afs/<cell>/
+ */
+int afs_proc_cell_setup(struct afs_cell *cell)
+{
+ struct proc_dir_entry *dir;
+ struct afs_net *net = cell->net;
+
+ _enter("%p{%s},%p", cell, cell->name, net->proc_afs);
+
+ dir = proc_net_mkdir(net->net, cell->name, net->proc_afs);
+ if (!dir)
+ goto error_dir;
+
+ if (!proc_create_net_data("vlservers", 0444, dir,
+ &afs_proc_cell_vlservers_ops,
+ sizeof(struct seq_net_private),
+ cell) ||
+ !proc_create_net_data("volumes", 0444, dir,
+ &afs_proc_cell_volumes_ops,
+ sizeof(struct seq_net_private),
+ cell))
+ goto error_tree;
+
+ _leave(" = 0");
+ return 0;
+
+error_tree:
+ remove_proc_subtree(cell->name, net->proc_afs);
+error_dir:
+ _leave(" = -ENOMEM");
+ return -ENOMEM;
+}
+
+/*
+ * remove /proc/fs/afs/<cell>/
+ */
+void afs_proc_cell_remove(struct afs_cell *cell)
+{
+ struct afs_net *net = cell->net;
+
+ _enter("");
+ remove_proc_subtree(cell->name, net->proc_afs);
+ _leave("");
+}
+
+/*
+ * initialise the /proc/fs/afs/ directory
+ */
+int afs_proc_init(struct afs_net *net)
+{
+ struct proc_dir_entry *p;
+
+ _enter("");
+
+ p = proc_net_mkdir(net->net, "afs", net->net->proc_net);
+ if (!p)
+ goto error_dir;
+
+ if (!proc_create_net_data_write("cells", 0644, p,
+ &afs_proc_cells_ops,
+ afs_proc_cells_write,
+ sizeof(struct seq_net_private),
+ NULL) ||
+ !proc_create_net_single_write("rootcell", 0644, p,
+ afs_proc_rootcell_show,
+ afs_proc_rootcell_write,
+ NULL) ||
+ !proc_create_net("servers", 0444, p, &afs_proc_servers_ops,
+ sizeof(struct seq_net_private)) ||
+ !proc_create_net_single("stats", 0444, p, afs_proc_stats_show, NULL) ||
+ !proc_create_net_data_write("sysname", 0644, p,
+ &afs_proc_sysname_ops,
+ afs_proc_sysname_write,
+ sizeof(struct seq_net_private),
+ NULL))
+ goto error_tree;
+
+ net->proc_afs = p;
+ _leave(" = 0");
+ return 0;
+
+error_tree:
+ proc_remove(p);
+error_dir:
+ _leave(" = -ENOMEM");
+ return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/afs/ directory
+ */
+void afs_proc_cleanup(struct afs_net *net)
+{
+ proc_remove(net->proc_afs);
+ net->proc_afs = NULL;
+}
_enter("");
- ret = sock_create_kern(&init_net, AF_RXRPC, SOCK_DGRAM, PF_INET6, &socket);
+ ret = sock_create_kern(net->net, AF_RXRPC, SOCK_DGRAM, PF_INET6, &socket);
if (ret < 0)
goto error_1;
trace_afs_notify_call(rxcall, call);
call->need_attention = true;
- u = __atomic_add_unless(&call->usage, 1, 0);
+ u = atomic_fetch_add_unless(&call->usage, 1, 0);
if (u != 0) {
trace_afs_call(call, afs_call_trace_wake, u,
atomic_read(&call->net->nr_outstanding_calls),
server->flags = (1UL << AFS_SERVER_FL_NEW);
server->update_at = ktime_get_real_seconds() + afs_server_update_delay;
rwlock_init(&server->fs_lock);
- INIT_LIST_HEAD(&server->cb_interests);
+ INIT_HLIST_HEAD(&server->cb_volumes);
rwlock_init(&server->cb_break_lock);
afs_inc_servers_outstanding(net);
};
MODULE_ALIAS_FS("afs");
+int afs_net_id;
+
static const struct super_operations afs_super_ops = {
.statfs = afs_statfs,
.alloc_inode = afs_alloc_inode,
/*
* clean up the filesystem
*/
-void __exit afs_fs_exit(void)
+void afs_fs_exit(void)
{
_enter("");
struct afs_super_info *as1 = data;
struct afs_super_info *as = AFS_FS_S(sb);
- return (as->net == as1->net &&
+ return (as->net_ns == as1->net_ns &&
as->volume &&
- as->volume->vid == as1->volume->vid);
+ as->volume->vid == as1->volume->vid &&
+ !as->dyn_root);
}
static int afs_dynroot_test_super(struct super_block *sb, void *data)
{
- return false;
+ struct afs_super_info *as1 = data;
+ struct afs_super_info *as = AFS_FS_S(sb);
+
+ return (as->net_ns == as1->net_ns &&
+ as->dyn_root);
}
static int afs_set_super(struct super_block *sb, void *data)
if (!sb->s_root)
goto error;
- if (params->dyn_root)
+ if (as->dyn_root) {
sb->s_d_op = &afs_dynroot_dentry_operations;
- else
+ ret = afs_dynroot_populate(sb);
+ if (ret < 0)
+ goto error;
+ } else {
sb->s_d_op = &afs_fs_dentry_operations;
+ }
_leave(" = 0");
return 0;
as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
if (as) {
- as->net = afs_get_net(params->net);
+ as->net_ns = get_net(params->net_ns);
if (params->dyn_root)
as->dyn_root = true;
else
{
if (as) {
afs_put_volume(as->cell, as->volume);
- afs_put_cell(as->net, as->cell);
- afs_put_net(as->net);
+ afs_put_cell(afs_net(as->net_ns), as->cell);
+ put_net(as->net_ns);
kfree(as);
}
}
+static void afs_kill_super(struct super_block *sb)
+{
+ struct afs_super_info *as = AFS_FS_S(sb);
+ struct afs_net *net = afs_net(as->net_ns);
+
+ if (as->dyn_root)
+ afs_dynroot_depopulate(sb);
+
+ /* Clear the callback interests (which will do ilookup5) before
+ * deactivating the superblock.
+ */
+ if (as->volume)
+ afs_clear_callback_interests(net, as->volume->servers);
+ kill_anon_super(sb);
+ if (as->volume)
+ afs_deactivate_volume(as->volume);
+ afs_destroy_sbi(as);
+}
+
/*
* get an AFS superblock
*/
_enter(",,%s,%p", dev_name, options);
memset(¶ms, 0, sizeof(params));
- params.net = &__afs_net;
ret = -EINVAL;
if (current->nsproxy->net_ns != &init_net)
goto error;
-
+ params.net_ns = current->nsproxy->net_ns;
+ params.net = afs_net(params.net_ns);
+
/* parse the options and device name */
if (options) {
ret = afs_parse_options(¶ms, options, &dev_name);
return ERR_PTR(ret);
}
-static void afs_kill_super(struct super_block *sb)
-{
- struct afs_super_info *as = AFS_FS_S(sb);
-
- /* Clear the callback interests (which will do ilookup5) before
- * deactivating the superblock.
- */
- if (as->volume)
- afs_clear_callback_interests(as->net, as->volume->servers);
- kill_anon_super(sb);
- if (as->volume)
- afs_deactivate_volume(as->volume);
- afs_destroy_sbi(as);
-}
-
/*
* Initialise an inode cache slab element prior to any use. Note that
* afs_alloc_inode() *must* reset anything that could incorrectly leak from one
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/backing-dev.h>
+#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/sched/signal.h>
struct poll_iocb {
struct file *file;
- __poll_t events;
struct wait_queue_head *head;
-
- union {
- struct wait_queue_entry wait;
- struct work_struct work;
- };
+ __poll_t events;
+ bool woken;
+ bool cancelled;
+ struct wait_queue_entry wait;
+ struct work_struct work;
};
struct aio_kiocb {
struct list_head ki_list; /* the aio core uses this
* for cancellation */
+ refcount_t ki_refcnt;
/*
* If the aio_resfd field of the userspace iocb is not zero,
static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
- struct qstr this = QSTR_INIT("[aio]", 5);
struct file *file;
- struct path path;
struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
if (IS_ERR(inode))
return ERR_CAST(inode);
inode->i_mapping->private_data = ctx;
inode->i_size = PAGE_SIZE * nr_pages;
- path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
- if (!path.dentry) {
+ file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
+ O_RDWR, &aio_ring_fops);
+ if (IS_ERR(file))
iput(inode);
- return ERR_PTR(-ENOMEM);
- }
- path.mnt = mntget(aio_mnt);
-
- d_instantiate(path.dentry, inode);
- file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
- if (IS_ERR(file)) {
- path_put(&path);
- return file;
- }
-
- file->f_flags = O_RDWR;
return file;
}
static struct dentry *aio_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- static const struct dentry_operations ops = {
- .d_dname = simple_dname,
- };
- struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+ struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL,
AIO_RING_MAGIC);
if (!IS_ERR(root))
percpu_ref_get(&ctx->reqs);
INIT_LIST_HEAD(&req->ki_list);
+ refcount_set(&req->ki_refcnt, 0);
req->ki_ctx = ctx;
return req;
out_put:
return ret;
}
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+ if (refcount_read(&iocb->ki_refcnt) == 0 ||
+ refcount_dec_and_test(&iocb->ki_refcnt)) {
+ percpu_ref_put(&iocb->ki_ctx->reqs);
+ kmem_cache_free(kiocb_cachep, iocb);
+ }
+}
+
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
eventfd_ctx_put(iocb->ki_eventfd);
}
- kmem_cache_free(kiocb_cachep, iocb);
-
/*
* We have to order our ring_info tail store above and test
* of the wait list below outside the wait lock. This is
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
-
- percpu_ref_put(&ctx->reqs);
+ iocb_put(iocb);
}
/* aio_read_events_ring
if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
iocb->aio_rw_flags))
return -EINVAL;
+
req->file = fget(iocb->aio_fildes);
if (unlikely(!req->file))
return -EBADF;
return 0;
}
-/* need to use list_del_init so we can check if item was present */
-static inline bool __aio_poll_remove(struct poll_iocb *req)
+static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
{
- if (list_empty(&req->wait.entry))
- return false;
- list_del_init(&req->wait.entry);
- return true;
-}
+ struct file *file = iocb->poll.file;
-static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
- fput(iocb->poll.file);
aio_complete(iocb, mangle_poll(mask), 0);
+ fput(file);
}
-static void aio_poll_work(struct work_struct *work)
+static void aio_poll_complete_work(struct work_struct *work)
{
- struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
+ struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+ struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+ struct poll_table_struct pt = { ._key = req->events };
+ struct kioctx *ctx = iocb->ki_ctx;
+ __poll_t mask = 0;
- if (!list_empty_careful(&iocb->ki_list))
- aio_remove_iocb(iocb);
- __aio_poll_complete(iocb, iocb->poll.events);
+ if (!READ_ONCE(req->cancelled))
+ mask = vfs_poll(req->file, &pt) & req->events;
+
+ /*
+ * Note that ->ki_cancel callers also delete iocb from active_reqs after
+ * calling ->ki_cancel. We need the ctx_lock roundtrip here to
+ * synchronize with them. In the cancellation case the list_del_init
+ * itself is not actually needed, but harmless so we keep it in to
+ * avoid further branches in the fast path.
+ */
+ spin_lock_irq(&ctx->ctx_lock);
+ if (!mask && !READ_ONCE(req->cancelled)) {
+ add_wait_queue(req->head, &req->wait);
+ spin_unlock_irq(&ctx->ctx_lock);
+ return;
+ }
+ list_del_init(&iocb->ki_list);
+ spin_unlock_irq(&ctx->ctx_lock);
+
+ aio_poll_complete(iocb, mask);
}
+/* assumes we are called with irqs disabled */
static int aio_poll_cancel(struct kiocb *iocb)
{
struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
struct poll_iocb *req = &aiocb->poll;
- struct wait_queue_head *head = req->head;
- bool found = false;
-
- spin_lock(&head->lock);
- found = __aio_poll_remove(req);
- spin_unlock(&head->lock);
- if (found) {
- req->events = 0;
- INIT_WORK(&req->work, aio_poll_work);
- schedule_work(&req->work);
+ spin_lock(&req->head->lock);
+ WRITE_ONCE(req->cancelled, true);
+ if (!list_empty(&req->wait.entry)) {
+ list_del_init(&req->wait.entry);
+ schedule_work(&aiocb->poll.work);
}
+ spin_unlock(&req->head->lock);
+
return 0;
}
{
struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
- struct file *file = req->file;
__poll_t mask = key_to_poll(key);
- assert_spin_locked(&req->head->lock);
+ req->woken = true;
/* for instances that support it check for an event match first: */
- if (mask && !(mask & req->events))
- return 0;
+ if (mask) {
+ if (!(mask & req->events))
+ return 0;
+
+ /* try to complete the iocb inline if we can: */
+ if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+ list_del(&iocb->ki_list);
+ spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+ list_del_init(&req->wait.entry);
+ aio_poll_complete(iocb, mask);
+ return 1;
+ }
+ }
- mask = file->f_op->poll_mask(file, req->events);
- if (!mask)
- return 0;
+ list_del_init(&req->wait.entry);
+ schedule_work(&req->work);
+ return 1;
+}
- __aio_poll_remove(req);
+struct aio_poll_table {
+ struct poll_table_struct pt;
+ struct aio_kiocb *iocb;
+ int error;
+};
- /*
- * Try completing without a context switch if we can acquire ctx_lock
- * without spinning. Otherwise we need to defer to a workqueue to
- * avoid a deadlock due to the lock order.
- */
- if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
- list_del_init(&iocb->ki_list);
- spin_unlock(&iocb->ki_ctx->ctx_lock);
+static void
+aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+ struct poll_table_struct *p)
+{
+ struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
- __aio_poll_complete(iocb, mask);
- } else {
- req->events = mask;
- INIT_WORK(&req->work, aio_poll_work);
- schedule_work(&req->work);
+ /* multiple wait queues per file are not supported */
+ if (unlikely(pt->iocb->poll.head)) {
+ pt->error = -EINVAL;
+ return;
}
- return 1;
+ pt->error = 0;
+ pt->iocb->poll.head = head;
+ add_wait_queue(head, &pt->iocb->poll.wait);
}
static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
{
struct kioctx *ctx = aiocb->ki_ctx;
struct poll_iocb *req = &aiocb->poll;
+ struct aio_poll_table apt;
__poll_t mask;
/* reject any unknown events outside the normal event mask. */
if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
return -EINVAL;
+ INIT_WORK(&req->work, aio_poll_complete_work);
req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
req->file = fget(iocb->aio_fildes);
if (unlikely(!req->file))
return -EBADF;
- if (!file_has_poll_mask(req->file))
- goto out_fail;
-
- req->head = req->file->f_op->get_poll_head(req->file, req->events);
- if (!req->head)
- goto out_fail;
- if (IS_ERR(req->head)) {
- mask = EPOLLERR;
- goto done;
- }
+ apt.pt._qproc = aio_poll_queue_proc;
+ apt.pt._key = req->events;
+ apt.iocb = aiocb;
+ apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
+
+ /* initialized the list so that we can do list_empty checks */
+ INIT_LIST_HEAD(&req->wait.entry);
init_waitqueue_func_entry(&req->wait, aio_poll_wake);
- aiocb->ki_cancel = aio_poll_cancel;
+
+ /* one for removal from waitqueue, one for this function */
+ refcount_set(&aiocb->ki_refcnt, 2);
+
+ mask = vfs_poll(req->file, &apt.pt) & req->events;
+ if (unlikely(!req->head)) {
+ /* we did not manage to set up a waitqueue, done */
+ goto out;
+ }
spin_lock_irq(&ctx->ctx_lock);
spin_lock(&req->head->lock);
- mask = req->file->f_op->poll_mask(req->file, req->events);
- if (!mask) {
- __add_wait_queue(req->head, &req->wait);
+ if (req->woken) {
+ /* wake_up context handles the rest */
+ mask = 0;
+ apt.error = 0;
+ } else if (mask || apt.error) {
+ /* if we get an error or a mask we are done */
+ WARN_ON_ONCE(list_empty(&req->wait.entry));
+ list_del_init(&req->wait.entry);
+ } else {
+ /* actually waiting for an event */
list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+ aiocb->ki_cancel = aio_poll_cancel;
}
spin_unlock(&req->head->lock);
spin_unlock_irq(&ctx->ctx_lock);
-done:
+
+out:
+ if (unlikely(apt.error)) {
+ fput(req->file);
+ return apt.error;
+ }
+
if (mask)
- __aio_poll_complete(aiocb, mask);
+ aio_poll_complete(aiocb, mask);
+ iocb_put(aiocb);
return 0;
-out_fail:
- fput(req->file);
- return -EINVAL; /* same as no support for IOCB_CMD_POLL */
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
return ret;
}
+struct __aio_sigset {
+ const sigset_t __user *sigmask;
+ size_t sigsetsize;
+};
+
SYSCALL_DEFINE6(io_pgetevents,
aio_context_t, ctx_id,
long, min_nr,
const struct file_operations *fops,
void *priv, int flags)
{
- struct qstr this;
- struct path path;
struct file *file;
if (IS_ERR(anon_inode_inode))
if (fops->owner && !try_module_get(fops->owner))
return ERR_PTR(-ENOENT);
- /*
- * Link the inode to a directory entry by creating a unique name
- * using the inode sequence number.
- */
- file = ERR_PTR(-ENOMEM);
- this.name = name;
- this.len = strlen(name);
- this.hash = 0;
- path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
- if (!path.dentry)
- goto err_module;
-
- path.mnt = mntget(anon_inode_mnt);
/*
* We know the anon_inode inode count is always greater than zero,
* so ihold() is safe.
*/
ihold(anon_inode_inode);
-
- d_instantiate(path.dentry, anon_inode_inode);
-
- file = alloc_file(&path, OPEN_FMODE(flags), fops);
+ file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name,
+ flags & (O_ACCMODE | O_NONBLOCK), fops);
if (IS_ERR(file))
- goto err_dput;
+ goto err;
+
file->f_mapping = anon_inode_inode->i_mapping;
- file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
file->private_data = priv;
return file;
-err_dput:
- path_put(&path);
-err_module:
+err:
+ iput(anon_inode_inode);
module_put(fops->owner);
return file;
}
* inode_newsize_ok - may this inode be truncated to a given size
* @inode: the inode to be truncated
* @offset: the new size to assign to the inode
- * @Returns: 0 on success, -ve errno on failure
*
* inode_newsize_ok must be called with i_mutex held.
*
* returned. @inode must be a file (not directory), with appropriate
* permissions to allow truncate (inode_newsize_ok does NOT check these
* conditions).
+ *
+ * Return: 0 on success, -ve errno on failure
*/
int inode_newsize_ok(const struct inode *inode, loff_t offset)
{
if (ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
if (ia_valid & ATTR_ATIME)
- inode->i_atime = timespec_trunc(attr->ia_atime,
- inode->i_sb->s_time_gran);
+ inode->i_atime = timespec64_trunc(attr->ia_atime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MTIME)
- inode->i_mtime = timespec_trunc(attr->ia_mtime,
- inode->i_sb->s_time_gran);
+ inode->i_mtime = timespec64_trunc(attr->ia_mtime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_CTIME)
- inode->i_ctime = timespec_trunc(attr->ia_ctime,
- inode->i_sb->s_time_gran);
+ inode->i_ctime = timespec64_trunc(attr->ia_ctime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
/**
* notify_change - modify attributes of a filesytem object
* @dentry: object affected
- * @iattr: new attributes
+ * @attr: new attributes
* @delegated_inode: returns inode, if the inode is delegated
*
* The caller must hold the i_mutex on the affected object.
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
int error;
- struct timespec now;
+ struct timespec64 now;
unsigned int ia_valid = attr->ia_valid;
WARN_ON_ONCE(!inode_is_locked(inode));
# Makefile for the linux autofs-filesystem routines.
#
-obj-$(CONFIG_AUTOFS_FS) += autofs.o
+obj-$(CONFIG_AUTOFS_FS) += autofs4.o
-autofs-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
+autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
cmd);
goto out;
}
+ } else {
+ unsigned int inr = _IOC_NR(cmd);
+
+ if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD ||
+ inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD ||
+ inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) {
+ err = -EINVAL;
+ goto out;
+ }
}
err = 0;
dev_t devid;
int err, fd;
- /* param->path has already been checked */
+ /* param->path has been checked in validate_dev_ioctl() */
+
if (!param->openmount.devid)
return -EINVAL;
dev_t devid;
int err = -ENOENT;
- if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
- err = -EINVAL;
- goto out;
- }
+ /* param->path has been checked in validate_dev_ioctl() */
devid = sbi->sb->s_dev;
unsigned int devid, magic;
int err = -ENOENT;
- if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
- err = -EINVAL;
- goto out;
- }
+ /* param->path has been checked in validate_dev_ioctl() */
name = param->path;
type = param->ismountpoint.in.type;
.kill_sb = autofs_kill_sb,
};
MODULE_ALIAS_FS("autofs");
-MODULE_ALIAS("autofs4");
+MODULE_ALIAS("autofs");
static int __init init_autofs_fs(void)
{
return -EIO;
}
-static int bad_inode_update_time(struct inode *inode, struct timespec *time,
+static int bad_inode_update_time(struct inode *inode, struct timespec64 *time,
int flags)
{
return -EIO;
static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
struct file *file, unsigned int open_flag,
- umode_t create_mode, int *opened)
+ umode_t create_mode)
{
return -EIO;
}
(fs/nls/Config.in)
* Added Configure.help entries for CONFIG_BEFS_FS and CONFIG_DEBUG_BEFS
- (Documentation/Configure.help)
+ (currently at fs/befs/Kconfig)
2001-08-??
==========
goto out_free_ph;
}
- len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
- ELF_MIN_ALIGN - 1);
- bss = eppnt->p_memsz + eppnt->p_vaddr;
+ len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr);
+ bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr);
if (bss > len) {
error = vm_brk(len, bss - len);
if (error)
if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
return -EINVAL;
size = round_up(size, PAGE_SIZE);
- data = vmalloc(size);
- if (!data)
+ data = kvmalloc(size, GFP_KERNEL);
+ if (ZERO_OR_NULL_PTR(data))
return -ENOMEM;
start_end_ofs = data + 2;
filename = file_path(file, name_curpos, remaining);
if (IS_ERR(filename)) {
if (PTR_ERR(filename) == -ENAMETOOLONG) {
- vfree(data);
+ kvfree(data);
size = size * 5 / 4;
goto alloc;
}
const struct user_regset *regset = &view->regsets[i];
do_thread_regset_writeback(t->task, regset);
if (regset->core_note_type && regset->get &&
- (!regset->active || regset->active(t->task, regset))) {
+ (!regset->active || regset->active(t->task, regset) > 0)) {
int ret;
size_t size = regset_size(t->task, regset);
void *data = kmalloc(size, GFP_KERNEL);
kfree(t);
}
kfree(info->psinfo.data);
- vfree(info->files.data);
+ kvfree(info->files.data);
}
#else
/* Free data possibly allocated by fill_files_note(): */
if (info->notes_files)
- vfree(info->notes_files->data);
+ kvfree(info->notes_files->data);
kfree(info->prstatus);
kfree(info->psinfo);
if (segs - 1 > ULONG_MAX / sizeof(*vma_filesz))
goto end_coredump;
- vma_filesz = vmalloc(array_size(sizeof(*vma_filesz), (segs - 1)));
- if (!vma_filesz)
+ vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
+ GFP_KERNEL);
+ if (ZERO_OR_NULL_PTR(vma_filesz))
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
cleanup:
free_note_info(&info);
kfree(shdr4extnum);
- vfree(vma_filesz);
+ kvfree(vma_filesz);
kfree(phdr4note);
kfree(elf);
out:
* Copyright (C) 1997 Richard Günther
*
* binfmt_misc detects binaries via a magic or filename extension and invokes
- * a specified wrapper. See Documentation/binfmt_misc.txt for more details.
+ * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
goto error;
if (fmt->flags & MISC_FMT_OPEN_FILE) {
- interp_file = filp_clone_open(fmt->interp_file);
+ interp_file = file_clone_open(fmt->interp_file);
if (!IS_ERR(interp_file))
deny_write_access(interp_file);
} else {
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
- return ret;
+ goto out;
ret = bio.bi_iter.bi_size;
if (iov_iter_rw(iter) == READ) {
put_page(bvec->bv_page);
}
- if (vecs != inline_vecs)
- kfree(vecs);
-
if (unlikely(bio.bi_status))
ret = blk_status_to_errno(bio.bi_status);
+out:
+ if (vecs != inline_vecs)
+ kfree(vecs);
+
bio_uninit(&bio);
return ret;
size_t size, struct bio *bio,
unsigned long bio_flags);
void btrfs_set_range_writeback(void *private_data, u64 start, u64 end);
-int btrfs_page_mkwrite(struct vm_fault *vmf);
+vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
struct extent_map *em;
u64 start = page_offset(page);
u64 end = start + PAGE_SIZE - 1;
- struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
- struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
+ struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
+ struct extent_io_tree *tree = &btrfs_inode->io_tree;
+ struct extent_map_tree *map = &btrfs_inode->extent_tree;
if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > SZ_16M) {
extent_map_end(em) - 1,
EXTENT_LOCKED | EXTENT_WRITEBACK,
0, NULL)) {
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &btrfs_inode->runtime_flags);
remove_extent_mapping(map, em);
/* once for the rb tree */
free_extent_map(em);
offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
- disko = 0;
flags = 0;
+ if (em->block_start < EXTENT_MAP_LAST_BYTE)
+ disko = em->block_start + offset_in_extent;
+ else
+ disko = 0;
/*
* bump off for our next call to get_extent
u64 bytenr = em->block_start -
(em->start - em->orig_start);
- disko = em->block_start + offset_in_extent;
-
/*
* As btrfs supports shared space, this information
* can be exported to userspace tools via
static void update_time_for_write(struct inode *inode)
{
- struct timespec now;
+ struct timespec64 now;
if (IS_NOCMTIME(inode))
return;
now = current_time(inode);
- if (!timespec_equal(&inode->i_mtime, &now))
+ if (!timespec64_equal(&inode->i_mtime, &now))
inode->i_mtime = now;
- if (!timespec_equal(&inode->i_ctime, &now))
+ if (!timespec64_equal(&inode->i_ctime, &now))
inode->i_ctime = now;
if (IS_I_VERSION(inode))
inode->i_mtime = current_time(inode);
inode->i_atime = inode->i_mtime;
inode->i_ctime = inode->i_mtime;
- BTRFS_I(inode)->i_otime = inode->i_mtime;
+ BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
return inode;
}
* This is a copy of file_update_time. We need this so we can return error on
* ENOSPC for updating the inode in the case of file write and mmap writes.
*/
-static int btrfs_update_time(struct inode *inode, struct timespec *now,
+static int btrfs_update_time(struct inode *inode, struct timespec64 *now,
int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
location->type = BTRFS_INODE_ITEM_KEY;
ret = btrfs_insert_inode_locked(inode);
- if (ret < 0)
+ if (ret < 0) {
+ iput(inode);
goto fail;
+ }
path->leave_spinning = 1;
ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
inode->i_mtime = current_time(inode);
inode->i_atime = inode->i_mtime;
inode->i_ctime = inode->i_mtime;
- BTRFS_I(inode)->i_otime = inode->i_mtime;
+ BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_inode_item);
return inode;
fail_unlock:
- unlock_new_inode(inode);
+ discard_new_inode(inode);
fail:
if (dir && name)
BTRFS_I(dir)->index_cnt--;
btrfs_free_path(path);
- iput(inode);
return ERR_PTR(ret);
}
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = NULL;
int err;
- int drop_inode = 0;
u64 objectid;
u64 index = 0;
mode, &index);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
+ inode = NULL;
goto out_unlock;
}
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- goto out_unlock_inode;
+ goto out_unlock;
err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
0, index);
- if (err) {
- goto out_unlock_inode;
- } else {
- btrfs_update_inode(trans, root, inode);
- d_instantiate_new(dentry, inode);
- }
+ if (err)
+ goto out_unlock;
+
+ btrfs_update_inode(trans, root, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
btrfs_btree_balance_dirty(fs_info);
- if (drop_inode) {
+ if (err && inode) {
inode_dec_link_count(inode);
- iput(inode);
+ discard_new_inode(inode);
}
return err;
-
-out_unlock_inode:
- drop_inode = 1;
- unlock_new_inode(inode);
- goto out_unlock;
-
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = NULL;
- int drop_inode_on_err = 0;
int err;
u64 objectid;
u64 index = 0;
mode, &index);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
+ inode = NULL;
goto out_unlock;
}
- drop_inode_on_err = 1;
/*
* If the active LSM wants to access the inode during
* d_instantiate it needs these. Smack checks to see
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- goto out_unlock_inode;
+ goto out_unlock;
err = btrfs_update_inode(trans, root, inode);
if (err)
- goto out_unlock_inode;
+ goto out_unlock;
err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
0, index);
if (err)
- goto out_unlock_inode;
+ goto out_unlock;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
- if (err && drop_inode_on_err) {
+ if (err && inode) {
inode_dec_link_count(inode);
- iput(inode);
+ discard_new_inode(inode);
}
btrfs_btree_balance_dirty(fs_info);
return err;
-
-out_unlock_inode:
- unlock_new_inode(inode);
- goto out_unlock;
-
}
static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
S_IFDIR | mode, &index);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
+ inode = NULL;
goto out_fail;
}
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- goto out_fail_inode;
+ goto out_fail;
btrfs_i_size_write(BTRFS_I(inode), 0);
err = btrfs_update_inode(trans, root, inode);
if (err)
- goto out_fail_inode;
+ goto out_fail;
err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
dentry->d_name.name,
dentry->d_name.len, 0, index);
if (err)
- goto out_fail_inode;
+ goto out_fail;
d_instantiate_new(dentry, inode);
drop_on_err = 0;
out_fail:
btrfs_end_transaction(trans);
- if (drop_on_err) {
+ if (err && inode) {
inode_dec_link_count(inode);
- iput(inode);
+ discard_new_inode(inode);
}
btrfs_btree_balance_dirty(fs_info);
return err;
-
-out_fail_inode:
- unlock_new_inode(inode);
- goto out_fail;
}
static noinline int uncompress_inline(struct btrfs_path *path,
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
*/
-int btrfs_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
char *kaddr;
unsigned long zero_start;
loff_t size;
- int ret;
+ vm_fault_t ret;
+ int ret2;
int reserved = 0;
u64 reserved_space;
u64 page_start;
* end up waiting indefinitely to get a lock on the page currently
* being processed by btrfs_page_mkwrite() function.
*/
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
+ ret2 = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
reserved_space);
- if (!ret) {
- ret = file_update_time(vmf->vma->vm_file);
+ if (!ret2) {
+ ret2 = file_update_time(vmf->vma->vm_file);
reserved = 1;
}
- if (ret) {
- if (ret == -ENOMEM)
- ret = VM_FAULT_OOM;
- else /* -ENOSPC, -EIO, etc */
- ret = VM_FAULT_SIGBUS;
+ if (ret2) {
+ ret = vmf_error(ret2);
if (reserved)
goto out;
goto out_noreserve;
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state);
- ret = btrfs_set_extent_delalloc(inode, page_start, end, 0,
+ ret2 = btrfs_set_extent_delalloc(inode, page_start, end, 0,
&cached_state, 0);
- if (ret) {
+ if (ret2) {
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state);
ret = VM_FAULT_SIGBUS;
goto out_unlock;
}
- ret = 0;
+ ret2 = 0;
/* page is wholly or partially inside EOF */
if (page_start + PAGE_SIZE > size)
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
-out_unlock:
- if (!ret) {
+ if (!ret2) {
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
}
+
+out_unlock:
unlock_page(page);
out:
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = new_dentry->d_inode;
struct inode *old_inode = old_dentry->d_inode;
- struct timespec ctime = current_time(old_inode);
+ struct timespec64 ctime = current_time(old_inode);
struct dentry *parent;
u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
u64 new_idx = 0;
u64 root_objectid;
int ret;
+ int ret2;
bool root_log_pinned = false;
bool dest_log_pinned = false;
dest_log_pinned = false;
}
}
- ret = btrfs_end_transaction(trans);
+ ret2 = btrfs_end_transaction(trans);
+ ret = ret ? ret : ret2;
out_notrans:
if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&fs_info->subvol_sem);
struct btrfs_key key;
struct inode *inode = NULL;
int err;
- int drop_inode = 0;
u64 objectid;
u64 index = 0;
int name_len;
objectid, S_IFLNK|S_IRWXUGO, &index);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
+ inode = NULL;
goto out_unlock;
}
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- goto out_unlock_inode;
+ goto out_unlock;
path = btrfs_alloc_path();
if (!path) {
err = -ENOMEM;
- goto out_unlock_inode;
+ goto out_unlock;
}
key.objectid = btrfs_ino(BTRFS_I(inode));
key.offset = 0;
datasize);
if (err) {
btrfs_free_path(path);
- goto out_unlock_inode;
+ goto out_unlock;
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
if (!err)
err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
BTRFS_I(inode), 0, index);
- if (err) {
- drop_inode = 1;
- goto out_unlock_inode;
- }
+ if (err)
+ goto out_unlock;
d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
- if (drop_inode) {
+ if (err && inode) {
inode_dec_link_count(inode);
- iput(inode);
+ discard_new_inode(inode);
}
btrfs_btree_balance_dirty(fs_info);
return err;
-
-out_unlock_inode:
- drop_inode = 1;
- unlock_new_inode(inode);
- goto out_unlock;
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
ret = btrfs_init_inode_security(trans, inode, dir, NULL);
if (ret)
- goto out_inode;
+ goto out;
ret = btrfs_update_inode(trans, root, inode);
if (ret)
- goto out_inode;
+ goto out;
ret = btrfs_orphan_add(trans, BTRFS_I(inode));
if (ret)
- goto out_inode;
+ goto out;
/*
* We set number of links to 0 in btrfs_new_inode(), and here we set
* d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
*/
set_nlink(inode, 1);
- unlock_new_inode(inode);
d_tmpfile(dentry, inode);
+ unlock_new_inode(inode);
mark_inode_dirty(inode);
-
out:
btrfs_end_transaction(trans);
- if (ret)
- iput(inode);
+ if (ret && inode)
+ discard_new_inode(inode);
btrfs_btree_balance_dirty(fs_info);
return ret;
-
-out_inode:
- unlock_new_inode(inode);
- goto out;
-
}
__attribute__((const))
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *new_root;
struct btrfs_block_rsv block_rsv;
- struct timespec cur_time = current_time(dir);
+ struct timespec64 cur_time = current_time(dir);
struct inode *inode;
int ret;
int err;
}
temp_inode = btrfs_iget(sb, &key2, root, NULL);
+ if (IS_ERR(temp_inode)) {
+ ret = PTR_ERR(temp_inode);
+ goto out;
+ }
ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC);
iput(temp_inode);
if (ret) {
if (pg) {
unlock_page(pg);
put_page(pg);
+ cmp->src_pages[i] = NULL;
}
pg = cmp->dst_pages[i];
if (pg) {
unlock_page(pg);
put_page(pg);
+ cmp->dst_pages[i] = NULL;
}
}
}
ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
dst, dst_loff, &cmp);
if (ret)
- goto out_unlock;
+ goto out_free;
loff += BTRFS_MAX_DEDUPE_LEN;
dst_loff += BTRFS_MAX_DEDUPE_LEN;
ret = btrfs_extent_same_range(src, loff, tail_len, dst,
dst_loff, &cmp);
+out_free:
+ kvfree(cmp.src_pages);
+ kvfree(cmp.dst_pages);
+
out_unlock:
if (same_inode)
inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
-out_free:
- kvfree(cmp.src_pages);
- kvfree(cmp.dst_pages);
-
return ret;
}
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root_item *root_item = &root->root_item;
struct btrfs_trans_handle *trans;
- struct timespec ct = current_time(inode);
+ struct timespec64 ct = current_time(inode);
int ret = 0;
int received_uuid_changed;
free_extent_buffer(scratch_leaf);
}
- if (done && !ret)
+ if (done && !ret) {
ret = 1;
+ fs_info->qgroup_rescan_progress.objectid = (u64)-1;
+ }
return ret;
}
if (!init_flags) {
/* we're resuming qgroup rescan at mount time */
- if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+ if (!(fs_info->qgroup_flags &
+ BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup is not enabled");
- else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+ ret = -EINVAL;
+ } else if (!(fs_info->qgroup_flags &
+ BTRFS_QGROUP_STATUS_FLAG_ON)) {
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup rescan is not queued");
- return -EINVAL;
+ ret = -EINVAL;
+ }
+
+ if (ret)
+ return ret;
}
mutex_lock(&fs_info->qgroup_rescan_lock);
struct btrfs_root *root)
{
struct btrfs_root_item *item = &root->root_item;
- struct timespec ct;
+ struct timespec64 ct;
- ktime_get_real_ts(&ct);
+ ktime_get_real_ts64(&ct);
spin_lock(&root->root_item_lock);
btrfs_set_root_ctransid(item, trans->transid);
btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
return ret;
}
- if (sctx->is_dev_replace && !is_metadata && !have_csum) {
- sblocks_for_recheck = NULL;
- goto nodatasum_case;
- }
-
/*
* read all mirrors one after the other. This includes to
* re-read the extent or metadata block that failed (that was
goto out;
}
- if (!is_metadata && !have_csum) {
+ /*
+ * NOTE: Even for nodatasum case, it's still possible that it's a
+ * compressed data extent, thus scrub_fixup_nodatasum(), which write
+ * inode page cache onto disk, could cause serious data corruption.
+ *
+ * So here we could only read from disk, and hope our recovery could
+ * reach disk before the newer write.
+ */
+ if (0 && !is_metadata && !have_csum) {
struct scrub_fixup_nodatasum *fixup_nodatasum;
WARN_ON(sctx->is_dev_replace);
-nodatasum_case:
-
/*
* !is_metadata and !have_csum, this means that the data
* might not be COWed, that it might be modified
have_csum = scrub_find_csum(sctx, logical, csum);
if (have_csum == 0)
++sctx->stat.no_csum;
- if (sctx->is_dev_replace && !have_csum) {
+ if (0 && sctx->is_dev_replace && !have_csum) {
ret = copy_nocow_pages(sctx, logical, l,
mirror_num,
physical_for_dev_replace);
struct dentry *dentry;
struct extent_buffer *tmp;
struct extent_buffer *old;
- struct timespec cur_time;
+ struct timespec64 cur_time;
int ret = 0;
u64 to_reserve = 0;
u64 index = 0;
{
int ret;
+ mutex_lock(&uuid_mutex);
mutex_lock(&fs_devices->device_list_mutex);
if (fs_devices->opened) {
fs_devices->opened++;
ret = open_fs_devices(fs_devices, flags, holder);
}
mutex_unlock(&fs_devices->device_list_mutex);
+ mutex_unlock(&uuid_mutex);
return ret;
}
"%s",
fsdef->dentry->d_sb->s_id);
- fscache_object_init(&fsdef->fscache, NULL, &cache->cache);
+ fscache_object_init(&fsdef->fscache, &fscache_fsdef_index,
+ &cache->cache);
ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag);
if (ret < 0)
* need to wait for it to be destroyed */
wait_for_old_object:
trace_cachefiles_wait_active(object, dentry, xobject);
+ clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
if (fscache_object_is_live(&xobject->fscache)) {
pr_err("\n");
pr_err("Error: Unexpected object collision\n");
cachefiles_printk_object(object, xobject);
- BUG();
}
atomic_inc(&xobject->usage);
write_unlock(&cache->active_lock);
goto try_again;
requeue:
- clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo);
_leave(" = -ETIMEDOUT");
return -ETIMEDOUT;
struct cachefiles_one_read *monitor =
container_of(wait, struct cachefiles_one_read, monitor);
struct cachefiles_object *object;
+ struct fscache_retrieval *op = monitor->op;
struct wait_bit_key *key = _key;
struct page *page = wait->private;
list_del(&wait->entry);
/* move onto the action list and queue for FS-Cache thread pool */
- ASSERT(monitor->op);
+ ASSERT(op);
- object = container_of(monitor->op->op.object,
- struct cachefiles_object, fscache);
+ /* We need to temporarily bump the usage count as we don't own a ref
+ * here otherwise cachefiles_read_copier() may free the op between the
+ * monitor being enqueued on the op->to_do list and the op getting
+ * enqueued on the work queue.
+ */
+ fscache_get_retrieval(op);
+ object = container_of(op->op.object, struct cachefiles_object, fscache);
spin_lock(&object->work_lock);
- list_add_tail(&monitor->op_link, &monitor->op->to_do);
+ list_add_tail(&monitor->op_link, &op->to_do);
spin_unlock(&object->work_lock);
- fscache_enqueue_retrieval(monitor->op);
+ fscache_enqueue_retrieval(op);
+ fscache_put_retrieval(op);
return 0;
}
*/
static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
{
+ struct timespec ts;
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_fs_client *fsc;
set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
set_page_writeback(page);
+ ts = timespec64_to_timespec(inode->i_mtime);
err = ceph_osdc_writepages(&fsc->client->osdc, ceph_vino(inode),
&ci->i_layout, snapc, page_off, len,
ceph_wbc.truncate_seq,
ceph_wbc.truncate_size,
- &inode->i_mtime, &page, 1);
+ &ts, &page, 1);
if (err < 0) {
struct writeback_control tmp_wbc;
if (!wbc)
pages = NULL;
}
- req->r_mtime = inode->i_mtime;
+ req->r_mtime = timespec64_to_timespec(inode->i_mtime);
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
BUG_ON(rc);
req = NULL;
goto out;
}
- req->r_mtime = inode->i_mtime;
+ req->r_mtime = timespec64_to_timespec(inode->i_mtime);
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
goto out_put;
}
- req->r_mtime = inode->i_mtime;
+ req->r_mtime = timespec64_to_timespec(inode->i_mtime);
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
0, false, true);
err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
- wr_req->r_mtime = ci->vfs_inode.i_mtime;
- wr_req->r_abort_on_full = true;
+ wr_req->r_mtime = timespec64_to_timespec(ci->vfs_inode.i_mtime);
err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
if (!err)
memset(&aux, 0, sizeof(aux));
aux.version = ci->i_version;
- aux.mtime = inode->i_mtime;
+ aux.mtime = timespec64_to_timespec(inode->i_mtime);
if (memcmp(data, &aux, sizeof(aux)) != 0)
return FSCACHE_CHECKAUX_OBSOLETE;
if (!ci->fscache) {
memset(&aux, 0, sizeof(aux));
aux.version = ci->i_version;
- aux.mtime = inode->i_mtime;
+ aux.mtime = timespec64_to_timespec(inode->i_mtime);
ci->fscache = fscache_acquire_cookie(fsc->fscache,
&ceph_fscache_inode_object_def,
&ci->i_vino, sizeof(ci->i_vino),
*s++ = 'w';
if (c & CEPH_CAP_GBUFFER)
*s++ = 'b';
+ if (c & CEPH_CAP_GWREXTEND)
+ *s++ = 'a';
if (c & CEPH_CAP_GLAZYIO)
*s++ = 'l';
return s;
arg.xattr_buf = NULL;
}
- arg.mtime = inode->i_mtime;
- arg.atime = inode->i_atime;
- arg.ctime = inode->i_ctime;
+ arg.mtime = timespec64_to_timespec(inode->i_mtime);
+ arg.atime = timespec64_to_timespec(inode->i_atime);
+ arg.ctime = timespec64_to_timespec(inode->i_ctime);
arg.op = op;
arg.caps = cap->implemented;
dput(prev);
}
+struct cap_extra_info {
+ struct ceph_string *pool_ns;
+ /* inline data */
+ u64 inline_version;
+ void *inline_data;
+ u32 inline_len;
+ /* dirstat */
+ bool dirstat_valid;
+ u64 nfiles;
+ u64 nsubdirs;
+ /* currently issued */
+ int issued;
+};
+
/*
* Handle a cap GRANT message from the MDS. (Note that a GRANT may
* actually be a revocation if it specifies a smaller cap set.)
*
* caller holds s_mutex and i_ceph_lock, we drop both.
*/
-static void handle_cap_grant(struct ceph_mds_client *mdsc,
- struct inode *inode, struct ceph_mds_caps *grant,
- struct ceph_string **pns, u64 inline_version,
- void *inline_data, u32 inline_len,
- struct ceph_buffer *xattr_buf,
+static void handle_cap_grant(struct inode *inode,
struct ceph_mds_session *session,
- struct ceph_cap *cap, int issued)
+ struct ceph_cap *cap,
+ struct ceph_mds_caps *grant,
+ struct ceph_buffer *xattr_buf,
+ struct cap_extra_info *extra_info)
__releases(ci->i_ceph_lock)
- __releases(mdsc->snap_rwsem)
+ __releases(session->s_mdsc->snap_rwsem)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- int mds = session->s_mds;
int seq = le32_to_cpu(grant->seq);
int newcaps = le32_to_cpu(grant->caps);
int used, wanted, dirty;
u64 size = le64_to_cpu(grant->size);
u64 max_size = le64_to_cpu(grant->max_size);
- struct timespec mtime, atime, ctime;
int check_caps = 0;
bool wake = false;
bool writeback = false;
bool fill_inline = false;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
- inode, cap, mds, seq, ceph_cap_string(newcaps));
+ inode, cap, session->s_mds, seq, ceph_cap_string(newcaps));
dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
inode->i_size);
__check_cap_issue(ci, cap, newcaps);
if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
- (issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ (extra_info->issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
- (issued & CEPH_CAP_LINK_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_LINK_SHARED) &&
+ (extra_info->issued & CEPH_CAP_LINK_EXCL) == 0) {
set_nlink(inode, le32_to_cpu(grant->nlink));
if (inode->i_nlink == 0 &&
(newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
deleted_inode = true;
}
- if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
+ if ((extra_info->issued & CEPH_CAP_XATTR_EXCL) == 0 &&
+ grant->xattr_len) {
int len = le32_to_cpu(grant->xattr_len);
u64 version = le64_to_cpu(grant->xattr_version);
}
if (newcaps & CEPH_CAP_ANY_RD) {
+ struct timespec mtime, atime, ctime;
/* ctime/mtime/atime? */
ceph_decode_timespec(&mtime, &grant->mtime);
ceph_decode_timespec(&atime, &grant->atime);
ceph_decode_timespec(&ctime, &grant->ctime);
- ceph_fill_file_time(inode, issued,
+ ceph_fill_file_time(inode, extra_info->issued,
le32_to_cpu(grant->time_warp_seq),
&ctime, &mtime, &atime);
}
+ if ((newcaps & CEPH_CAP_FILE_SHARED) && extra_info->dirstat_valid) {
+ ci->i_files = extra_info->nfiles;
+ ci->i_subdirs = extra_info->nsubdirs;
+ }
+
if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
/* file layout may have changed */
s64 old_pool = ci->i_layout.pool_id;
ceph_file_layout_from_legacy(&ci->i_layout, &grant->layout);
old_ns = rcu_dereference_protected(ci->i_layout.pool_ns,
lockdep_is_held(&ci->i_ceph_lock));
- rcu_assign_pointer(ci->i_layout.pool_ns, *pns);
+ rcu_assign_pointer(ci->i_layout.pool_ns, extra_info->pool_ns);
- if (ci->i_layout.pool_id != old_pool || *pns != old_ns)
+ if (ci->i_layout.pool_id != old_pool ||
+ extra_info->pool_ns != old_ns)
ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
- *pns = old_ns;
+ extra_info->pool_ns = old_ns;
/* size/truncate_seq? */
- queue_trunc = ceph_fill_file_size(inode, issued,
+ queue_trunc = ceph_fill_file_size(inode, extra_info->issued,
le32_to_cpu(grant->truncate_seq),
le64_to_cpu(grant->truncate_size),
size);
}
BUG_ON(cap->issued & ~cap->implemented);
- if (inline_version > 0 && inline_version >= ci->i_inline_version) {
- ci->i_inline_version = inline_version;
+ if (extra_info->inline_version > 0 &&
+ extra_info->inline_version >= ci->i_inline_version) {
+ ci->i_inline_version = extra_info->inline_version;
if (ci->i_inline_version != CEPH_INLINE_NONE &&
(newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
fill_inline = true;
}
if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
- if (newcaps & ~issued)
+ if (newcaps & ~extra_info->issued)
wake = true;
- kick_flushing_inode_caps(mdsc, session, inode);
- up_read(&mdsc->snap_rwsem);
+ kick_flushing_inode_caps(session->s_mdsc, session, inode);
+ up_read(&session->s_mdsc->snap_rwsem);
} else {
spin_unlock(&ci->i_ceph_lock);
}
if (fill_inline)
- ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
+ ceph_fill_inline_data(inode, NULL, extra_info->inline_data,
+ extra_info->inline_len);
if (queue_trunc)
ceph_queue_vmtruncate(inode);
struct ceph_msg *msg)
{
struct ceph_mds_client *mdsc = session->s_mdsc;
- struct super_block *sb = mdsc->fsc->sb;
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_cap *cap;
struct ceph_mds_caps *h;
struct ceph_mds_cap_peer *peer = NULL;
struct ceph_snap_realm *realm = NULL;
- struct ceph_string *pool_ns = NULL;
- int mds = session->s_mds;
- int op, issued;
+ int op;
+ int msg_version = le16_to_cpu(msg->hdr.version);
u32 seq, mseq;
struct ceph_vino vino;
- u64 tid;
- u64 inline_version = 0;
- void *inline_data = NULL;
- u32 inline_len = 0;
void *snaptrace;
size_t snaptrace_len;
void *p, *end;
+ struct cap_extra_info extra_info = {};
- dout("handle_caps from mds%d\n", mds);
+ dout("handle_caps from mds%d\n", session->s_mds);
/* decode */
end = msg->front.iov_base + msg->front.iov_len;
- tid = le64_to_cpu(msg->hdr.tid);
if (msg->front.iov_len < sizeof(*h))
goto bad;
h = msg->front.iov_base;
snaptrace_len = le32_to_cpu(h->snap_trace_len);
p = snaptrace + snaptrace_len;
- if (le16_to_cpu(msg->hdr.version) >= 2) {
+ if (msg_version >= 2) {
u32 flock_len;
ceph_decode_32_safe(&p, end, flock_len, bad);
if (p + flock_len > end)
p += flock_len;
}
- if (le16_to_cpu(msg->hdr.version) >= 3) {
+ if (msg_version >= 3) {
if (op == CEPH_CAP_OP_IMPORT) {
if (p + sizeof(*peer) > end)
goto bad;
}
}
- if (le16_to_cpu(msg->hdr.version) >= 4) {
- ceph_decode_64_safe(&p, end, inline_version, bad);
- ceph_decode_32_safe(&p, end, inline_len, bad);
- if (p + inline_len > end)
+ if (msg_version >= 4) {
+ ceph_decode_64_safe(&p, end, extra_info.inline_version, bad);
+ ceph_decode_32_safe(&p, end, extra_info.inline_len, bad);
+ if (p + extra_info.inline_len > end)
goto bad;
- inline_data = p;
- p += inline_len;
+ extra_info.inline_data = p;
+ p += extra_info.inline_len;
}
- if (le16_to_cpu(msg->hdr.version) >= 5) {
+ if (msg_version >= 5) {
struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
u32 epoch_barrier;
ceph_osdc_update_epoch_barrier(osdc, epoch_barrier);
}
- if (le16_to_cpu(msg->hdr.version) >= 8) {
+ if (msg_version >= 8) {
u64 flush_tid;
u32 caller_uid, caller_gid;
u32 pool_ns_len;
ceph_decode_32_safe(&p, end, pool_ns_len, bad);
if (pool_ns_len > 0) {
ceph_decode_need(&p, end, pool_ns_len, bad);
- pool_ns = ceph_find_or_create_string(p, pool_ns_len);
+ extra_info.pool_ns =
+ ceph_find_or_create_string(p, pool_ns_len);
p += pool_ns_len;
}
}
+ if (msg_version >= 11) {
+ struct ceph_timespec *btime;
+ u64 change_attr;
+ u32 flags;
+
+ /* version >= 9 */
+ if (p + sizeof(*btime) > end)
+ goto bad;
+ btime = p;
+ p += sizeof(*btime);
+ ceph_decode_64_safe(&p, end, change_attr, bad);
+ /* version >= 10 */
+ ceph_decode_32_safe(&p, end, flags, bad);
+ /* version >= 11 */
+ extra_info.dirstat_valid = true;
+ ceph_decode_64_safe(&p, end, extra_info.nfiles, bad);
+ ceph_decode_64_safe(&p, end, extra_info.nsubdirs, bad);
+ }
+
/* lookup ino */
- inode = ceph_find_inode(sb, vino);
+ inode = ceph_find_inode(mdsc->fsc->sb, vino);
ci = ceph_inode(inode);
dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
vino.snap, inode);
/* these will work even if we don't have a cap yet */
switch (op) {
case CEPH_CAP_OP_FLUSHSNAP_ACK:
- handle_cap_flushsnap_ack(inode, tid, h, session);
+ handle_cap_flushsnap_ack(inode, le64_to_cpu(msg->hdr.tid),
+ h, session);
goto done;
case CEPH_CAP_OP_EXPORT:
down_read(&mdsc->snap_rwsem);
}
handle_cap_import(mdsc, inode, h, peer, session,
- &cap, &issued);
- handle_cap_grant(mdsc, inode, h, &pool_ns,
- inline_version, inline_data, inline_len,
- msg->middle, session, cap, issued);
+ &cap, &extra_info.issued);
+ handle_cap_grant(inode, session, cap,
+ h, msg->middle, &extra_info);
if (realm)
ceph_put_snap_realm(mdsc, realm);
goto done_unlocked;
/* the rest require a cap */
spin_lock(&ci->i_ceph_lock);
- cap = __get_cap_for_mds(ceph_inode(inode), mds);
+ cap = __get_cap_for_mds(ceph_inode(inode), session->s_mds);
if (!cap) {
dout(" no cap on %p ino %llx.%llx from mds%d\n",
- inode, ceph_ino(inode), ceph_snap(inode), mds);
+ inode, ceph_ino(inode), ceph_snap(inode),
+ session->s_mds);
spin_unlock(&ci->i_ceph_lock);
goto flush_cap_releases;
}
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
- __ceph_caps_issued(ci, &issued);
- issued |= __ceph_caps_dirty(ci);
- handle_cap_grant(mdsc, inode, h, &pool_ns,
- inline_version, inline_data, inline_len,
- msg->middle, session, cap, issued);
+ __ceph_caps_issued(ci, &extra_info.issued);
+ extra_info.issued |= __ceph_caps_dirty(ci);
+ handle_cap_grant(inode, session, cap,
+ h, msg->middle, &extra_info);
goto done_unlocked;
case CEPH_CAP_OP_FLUSH_ACK:
- handle_cap_flush_ack(inode, tid, h, session, cap);
+ handle_cap_flush_ack(inode, le64_to_cpu(msg->hdr.tid),
+ h, session, cap);
break;
case CEPH_CAP_OP_TRUNC:
mutex_unlock(&session->s_mutex);
done_unlocked:
iput(inode);
- ceph_put_string(pool_ns);
+ ceph_put_string(extra_info.pool_ns);
return;
bad:
.release = ceph_release,
.unlocked_ioctl = ceph_ioctl,
.fsync = ceph_fsync,
+ .lock = ceph_lock,
+ .flock = ceph_flock,
};
const struct file_operations ceph_snapdir_fops = {
* file or symlink, return 1 so the VFS can retry.
*/
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t mode,
- int *opened)
+ struct file *file, unsigned flags, umode_t mode)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
ceph_init_inode_acls(d_inode(dentry), &acls);
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
}
- err = finish_open(file, dentry, ceph_open, opened);
+ err = finish_open(file, dentry, ceph_open);
}
out_req:
if (!req->r_err && req->r_target_inode)
req->r_callback = ceph_aio_complete_req;
req->r_inode = inode;
req->r_priv = aio_req;
- req->r_abort_on_full = true;
ret = ceph_osdc_start_request(req->r_osdc, req, false);
out:
int num_pages = 0;
int flags;
int ret;
- struct timespec mtime = current_time(inode);
+ struct timespec mtime = timespec64_to_timespec(current_time(inode));
size_t count = iov_iter_count(iter);
loff_t pos = iocb->ki_pos;
bool write = iov_iter_rw(iter) == WRITE;
int flags;
int ret;
bool check_caps = false;
- struct timespec mtime = current_time(inode);
+ struct timespec mtime = timespec64_to_timespec(current_time(inode));
size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
goto out;
}
- req->r_mtime = inode->i_mtime;
+ req->r_mtime = timespec64_to_timespec(inode->i_mtime);
ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!ret) {
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
struct timespec *mtime, struct timespec *atime)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ struct timespec64 ctime64 = timespec_to_timespec64(*ctime);
+ struct timespec64 mtime64 = timespec_to_timespec64(*mtime);
+ struct timespec64 atime64 = timespec_to_timespec64(*atime);
int warn = 0;
if (issued & (CEPH_CAP_FILE_EXCL|
CEPH_CAP_AUTH_EXCL|
CEPH_CAP_XATTR_EXCL)) {
if (ci->i_version == 0 ||
- timespec_compare(ctime, &inode->i_ctime) > 0) {
- dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
- inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
- ctime->tv_sec, ctime->tv_nsec);
- inode->i_ctime = *ctime;
+ timespec64_compare(&ctime64, &inode->i_ctime) > 0) {
+ dout("ctime %lld.%09ld -> %lld.%09ld inc w/ cap\n",
+ (long long)inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
+ (long long)ctime->tv_sec, ctime->tv_nsec);
+ inode->i_ctime = ctime64;
}
if (ci->i_version == 0 ||
ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
/* the MDS did a utimes() */
- dout("mtime %ld.%09ld -> %ld.%09ld "
+ dout("mtime %lld.%09ld -> %lld.%09ld "
"tw %d -> %d\n",
- inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
- mtime->tv_sec, mtime->tv_nsec,
+ (long long)inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
+ (long long)mtime->tv_sec, mtime->tv_nsec,
ci->i_time_warp_seq, (int)time_warp_seq);
- inode->i_mtime = *mtime;
- inode->i_atime = *atime;
+ inode->i_mtime = mtime64;
+ inode->i_atime = atime64;
ci->i_time_warp_seq = time_warp_seq;
} else if (time_warp_seq == ci->i_time_warp_seq) {
/* nobody did utimes(); take the max */
- if (timespec_compare(mtime, &inode->i_mtime) > 0) {
- dout("mtime %ld.%09ld -> %ld.%09ld inc\n",
- inode->i_mtime.tv_sec,
+ if (timespec64_compare(&mtime64, &inode->i_mtime) > 0) {
+ dout("mtime %lld.%09ld -> %lld.%09ld inc\n",
+ (long long)inode->i_mtime.tv_sec,
inode->i_mtime.tv_nsec,
- mtime->tv_sec, mtime->tv_nsec);
- inode->i_mtime = *mtime;
+ (long long)mtime->tv_sec, mtime->tv_nsec);
+ inode->i_mtime = mtime64;
}
- if (timespec_compare(atime, &inode->i_atime) > 0) {
- dout("atime %ld.%09ld -> %ld.%09ld inc\n",
- inode->i_atime.tv_sec,
+ if (timespec64_compare(&atime64, &inode->i_atime) > 0) {
+ dout("atime %lld.%09ld -> %lld.%09ld inc\n",
+ (long long)inode->i_atime.tv_sec,
inode->i_atime.tv_nsec,
- atime->tv_sec, atime->tv_nsec);
- inode->i_atime = *atime;
+ (long long)atime->tv_sec, atime->tv_nsec);
+ inode->i_atime = atime64;
}
} else if (issued & CEPH_CAP_FILE_EXCL) {
/* we did a utimes(); ignore mds values */
} else {
/* we have no write|excl caps; whatever the MDS says is true */
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
- inode->i_ctime = *ctime;
- inode->i_mtime = *mtime;
- inode->i_atime = *atime;
+ inode->i_ctime = ctime64;
+ inode->i_mtime = mtime64;
+ inode->i_atime = atime64;
ci->i_time_warp_seq = time_warp_seq;
} else {
warn = 1;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_reply_inode *info = iinfo->in;
struct ceph_inode_info *ci = ceph_inode(inode);
- int issued = 0, implemented, new_issued;
+ int issued, new_issued, info_caps;
struct timespec mtime, atime, ctime;
struct ceph_buffer *xattr_blob = NULL;
struct ceph_string *pool_ns = NULL;
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
+ info_caps = le32_to_cpu(info->cap.caps);
+
/* prealloc new cap struct */
- if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+ if (info_caps && ceph_snap(inode) == CEPH_NOSNAP)
new_cap = ceph_get_cap(mdsc, caps_reservation);
/*
le64_to_cpu(info->version) > (ci->i_version & ~1)))
new_version = true;
- issued = __ceph_caps_issued(ci, &implemented);
- issued |= implemented | __ceph_caps_dirty(ci);
- new_issued = ~issued & le32_to_cpu(info->cap.caps);
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+ new_issued = ~issued & info_caps;
/* update inode */
inode->i_rdev = le32_to_cpu(info->rdev);
&ctime, &mtime, &atime);
}
+ if (new_version || (info_caps & CEPH_CAP_FILE_SHARED)) {
+ ci->i_files = le64_to_cpu(info->files);
+ ci->i_subdirs = le64_to_cpu(info->subdirs);
+ }
+
if (new_version ||
(new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
s64 old_pool = ci->i_layout.pool_id;
}
}
+ /* layout and rstat are not tracked by capability, update them if
+ * the inode info is from auth mds */
+ if (new_version || (info->cap.flags & CEPH_CAP_FLAG_AUTH)) {
+ if (S_ISDIR(inode->i_mode)) {
+ ci->i_dir_layout = iinfo->dir_layout;
+ ci->i_rbytes = le64_to_cpu(info->rbytes);
+ ci->i_rfiles = le64_to_cpu(info->rfiles);
+ ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
+ ceph_decode_timespec(&ci->i_rctime, &info->rctime);
+ }
+ }
+
/* xattrs */
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) &&
}
/* finally update i_version */
- ci->i_version = le64_to_cpu(info->version);
+ if (le64_to_cpu(info->version) > ci->i_version)
+ ci->i_version = le64_to_cpu(info->version);
inode->i_mapping->a_ops = &ceph_aops;
case S_IFDIR:
inode->i_op = &ceph_dir_iops;
inode->i_fop = &ceph_dir_fops;
-
- ci->i_dir_layout = iinfo->dir_layout;
-
- ci->i_files = le64_to_cpu(info->files);
- ci->i_subdirs = le64_to_cpu(info->subdirs);
- ci->i_rbytes = le64_to_cpu(info->rbytes);
- ci->i_rfiles = le64_to_cpu(info->rfiles);
- ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
- ceph_decode_timespec(&ci->i_rctime, &info->rctime);
break;
default:
pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
}
/* were we issued a capability? */
- if (info->cap.caps) {
+ if (info_caps) {
if (ceph_snap(inode) == CEPH_NOSNAP) {
- unsigned caps = le32_to_cpu(info->cap.caps);
ceph_add_cap(inode, session,
le64_to_cpu(info->cap.cap_id),
- cap_fmode, caps,
+ cap_fmode, info_caps,
le32_to_cpu(info->cap.wanted),
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
/* set dir completion flag? */
if (S_ISDIR(inode->i_mode) &&
ci->i_files == 0 && ci->i_subdirs == 0 &&
- (caps & CEPH_CAP_FILE_SHARED) &&
+ (info_caps & CEPH_CAP_FILE_SHARED) &&
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
!__ceph_dir_is_complete(ci)) {
dout(" marking %p complete (empty)\n", inode);
wake = true;
} else {
dout(" %p got snap_caps %s\n", inode,
- ceph_cap_string(le32_to_cpu(info->cap.caps)));
- ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
+ ceph_cap_string(info_caps));
+ ci->i_snap_caps |= info_caps;
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
}
int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
ci->i_inline_version = iinfo->inline_version;
if (ci->i_inline_version != CEPH_INLINE_NONE &&
- (locked_page ||
- (le32_to_cpu(info->cap.caps) & cache_caps)))
+ (locked_page || (info_caps & cache_caps)))
fill_inline = true;
}
if (IS_ERR(realdn)) {
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
+ dput(dn);
dn = realdn; /* note realdn contains the error */
goto out;
} else if (realdn) {
int err = 0;
int inode_dirty_flags = 0;
bool lock_snap_rwsem = false;
+ struct timespec ts;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
}
if (ia_valid & ATTR_ATIME) {
- dout("setattr %p atime %ld.%ld -> %ld.%ld\n", inode,
- inode->i_atime.tv_sec, inode->i_atime.tv_nsec,
- attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
+ dout("setattr %p atime %lld.%ld -> %lld.%ld\n", inode,
+ (long long)inode->i_atime.tv_sec, inode->i_atime.tv_nsec,
+ (long long)attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
if (issued & CEPH_CAP_FILE_EXCL) {
ci->i_time_warp_seq++;
inode->i_atime = attr->ia_atime;
dirtied |= CEPH_CAP_FILE_EXCL;
} else if ((issued & CEPH_CAP_FILE_WR) &&
- timespec_compare(&inode->i_atime,
+ timespec64_compare(&inode->i_atime,
&attr->ia_atime) < 0) {
inode->i_atime = attr->ia_atime;
dirtied |= CEPH_CAP_FILE_WR;
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
- !timespec_equal(&inode->i_atime, &attr->ia_atime)) {
- ceph_encode_timespec(&req->r_args.setattr.atime,
- &attr->ia_atime);
+ !timespec64_equal(&inode->i_atime, &attr->ia_atime)) {
+ ts = timespec64_to_timespec(attr->ia_atime);
+ ceph_encode_timespec(&req->r_args.setattr.atime, &ts);
mask |= CEPH_SETATTR_ATIME;
release |= CEPH_CAP_FILE_SHARED |
CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
}
}
if (ia_valid & ATTR_MTIME) {
- dout("setattr %p mtime %ld.%ld -> %ld.%ld\n", inode,
- inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
- attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
+ dout("setattr %p mtime %lld.%ld -> %lld.%ld\n", inode,
+ (long long)inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
+ (long long)attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
if (issued & CEPH_CAP_FILE_EXCL) {
ci->i_time_warp_seq++;
inode->i_mtime = attr->ia_mtime;
dirtied |= CEPH_CAP_FILE_EXCL;
} else if ((issued & CEPH_CAP_FILE_WR) &&
- timespec_compare(&inode->i_mtime,
+ timespec64_compare(&inode->i_mtime,
&attr->ia_mtime) < 0) {
inode->i_mtime = attr->ia_mtime;
dirtied |= CEPH_CAP_FILE_WR;
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
- !timespec_equal(&inode->i_mtime, &attr->ia_mtime)) {
- ceph_encode_timespec(&req->r_args.setattr.mtime,
- &attr->ia_mtime);
+ !timespec64_equal(&inode->i_mtime, &attr->ia_mtime)) {
+ ts = timespec64_to_timespec(attr->ia_mtime);
+ ceph_encode_timespec(&req->r_args.setattr.mtime, &ts);
mask |= CEPH_SETATTR_MTIME;
release |= CEPH_CAP_FILE_SHARED |
CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
if (ia_valid & ATTR_CTIME) {
bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME|
ATTR_MODE|ATTR_UID|ATTR_GID)) == 0;
- dout("setattr %p ctime %ld.%ld -> %ld.%ld (%s)\n", inode,
- inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
- attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
+ dout("setattr %p ctime %lld.%ld -> %lld.%ld (%s)\n", inode,
+ (long long)inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
+ (long long)attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
only ? "ctime only" : "ignored");
if (only) {
/*
req->r_inode_drop = release;
req->r_args.setattr.mask = cpu_to_le32(mask);
req->r_num_caps = 1;
- req->r_stamp = attr->ia_ctime;
+ req->r_stamp = timespec64_to_timespec(attr->ia_ctime);
err = ceph_mdsc_do_request(mdsc, NULL, req);
}
dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
+ int mode;
int err;
if (ceph_snap(inode) == CEPH_SNAPDIR) {
if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
return 0;
- req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
+ mode = (mask & CEPH_STAT_RSTAT) ? USE_AUTH_MDS : USE_ANY_MDS;
+ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
stat->size = ci->i_files + ci->i_subdirs;
stat->blocks = 0;
stat->blksize = 65536;
+ /*
+ * Some applications rely on the number of st_nlink
+ * value on directories to be either 0 (if unlinked)
+ * or 2 + number of subdirectories.
+ */
+ if (stat->nlink == 1)
+ /* '.' + '..' + subdirs */
+ stat->nlink = 1 + 1 + ci->i_subdirs;
}
}
return err;
rec.v2.flock_len = (__force __le32)
((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1);
} else {
+ struct timespec ts;
rec.v1.cap_id = cpu_to_le64(cap->cap_id);
rec.v1.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
rec.v1.issued = cpu_to_le32(cap->issued);
rec.v1.size = cpu_to_le64(inode->i_size);
- ceph_encode_timespec(&rec.v1.mtime, &inode->i_mtime);
- ceph_encode_timespec(&rec.v1.atime, &inode->i_atime);
+ ts = timespec64_to_timespec(inode->i_mtime);
+ ceph_encode_timespec(&rec.v1.mtime, &ts);
+ ts = timespec64_to_timespec(inode->i_atime);
+ ceph_encode_timespec(&rec.v1.atime, &ts);
rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
rec.v1.pathbase = cpu_to_le64(pathbase);
}
BUG_ON(capsnap->writing);
capsnap->size = inode->i_size;
- capsnap->mtime = inode->i_mtime;
- capsnap->atime = inode->i_atime;
- capsnap->ctime = inode->i_ctime;
+ capsnap->mtime = timespec64_to_timespec(inode->i_mtime);
+ capsnap->atime = timespec64_to_timespec(inode->i_atime);
+ capsnap->ctime = timespec64_to_timespec(inode->i_ctime);
capsnap->time_warp_seq = ci->i_time_warp_seq;
capsnap->truncate_size = ci->i_truncate_size;
capsnap->truncate_seq = ci->i_truncate_seq;
static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry));
- struct ceph_monmap *monmap = fsc->client->monc.monmap;
+ struct ceph_mon_client *monc = &fsc->client->monc;
struct ceph_statfs st;
u64 fsid;
int err;
}
dout("statfs\n");
- err = ceph_monc_do_statfs(&fsc->client->monc, data_pool, &st);
+ err = ceph_monc_do_statfs(monc, data_pool, &st);
if (err < 0)
return err;
buf->f_namelen = NAME_MAX;
/* Must convert the fsid, for consistent values across arches */
- fsid = le64_to_cpu(*(__le64 *)(&monmap->fsid)) ^
- le64_to_cpu(*((__le64 *)&monmap->fsid + 1));
+ mutex_lock(&monc->mutex);
+ fsid = le64_to_cpu(*(__le64 *)(&monc->monmap->fsid)) ^
+ le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1));
+ mutex_unlock(&monc->mutex);
+
buf->f_fsid.val[0] = fsid & 0xffffffff;
buf->f_fsid.val[1] = fsid >> 32;
break;
/* misc */
case Opt_wsize:
- if (intval < PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
+ if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
return -EINVAL;
fsopt->wsize = ALIGN(intval, PAGE_SIZE);
break;
case Opt_rsize:
- if (intval < PAGE_SIZE || intval > CEPH_MAX_READ_SIZE)
+ if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_READ_SIZE)
return -EINVAL;
fsopt->rsize = ALIGN(intval, PAGE_SIZE);
break;
case Opt_rasize:
if (intval < 0)
return -EINVAL;
- fsopt->rasize = ALIGN(intval + PAGE_SIZE - 1, PAGE_SIZE);
+ fsopt->rasize = ALIGN(intval, PAGE_SIZE);
break;
case Opt_caps_wanted_delay_min:
if (intval < 1)
fsopt->max_readdir = intval;
break;
case Opt_readdir_max_bytes:
- if (intval < PAGE_SIZE && intval != 0)
+ if (intval < (int)PAGE_SIZE && intval != 0)
return -EINVAL;
fsopt->max_readdir_bytes = intval;
break;
seq_puts(m, ",noasyncreaddir");
if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0)
seq_puts(m, ",nodcache");
+ if (fsopt->flags & CEPH_MOUNT_OPT_INO32)
+ seq_puts(m, ",ino32");
if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) {
seq_show_option(m, "fsc", fsopt->fscache_uniq);
}
if (fsopt->mds_namespace)
seq_show_option(m, "mds_namespace", fsopt->mds_namespace);
- if (fsopt->wsize)
+ if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
seq_printf(m, ",wsize=%d", fsopt->wsize);
if (fsopt->rsize != CEPH_MAX_READ_SIZE)
seq_printf(m, ",rsize=%d", fsopt->rsize);
err = PTR_ERR(fsc->client);
goto fail;
}
+
fsc->client->extra_mon_dispatch = extra_mon_dispatch;
+ fsc->client->osdc.abort_on_full = true;
if (!fsopt->mds_namespace) {
ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP,
return ERR_PTR(err);
}
+static void flush_fs_workqueues(struct ceph_fs_client *fsc)
+{
+ flush_workqueue(fsc->wb_wq);
+ flush_workqueue(fsc->pg_inv_wq);
+ flush_workqueue(fsc->trunc_wq);
+}
+
static void destroy_fs_client(struct ceph_fs_client *fsc)
{
dout("destroy_fs_client %p\n", fsc);
if (!fsc)
return;
fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
+ ceph_osdc_abort_requests(&fsc->client->osdc, -EIO);
ceph_mdsc_force_umount(fsc->mdsc);
return;
}
dout("kill_sb %p\n", s);
ceph_mdsc_pre_umount(fsc->mdsc);
+ flush_fs_workqueues(fsc);
+
generic_shutdown_super(s);
fsc->client->extra_mon_dispatch = NULL;
extern int ceph_renew_caps(struct inode *inode);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t mode,
- int *opened);
+ struct file *file, unsigned flags, umode_t mode);
extern int ceph_release(struct inode *inode, struct file *filp);
extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
char *data, size_t len);
size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
- bool readonly, hidden;
bool (*exists_cb)(struct ceph_inode_info *ci);
+ unsigned int flags;
};
+#define VXATTR_FLAG_READONLY (1<<0)
+#define VXATTR_FLAG_HIDDEN (1<<1)
+#define VXATTR_FLAG_RSTAT (1<<2)
+
/* layouts */
static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
#define CEPH_XATTR_NAME2(_type, _name, _name2) \
XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
-#define XATTR_NAME_CEPH(_type, _name) \
+#define XATTR_NAME_CEPH(_type, _name, _flags) \
{ \
.name = CEPH_XATTR_NAME(_type, _name), \
.name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
.getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
- .readonly = true, \
- .hidden = false, \
- .exists_cb = NULL, \
+ .exists_cb = NULL, \
+ .flags = (VXATTR_FLAG_READONLY | _flags), \
}
+#define XATTR_RSTAT_FIELD(_type, _name) \
+ XATTR_NAME_CEPH(_type, _name, VXATTR_FLAG_RSTAT)
#define XATTR_LAYOUT_FIELD(_type, _name, _field) \
{ \
.name = CEPH_XATTR_NAME2(_type, _name, _field), \
.name_size = sizeof (CEPH_XATTR_NAME2(_type, _name, _field)), \
.getxattr_cb = ceph_vxattrcb_ ## _name ## _ ## _field, \
- .readonly = false, \
- .hidden = true, \
.exists_cb = ceph_vxattrcb_layout_exists, \
+ .flags = VXATTR_FLAG_HIDDEN, \
}
#define XATTR_QUOTA_FIELD(_type, _name) \
{ \
.name = CEPH_XATTR_NAME(_type, _name), \
.name_size = sizeof(CEPH_XATTR_NAME(_type, _name)), \
.getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
- .readonly = false, \
- .hidden = true, \
.exists_cb = ceph_vxattrcb_quota_exists, \
+ .flags = VXATTR_FLAG_HIDDEN, \
}
static struct ceph_vxattr ceph_dir_vxattrs[] = {
.name = "ceph.dir.layout",
.name_size = sizeof("ceph.dir.layout"),
.getxattr_cb = ceph_vxattrcb_layout,
- .readonly = false,
- .hidden = true,
.exists_cb = ceph_vxattrcb_layout_exists,
+ .flags = VXATTR_FLAG_HIDDEN,
},
XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
XATTR_LAYOUT_FIELD(dir, layout, object_size),
XATTR_LAYOUT_FIELD(dir, layout, pool),
XATTR_LAYOUT_FIELD(dir, layout, pool_namespace),
- XATTR_NAME_CEPH(dir, entries),
- XATTR_NAME_CEPH(dir, files),
- XATTR_NAME_CEPH(dir, subdirs),
- XATTR_NAME_CEPH(dir, rentries),
- XATTR_NAME_CEPH(dir, rfiles),
- XATTR_NAME_CEPH(dir, rsubdirs),
- XATTR_NAME_CEPH(dir, rbytes),
- XATTR_NAME_CEPH(dir, rctime),
+ XATTR_NAME_CEPH(dir, entries, 0),
+ XATTR_NAME_CEPH(dir, files, 0),
+ XATTR_NAME_CEPH(dir, subdirs, 0),
+ XATTR_RSTAT_FIELD(dir, rentries),
+ XATTR_RSTAT_FIELD(dir, rfiles),
+ XATTR_RSTAT_FIELD(dir, rsubdirs),
+ XATTR_RSTAT_FIELD(dir, rbytes),
+ XATTR_RSTAT_FIELD(dir, rctime),
{
.name = "ceph.quota",
.name_size = sizeof("ceph.quota"),
.getxattr_cb = ceph_vxattrcb_quota,
- .readonly = false,
- .hidden = true,
.exists_cb = ceph_vxattrcb_quota_exists,
+ .flags = VXATTR_FLAG_HIDDEN,
},
XATTR_QUOTA_FIELD(quota, max_bytes),
XATTR_QUOTA_FIELD(quota, max_files),
.name = "ceph.file.layout",
.name_size = sizeof("ceph.file.layout"),
.getxattr_cb = ceph_vxattrcb_layout,
- .readonly = false,
- .hidden = true,
.exists_cb = ceph_vxattrcb_layout_exists,
+ .flags = VXATTR_FLAG_HIDDEN,
},
XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
XATTR_LAYOUT_FIELD(file, layout, stripe_count),
struct ceph_vxattr *vxattr;
size_t size = 0;
- for (vxattr = vxattrs; vxattr->name; vxattr++)
- if (!vxattr->hidden)
+ for (vxattr = vxattrs; vxattr->name; vxattr++) {
+ if (!(vxattr->flags & VXATTR_FLAG_HIDDEN))
size += vxattr->name_size;
+ }
return size;
}
/* let's see if a virtual xattr was requested */
vxattr = ceph_match_vxattr(inode, name);
if (vxattr) {
- err = ceph_do_getattr(inode, 0, true);
+ int mask = 0;
+ if (vxattr->flags & VXATTR_FLAG_RSTAT)
+ mask |= CEPH_STAT_RSTAT;
+ err = ceph_do_getattr(inode, mask, true);
if (err)
return err;
err = -ENODATA;
err = namelen;
if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
- if (!vxattrs[i].hidden &&
+ if (!(vxattrs[i].flags & VXATTR_FLAG_HIDDEN) &&
!(vxattrs[i].exists_cb &&
!vxattrs[i].exists_cb(ci))) {
len = sprintf(names, "%s", vxattrs[i].name);
vxattr = ceph_match_vxattr(inode, name);
if (vxattr) {
- if (vxattr->readonly)
+ if (vxattr->flags & VXATTR_FLAG_READONLY)
return -EOPNOTSUPP;
if (value && !strncmp(vxattr->name, "ceph.quota", 10))
check_realm = true;
memset(&auxdata, 0, sizeof(auxdata));
auxdata.eof = cifsi->server_eof;
- auxdata.last_write_time = cifsi->vfs_inode.i_mtime;
- auxdata.last_change_time = cifsi->vfs_inode.i_ctime;
+ auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
+ auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
if (memcmp(data, &auxdata, datalen) != 0)
return FSCACHE_CHECKAUX_OBSOLETE;
seq_putc(m, '\n');
}
+static void
+cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface)
+{
+ struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr;
+ struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&iface->sockaddr;
+
+ seq_printf(m, "\t\tSpeed: %zu bps\n", iface->speed);
+ seq_puts(m, "\t\tCapabilities: ");
+ if (iface->rdma_capable)
+ seq_puts(m, "rdma ");
+ if (iface->rss_capable)
+ seq_puts(m, "rss ");
+ seq_putc(m, '\n');
+ if (iface->sockaddr.ss_family == AF_INET)
+ seq_printf(m, "\t\tIPv4: %pI4\n", &ipv4->sin_addr);
+ else if (iface->sockaddr.ss_family == AF_INET6)
+ seq_printf(m, "\t\tIPv6: %pI6\n", &ipv6->sin6_addr);
+}
+
static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
{
struct list_head *tmp1, *tmp2, *tmp3;
mid_entry->mid);
}
spin_unlock(&GlobalMid_Lock);
+
+ spin_lock(&ses->iface_lock);
+ if (ses->iface_count)
+ seq_printf(m, "\n\tServer interfaces: %zu\n",
+ ses->iface_count);
+ for (j = 0; j < ses->iface_count; j++) {
+ seq_printf(m, "\t%d)\n", j);
+ cifs_dump_iface(m, &ses->iface_list[j]);
+ }
+ spin_unlock(&ses->iface_lock);
}
}
spin_unlock(&cifs_tcp_ses_lock);
#include <crypto/aead.h>
int __cifs_calc_signature(struct smb_rqst *rqst,
- int start,
struct TCP_Server_Info *server, char *signature,
struct shash_desc *shash)
{
int rc;
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
+ int is_smb2 = server->vals->header_preamble_size == 0;
- for (i = start; i < n_vec; i++) {
+ /* iov[0] is actual data and not the rfc1002 length for SMB2+ */
+ if (is_smb2) {
+ if (iov[0].iov_len <= 4)
+ return -EIO;
+ i = 0;
+ } else {
+ if (n_vec < 2 || iov[0].iov_len != 4)
+ return -EIO;
+ i = 1; /* skip rfc1002 length */
+ }
+
+ for (; i < n_vec; i++) {
if (iov[i].iov_len == 0)
continue;
if (iov[i].iov_base == NULL) {
cifs_dbg(VFS, "null iovec entry\n");
return -EIO;
}
- if (i == 1 && iov[1].iov_len <= 4)
- break; /* nothing to sign or corrupt header */
+
rc = crypto_shash_update(shash,
iov[i].iov_base, iov[i].iov_len);
if (rc) {
return rc;
}
- return __cifs_calc_signature(rqst, 1, server, signature,
+ return __cifs_calc_signature(rqst, server, signature,
&server->secmech.sdescmd5->shash);
}
extern int cifs_create(struct inode *, struct dentry *, umode_t,
bool excl);
extern int cifs_atomic_open(struct inode *, struct dentry *,
- struct file *, unsigned, umode_t,
- int *);
+ struct file *, unsigned, umode_t);
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
unsigned int);
extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */
+#define CIFS_PORT 445
+#define RFC1001_PORT 139
+
/*
* The sizes of various internal tables and strings
*/
/* send echo request */
int (*echo)(struct TCP_Server_Info *);
/* create directory */
+ int (*posix_mkdir)(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb);
int (*mkdir)(const unsigned int, struct cifs_tcon *, const char *,
struct cifs_sb_info *);
/* set info on created directory */
void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int,
bool *);
/* create lease context buffer for CREATE request */
- char * (*create_lease_buf)(u8 *, u8);
+ char * (*create_lease_buf)(u8 *lease_key, u8 oplock);
/* parse lease context buffer and return oplock/epoch info */
__u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
ssize_t (*copychunk_range)(const unsigned int,
#endif
+struct cifs_server_iface {
+ size_t speed;
+ unsigned int rdma_capable : 1;
+ unsigned int rss_capable : 1;
+ struct sockaddr_storage sockaddr;
+};
+
/*
* Session structure. One of these for each uid session with a particular host
*/
#ifdef CONFIG_CIFS_SMB311
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
#endif /* 3.1.1 */
+
+ /*
+ * Network interfaces available on the server this session is
+ * connected to.
+ *
+ * Other channels can be opened by connecting and binding this
+ * session to interfaces from this list.
+ *
+ * iface_lock should be taken when accessing any of these fields
+ */
+ spinlock_t iface_lock;
+ struct cifs_server_iface *iface_list;
+ size_t iface_count;
+ unsigned long iface_last_update; /* jiffies */
};
static inline bool
return ses->server->vals->cap_unix & ses->capabilities;
}
+struct cached_fid {
+ bool is_valid:1; /* Do we have a useable root fid */
+ struct cifs_fid *fid;
+ struct mutex fid_mutex;
+ struct cifs_tcon *tcon;
+ struct work_struct lease_break;
+};
+
/*
* there is one of these for each connection to a resource on a particular
* session
struct fscache_cookie *fscache; /* cookie for share */
#endif
struct list_head pending_opens; /* list of incomplete opens */
- bool valid_root_fid:1; /* Do we have a useable root fid */
- struct mutex prfid_mutex; /* prevents reopen race after dead ses*/
- struct cifs_fid *prfid; /* handle to the directory at top of share */
+ struct cached_fid crfid; /* Cached root fid */
/* BB add field for back pointer to sb struct(s)? */
};
/* one of these for every pending CIFS request to the server */
struct mid_q_entry {
struct list_head qhead; /* mids waiting on reply from this server */
+ struct kref refcount;
struct TCP_Server_Info *server; /* server corresponding to this mid */
__u64 mid; /* multiplex id */
__u32 pid; /* process id */
struct TCP_Server_Info *server);
extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
extern void cifs_delete_mid(struct mid_q_entry *mid);
+extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry);
extern void cifs_wake_up_task(struct mid_q_entry *mid);
extern int cifs_handle_standard(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
struct kvec *, int /* nvec to send */,
int * /* type of buf returned */, const int flags,
struct kvec * /* resp vec */);
-extern int smb2_send_recv(const unsigned int xid, struct cifs_ses *pses,
- struct kvec *pkvec, int nvec_to_send,
- int *pbuftype, const int flags,
- struct kvec *presp);
extern int SendReceiveBlockingLock(const unsigned int xid,
struct cifs_tcon *ptcon,
struct smb_hdr *in_buf ,
struct cifs_sb_info *cifs_sb,
const unsigned char *path, char *pbuf,
unsigned int *pbytes_written);
-int __cifs_calc_signature(struct smb_rqst *rqst, int start,
+int __cifs_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server, char *signature,
struct shash_desc *shash);
enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,
struct cifs_aio_ctx *cifs_aio_ctx_alloc(void);
void cifs_aio_ctx_release(struct kref *refcount);
int setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw);
+void smb2_cached_lease_break(struct work_struct *work);
int cifs_alloc_hash(const char *name, struct crypto_shash **shash,
struct sdesc **sdesc);
}
spin_unlock(&tcon->open_file_lock);
- mutex_lock(&tcon->prfid_mutex);
- tcon->valid_root_fid = false;
- memset(tcon->prfid, 0, sizeof(struct cifs_fid));
- mutex_unlock(&tcon->prfid_mutex);
+ mutex_lock(&tcon->crfid.fid_mutex);
+ tcon->crfid.is_valid = false;
+ memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->crfid.fid_mutex);
/*
* BB Add call to invalidate_inodes(sb) for all superblocks mounted
* greater than cifs socket timeout which is 7 seconds
*/
while (server->tcpStatus == CifsNeedReconnect) {
- wait_event_interruptible_timeout(server->response_q,
- (server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+ rc = wait_event_interruptible_timeout(server->response_q,
+ (server->tcpStatus != CifsNeedReconnect),
+ 10 * HZ);
+ if (rc < 0) {
+ cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+ " signal by the process\n", __func__);
+ return -ERESTARTSYS;
+ }
/* are we still trying to reconnect? */
if (server->tcpStatus != CifsNeedReconnect)
#include "smb2proto.h"
#include "smbdirect.h"
-#define CIFS_PORT 445
-#define RFC1001_PORT 139
-
extern mempool_t *cifs_req_poolp;
extern bool disable_legacy_dialects;
server->pdu_size = next_offset;
}
+ mid_entry = NULL;
if (server->ops->is_transform_hdr &&
server->ops->receive_transform &&
server->ops->is_transform_hdr(buf)) {
length = mid_entry->receive(server, mid_entry);
}
- if (length < 0)
+ if (length < 0) {
+ if (mid_entry)
+ cifs_mid_q_entry_release(mid_entry);
continue;
+ }
if (server->large_buf)
buf = server->bigbuf;
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
+
+ cifs_mid_q_entry_release(mid_entry);
} else if (server->ops->is_oplock_break &&
server->ops->is_oplock_break(buf, server)) {
cifs_dbg(FYI, "Received oplock break\n");
#ifdef CONFIG_CIFS_SMB311
if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
- if (ses->server->vals->protocol_id == SMB311_PROT_ID)
+ if (ses->server->vals->protocol_id == SMB311_PROT_ID) {
tcon->posix_extensions = true;
+ printk_once(KERN_WARNING
+ "SMB3.11 POSIX Extensions are experimental\n");
+ }
}
#endif /* 311 */
int
cifs_atomic_open(struct inode *inode, struct dentry *direntry,
- struct file *file, unsigned oflags, umode_t mode,
- int *opened)
+ struct file *file, unsigned oflags, umode_t mode)
{
int rc;
unsigned int xid;
}
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
- rc = finish_open(file, direntry, generic_file_open, opened);
+ rc = finish_open(file, direntry, generic_file_open);
if (rc) {
if (server->ops->close)
server->ops->close(xid, tcon, &fid);
memset(&auxdata, 0, sizeof(auxdata));
auxdata.eof = cifsi->server_eof;
- auxdata.last_write_time = cifsi->vfs_inode.i_mtime;
- auxdata.last_change_time = cifsi->vfs_inode.i_ctime;
+ auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
+ auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
cifsi->fscache =
fscache_acquire_cookie(tcon->fscache,
if (cifsi->fscache) {
memset(&auxdata, 0, sizeof(auxdata));
auxdata.eof = cifsi->server_eof;
- auxdata.last_write_time = cifsi->vfs_inode.i_mtime;
- auxdata.last_change_time = cifsi->vfs_inode.i_ctime;
+ auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
+ auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache);
fscache_relinquish_cookie(cifsi->fscache, &auxdata, false);
cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+ struct timespec ts;
cifs_dbg(FYI, "%s: revalidating inode %llu\n",
__func__, cifs_i->uniqueid);
}
/* revalidate if mtime or size have changed */
- if (timespec_equal(&inode->i_mtime, &fattr->cf_mtime) &&
+ ts = timespec64_to_timespec(inode->i_mtime);
+ if (timespec_equal(&ts, &fattr->cf_mtime) &&
cifs_i->server_eof == fattr->cf_eof) {
cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
__func__, cifs_i->uniqueid);
cifs_revalidate_cache(inode, fattr);
spin_lock(&inode->i_lock);
- inode->i_atime = fattr->cf_atime;
- inode->i_mtime = fattr->cf_mtime;
- inode->i_ctime = fattr->cf_ctime;
+ inode->i_atime = timespec_to_timespec64(fattr->cf_atime);
+ inode->i_mtime = timespec_to_timespec64(fattr->cf_mtime);
+ inode->i_ctime = timespec_to_timespec64(fattr->cf_ctime);
inode->i_rdev = fattr->cf_rdev;
cifs_nlink_fattr_to_inode(inode, fattr);
inode->i_uid = fattr->cf_uid;
if (attrs->ia_valid & ATTR_ATIME) {
set_time = true;
info_buf.LastAccessTime =
- cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
+ cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime)));
} else
info_buf.LastAccessTime = 0;
if (attrs->ia_valid & ATTR_MTIME) {
set_time = true;
info_buf.LastWriteTime =
- cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
+ cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime)));
} else
info_buf.LastWriteTime = 0;
if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
cifs_dbg(FYI, "CIFS - CTIME changed\n");
info_buf.ChangeTime =
- cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
+ cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime)));
} else
info_buf.ChangeTime = 0;
goto mkdir_out;
}
+ server = tcon->ses->server;
+
+#ifdef CONFIG_CIFS_SMB311
+ if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) {
+ rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path,
+ cifs_sb);
+ d_drop(direntry); /* for time being always refresh inode info */
+ goto mkdir_out;
+ }
+#endif /* SMB311 */
+
if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_mkdir(inode, direntry, mode, full_path, cifs_sb,
goto mkdir_out;
}
- server = tcon->ses->server;
-
if (!server->ops->mkdir) {
rc = -ENOSYS;
goto mkdir_out;
/* old CIFS Unix Extensions doesn't return create time */
if (CIFS_I(inode)->createtime) {
stat->result_mask |= STATX_BTIME;
- stat->btime =
- cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
+ stat->btime = timespec_to_timespec64(
+ cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)));
}
stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
args->gid = INVALID_GID; /* no change */
if (attrs->ia_valid & ATTR_ATIME)
- args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
+ args->atime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime));
else
args->atime = NO_CHANGE_64;
if (attrs->ia_valid & ATTR_MTIME)
- args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
+ args->mtime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime));
else
args->mtime = NO_CHANGE_64;
if (attrs->ia_valid & ATTR_CTIME)
- args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
+ args->ctime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime));
else
args->ctime = NO_CHANGE_64;
INIT_LIST_HEAD(&ret_buf->smb_ses_list);
INIT_LIST_HEAD(&ret_buf->tcon_list);
mutex_init(&ret_buf->session_mutex);
+ spin_lock_init(&ret_buf->iface_lock);
}
return ret_buf;
}
kfree(buf_to_free->user_name);
kfree(buf_to_free->domainName);
kzfree(buf_to_free->auth_key.response);
+ kfree(buf_to_free->iface_list);
kzfree(buf_to_free);
}
INIT_LIST_HEAD(&ret_buf->openFileList);
INIT_LIST_HEAD(&ret_buf->tcon_list);
spin_lock_init(&ret_buf->open_file_lock);
- mutex_init(&ret_buf->prfid_mutex);
- ret_buf->prfid = kzalloc(sizeof(struct cifs_fid), GFP_KERNEL);
+ mutex_init(&ret_buf->crfid.fid_mutex);
+ ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid),
+ GFP_KERNEL);
#ifdef CONFIG_CIFS_STATS
spin_lock_init(&ret_buf->stat_lock);
#endif
atomic_dec(&tconInfoAllocCount);
kfree(buf_to_free->nativeFileSystem);
kzfree(buf_to_free->password);
- kfree(buf_to_free->prfid);
+ kfree(buf_to_free->crfid.fid);
kfree(buf_to_free);
}
if (compare_mid(mid->mid, buf) &&
mid->mid_state == MID_REQUEST_SUBMITTED &&
le16_to_cpu(mid->command) == buf->Command) {
+ kref_get(&mid->refcount);
spin_unlock(&GlobalMid_Lock);
return mid;
}
int rc;
__le16 *smb2_path;
struct smb2_file_all_info *smb2_data = NULL;
- __u8 smb2_oplock[17];
+ __u8 smb2_oplock;
struct cifs_fid *fid = oparms->fid;
struct network_resiliency_req nr_ioctl_req;
}
oparms->desired_access |= FILE_READ_ATTRIBUTES;
- *smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
+ smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
- if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
- memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE);
-
- rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL,
+ rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL,
NULL);
if (rc)
goto out;
move_smb2_info_to_cifs(buf, smb2_data);
}
- *oplock = *smb2_oplock;
+ *oplock = smb2_oplock;
out:
kfree(smb2_data);
kfree(smb2_path);
#ifdef CONFIG_CIFS_SMB311
/* SMB311 POSIX extensions paths do not include leading slash */
else if (cifs_sb_master_tlink(cifs_sb) &&
- cifs_sb_master_tcon(cifs_sb)->posix_extensions) {
+ cifs_sb_master_tcon(cifs_sb)->posix_extensions &&
+ (from[0] == '/')) {
start_of_path = from + 1;
}
#endif /* 311 */
{
struct smb2_lease_break_work *lw = container_of(work,
struct smb2_lease_break_work, lease_break);
- int rc;
+ int rc = 0;
rc = SMB2_lease_break(0, tlink_tcon(lw->tlink), lw->lease_key,
lw->lease_state);
+
cifs_dbg(FYI, "Lease release rc %d\n", rc);
cifs_put_tlink(lw->tlink);
kfree(lw);
open->oplock = lease_state;
}
+
return found;
}
return true;
}
spin_unlock(&tcon->open_file_lock);
+
+ if (tcon->crfid.is_valid &&
+ !memcmp(rsp->LeaseKey,
+ tcon->crfid.fid->lease_key,
+ SMB2_LEASE_KEY_SIZE)) {
+ INIT_WORK(&tcon->crfid.lease_break,
+ smb2_cached_lease_break);
+ queue_work(cifsiod_wq,
+ &tcon->crfid.lease_break);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
+ }
}
}
}
if ((mid->mid == wire_mid) &&
(mid->mid_state == MID_REQUEST_SUBMITTED) &&
(mid->command == shdr->Command)) {
+ kref_get(&mid->refcount);
spin_unlock(&GlobalMid_Lock);
return mid;
}
return rsize;
}
-#ifdef CONFIG_CIFS_STATS2
+
+static int
+parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
+ size_t buf_len,
+ struct cifs_server_iface **iface_list,
+ size_t *iface_count)
+{
+ struct network_interface_info_ioctl_rsp *p;
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+ struct iface_info_ipv4 *p4;
+ struct iface_info_ipv6 *p6;
+ struct cifs_server_iface *info;
+ ssize_t bytes_left;
+ size_t next = 0;
+ int nb_iface = 0;
+ int rc = 0;
+
+ *iface_list = NULL;
+ *iface_count = 0;
+
+ /*
+ * Fist pass: count and sanity check
+ */
+
+ bytes_left = buf_len;
+ p = buf;
+ while (bytes_left >= sizeof(*p)) {
+ nb_iface++;
+ next = le32_to_cpu(p->Next);
+ if (!next) {
+ bytes_left -= sizeof(*p);
+ break;
+ }
+ p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next);
+ bytes_left -= next;
+ }
+
+ if (!nb_iface) {
+ cifs_dbg(VFS, "%s: malformed interface info\n", __func__);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (bytes_left || p->Next)
+ cifs_dbg(VFS, "%s: incomplete interface info\n", __func__);
+
+
+ /*
+ * Second pass: extract info to internal structure
+ */
+
+ *iface_list = kcalloc(nb_iface, sizeof(**iface_list), GFP_KERNEL);
+ if (!*iface_list) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ info = *iface_list;
+ bytes_left = buf_len;
+ p = buf;
+ while (bytes_left >= sizeof(*p)) {
+ info->speed = le64_to_cpu(p->LinkSpeed);
+ info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE);
+ info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE);
+
+ cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count);
+ cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed);
+ cifs_dbg(FYI, "%s: capabilities 0x%08x\n", __func__,
+ le32_to_cpu(p->Capability));
+
+ switch (p->Family) {
+ /*
+ * The kernel and wire socket structures have the same
+ * layout and use network byte order but make the
+ * conversion explicit in case either one changes.
+ */
+ case INTERNETWORK:
+ addr4 = (struct sockaddr_in *)&info->sockaddr;
+ p4 = (struct iface_info_ipv4 *)p->Buffer;
+ addr4->sin_family = AF_INET;
+ memcpy(&addr4->sin_addr, &p4->IPv4Address, 4);
+
+ /* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */
+ addr4->sin_port = cpu_to_be16(CIFS_PORT);
+
+ cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__,
+ &addr4->sin_addr);
+ break;
+ case INTERNETWORKV6:
+ addr6 = (struct sockaddr_in6 *)&info->sockaddr;
+ p6 = (struct iface_info_ipv6 *)p->Buffer;
+ addr6->sin6_family = AF_INET6;
+ memcpy(&addr6->sin6_addr, &p6->IPv6Address, 16);
+
+ /* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */
+ addr6->sin6_flowinfo = 0;
+ addr6->sin6_scope_id = 0;
+ addr6->sin6_port = cpu_to_be16(CIFS_PORT);
+
+ cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__,
+ &addr6->sin6_addr);
+ break;
+ default:
+ cifs_dbg(VFS,
+ "%s: skipping unsupported socket family\n",
+ __func__);
+ goto next_iface;
+ }
+
+ (*iface_count)++;
+ info++;
+next_iface:
+ next = le32_to_cpu(p->Next);
+ if (!next)
+ break;
+ p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next);
+ bytes_left -= next;
+ }
+
+ if (!*iface_count) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+out:
+ if (rc) {
+ kfree(*iface_list);
+ *iface_count = 0;
+ *iface_list = NULL;
+ }
+ return rc;
+}
+
+
static int
SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
{
int rc;
unsigned int ret_data_len = 0;
- struct network_interface_info_ioctl_rsp *out_buf;
+ struct network_interface_info_ioctl_rsp *out_buf = NULL;
+ struct cifs_server_iface *iface_list;
+ size_t iface_count;
+ struct cifs_ses *ses = tcon->ses;
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
NULL /* no data input */, 0 /* no data input */,
(char **)&out_buf, &ret_data_len);
- if (rc != 0)
+ if (rc != 0) {
cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
- else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) {
- cifs_dbg(VFS, "server returned bad net interface info buf\n");
- rc = -EINVAL;
- } else {
- /* Dump info on first interface */
- cifs_dbg(FYI, "Adapter Capability 0x%x\t",
- le32_to_cpu(out_buf->Capability));
- cifs_dbg(FYI, "Link Speed %lld\n",
- le64_to_cpu(out_buf->LinkSpeed));
+ goto out;
}
+
+ rc = parse_server_interfaces(out_buf, ret_data_len,
+ &iface_list, &iface_count);
+ if (rc)
+ goto out;
+
+ spin_lock(&ses->iface_lock);
+ kfree(ses->iface_list);
+ ses->iface_list = iface_list;
+ ses->iface_count = iface_count;
+ ses->iface_last_update = jiffies;
+ spin_unlock(&ses->iface_lock);
+
+out:
kfree(out_buf);
return rc;
}
-#endif /* STATS2 */
+
+void
+smb2_cached_lease_break(struct work_struct *work)
+{
+ struct cached_fid *cfid = container_of(work,
+ struct cached_fid, lease_break);
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->is_valid) {
+ cifs_dbg(FYI, "clear cached root file handle\n");
+ SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
+ cfid->fid->volatile_fid);
+ cfid->is_valid = false;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+}
/*
* Open the directory at the root of a share
struct cifs_open_parms oparams;
int rc;
__le16 srch_path = 0; /* Null - since an open of top of share */
- u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+ u8 oplock = SMB2_OPLOCK_LEVEL_II;
- mutex_lock(&tcon->prfid_mutex);
- if (tcon->valid_root_fid) {
+ mutex_lock(&tcon->crfid.fid_mutex);
+ if (tcon->crfid.is_valid) {
cifs_dbg(FYI, "found a cached root file handle\n");
- memcpy(pfid, tcon->prfid, sizeof(struct cifs_fid));
- mutex_unlock(&tcon->prfid_mutex);
+ memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->crfid.fid_mutex);
return 0;
}
rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL, NULL);
if (rc == 0) {
- memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid));
- tcon->valid_root_fid = true;
+ memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
+ tcon->crfid.tcon = tcon;
+ tcon->crfid.is_valid = true;
}
- mutex_unlock(&tcon->prfid_mutex);
+ mutex_unlock(&tcon->crfid.fid_mutex);
return rc;
}
if (rc)
return;
-#ifdef CONFIG_CIFS_STATS2
SMB3_request_interfaces(xid, tcon);
-#endif /* STATS2 */
SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
FS_ATTRIBUTE_INFORMATION);
struct cifs_open_parms oparms;
struct cifs_fid fid;
- if ((*full_path == 0) && tcon->valid_root_fid)
+ if ((*full_path == 0) && tcon->crfid.is_valid)
return 0;
utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea,
len);
+ kfree(ea);
+
SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
return rc;
if (!buf)
return NULL;
- buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
- buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+ memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
buf->ccontext.DataOffset = cpu_to_le16(offsetof
if (!buf)
return NULL;
- buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
- buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+ memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
buf->ccontext.DataOffset = cpu_to_le16(offsetof
if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
return SMB2_OPLOCK_LEVEL_NOCHANGE;
if (lease_key)
- memcpy(lease_key, &lc->lcontext.LeaseKeyLow,
- SMB2_LEASE_KEY_SIZE);
+ memcpy(lease_key, &lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
return le32_to_cpu(lc->lcontext.LeaseState);
}
struct smb_rqst *old_rq)
{
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)old_rq->rq_iov[0].iov_base;
memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
}
/* Assumes:
- * rqst->rq_iov[0] is rfc1002 length
- * rqst->rq_iov[1] is tranform header
- * rqst->rq_iov[2+] data to be encrypted/decrypted
+ * rqst->rq_iov[0] is transform header
+ * rqst->rq_iov[1+] data to be encrypted/decrypted
*/
static struct scatterlist *
init_sg(struct smb_rqst *rqst, u8 *sign)
{
- unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages;
+ unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
struct scatterlist *sg;
unsigned int i;
return NULL;
sg_init_table(sg, sg_len);
- smb2_sg_set_buf(&sg[0], rqst->rq_iov[1].iov_base + 20, assoc_data_len);
- for (i = 1; i < rqst->rq_nvec - 1; i++)
- smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base,
- rqst->rq_iov[i+1].iov_len);
+ smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len);
+ for (i = 1; i < rqst->rq_nvec; i++)
+ smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
+ rqst->rq_iov[i].iov_len);
for (j = 0; i < sg_len - 1; i++, j++) {
unsigned int len, offset;
return 1;
}
/*
- * Encrypt or decrypt @rqst message. @rqst has the following format:
- * iov[0] - rfc1002 length
- * iov[1] - transform header (associate data),
- * iov[2-N] and pages - data to encrypt.
- * On success return encrypted data in iov[2-N] and pages, leave iov[0-1]
+ * Encrypt or decrypt @rqst message. @rqst[0] has the following format:
+ * iov[0] - transform header (associate data),
+ * iov[1-N] - SMB2 header and pages - data to encrypt.
+ * On success return encrypted data in iov[1-N] and pages, leave iov[0]
* untouched.
*/
static int
crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
{
struct smb2_transform_hdr *tr_hdr =
- (struct smb2_transform_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
int rc = 0;
struct scatterlist *sg;
return rc;
}
-/*
- * This is called from smb_send_rqst. At this point we have the rfc1002
- * header as the first element in the vector.
- */
static int
smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
struct smb_rqst *old_rq)
struct page **pages;
struct smb2_transform_hdr *tr_hdr;
unsigned int npages = old_rq->rq_npages;
- unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
+ unsigned int orig_len;
int i;
int rc = -ENOMEM;
goto err_free_pages;
}
- /* Make space for one extra iov to hold the transform header */
iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
GFP_KERNEL);
if (!iov)
goto err_free_pages;
- /* copy all iovs from the old except the 1st one (rfc1002 length) */
- memcpy(&iov[2], &old_rq->rq_iov[1],
- sizeof(struct kvec) * (old_rq->rq_nvec - 1));
- /* copy the rfc1002 iov */
- iov[0].iov_base = old_rq->rq_iov[0].iov_base;
- iov[0].iov_len = old_rq->rq_iov[0].iov_len;
+ /* copy all iovs from the old */
+ memcpy(&iov[1], &old_rq->rq_iov[0],
+ sizeof(struct kvec) * old_rq->rq_nvec);
new_rq->rq_iov = iov;
new_rq->rq_nvec = old_rq->rq_nvec + 1;
if (!tr_hdr)
goto err_free_iov;
+ orig_len = smb_rqst_len(server, old_rq);
+
/* fill the 2nd iov with a transform header */
fill_transform_hdr(tr_hdr, orig_len, old_rq);
- new_rq->rq_iov[1].iov_base = tr_hdr;
- new_rq->rq_iov[1].iov_len = sizeof(struct smb2_transform_hdr);
-
- /* Update rfc1002 header */
- inc_rfc1001_len(new_rq->rq_iov[0].iov_base,
- sizeof(struct smb2_transform_hdr));
+ new_rq->rq_iov[0].iov_base = tr_hdr;
+ new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
/* copy pages form the old */
for (i = 0; i < npages; i++) {
put_page(rqst->rq_pages[i]);
kfree(rqst->rq_pages);
/* free transform header */
- kfree(rqst->rq_iov[1].iov_base);
+ kfree(rqst->rq_iov[0].iov_base);
kfree(rqst->rq_iov);
}
unsigned int buf_data_size, struct page **pages,
unsigned int npages, unsigned int page_data_size)
{
- struct kvec iov[3];
+ struct kvec iov[2];
struct smb_rqst rqst = {NULL};
int rc;
- iov[0].iov_base = NULL;
- iov[0].iov_len = 0;
- iov[1].iov_base = buf;
- iov[1].iov_len = sizeof(struct smb2_transform_hdr);
- iov[2].iov_base = buf + sizeof(struct smb2_transform_hdr);
- iov[2].iov_len = buf_data_size;
+ iov[0].iov_base = buf;
+ iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+ iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
+ iov[1].iov_len = buf_data_size;
rqst.rq_iov = iov;
- rqst.rq_nvec = 3;
+ rqst.rq_nvec = 2;
rqst.rq_pages = pages;
rqst.rq_npages = npages;
rqst.rq_pagesz = PAGE_SIZE;
if (rc)
return rc;
- memmove(buf, iov[2].iov_base, buf_data_size);
+ memmove(buf, iov[1].iov_base, buf_data_size);
server->total_read = buf_data_size + page_data_size;
.set_compression = smb2_set_compression,
.mkdir = smb2_mkdir,
.mkdir_setinfo = smb2_mkdir_setinfo,
+ .posix_mkdir = smb311_posix_mkdir,
.rmdir = smb2_rmdir,
.unlink = smb2_unlink,
.rename = smb2_rename_path,
static int
smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
{
- int rc = 0;
+ int rc;
struct nls_table *nls_codepage;
struct cifs_ses *ses;
struct TCP_Server_Info *server;
* for those three - in the calling routine.
*/
if (tcon == NULL)
- return rc;
+ return 0;
if (smb2_command == SMB2_TREE_CONNECT)
- return rc;
+ return 0;
if (tcon->tidStatus == CifsExiting) {
/*
return -EAGAIN;
}
- wait_event_interruptible_timeout(server->response_q,
- (server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+ rc = wait_event_interruptible_timeout(server->response_q,
+ (server->tcpStatus != CifsNeedReconnect),
+ 10 * HZ);
+ if (rc < 0) {
+ cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+ " signal by the process\n", __func__);
+ return -ERESTARTSYS;
+ }
/* are we still trying to reconnect? */
if (server->tcpStatus != CifsNeedReconnect)
}
if (!tcon->ses->need_reconnect && !tcon->need_reconnect)
- return rc;
+ return 0;
nls_codepage = load_nls_default();
return rc;
/* BB eventually switch this to SMB2 specific small buf size */
- *request_buf = cifs_small_buf_get();
+ if (smb2_command == SMB2_SET_INFO)
+ *request_buf = cifs_buf_get();
+ else
+ *request_buf = cifs_small_buf_get();
if (*request_buf == NULL) {
/* BB should we add a retry in here if not a writepage? */
return -ENOMEM;
int
SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
{
+ struct smb_rqst rqst;
struct smb2_negotiate_req *req;
struct smb2_negotiate_rsp *rsp;
struct kvec iov[1];
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base;
/*
req->PreviousSessionId = sess_data->previous_session;
req->Flags = 0; /* MBZ */
- /* to enable echos and oplocks */
- req->sync_hdr.CreditRequest = cpu_to_le16(3);
+
+ /* enough to enable echos and oplocks and one max size write */
+ req->sync_hdr.CreditRequest = cpu_to_le16(130);
/* only one of SMB2 signing flags may be set in SMB2 request */
if (server->sign)
SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
{
int rc;
+ struct smb_rqst rqst;
struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base;
struct kvec rsp_iov = { NULL, 0 };
cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */);
req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len);
- /* BB add code to build os and lm fields */
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = sess_data->iov;
+ rqst.rq_nvec = 2;
- rc = smb2_send_recv(sess_data->xid, sess_data->ses,
- sess_data->iov, 2,
+ /* BB add code to build os and lm fields */
+ rc = cifs_send_recv(sess_data->xid, sess_data->ses,
+ &rqst,
&sess_data->buf0_type,
CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov);
cifs_small_buf_release(sess_data->iov[0].iov_base);
int
SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
{
+ struct smb_rqst rqst;
struct smb2_logoff_req *req; /* response is also trivial struct */
int rc = 0;
struct TCP_Server_Info *server;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
/*
* No tcon so can't do
SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
struct cifs_tcon *tcon, const struct nls_table *cp)
{
+ struct smb_rqst rqst;
struct smb2_tree_connect_req *req;
struct smb2_tree_connect_rsp *rsp = NULL;
struct kvec iov[2];
!smb3_encryption_required(tcon))
req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
- rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
int
SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
{
+ struct smb_rqst rqst;
struct smb2_tree_disconnect_req *req; /* response is trivial */
int rc = 0;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc)
cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE);
static int
add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
- unsigned int *num_iovec, __u8 *oplock)
+ unsigned int *num_iovec, u8 *lease_key, __u8 *oplock)
{
struct smb2_create_req *req = iov[0].iov_base;
unsigned int num = *num_iovec;
- iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock);
+ iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock);
if (iov[num].iov_base == NULL)
return -ENOMEM;
iov[num].iov_len = server->vals->create_lease_size;
return 0;
}
+#ifdef CONFIG_CIFS_SMB311
+int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb)
+{
+ struct smb_rqst rqst;
+ struct smb2_create_req *req;
+ struct smb2_create_rsp *rsp;
+ struct TCP_Server_Info *server;
+ struct cifs_ses *ses = tcon->ses;
+ struct kvec iov[3]; /* make sure at least one for each open context */
+ struct kvec rsp_iov = {NULL, 0};
+ int resp_buftype;
+ int uni_path_len;
+ __le16 *copy_path = NULL;
+ int copy_size;
+ int rc = 0;
+ unsigned int n_iov = 2;
+ __u32 file_attributes = 0;
+ char *pc_buf = NULL;
+ int flags = 0;
+ unsigned int total_len;
+ __le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+
+ if (!path)
+ return -ENOMEM;
+
+ cifs_dbg(FYI, "mkdir\n");
+
+ if (ses && (ses->server))
+ server = ses->server;
+ else
+ return -EIO;
+
+ rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
+
+ if (rc)
+ return rc;
+
+ if (smb3_encryption_required(tcon))
+ flags |= CIFS_TRANSFORM_REQ;
+
+
+ req->ImpersonationLevel = IL_IMPERSONATION;
+ req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES);
+ /* File attributes ignored on open (used in create though) */
+ req->FileAttributes = cpu_to_le32(file_attributes);
+ req->ShareAccess = FILE_SHARE_ALL_LE;
+ req->CreateDisposition = cpu_to_le32(FILE_CREATE);
+ req->CreateOptions = cpu_to_le32(CREATE_NOT_FILE);
+
+ iov[0].iov_base = (char *)req;
+ /* -1 since last byte is buf[0] which is sent below (path) */
+ iov[0].iov_len = total_len - 1;
+
+ req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req));
+
+ /* [MS-SMB2] 2.2.13 NameOffset:
+ * If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of
+ * the SMB2 header, the file name includes a prefix that will
+ * be processed during DFS name normalization as specified in
+ * section 3.3.5.9. Otherwise, the file name is relative to
+ * the share that is identified by the TreeId in the SMB2
+ * header.
+ */
+ if (tcon->share_flags & SHI1005_FLAGS_DFS) {
+ int name_len;
+
+ req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+ rc = alloc_path_with_tree_prefix(©_path, ©_size,
+ &name_len,
+ tcon->treeName, path);
+ if (rc) {
+ cifs_small_buf_release(req);
+ return rc;
+ }
+ req->NameLength = cpu_to_le16(name_len * 2);
+ uni_path_len = copy_size;
+ path = copy_path;
+ } else {
+ uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+ /* MUST set path len (NameLength) to 0 opening root of share */
+ req->NameLength = cpu_to_le16(uni_path_len - 2);
+ if (uni_path_len % 8 != 0) {
+ copy_size = roundup(uni_path_len, 8);
+ copy_path = kzalloc(copy_size, GFP_KERNEL);
+ if (!copy_path) {
+ cifs_small_buf_release(req);
+ return -ENOMEM;
+ }
+ memcpy((char *)copy_path, (const char *)path,
+ uni_path_len);
+ uni_path_len = copy_size;
+ path = copy_path;
+ }
+ }
+
+ iov[1].iov_len = uni_path_len;
+ iov[1].iov_base = path;
+ req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE;
+
+ if (tcon->posix_extensions) {
+ if (n_iov > 2) {
+ struct create_context *ccontext =
+ (struct create_context *)iov[n_iov-1].iov_base;
+ ccontext->Next =
+ cpu_to_le32(iov[n_iov-1].iov_len);
+ }
+
+ rc = add_posix_context(iov, &n_iov, mode);
+ if (rc) {
+ cifs_small_buf_release(req);
+ kfree(copy_path);
+ return rc;
+ }
+ pc_buf = iov[n_iov-1].iov_base;
+ }
+
+
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
+ &rsp_iov);
+
+ cifs_small_buf_release(req);
+ rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+
+ if (rc != 0) {
+ cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
+ trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid,
+ CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc);
+ goto smb311_mkdir_exit;
+ } else
+ trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+ ses->Suid, CREATE_NOT_FILE,
+ FILE_WRITE_ATTRIBUTES);
+
+ SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
+
+ /* Eventually save off posix specific response info and timestaps */
+
+smb311_mkdir_exit:
+ kfree(copy_path);
+ kfree(pc_buf);
+ free_rsp_buf(resp_buftype, rsp);
+ return rc;
+
+}
+#endif /* SMB311 */
+
int
SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
__u8 *oplock, struct smb2_file_all_info *buf,
struct kvec *err_iov, int *buftype)
{
+ struct smb_rqst rqst;
struct smb2_create_req *req;
struct smb2_create_rsp *rsp;
struct TCP_Server_Info *server;
*oplock == SMB2_OPLOCK_LEVEL_NONE)
req->RequestedOplockLevel = *oplock;
else {
- rc = add_lease_context(server, iov, &n_iov, oplock);
+ rc = add_lease_context(server, iov, &n_iov,
+ oparms->fid->lease_key, oplock);
if (rc) {
cifs_small_buf_release(req);
kfree(copy_path);
}
#endif /* SMB311 */
- rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
char *in_data, u32 indatalen,
char **out_data, u32 *plen /* returned data len */)
{
+ struct smb_rqst rqst;
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp;
struct cifs_ses *ses;
if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO)
req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
- rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, int flags)
{
+ struct smb_rqst rqst;
struct smb2_close_req *req;
struct smb2_close_rsp *rsp;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
u32 additional_info, size_t output_len, size_t min_len, void **data,
u32 *dlen)
{
+ struct smb_rqst rqst;
struct smb2_query_info_req *req;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov[2];
/* 1 for Buffer */
iov[0].iov_len = total_len - 1;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
{
struct smb2_echo_req *req;
int rc = 0;
- struct kvec iov[2];
+ struct kvec iov[1];
struct smb_rqst rqst = { .rq_iov = iov,
- .rq_nvec = 2 };
+ .rq_nvec = 1 };
unsigned int total_len;
- __be32 rfc1002_marker;
cifs_dbg(FYI, "In echo request\n");
req->sync_hdr.CreditRequest = cpu_to_le16(1);
- iov[0].iov_len = 4;
- rfc1002_marker = cpu_to_be32(total_len);
- iov[0].iov_base = &rfc1002_marker;
- iov[1].iov_len = total_len;
- iov[1].iov_base = (char *)req;
+ iov[0].iov_len = total_len;
+ iov[0].iov_base = (char *)req;
rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, NULL,
server, CIFS_ECHO_OP);
SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
u64 volatile_fid)
{
+ struct smb_rqst rqst;
struct smb2_flush_req *req;
struct cifs_ses *ses = tcon->ses;
struct kvec iov[1];
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc != 0) {
struct smb2_sync_hdr *shdr;
struct cifs_io_parms io_parms;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
- .rq_nvec = 2 };
+ .rq_nvec = 1 };
struct TCP_Server_Info *server;
unsigned int total_len;
- __be32 req_len;
cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
__func__, rdata->offset, rdata->bytes);
if (smb3_encryption_required(io_parms.tcon))
flags |= CIFS_TRANSFORM_REQ;
- req_len = cpu_to_be32(total_len);
-
- rdata->iov[0].iov_base = &req_len;
- rdata->iov[0].iov_len = sizeof(__be32);
- rdata->iov[1].iov_base = buf;
- rdata->iov[1].iov_len = total_len;
+ rdata->iov[0].iov_base = buf;
+ rdata->iov[0].iov_len = total_len;
shdr = (struct smb2_sync_hdr *)buf;
SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, char **buf, int *buf_type)
{
+ struct smb_rqst rqst;
int resp_buftype, rc = -EACCES;
struct smb2_read_plain_req *req = NULL;
struct smb2_read_rsp *rsp = NULL;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
struct smb2_sync_hdr *shdr;
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
- struct kvec iov[2];
+ struct kvec iov[1];
struct smb_rqst rqst = { };
unsigned int total_len;
- __be32 rfc1002_marker;
rc = smb2_plain_req_init(SMB2_WRITE, tcon, (void **) &req, &total_len);
if (rc) {
v1->length = cpu_to_le32(wdata->mr->mr->length);
}
#endif
- /* 4 for rfc1002 length field and 1 for Buffer */
- iov[0].iov_len = 4;
- rfc1002_marker = cpu_to_be32(total_len - 1 + wdata->bytes);
- iov[0].iov_base = &rfc1002_marker;
- iov[1].iov_len = total_len - 1;
- iov[1].iov_base = (char *)req;
+ iov[0].iov_len = total_len - 1;
+ iov[0].iov_base = (char *)req;
rqst.rq_iov = iov;
- rqst.rq_nvec = 2;
+ rqst.rq_nvec = 1;
rqst.rq_pages = wdata->pages;
rqst.rq_offset = wdata->page_offset;
rqst.rq_npages = wdata->nr_pages;
rqst.rq_tailsz = wdata->tailsz;
#ifdef CONFIG_CIFS_SMB_DIRECT
if (wdata->mr) {
- iov[1].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
+ iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
rqst.rq_npages = 0;
}
#endif
SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, struct kvec *iov, int n_vec)
{
+ struct smb_rqst rqst;
int rc = 0;
struct smb2_write_req *req = NULL;
struct smb2_write_rsp *rsp = NULL;
/* 1 for Buffer */
iov[0].iov_len = total_len - 1;
- rc = smb2_send_recv(xid, io_parms->tcon->ses, iov, n_vec + 1,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_vec + 1;
+
+ rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst,
&resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
u64 persistent_fid, u64 volatile_fid, int index,
struct cifs_search_info *srch_inf)
{
+ struct smb_rqst rqst;
struct smb2_query_directory_req *req;
struct smb2_query_directory_rsp *rsp = NULL;
struct kvec iov[2];
iov[1].iov_base = (char *)(req->Buffer);
iov[1].iov_len = len;
- rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
u8 info_type, u32 additional_info, unsigned int num,
void **data, unsigned int *size)
{
+ struct smb_rqst rqst;
struct smb2_set_info_req *req;
struct smb2_set_info_rsp *rsp = NULL;
struct kvec *iov;
iov[i].iov_len = size[i];
}
- rc = smb2_send_recv(xid, ses, iov, num, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = num;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
- cifs_small_buf_release(req);
+ cifs_buf_release(req);
rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
if (rc != 0) {
const u64 persistent_fid, const u64 volatile_fid,
__u8 oplock_level)
{
+ struct smb_rqst rqst;
int rc;
struct smb2_oplock_break *req = NULL;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc) {
SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
{
+ struct smb_rqst rqst;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov;
struct kvec rsp_iov;
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = &iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(iov.iov_base);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, int level)
{
+ struct smb_rqst rqst;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov;
struct kvec rsp_iov;
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = &iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(iov.iov_base);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
const __u64 persist_fid, const __u64 volatile_fid, const __u32 pid,
const __u32 num_lock, struct smb2_lock_element *buf)
{
+ struct smb_rqst rqst;
int rc = 0;
struct smb2_lock_req *req = NULL;
struct kvec iov[2];
iov[1].iov_len = count;
cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
- rc = smb2_send_recv(xid, tcon->ses, iov, 2, &resp_buf_type, flags,
+
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, tcon->ses, &rqst, &resp_buf_type, flags,
&rsp_iov);
cifs_small_buf_release(req);
if (rc) {
SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
__u8 *lease_key, const __le32 lease_state)
{
+ struct smb_rqst rqst;
int rc;
struct smb2_lease_ack *req = NULL;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc) {
#define SMB2_LEASE_KEY_SIZE 16
struct lease_context {
- __le64 LeaseKeyLow;
- __le64 LeaseKeyHigh;
+ u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
__le32 LeaseState;
__le32 LeaseFlags;
__le64 LeaseDuration;
} __packed;
struct lease_context_v2 {
- __le64 LeaseKeyLow;
- __le64 LeaseKeyHigh;
+ u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
__le32 LeaseState;
__le32 LeaseFlags;
__le64 LeaseDuration;
__le16 Dialect; /* Dialect in use for the connection */
} __packed;
-#define RSS_CAPABLE 0x00000001
-#define RDMA_CAPABLE 0x00000002
+#define RSS_CAPABLE cpu_to_le32(0x00000001)
+#define RDMA_CAPABLE cpu_to_le32(0x00000002)
+
+#define INTERNETWORK cpu_to_le16(0x0002)
+#define INTERNETWORKV6 cpu_to_le16(0x0017)
struct network_interface_info_ioctl_rsp {
__le32 Next; /* next interface. zero if this is last one */
__le32 Capability; /* RSS or RDMA Capable */
__le32 Reserved;
__le64 LinkSpeed;
- char SockAddr_Storage[128];
+ __le16 Family;
+ __u8 Buffer[126];
+} __packed;
+
+struct iface_info_ipv4 {
+ __be16 Port;
+ __be32 IPv4Address;
+ __be64 Reserved;
+} __packed;
+
+struct iface_info_ipv6 {
+ __be16 Port;
+ __be32 FlowInfo;
+ __u8 IPv6Address[16];
+ __be32 ScopeId;
} __packed;
#define NO_FILE_ID 0xFFFFFFFFFFFFFFFFULL /* general ioctls to srv not to file */
struct cifs_sb_info *cifs_sb, bool set_alloc);
extern int smb2_set_file_info(struct inode *inode, const char *full_path,
FILE_BASIC_INFO *buf, const unsigned int xid);
+extern int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb);
extern int smb2_mkdir(const unsigned int xid, struct cifs_tcon *tcon,
const char *name, struct cifs_sb_info *cifs_sb);
extern void smb2_mkdir_setinfo(struct inode *inode, const char *full_path,
extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
extern void smb2_reconnect_server(struct work_struct *work);
extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
+extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
+ struct smb_rqst *rqst);
/*
* SMB2 Worker functions - most of protocol specific implementation details
unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
unsigned char *sigptr = smb2_signature;
struct kvec *iov = rqst->rq_iov;
- int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base;
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
+ struct shash_desc *shash = &server->secmech.sdeschmacsha256->shash;
+ struct smb_rqst drqst;
ses = smb2_find_smb_ses(server, shdr->SessionId);
if (!ses) {
}
rc = crypto_shash_setkey(server->secmech.hmacsha256,
- ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
+ ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
if (rc) {
cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
return rc;
}
- rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash);
+ rc = crypto_shash_init(shash);
if (rc) {
cifs_dbg(VFS, "%s: Could not init sha256", __func__);
return rc;
}
- rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr,
- &server->secmech.sdeschmacsha256->shash);
+ /*
+ * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+ * data, that is, iov[0] should not contain a rfc1002 length.
+ *
+ * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+ * __cifs_calc_signature().
+ */
+ drqst = *rqst;
+ if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+ rc = crypto_shash_update(shash, iov[0].iov_base,
+ iov[0].iov_len);
+ if (rc) {
+ cifs_dbg(VFS, "%s: Could not update with payload\n",
+ __func__);
+ return rc;
+ }
+ drqst.rq_iov++;
+ drqst.rq_nvec--;
+ }
+ rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
if (!rc)
memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
int
smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
- int rc = 0;
+ int rc;
unsigned char smb3_signature[SMB2_CMACAES_SIZE];
unsigned char *sigptr = smb3_signature;
struct kvec *iov = rqst->rq_iov;
- int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base;
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
+ struct shash_desc *shash = &server->secmech.sdesccmacaes->shash;
+ struct smb_rqst drqst;
ses = smb2_find_smb_ses(server, shdr->SessionId);
if (!ses) {
memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
rc = crypto_shash_setkey(server->secmech.cmacaes,
- ses->smb3signingkey, SMB2_CMACAES_SIZE);
-
+ ses->smb3signingkey, SMB2_CMACAES_SIZE);
if (rc) {
cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__);
return rc;
* so unlike smb2 case we do not have to check here if secmech are
* initialized
*/
- rc = crypto_shash_init(&server->secmech.sdesccmacaes->shash);
+ rc = crypto_shash_init(shash);
if (rc) {
cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__);
return rc;
}
- rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr,
- &server->secmech.sdesccmacaes->shash);
+ /*
+ * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+ * data, that is, iov[0] should not contain a rfc1002 length.
+ *
+ * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+ * __cifs_calc_signature().
+ */
+ drqst = *rqst;
+ if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+ rc = crypto_shash_update(shash, iov[0].iov_base,
+ iov[0].iov_len);
+ if (rc) {
+ cifs_dbg(VFS, "%s: Could not update with payload\n",
+ __func__);
+ return rc;
+ }
+ drqst.rq_iov++;
+ drqst.rq_nvec--;
+ }
+ rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
if (!rc)
memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
{
int rc = 0;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
if (!(shdr->Flags & SMB2_FLAGS_SIGNED) ||
server->tcpStatus == CifsNeedNegotiate)
temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
memset(temp, 0, sizeof(struct mid_q_entry));
+ kref_init(&temp->refcount);
temp->mid = le64_to_cpu(shdr->MessageId);
temp->pid = current->pid;
temp->command = shdr->Command; /* Always LE */
{
int rc;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
smb2_seq_num_into_buf(ses->server, shdr);
{
int rc;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
smb2_seq_num_into_buf(server, shdr);
#include "smbdirect.h"
#include "cifs_debug.h"
#include "cifsproto.h"
+#include "smb2proto.h"
static struct smbd_response *get_empty_queue_buffer(
struct smbd_connection *info);
* rqst: the data to write
* return value: 0 if successfully write, otherwise error code
*/
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
+ struct smbd_connection *info = server->smbd_conn;
struct kvec vec;
int nvecs;
int size;
- unsigned int buflen = 0, remaining_data_length;
+ unsigned int buflen, remaining_data_length;
int start, i, j;
int max_iov_size =
info->max_send_size - sizeof(struct smbd_data_transfer);
log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len);
return -EINVAL;
}
- iov = &rqst->rq_iov[1];
-
- /* total up iov array first */
- for (i = 0; i < rqst->rq_nvec-1; i++) {
- buflen += iov[i].iov_len;
- }
/*
* Add in the page array if there is one. The caller needs to set
* rq_tailsz to PAGE_SIZE when the buffer has multiple pages and
* ends at page boundary
*/
- if (rqst->rq_npages) {
- if (rqst->rq_npages == 1)
- buflen += rqst->rq_tailsz;
- else
- buflen += rqst->rq_pagesz * (rqst->rq_npages - 1) -
- rqst->rq_offset + rqst->rq_tailsz;
- }
+ buflen = smb_rqst_len(server, rqst);
if (buflen + sizeof(struct smbd_data_transfer) >
info->max_fragmented_send_size) {
goto done;
}
+ iov = &rqst->rq_iov[1];
+
cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen);
for (i = 0; i < rqst->rq_nvec-1; i++)
dump_smb(iov[i].iov_base, iov[i].iov_len);
/* Interface for carrying upper layer I/O through send/recv */
int smbd_recv(struct smbd_connection *info, struct msghdr *msg);
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst);
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst);
enum mr_state {
MR_READY,
static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; }
static inline void smbd_destroy(struct smbd_connection *info) {}
static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; }
-static inline int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) {return -1; }
+static inline int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) {return -1; }
#endif
#endif
TP_ARGS(xid, tid, sesid, create_options, desired_access, rc))
DEFINE_SMB3_OPEN_ERR_EVENT(open_err);
-
+DEFINE_SMB3_OPEN_ERR_EVENT(posix_mkdir_err);
DECLARE_EVENT_CLASS(smb3_open_done_class,
TP_PROTO(unsigned int xid,
TP_ARGS(xid, fid, tid, sesid, create_options, desired_access))
DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
+DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done);
#endif /* _CIFS_TRACE_H */
temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
memset(temp, 0, sizeof(struct mid_q_entry));
+ kref_init(&temp->refcount);
temp->mid = get_mid(smb_buffer);
temp->pid = current->pid;
temp->command = cpu_to_le16(smb_buffer->Command);
return temp;
}
+static void _cifs_mid_q_entry_release(struct kref *refcount)
+{
+ struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry,
+ refcount);
+
+ mempool_free(mid, cifs_mid_poolp);
+}
+
+void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
+{
+ spin_lock(&GlobalMid_Lock);
+ kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
+ spin_unlock(&GlobalMid_Lock);
+}
+
void
DeleteMidQEntry(struct mid_q_entry *midEntry)
{
}
}
#endif
- mempool_free(midEntry, cifs_mid_poolp);
+ cifs_mid_q_entry_release(midEntry);
}
void
return 0;
}
-static unsigned long
-rqst_len(struct smb_rqst *rqst)
+unsigned long
+smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
unsigned int i;
- struct kvec *iov = rqst->rq_iov;
+ struct kvec *iov;
+ int nvec;
unsigned long buflen = 0;
+ if (server->vals->header_preamble_size == 0 &&
+ rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) {
+ iov = &rqst->rq_iov[1];
+ nvec = rqst->rq_nvec - 1;
+ } else {
+ iov = rqst->rq_iov;
+ nvec = rqst->rq_nvec;
+ }
+
/* total up iov array first */
- for (i = 0; i < rqst->rq_nvec; i++)
+ for (i = 0; i < nvec; i++)
buflen += iov[i].iov_len;
/*
}
static int
-__smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+__smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
+ struct smb_rqst *rqst)
{
- int rc;
- struct kvec *iov = rqst->rq_iov;
- int n_vec = rqst->rq_nvec;
- unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
- unsigned long send_length;
- unsigned int i;
+ int rc = 0;
+ struct kvec *iov;
+ int n_vec;
+ unsigned int send_length = 0;
+ unsigned int i, j;
size_t total_len = 0, sent, size;
struct socket *ssocket = server->ssocket;
struct msghdr smb_msg;
int val = 1;
+ __be32 rfc1002_marker;
+
if (cifs_rdma_enabled(server) && server->smbd_conn) {
- rc = smbd_send(server->smbd_conn, rqst);
+ rc = smbd_send(server, rqst);
goto smbd_done;
}
if (ssocket == NULL)
return -ENOTSOCK;
- /* sanity check send length */
- send_length = rqst_len(rqst);
- if (send_length != smb_buf_length + 4) {
- WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
- send_length, smb_buf_length);
- return -EIO;
- }
-
- if (n_vec < 2)
- return -EIO;
-
- cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
- dump_smb(iov[0].iov_base, iov[0].iov_len);
- dump_smb(iov[1].iov_base, iov[1].iov_len);
-
/* cork the socket */
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
- size = 0;
- for (i = 0; i < n_vec; i++)
- size += iov[i].iov_len;
+ for (j = 0; j < num_rqst; j++)
+ send_length += smb_rqst_len(server, &rqst[j]);
+ rfc1002_marker = cpu_to_be32(send_length);
- iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size);
+ /* Generate a rfc1002 marker for SMB2+ */
+ if (server->vals->header_preamble_size == 0) {
+ struct kvec hiov = {
+ .iov_base = &rfc1002_marker,
+ .iov_len = 4
+ };
+ iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov,
+ 1, 4);
+ rc = smb_send_kvec(server, &smb_msg, &sent);
+ if (rc < 0)
+ goto uncork;
- rc = smb_send_kvec(server, &smb_msg, &sent);
- if (rc < 0)
- goto uncork;
+ total_len += sent;
+ send_length += 4;
+ }
- total_len += sent;
+ cifs_dbg(FYI, "Sending smb: smb_len=%u\n", send_length);
- /* now walk the page array and send each page in it */
- for (i = 0; i < rqst->rq_npages; i++) {
- struct bio_vec bvec;
+ for (j = 0; j < num_rqst; j++) {
+ iov = rqst[j].rq_iov;
+ n_vec = rqst[j].rq_nvec;
+
+ size = 0;
+ for (i = 0; i < n_vec; i++) {
+ dump_smb(iov[i].iov_base, iov[i].iov_len);
+ size += iov[i].iov_len;
+ }
- bvec.bv_page = rqst->rq_pages[i];
- rqst_page_get_length(rqst, i, &bvec.bv_len, &bvec.bv_offset);
+ iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC,
+ iov, n_vec, size);
- iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
- &bvec, 1, bvec.bv_len);
rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
- break;
+ goto uncork;
total_len += sent;
+
+ /* now walk the page array and send each page in it */
+ for (i = 0; i < rqst[j].rq_npages; i++) {
+ struct bio_vec bvec;
+
+ bvec.bv_page = rqst[j].rq_pages[i];
+ rqst_page_get_length(&rqst[j], i, &bvec.bv_len,
+ &bvec.bv_offset);
+
+ iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
+ &bvec, 1, bvec.bv_len);
+ rc = smb_send_kvec(server, &smb_msg, &sent);
+ if (rc < 0)
+ break;
+
+ total_len += sent;
+ }
}
uncork:
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
- if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
+ if ((total_len > 0) && (total_len != send_length)) {
cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n",
- smb_buf_length + 4, total_len);
+ send_length, total_len);
/*
* If we have only sent part of an SMB then the next SMB could
* be taken as the remainder of this one. We need to kill the
int rc;
if (!(flags & CIFS_TRANSFORM_REQ))
- return __smb_send_rqst(server, rqst);
+ return __smb_send_rqst(server, 1, rqst);
if (!server->ops->init_transform_rq ||
!server->ops->free_transform_rq) {
if (rc)
return rc;
- rc = __smb_send_rqst(server, &cur_rqst);
+ rc = __smb_send_rqst(server, 1, &cur_rqst);
server->ops->free_transform_rq(&cur_rqst);
return rc;
}
iov[1].iov_base = (char *)smb_buffer + 4;
iov[1].iov_len = smb_buf_length;
- return __smb_send_rqst(server, &rqst);
+ return __smb_send_rqst(server, 1, &rqst);
}
static int
* to the same server. We may make this configurable later or
* use ses->maxReq.
*/
-
rc = wait_for_free_request(ses->server, timeout, optype);
if (rc)
return rc;
#ifdef CONFIG_CIFS_SMB311
if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
- smb311_update_preauth_hash(ses, rqst->rq_iov+1,
- rqst->rq_nvec-1);
+ smb311_update_preauth_hash(ses, rqst->rq_iov,
+ rqst->rq_nvec);
#endif
if (timeout == CIFS_ASYNC_OP)
#ifdef CONFIG_CIFS_SMB311
if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
struct kvec iov = {
- .iov_base = buf,
- .iov_len = midQ->resp_buf_size
+ .iov_base = resp_iov->iov_base,
+ .iov_len = resp_iov->iov_len
};
smb311_update_preauth_hash(ses, &iov, 1);
}
return rc;
}
-/* Like SendReceive2 but iov[0] does not contain an rfc1002 header */
-int
-smb2_send_recv(const unsigned int xid, struct cifs_ses *ses,
- struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
- const int flags, struct kvec *resp_iov)
-{
- struct smb_rqst rqst;
- struct kvec s_iov[CIFS_MAX_IOV_SIZE], *new_iov;
- int rc;
- int i;
- __u32 count;
- __be32 rfc1002_marker;
-
- if (n_vec + 1 > CIFS_MAX_IOV_SIZE) {
- new_iov = kmalloc_array(n_vec + 1, sizeof(struct kvec),
- GFP_KERNEL);
- if (!new_iov)
- return -ENOMEM;
- } else
- new_iov = s_iov;
-
- /* 1st iov is an RFC1002 Session Message length */
- memcpy(new_iov + 1, iov, (sizeof(struct kvec) * n_vec));
-
- count = 0;
- for (i = 1; i < n_vec + 1; i++)
- count += new_iov[i].iov_len;
-
- rfc1002_marker = cpu_to_be32(count);
-
- new_iov[0].iov_base = &rfc1002_marker;
- new_iov[0].iov_len = 4;
-
- memset(&rqst, 0, sizeof(struct smb_rqst));
- rqst.rq_iov = new_iov;
- rqst.rq_nvec = n_vec + 1;
-
- rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov);
- if (n_vec + 1 > CIFS_MAX_IOV_SIZE)
- kfree(new_iov);
- return rc;
-}
-
int
SendReceive(const unsigned int xid, struct cifs_ses *ses,
struct smb_hdr *in_buf, struct smb_hdr *out_buf,
if (attr->va_size != -1)
inode->i_blocks = (attr->va_size + 511) >> 9;
if (attr->va_atime.tv_sec != -1)
- inode->i_atime = attr->va_atime;
+ inode->i_atime = timespec_to_timespec64(attr->va_atime);
if (attr->va_mtime.tv_sec != -1)
- inode->i_mtime = attr->va_mtime;
+ inode->i_mtime = timespec_to_timespec64(attr->va_mtime);
if (attr->va_ctime.tv_sec != -1)
- inode->i_ctime = attr->va_ctime;
+ inode->i_ctime = timespec_to_timespec64(attr->va_ctime);
}
vattr->va_size = iattr->ia_size;
}
if ( valid & ATTR_ATIME ) {
- vattr->va_atime = iattr->ia_atime;
+ vattr->va_atime = timespec64_to_timespec(iattr->ia_atime);
}
if ( valid & ATTR_MTIME ) {
- vattr->va_mtime = iattr->ia_mtime;
+ vattr->va_mtime = timespec64_to_timespec(iattr->ia_mtime);
}
if ( valid & ATTR_CTIME ) {
- vattr->va_ctime = iattr->ia_ctime;
+ vattr->va_ctime = timespec64_to_timespec(iattr->ia_ctime);
}
}
if (ia_valid & ATTR_GID)
sd_iattr->ia_gid = iattr->ia_gid;
if (ia_valid & ATTR_ATIME)
- sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime,
- inode->i_sb->s_time_gran);
+ sd_iattr->ia_atime = timespec64_trunc(iattr->ia_atime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MTIME)
- sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime,
- inode->i_sb->s_time_gran);
+ sd_iattr->ia_mtime = timespec64_trunc(iattr->ia_mtime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_CTIME)
- sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime,
- inode->i_sb->s_time_gran);
+ sd_iattr->ia_ctime = timespec64_trunc(iattr->ia_ctime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
const struct cramfs_inode *cramfs_inode, unsigned int offset)
{
struct inode *inode;
- static struct timespec zerotime;
+ static struct timespec64 zerotime;
inode = iget_locked(sb, cramino(cramfs_inode, offset));
if (!inode)
__releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
- bool hashed = !d_unhashed(dentry);
- if (hashed)
- raw_write_seqcount_begin(&dentry->d_seq);
+ raw_write_seqcount_begin(&dentry->d_seq);
__d_clear_type_and_inode(dentry);
hlist_del_init(&dentry->d_u.d_alias);
- if (hashed)
- raw_write_seqcount_end(&dentry->d_seq);
+ raw_write_seqcount_end(&dentry->d_seq);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
if (dentry->d_lockref.count > 1) {
dentry->d_lockref.count--;
spin_unlock(&dentry->d_lock);
- return 1;
+ return true;
}
- return 0;
+ return false;
}
/*
* If we weren't the last ref, we're done.
*/
if (ret)
- return 1;
+ return true;
/*
* Careful, careful. The reference count went down
/* Nothing to do? Dropping the reference was all we needed? */
if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
- return 1;
+ return true;
/*
* Not the fast normal case? Get the lock. We've already decremented
*/
if (dentry->d_lockref.count) {
spin_unlock(&dentry->d_lock);
- return 1;
+ return true;
}
/*
* set it to 1.
*/
dentry->d_lockref.count = 1;
- return 0;
+ return false;
}
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
WARN_ON(!(inode->i_state & I_NEW));
- inode->i_state &= ~I_NEW;
+ inode->i_state &= ~I_NEW & ~I_CREATING;
smp_mb();
wake_up_bit(&inode->i_state, __I_NEW);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_instantiate_new);
-/**
- * d_instantiate_no_diralias - instantiate a non-aliased dentry
- * @entry: dentry to complete
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry. If a directory alias is found, then
- * return an error (and drop inode). Together with d_materialise_unique() this
- * guarantees that a directory inode may never have more than one alias.
- */
-int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
-{
- BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
- security_d_instantiate(entry, inode);
- spin_lock(&inode->i_lock);
- if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
- spin_unlock(&inode->i_lock);
- iput(inode);
- return -EBUSY;
- }
- __d_instantiate(entry, inode);
- spin_unlock(&inode->i_lock);
-
- return 0;
-}
-EXPORT_SYMBOL(d_instantiate_no_diralias);
-
struct dentry *d_make_root(struct inode *root_inode)
{
struct dentry *res = NULL;
if (root_inode) {
res = d_alloc_anon(root_inode->i_sb);
- if (res)
+ if (res) {
+ res->d_flags |= DCACHE_RCUACCESS;
d_instantiate(res, root_inode);
- else
+ } else {
iput(root_inode);
+ }
}
return res;
}
}
EXPORT_SYMBOL(d_exact_alias);
-/**
- * dentry_update_name_case - update case insensitive dentry with a new name
- * @dentry: dentry to be updated
- * @name: new name
- *
- * Update a case insensitive dentry with new case of name.
- *
- * dentry must have been returned by d_lookup with name @name. Old and new
- * name lengths must match (ie. no d_compare which allows mismatched name
- * lengths).
- *
- * Parent inode i_mutex must be held over d_lookup and into this call (to
- * keep renames and concurrent inserts, and readdir(2) away).
- */
-void dentry_update_name_case(struct dentry *dentry, const struct qstr *name)
-{
- BUG_ON(!inode_is_locked(dentry->d_parent->d_inode));
- BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
-
- spin_lock(&dentry->d_lock);
- write_seqcount_begin(&dentry->d_seq);
- memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
- write_seqcount_end(&dentry->d_seq);
- spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_update_name_case);
-
static void swap_names(struct dentry *dentry, struct dentry *target)
{
if (unlikely(dname_external(target))) {
/* length of the variable name itself: remove GUID and separator */
namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
- uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+ err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+ if (err)
+ goto out;
if (efivar_variable_is_removable(var->var.VendorGuid,
dentry->d_name.name, namelen))
return 0;
}
-static struct wait_queue_head *
-eventfd_get_poll_head(struct file *file, __poll_t events)
-{
- struct eventfd_ctx *ctx = file->private_data;
-
- return &ctx->wqh;
-}
-
-static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
{
struct eventfd_ctx *ctx = file->private_data;
__poll_t events = 0;
u64 count;
+ poll_wait(file, &ctx->wqh, wait);
+
/*
* All writes to ctx->count occur within ctx->wqh.lock. This read
* can be done outside ctx->wqh.lock because we know that poll_wait
.show_fdinfo = eventfd_show_fdinfo,
#endif
.release = eventfd_release,
- .get_poll_head = eventfd_get_poll_head,
- .poll_mask = eventfd_poll_mask,
+ .poll = eventfd_poll,
.read = eventfd_read,
.write = eventfd_write,
.llseek = noop_llseek,
struct vm_area_struct *vma = NULL;
struct mm_struct *mm = bprm->mm;
- bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ bprm->vma = vma = vm_area_alloc(mm);
if (!vma)
return -ENOMEM;
+ vma_set_anonymous(vma);
if (down_write_killable(&mm->mmap_sem)) {
err = -EINTR;
goto err_free;
}
- vma->vm_mm = mm;
/*
* Place the stack at the largest stack address the architecture
vma->vm_start = vma->vm_end - PAGE_SIZE;
vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
- INIT_LIST_HEAD(&vma->anon_vma_chain);
err = insert_vm_struct(mm, vma);
if (err)
up_write(&mm->mmap_sem);
err_free:
bprm->vma = NULL;
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return err;
}
struct ore_io_state **pios)
{
struct ore_io_state *ios;
- struct page **pages;
- struct osd_sg_entry *sgilist;
+ size_t size_ios, size_extra, size_total;
+ void *ios_extra;
+
+ /*
+ * The desired layout looks like this, with the extra_allocation
+ * items pointed at from fields within ios or per_dev:
+
struct __alloc_all_io_state {
struct ore_io_state ios;
struct ore_per_dev_state per_dev[numdevs];
union {
struct osd_sg_entry sglist[sgs_per_dev * numdevs];
struct page *pages[num_par_pages];
- };
- } *_aios;
-
- if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
- _aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
- if (unlikely(!_aios)) {
- ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
- sizeof(*_aios));
+ } extra_allocation;
+ } whole_allocation;
+
+ */
+
+ /* This should never happen, so abort early if it ever does. */
+ if (sgs_per_dev && num_par_pages) {
+ ORE_DBGMSG("Tried to use both pages and sglist\n");
+ *pios = NULL;
+ return -EINVAL;
+ }
+
+ if (numdevs > (INT_MAX - sizeof(*ios)) /
+ sizeof(struct ore_per_dev_state))
+ return -ENOMEM;
+ size_ios = sizeof(*ios) + sizeof(struct ore_per_dev_state) * numdevs;
+
+ if (sgs_per_dev * numdevs > INT_MAX / sizeof(struct osd_sg_entry))
+ return -ENOMEM;
+ if (num_par_pages > INT_MAX / sizeof(struct page *))
+ return -ENOMEM;
+ size_extra = max(sizeof(struct osd_sg_entry) * (sgs_per_dev * numdevs),
+ sizeof(struct page *) * num_par_pages);
+
+ size_total = size_ios + size_extra;
+
+ if (likely(size_total <= PAGE_SIZE)) {
+ ios = kzalloc(size_total, GFP_KERNEL);
+ if (unlikely(!ios)) {
+ ORE_DBGMSG("Failed kzalloc bytes=%zd\n", size_total);
*pios = NULL;
return -ENOMEM;
}
- pages = num_par_pages ? _aios->pages : NULL;
- sgilist = sgs_per_dev ? _aios->sglist : NULL;
- ios = &_aios->ios;
+ ios_extra = (char *)ios + size_ios;
} else {
- struct __alloc_small_io_state {
- struct ore_io_state ios;
- struct ore_per_dev_state per_dev[numdevs];
- } *_aio_small;
- union __extra_part {
- struct osd_sg_entry sglist[sgs_per_dev * numdevs];
- struct page *pages[num_par_pages];
- } *extra_part;
-
- _aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
- if (unlikely(!_aio_small)) {
+ ios = kzalloc(size_ios, GFP_KERNEL);
+ if (unlikely(!ios)) {
ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
- sizeof(*_aio_small));
+ size_ios);
*pios = NULL;
return -ENOMEM;
}
- extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
- if (unlikely(!extra_part)) {
+ ios_extra = kzalloc(size_extra, GFP_KERNEL);
+ if (unlikely(!ios_extra)) {
ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
- sizeof(*extra_part));
- kfree(_aio_small);
+ size_extra);
+ kfree(ios);
*pios = NULL;
return -ENOMEM;
}
- pages = num_par_pages ? extra_part->pages : NULL;
- sgilist = sgs_per_dev ? extra_part->sglist : NULL;
/* In this case the per_dev[0].sgilist holds the pointer to
* be freed
*/
- ios = &_aio_small->ios;
ios->extra_part_alloc = true;
}
- if (pages) {
- ios->parity_pages = pages;
+ if (num_par_pages) {
+ ios->parity_pages = ios_extra;
ios->max_par_pages = num_par_pages;
}
- if (sgilist) {
+ if (sgs_per_dev) {
+ struct osd_sg_entry *sgilist = ios_extra;
unsigned d;
for (d = 0; d < numdevs; ++d) {
{
struct __stripe_pages_2d *sp2d;
unsigned data_devs = group_width - parity;
+
+ /*
+ * Desired allocation layout is, though when larger than PAGE_SIZE,
+ * each struct __alloc_1p_arrays is separately allocated:
+
struct _alloc_all_bytes {
struct __alloc_stripe_pages_2d {
struct __stripe_pages_2d sp2d;
char page_is_read[data_devs];
} __a1pa[pages_in_unit];
} *_aab;
+
struct __alloc_1p_arrays *__a1pa;
struct __alloc_1p_arrays *__a1pa_end;
- const unsigned sizeof__a1pa = sizeof(_aab->__a1pa[0]);
+
+ */
+
+ char *__a1pa;
+ char *__a1pa_end;
+
+ const size_t sizeof_stripe_pages_2d =
+ sizeof(struct __stripe_pages_2d) +
+ sizeof(struct __1_page_stripe) * pages_in_unit;
+ const size_t sizeof__a1pa =
+ ALIGN(sizeof(struct page *) * (2 * group_width) + data_devs,
+ sizeof(void *));
+ const size_t sizeof__a1pa_arrays = sizeof__a1pa * pages_in_unit;
+ const size_t alloc_total = sizeof_stripe_pages_2d +
+ sizeof__a1pa_arrays;
+
unsigned num_a1pa, alloc_size, i;
/* FIXME: check these numbers in ore_verify_layout */
- BUG_ON(sizeof(_aab->__asp2d) > PAGE_SIZE);
+ BUG_ON(sizeof_stripe_pages_2d > PAGE_SIZE);
BUG_ON(sizeof__a1pa > PAGE_SIZE);
- if (sizeof(*_aab) > PAGE_SIZE) {
- num_a1pa = (PAGE_SIZE - sizeof(_aab->__asp2d)) / sizeof__a1pa;
- alloc_size = sizeof(_aab->__asp2d) + sizeof__a1pa * num_a1pa;
+ /*
+ * If alloc_total would be larger than PAGE_SIZE, only allocate
+ * as many a1pa items as would fill the rest of the page, instead
+ * of the full pages_in_unit count.
+ */
+ if (alloc_total > PAGE_SIZE) {
+ num_a1pa = (PAGE_SIZE - sizeof_stripe_pages_2d) / sizeof__a1pa;
+ alloc_size = sizeof_stripe_pages_2d + sizeof__a1pa * num_a1pa;
} else {
num_a1pa = pages_in_unit;
- alloc_size = sizeof(*_aab);
+ alloc_size = alloc_total;
}
- _aab = kzalloc(alloc_size, GFP_KERNEL);
- if (unlikely(!_aab)) {
+ *psp2d = sp2d = kzalloc(alloc_size, GFP_KERNEL);
+ if (unlikely(!sp2d)) {
ORE_DBGMSG("!! Failed to alloc sp2d size=%d\n", alloc_size);
return -ENOMEM;
}
+ /* From here Just call _sp2d_free */
- sp2d = &_aab->__asp2d.sp2d;
- *psp2d = sp2d; /* From here Just call _sp2d_free */
-
- __a1pa = _aab->__a1pa;
- __a1pa_end = __a1pa + num_a1pa;
+ /* Find start of a1pa area. */
+ __a1pa = (char *)sp2d + sizeof_stripe_pages_2d;
+ /* Find end of the _allocated_ a1pa area. */
+ __a1pa_end = __a1pa + alloc_size;
+ /* Allocate additionally needed a1pa items in PAGE_SIZE chunks. */
for (i = 0; i < pages_in_unit; ++i) {
+ struct __1_page_stripe *stripe = &sp2d->_1p_stripes[i];
+
if (unlikely(__a1pa >= __a1pa_end)) {
num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa,
pages_in_unit - i);
+ alloc_size = sizeof__a1pa * num_a1pa;
- __a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL);
+ __a1pa = kzalloc(alloc_size, GFP_KERNEL);
if (unlikely(!__a1pa)) {
ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n",
num_a1pa);
return -ENOMEM;
}
- __a1pa_end = __a1pa + num_a1pa;
+ __a1pa_end = __a1pa + alloc_size;
/* First *pages is marked for kfree of the buffer */
- sp2d->_1p_stripes[i].alloc = true;
+ stripe->alloc = true;
}
- sp2d->_1p_stripes[i].pages = __a1pa->pages;
- sp2d->_1p_stripes[i].scribble = __a1pa->scribble ;
- sp2d->_1p_stripes[i].page_is_read = __a1pa->page_is_read;
- ++__a1pa;
+ /*
+ * Attach all _lp_stripes pointers to the allocation for
+ * it which was either part of the original PAGE_SIZE
+ * allocation or the subsequent allocation in this loop.
+ */
+ stripe->pages = (void *)__a1pa;
+ stripe->scribble = stripe->pages + group_width;
+ stripe->page_is_read = (char *)stripe->scribble + group_width;
+ __a1pa += sizeof__a1pa;
}
sp2d->parity = parity;
static int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs,
struct exofs_dev **peds)
{
- struct __alloc_ore_devs_and_exofs_devs {
- /* Twice bigger table: See exofs_init_comps() and comment at
- * exofs_read_lookup_dev_table()
- */
- struct ore_dev *oreds[numdevs * 2 - 1];
- struct exofs_dev eds[numdevs];
- } *aoded;
+ /* Twice bigger table: See exofs_init_comps() and comment at
+ * exofs_read_lookup_dev_table()
+ */
+ const size_t numores = numdevs * 2 - 1;
struct exofs_dev *eds;
unsigned i;
- aoded = kzalloc(sizeof(*aoded), GFP_KERNEL);
- if (unlikely(!aoded)) {
+ sbi->oc.ods = kzalloc(numores * sizeof(struct ore_dev *) +
+ numdevs * sizeof(struct exofs_dev), GFP_KERNEL);
+ if (unlikely(!sbi->oc.ods)) {
EXOFS_ERR("ERROR: failed allocating Device array[%d]\n",
numdevs);
return -ENOMEM;
}
- sbi->oc.ods = aoded->oreds;
- *peds = eds = aoded->eds;
+ /* Start of allocated struct exofs_dev entries */
+ *peds = eds = (void *)sbi->oc.ods[numores];
+ /* Initialize pointers into struct exofs_dev */
for (i = 0; i < numdevs; ++i)
- aoded->oreds[i] = &eds[i].ored;
+ sbi->oc.ods[i] = &eds[i].ored;
return 0;
}
unsigned long);
extern unsigned long ext2_count_free_blocks (struct super_block *);
extern unsigned long ext2_count_dirs (struct super_block *);
-extern void ext2_check_blocks_bitmap (struct super_block *);
extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh);
extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
extern void ext2_free_inode (struct inode *);
extern unsigned long ext2_count_free_inodes (struct super_block *);
-extern void ext2_check_inodes_bitmap (struct super_block *);
extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
/* inode.c */
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
clear_nlink(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return ERR_PTR(err);
fail:
return 0;
}
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return err;
}
out_fail:
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput (inode);
+ discard_new_inode(inode);
goto out;
}
out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
out_dir:
inode_dec_link_count(dir);
goto out;
set_opt (opts->s_mount_opt, NO_UID32);
break;
case Opt_nocheck:
+ ext2_msg(sb, KERN_WARNING,
+ "Option nocheck/check=none is deprecated and"
+ " will be removed in June 2020.");
clear_opt (opts->s_mount_opt, CHECK);
break;
case Opt_debug:
new_opts.s_resgid = sbi->s_resgid;
spin_unlock(&sbi->s_lock);
- /*
- * Allow the "check" option to be passed as a remount option.
- */
if (!parse_options(data, sb, &new_opts))
return -EINVAL;
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
- int flex_bg = 0;
J_ASSERT_BH(bh, buffer_locked(bh));
start = ext4_group_first_block_no(sb, block_group);
- if (ext4_has_feature_flex_bg(sb))
- flex_bg = 1;
-
/* Set bits for block and inode bitmaps, and inode table */
tmp = ext4_block_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
}
return -EFSCORRUPTED;
ext4_lock_group(sb, block_group);
+ if (buffer_verified(bh))
+ goto verified;
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
return -EFSCORRUPTED;
}
set_buffer_verified(bh);
+verified:
ext4_unlock_group(sb, block_group);
return 0;
}
goto verify;
}
ext4_lock_group(sb, block_group);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ if (block_group == 0) {
+ ext4_unlock_group(sb, block_group);
+ unlock_buffer(bh);
+ ext4_error(sb, "Block bitmap for bg 0 marked "
+ "uninitialized");
+ err = -EFSCORRUPTED;
+ goto out;
+ }
err = ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
}
-#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
-do { \
- (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
- if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
- (raw_inode)->xtime ## _extra = \
- ext4_encode_extra_time(&(inode)->xtime); \
+#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
+do { \
+ (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
+ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\
+ struct timespec ts = timespec64_to_timespec((inode)->xtime); \
+ (raw_inode)->xtime ## _extra = \
+ ext4_encode_extra_time(&ts); \
+ } \
} while (0)
#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \
ext4_encode_extra_time(&(einode)->xtime); \
} while (0)
-#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
-do { \
- (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \
- if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
- ext4_decode_extra_time(&(inode)->xtime, \
- raw_inode->xtime ## _extra); \
- else \
- (inode)->xtime.tv_nsec = 0; \
+#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
+do { \
+ (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \
+ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \
+ struct timespec ts = timespec64_to_timespec((inode)->xtime); \
+ ext4_decode_extra_time(&ts, \
+ raw_inode->xtime ## _extra); \
+ (inode)->xtime = timespec_to_timespec64(ts); \
+ } \
+ else \
+ (inode)->xtime.tv_nsec = 0; \
} while (0)
+
#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
do { \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
{
return ino == EXT4_ROOT_INO ||
- ino == EXT4_USR_QUOTA_INO ||
- ino == EXT4_GRP_QUOTA_INO ||
- ino == EXT4_BOOT_LOADER_INO ||
- ino == EXT4_JOURNAL_INO ||
- ino == EXT4_RESIZE_INO ||
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
struct iomap;
extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
-extern int ext4_try_to_evict_inline_data(handle_t *handle,
- struct inode *inode,
- int needed);
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
extern int ext4_convert_inline_data(struct inode *inode);
};
#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
#define EXT4_EXTENT_TAIL_OFFSET(hdr) \
(sizeof(struct ext4_extent_header) + \
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
+ if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) {
+ EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d",
+ depth);
+ ret = -EFSCORRUPTED;
+ goto err;
+ }
if (path) {
ext4_ext_drop_refs(path);
return -EFSCORRUPTED;
ext4_lock_group(sb, block_group);
+ if (buffer_verified(bh))
+ goto verified;
blk = ext4_inode_bitmap(sb, desc);
if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
EXT4_INODES_PER_GROUP(sb) / 8)) {
return -EFSBADCRC;
}
set_buffer_verified(bh);
+verified:
ext4_unlock_group(sb, block_group);
return 0;
}
}
ext4_lock_group(sb, block_group);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+ if (block_group == 0) {
+ ext4_unlock_group(sb, block_group);
+ unlock_buffer(bh);
+ ext4_error(sb, "Inode bitmap for bg 0 marked "
+ "uninitialized");
+ err = -EFSCORRUPTED;
+ goto out;
+ }
memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
sb->s_blocksize * 8, bh->b_data);
/* recheck and clear flag under lock if we still need to */
ext4_lock_group(sb, group);
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
ext4_free_group_clusters_set(sb, gdp,
ext4_free_clusters_after_init(sb, group, gdp));
inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
- current_time(inode);
+ inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+ ei->i_crtime = timespec64_to_timespec(inode->i_mtime);
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ext4_itable_unused_count(sb, gdp)),
sbi->s_inodes_per_block);
- if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+ if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
+ ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp)) <
+ EXT4_FIRST_INO(sb)))) {
ext4_error(sb, "Something is wrong with group %u: "
"used itable blocks: %d; "
"itable unused count: %u",
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
+ memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) {
if (S_ISDIR(inode->i_mode) ||
goto convert;
}
+ ret = ext4_journal_get_write_access(handle, iloc.bh);
+ if (ret)
+ goto out;
+
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, 0, flags);
out_up_read:
up_read(&EXT4_I(inode)->xattr_sem);
out:
- if (handle)
+ if (handle && (ret != 1))
ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
ext4_write_unlock_xattr(inode, &no_expand);
brelse(iloc.bh);
+ mark_inode_dirty(inode);
out:
return copied;
}
flags |= AOP_FLAG_NOFS;
if (ret == -ENOSPC) {
+ ext4_journal_stop(handle);
ret = ext4_da_convert_inline_data_to_extent(mapping,
inode,
flags,
fsdata);
- ext4_journal_stop(handle);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
goto out;
}
-
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
if (ret < 0)
goto out_release_page;
}
+ ret = ext4_journal_get_write_access(handle, iloc.bh);
+ if (ret)
+ goto out_release_page;
up_read(&EXT4_I(inode)->xattr_sem);
*pagep = page;
unsigned len, unsigned copied,
struct page *page)
{
- int i_size_changed = 0;
int ret;
ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
* But it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
- if (pos+copied > inode->i_size) {
+ if (pos+copied > inode->i_size)
i_size_write(inode, pos+copied);
- i_size_changed = 1;
- }
unlock_page(page);
put_page(page);
* ordering of page lock and transaction start for journaling
* filesystems.
*/
- if (i_size_changed)
- mark_inode_dirty(inode);
+ mark_inode_dirty(inode);
return copied;
}
return (error < 0 ? error : 0);
}
-/*
- * Called during xattr set, and if we can sparse space 'needed',
- * just create the extent tree evict the data to the outer block.
- *
- * We use jbd2 instead of page cache to move data to the 1st block
- * so that the whole transaction can be committed as a whole and
- * the data isn't lost because of the delayed page cache write.
- */
-int ext4_try_to_evict_inline_data(handle_t *handle,
- struct inode *inode,
- int needed)
-{
- int error;
- struct ext4_xattr_entry *entry;
- struct ext4_inode *raw_inode;
- struct ext4_iloc iloc;
-
- error = ext4_get_inode_loc(inode, &iloc);
- if (error)
- return error;
-
- raw_inode = ext4_raw_inode(&iloc);
- entry = (struct ext4_xattr_entry *)((void *)raw_inode +
- EXT4_I(inode)->i_inline_off);
- if (EXT4_XATTR_LEN(entry->e_name_len) +
- EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
- error = -ENOSPC;
- goto out;
- }
-
- error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-out:
- brelse(iloc.bh);
- return error;
-}
-
int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
- "lblock %lu mapped to illegal pblock "
+ "lblock %lu mapped to illegal pblock %llu "
"(length %d)", (unsigned long) map->m_lblk,
- map->m_len);
+ map->m_pblk, map->m_len);
return -EFSCORRUPTED;
}
return 0;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
+ int inline_data = ext4_has_inline_data(inode);
trace_ext4_write_end(inode, pos, len, copied);
- if (ext4_has_inline_data(inode)) {
+ if (inline_data) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
* ordering of page lock and transaction start for journaling
* filesystems.
*/
- if (i_size_changed)
+ if (i_size_changed || inline_data)
ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && ext4_can_truncate(inode))
int partial = 0;
unsigned from, to;
int size_changed = 0;
+ int inline_data = ext4_has_inline_data(inode);
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
BUG_ON(!ext4_handle_valid(handle));
- if (ext4_has_inline_data(inode)) {
+ if (inline_data) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
- if (size_changed) {
+ if (size_changed || inline_data) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
if (inline_data) {
- BUFFER_TRACE(inode_bh, "get write access");
- ret = ext4_journal_get_write_access(handle, inode_bh);
-
- err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
-
+ ret = ext4_mark_inode_dirty(handle, inode);
} else {
ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
int inodes_per_block, inode_offset;
iloc->bh = NULL;
- if (!ext4_valid_inum(sb, inode->i_ino))
+ if (inode->i_ino < EXT4_ROOT_INO ||
+ inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return -EFSCORRUPTED;
iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
* initialize bb_free to be able to skip
* empty groups without initialization
*/
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
meta_group_info[i]->bb_free =
ext4_free_clusters_after_init(sb, group, desc);
} else {
#endif
ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
ext4_free_group_clusters_set(sb, gdp,
ext4_free_clusters_after_init(sb,
goto exit_thread;
}
- if (sb_rdonly(sb)) {
- ext4_warning(sb, "kmmpd being stopped since filesystem "
- "has been remounted as readonly.");
- goto exit_thread;
- }
+ if (sb_rdonly(sb))
+ break;
diff = jiffies - last_update_time;
if (diff < mmp_update_interval * HZ)
};
u8 new_file_type;
int retval;
- struct timespec ctime;
+ struct timespec64 ctime;
if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) &&
!projid_eq(EXT4_I(new_dir)->i_projid,
static void ext4_handle_error(struct super_block *sb)
{
+ if (test_opt(sb, WARN_ON_ERROR))
+ WARN_ON_ONCE(1);
+
if (sb_rdonly(sb))
return;
va_end(args);
}
+ if (test_opt(sb, WARN_ON_ERROR))
+ WARN_ON_ONCE(1);
+
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
return;
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
- Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+ Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
+ Opt_nowarn_on_error, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
{Opt_dax, "dax"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
+ {Opt_warn_on_error, "warn_on_error"},
+ {Opt_nowarn_on_error, "nowarn_on_error"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_CLEAR},
+ {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
+ {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
ext4_fsblk_t last_block;
+ ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0);
ext4_fsblk_t block_bitmap;
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
if (!sb_rdonly(sb))
return 0;
}
+ if (block_bitmap >= sb_block + 1 &&
+ block_bitmap <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
if (!sb_rdonly(sb))
return 0;
}
+ if (inode_bitmap >= sb_block + 1 &&
+ inode_bitmap <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
if (!sb_rdonly(sb))
return 0;
}
+ if (inode_table >= sb_block + 1 &&
+ inode_table <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *gdp = NULL;
+ if (!ext4_has_group_desc_csum(sb))
+ return ngroups;
+
for (group = 0; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp)
le32_to_cpu(es->s_log_block_size));
goto failed_mount;
}
+ if (le32_to_cpu(es->s_log_cluster_size) >
+ (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+ ext4_msg(sb, KERN_ERR,
+ "Invalid log cluster size: %u",
+ le32_to_cpu(es->s_log_cluster_size));
+ goto failed_mount;
+ }
if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
ext4_msg(sb, KERN_ERR,
} else {
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+ if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+ ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+ sbi->s_first_ino);
+ goto failed_mount;
+ }
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
(!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
"block size (%d)", clustersize, blocksize);
goto failed_mount;
}
- if (le32_to_cpu(es->s_log_cluster_size) >
- (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
- ext4_msg(sb, KERN_ERR,
- "Invalid log cluster size: %u",
- le32_to_cpu(es->s_log_cluster_size));
- goto failed_mount;
- }
sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
le32_to_cpu(es->s_log_block_size);
sbi->s_clusters_per_group =
}
} else {
if (clustersize != blocksize) {
- ext4_warning(sb, "fragment/cluster size (%d) != "
- "block size (%d)", clustersize,
- blocksize);
- clustersize = blocksize;
+ ext4_msg(sb, KERN_ERR,
+ "fragment/cluster size (%d) != "
+ "block size (%d)", clustersize, blocksize);
+ goto failed_mount;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
ext4_blocks_count(es));
goto failed_mount;
}
+ if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) &&
+ (sbi->s_cluster_ratio == 1)) {
+ ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
+ "block is 0 with a 1k block and cluster size");
+ goto failed_mount;
+ }
+
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
ret = -ENOMEM;
goto failed_mount;
}
+ if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+ le32_to_cpu(es->s_inodes_count)) {
+ ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+ le32_to_cpu(es->s_inodes_count),
+ ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+ ret = -EINVAL;
+ goto failed_mount;
+ }
bgl_lock_init(sbi->s_blockgroup_lock);
goto failed_mount2;
}
}
+ sbi->s_gdb_count = db_count;
if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
}
- sbi->s_gdb_count = db_count;
-
timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
/* Register extent status tree shrinker */
if (!sbh || block_device_ejected(sb))
return error;
+
+ /*
+ * The superblock bh should be mapped, but it might not be if the
+ * device was hot-removed. Not much we can do but fail the I/O.
+ */
+ if (!buffer_mapped(sbh))
+ return error;
+
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
} else {
/* Make sure we can mount this feature set readwrite */
if (ext4_has_feature_readonly(sb) ||
{
int error = -EFSCORRUPTED;
- if (buffer_verified(bh))
- return 0;
-
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
goto errout;
+ if (buffer_verified(bh))
+ return 0;
+
error = -EFSBADCRC;
if (!ext4_xattr_block_csum_verify(inode, bh))
goto errout;
handle_t *handle, struct inode *inode,
bool is_block)
{
- struct ext4_xattr_entry *last;
+ struct ext4_xattr_entry *last, *next;
struct ext4_xattr_entry *here = s->here;
size_t min_offs = s->end - s->base, name_len = strlen(i->name);
int in_inode = i->in_inode;
/* Compute min_offs and last. */
last = s->first;
- for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ for (; !IS_LAST_ENTRY(last); last = next) {
+ next = EXT4_XATTR_NEXT(last);
+ if ((void *)next >= s->end) {
+ EXT4_ERROR_INODE(inode, "corrupted xattr entries");
+ ret = -EFSCORRUPTED;
+ goto out;
+ }
if (!last->e_value_inum && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
- if (error) {
- if (error == -ENOSPC &&
- ext4_has_inline_data(inode)) {
- error = ext4_try_to_evict_inline_data(handle, inode,
- EXT4_XATTR_LEN(strlen(i->name) +
- EXT4_XATTR_SIZE(i->value_len)));
- if (error)
- return error;
- error = ext4_xattr_ibody_find(inode, i, is);
- if (error)
- return error;
- error = ext4_xattr_set_entry(i, s, handle, inode,
- false /* is_block */);
- }
- if (error)
- return error;
- }
+ if (error)
+ return error;
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
last = IFIRST(header);
/* Find the entry best suited to be pushed into EA block */
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ /* never move system.data out of the inode */
+ if ((last->e_name_len == 4) &&
+ (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) &&
+ !memcmp(last->e_name, "data", 4))
+ continue;
total_size = EXT4_XATTR_LEN(last->e_name_len);
if (!last->e_value_inum)
total_size += EXT4_XATTR_SIZE(
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
+ struct timespec ts;
bool ret;
if (dsync) {
i_size_read(inode) & ~PAGE_MASK)
return false;
- if (!timespec_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
+ ts = timespec64_to_timespec(inode->i_atime);
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time, &ts))
return false;
- if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
+ ts = timespec64_to_timespec(inode->i_ctime);
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &ts))
return false;
- if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
+ ts = timespec64_to_timespec(inode->i_mtime);
+ if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &ts))
return false;
if (!timespec_equal(F2FS_I(inode)->i_disk_time + 3,
&F2FS_I(inode)->i_crtime))
if (ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
if (ia_valid & ATTR_ATIME)
- inode->i_atime = timespec_trunc(attr->ia_atime,
- inode->i_sb->s_time_gran);
+ inode->i_atime = timespec64_trunc(attr->ia_atime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MTIME)
- inode->i_mtime = timespec_trunc(attr->ia_mtime,
- inode->i_sb->s_time_gran);
+ inode->i_mtime = timespec64_trunc(attr->ia_mtime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_CTIME)
- inode->i_ctime = timespec_trunc(attr->ia_ctime,
- inode->i_sb->s_time_gran);
+ inode->i_ctime = timespec64_trunc(attr->ia_ctime,
+ inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
}
- F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
- F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
- F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
+ F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime);
+ F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime);
+ F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime);
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
f2fs_put_page(node_page, 1);
if (inode->i_nlink == 0)
clear_inline_node(node_page);
- F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
- F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
- F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
+ F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime);
+ F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime);
+ F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime);
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
}
inode->i_ino = ino;
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime =
- F2FS_I(inode)->i_crtime = current_time(inode);
+ inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+ F2FS_I(inode)->i_crtime = timespec64_to_timespec(inode->i_mtime);
inode->i_generation = sbi->s_next_generation++;
if (S_ISDIR(inode->i_mode))
err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
if (err)
return err;
+ if (!phys) {
+ fat_fs_error(sb,
+ "invalid FAT chain (i_pos %lld, last_block %llu)",
+ MSDOS_I(inode)->i_pos,
+ (unsigned long long)last_block);
+ return -EIO;
+ }
- BUG_ON(!phys);
BUG_ON(*max_blocks != mapped_blocks);
set_buffer_new(bh_result);
map_bh(bh_result, sb, phys);
/* doesn't deal with root inode */
int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
+ struct timespec ts;
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
int error;
inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
& ~((loff_t)sbi->cluster_size - 1)) >> 9;
- fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0);
+ fat_time_fat2unix(sbi, &ts, de->time, de->date, 0);
+ inode->i_mtime = timespec_to_timespec64(ts);
if (sbi->options.isvfat) {
- fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime,
+ fat_time_fat2unix(sbi, &ts, de->ctime,
de->cdate, de->ctime_cs);
- fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0);
+ inode->i_ctime = timespec_to_timespec64(ts);
+ fat_time_fat2unix(sbi, &ts, 0, de->adate, 0);
+ inode->i_atime = timespec_to_timespec64(ts);
} else
inode->i_ctime = inode->i_atime = inode->i_mtime;
brelse(bh);
}
+static void fat_reset_iocharset(struct fat_mount_options *opts)
+{
+ if (opts->iocharset != fat_default_iocharset) {
+ /* Note: opts->iocharset can be NULL here */
+ kfree(opts->iocharset);
+ opts->iocharset = fat_default_iocharset;
+ }
+}
+
static void delayed_free(struct rcu_head *p)
{
struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu);
unload_nls(sbi->nls_disk);
unload_nls(sbi->nls_io);
- if (sbi->options.iocharset != fat_default_iocharset)
- kfree(sbi->options.iocharset);
+ fat_reset_iocharset(&sbi->options);
kfree(sbi);
}
static int __fat_write_inode(struct inode *inode, int wait)
{
+ struct timespec ts;
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct buffer_head *bh;
raw_entry->size = cpu_to_le32(inode->i_size);
raw_entry->attr = fat_make_attrs(inode);
fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart);
- fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time,
+ ts = timespec64_to_timespec(inode->i_mtime);
+ fat_time_unix2fat(sbi, &ts, &raw_entry->time,
&raw_entry->date, NULL);
if (sbi->options.isvfat) {
__le16 atime;
- fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime,
+ ts = timespec64_to_timespec(inode->i_ctime);
+ fat_time_unix2fat(sbi, &ts, &raw_entry->ctime,
&raw_entry->cdate, &raw_entry->ctime_cs);
- fat_time_unix2fat(sbi, &inode->i_atime, &atime,
+ ts = timespec64_to_timespec(inode->i_atime);
+ fat_time_unix2fat(sbi, &ts, &atime,
&raw_entry->adate, NULL);
}
spin_unlock(&sbi->inode_hash_lock);
opts->fs_fmask = opts->fs_dmask = current_umask();
opts->allow_utime = -1;
opts->codepage = fat_default_codepage;
- opts->iocharset = fat_default_iocharset;
+ fat_reset_iocharset(opts);
if (is_vfat) {
opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95;
opts->rodir = 0;
/* vfat specific */
case Opt_charset:
- if (opts->iocharset != fat_default_iocharset)
- kfree(opts->iocharset);
+ fat_reset_iocharset(opts);
iocharset = match_strdup(&args[0]);
if (!iocharset)
return -ENOMEM;
iput(fat_inode);
unload_nls(sbi->nls_io);
unload_nls(sbi->nls_disk);
- if (sbi->options.iocharset != fat_default_iocharset)
- kfree(sbi->options.iocharset);
+ fat_reset_iocharset(&sbi->options);
sb->s_fs_info = NULL;
kfree(sbi);
return error;
if (err)
return err;
- dir->i_ctime = dir->i_mtime = *ts;
+ dir->i_ctime = dir->i_mtime = timespec_to_timespec64(*ts);
if (IS_DIRSYNC(dir))
(void)fat_sync_inode(dir);
else
struct super_block *sb = dir->i_sb;
struct inode *inode = NULL;
struct fat_slot_info sinfo;
- struct timespec ts;
+ struct timespec64 ts;
+ struct timespec t;
unsigned char msdos_name[MSDOS_NAME];
int err, is_hid;
}
ts = current_time(dir);
- err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &ts, &sinfo);
+ t = timespec64_to_timespec(ts);
+ err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &t, &sinfo);
if (err)
goto out;
inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
struct fat_slot_info sinfo;
struct inode *inode;
unsigned char msdos_name[MSDOS_NAME];
- struct timespec ts;
+ struct timespec64 ts;
+ struct timespec t;
int err, is_hid, cluster;
mutex_lock(&MSDOS_SB(sb)->s_lock);
}
ts = current_time(dir);
- cluster = fat_alloc_new_dir(dir, &ts);
+ t = timespec64_to_timespec(ts);
+ cluster = fat_alloc_new_dir(dir, &t);
if (cluster < 0) {
err = cluster;
goto out;
}
- err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo);
+ err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &t, &sinfo);
if (err)
goto out_free;
inc_nlink(dir);
struct msdos_dir_entry *dotdot_de;
struct inode *old_inode, *new_inode;
struct fat_slot_info old_sinfo, sinfo;
- struct timespec ts;
+ struct timespec64 ts;
loff_t new_i_pos;
int err, old_attrs, is_dir, update_dotdot, corrupt = 0;
new_i_pos = MSDOS_I(new_inode)->i_pos;
fat_detach(new_inode);
} else {
+ struct timespec t = timespec64_to_timespec(ts);
err = msdos_add_entry(new_dir, new_name, is_dir, is_hid, 0,
- &ts, &sinfo);
+ &t, &sinfo);
if (err)
goto out;
new_i_pos = sinfo.i_pos;
goto cleanup;
/* update timestamp */
- dir->i_ctime = dir->i_mtime = dir->i_atime = *ts;
+ dir->i_ctime = dir->i_mtime = dir->i_atime = timespec_to_timespec64(*ts);
if (IS_DIRSYNC(dir))
(void)fat_sync_inode(dir);
else
struct super_block *sb = dir->i_sb;
struct inode *inode;
struct fat_slot_info sinfo;
- struct timespec ts;
+ struct timespec64 ts;
+ struct timespec t;
int err;
mutex_lock(&MSDOS_SB(sb)->s_lock);
ts = current_time(dir);
- err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo);
+ t = timespec64_to_timespec(ts);
+ err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &t, &sinfo);
if (err)
goto out;
inode_inc_iversion(dir);
struct super_block *sb = dir->i_sb;
struct inode *inode;
struct fat_slot_info sinfo;
- struct timespec ts;
+ struct timespec64 ts;
+ struct timespec t;
int err, cluster;
mutex_lock(&MSDOS_SB(sb)->s_lock);
ts = current_time(dir);
- cluster = fat_alloc_new_dir(dir, &ts);
+ t = timespec64_to_timespec(ts);
+ cluster = fat_alloc_new_dir(dir, &t);
if (cluster < 0) {
err = cluster;
goto out;
}
- err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo);
+ err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &t, &sinfo);
if (err)
goto out_free;
inode_inc_iversion(dir);
struct msdos_dir_entry *dotdot_de;
struct inode *old_inode, *new_inode;
struct fat_slot_info old_sinfo, sinfo;
- struct timespec ts;
+ struct timespec64 ts;
+ struct timespec t;
loff_t new_i_pos;
int err, is_dir, update_dotdot, corrupt = 0;
struct super_block *sb = old_dir->i_sb;
new_i_pos = MSDOS_I(new_inode)->i_pos;
fat_detach(new_inode);
} else {
+ t = timespec64_to_timespec(ts);
err = vfat_add_entry(new_dir, &new_dentry->d_name, is_dir, 0,
- &ts, &sinfo);
+ &t, &sinfo);
if (err)
goto out;
new_i_pos = sinfo.i_pos;
static inline void file_free(struct file *f)
{
+ security_file_free(f);
percpu_counter_dec(&nr_files);
call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}
* done, you will imbalance int the mount's writer count
* and a warning at __fput() time.
*/
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
{
- const struct cred *cred = current_cred();
static long old_max;
struct file *f;
int error;
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
- percpu_counter_inc(&nr_files);
f->f_cred = get_cred(cred);
error = security_file_alloc(f);
if (unlikely(error)) {
- file_free(f);
+ file_free_rcu(&f->f_u.fu_rcuhead);
return ERR_PTR(error);
}
spin_lock_init(&f->f_lock);
mutex_init(&f->f_pos_lock);
eventpoll_init_file(f);
+ f->f_flags = flags;
+ f->f_mode = OPEN_FMODE(flags);
/* f->f_version: 0 */
+ percpu_counter_inc(&nr_files);
return f;
over:
* alloc_file - allocate and initialize a 'struct file'
*
* @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
* @fop: the 'struct file_operations' for the new file
*/
-struct file *alloc_file(const struct path *path, fmode_t mode,
+static struct file *alloc_file(const struct path *path, int flags,
const struct file_operations *fop)
{
struct file *file;
- file = get_empty_filp();
+ file = alloc_empty_file(flags, current_cred());
if (IS_ERR(file))
return file;
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
- if ((mode & FMODE_READ) &&
+ if ((file->f_mode & FMODE_READ) &&
likely(fop->read || fop->read_iter))
- mode |= FMODE_CAN_READ;
- if ((mode & FMODE_WRITE) &&
+ file->f_mode |= FMODE_CAN_READ;
+ if ((file->f_mode & FMODE_WRITE) &&
likely(fop->write || fop->write_iter))
- mode |= FMODE_CAN_WRITE;
- file->f_mode = mode;
+ file->f_mode |= FMODE_CAN_WRITE;
+ file->f_mode |= FMODE_OPENED;
file->f_op = fop;
- if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+ if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(path->dentry->d_inode);
return file;
}
-EXPORT_SYMBOL(alloc_file);
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+ const char *name, int flags,
+ const struct file_operations *fops)
+{
+ static const struct dentry_operations anon_ops = {
+ .d_dname = simple_dname
+ };
+ struct qstr this = QSTR_INIT(name, strlen(name));
+ struct path path;
+ struct file *file;
+
+ path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+ if (!path.dentry)
+ return ERR_PTR(-ENOMEM);
+ if (!mnt->mnt_sb->s_d_op)
+ d_set_d_op(path.dentry, &anon_ops);
+ path.mnt = mntget(mnt);
+ d_instantiate(path.dentry, inode);
+ file = alloc_file(&path, flags, fops);
+ if (IS_ERR(file)) {
+ ihold(inode);
+ path_put(&path);
+ }
+ return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+ const struct file_operations *fops)
+{
+ struct file *f = alloc_file(&base->f_path, flags, fops);
+ if (!IS_ERR(f)) {
+ path_get(&f->f_path);
+ f->f_mapping = base->f_mapping;
+ }
+ return f;
+}
/* the real guts of fput() - releasing the last reference to file
*/
struct vfsmount *mnt = file->f_path.mnt;
struct inode *inode = file->f_inode;
+ if (unlikely(!(file->f_mode & FMODE_OPENED)))
+ goto out;
+
might_sleep();
fsnotify_close(file);
}
if (file->f_op->release)
file->f_op->release(inode, file);
- security_file_free(file);
if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
!(file->f_mode & FMODE_PATH))) {
cdev_put(inode->i_cdev);
put_write_access(inode);
__mnt_drop_write(mnt);
}
- file->f_path.dentry = NULL;
- file->f_path.mnt = NULL;
- file->f_inode = NULL;
- file_free(file);
dput(dentry);
mntput(mnt);
+out:
+ file_free(file);
}
static LLIST_HEAD(delayed_fput_list);
EXPORT_SYMBOL(fput);
-void put_filp(struct file *file)
-{
- if (atomic_long_dec_and_test(&file->f_count)) {
- security_file_free(file);
- file_free(file);
- }
-}
-
void __init files_init(void)
{
filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
{
struct fscache_cache_tag *tag;
+ ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index);
BUG_ON(!cache->ops);
BUG_ON(!ifsdef);
if (!cache->kobj)
goto error;
- ifsdef->cookie = &fscache_fsdef_index;
ifsdef->cache = cache;
cache->fsdef = ifsdef;
goto error;
}
+ ASSERTCMP(object->cookie, ==, cookie);
fscache_stat(&fscache_n_object_alloc);
object->debug_id = atomic_inc_return(&fscache_object_debug_id);
_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
+ ASSERTCMP(object->cookie, ==, cookie);
+
spin_lock(&cookie->lock);
/* there may be multiple initial creations of this object, but we only
spin_unlock(&cache->object_list_lock);
}
- /* attach to the cookie */
- object->cookie = cookie;
- fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
+ /* Attach to the cookie. The object already has a ref on it. */
hlist_add_head(&object->cookie_link, &cookie->backing_objects);
fscache_objlist_add(object);
object->store_limit_l = 0;
object->cache = cache;
object->cookie = cookie;
+ fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
object->parent = NULL;
#ifdef CONFIG_FSCACHE_OBJECT_LIST
RB_CLEAR_NODE(&object->objlist_link);
ASSERT(op->processor != NULL);
ASSERT(fscache_object_is_available(op->object));
ASSERTCMP(atomic_read(&op->usage), >, 0);
- ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+ ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS,
+ op->state, ==, FSCACHE_OP_ST_CANCELLED);
fscache_stat(&fscache_n_op_enqueue);
switch (op->flags & FSCACHE_OP_TYPE) {
struct fscache_cache *cache;
_enter("{OBJ%x OP%x,%d}",
- op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+ op->object ? op->object->debug_id : 0,
+ op->debug_id, atomic_read(&op->usage));
ASSERTCMP(atomic_read(&op->usage), >, 0);
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned flags,
- umode_t mode, int *opened)
+ umode_t mode)
{
int err;
struct inode *inode;
d_instantiate(entry, inode);
fuse_change_entry_timeout(entry, &outentry);
fuse_invalidate_attr(dir);
- err = finish_open(file, entry, generic_file_open, opened);
+ err = finish_open(file, entry, generic_file_open);
if (err) {
fuse_sync_release(ff, flags);
} else {
static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned flags,
- umode_t mode, int *opened)
+ umode_t mode)
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
goto no_open;
/* Only creates */
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
if (fc->no_create)
goto mknod;
- err = fuse_create_open(dir, entry, file, flags, mode, opened);
+ err = fuse_create_open(dir, entry, file, flags, mode);
if (err == -ENOSYS) {
fc->no_create = 1;
goto mknod;
{
struct fuse_entry_out outarg;
struct inode *inode;
+ struct dentry *d;
int err;
struct fuse_forget_link *forget;
}
kfree(forget);
- err = d_instantiate_no_diralias(entry, inode);
- if (err)
- return err;
+ d_drop(entry);
+ d = d_splice_alias(inode, entry);
+ if (IS_ERR(d))
+ return PTR_ERR(d);
- fuse_change_entry_timeout(entry, &outarg);
+ if (d) {
+ fuse_change_entry_timeout(d, &outarg);
+ dput(d);
+ } else {
+ fuse_change_entry_timeout(entry, &outarg);
+ }
fuse_invalidate_attr(dir);
return 0;
return;
}
- old_mtime = inode->i_mtime;
+ old_mtime = timespec64_to_timespec(inode->i_mtime);
fuse_change_attributes_common(inode, attr, attr_valid);
oldsize = inode->i_size;
struct buffer_head *bh;
struct gfs2_leaf *leaf;
struct gfs2_dirent *dent;
- struct timespec tv = current_time(inode);
+ struct timespec64 tv = current_time(inode);
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *bh = da->bh;
struct gfs2_dirent *dent = da->dent;
- struct timespec tv;
+ struct timespec64 tv;
struct gfs2_leaf *leaf;
int error;
const struct qstr *name = &dentry->d_name;
struct gfs2_dirent *dent, *prev = NULL;
struct buffer_head *bh;
- struct timespec tv = current_time(&dip->i_inode);
+ struct timespec64 tv = current_time(&dip->i_inode);
/* Returns _either_ the entry (if its first in block) or the
previous entry otherwise */
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
const struct gfs2_dinode *str = buf;
- struct timespec atime;
+ struct timespec64 atime;
u16 height, depth;
if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
atime.tv_sec = be64_to_cpu(str->di_atime);
atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
- if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+ if (timespec64_compare(&ip->i_inode.i_atime, &atime) < 0)
ip->i_inode.i_atime = atime;
ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
struct file *file,
umode_t mode, dev_t dev, const char *symname,
- unsigned int size, int excl, int *opened)
+ unsigned int size, int excl)
{
const struct qstr *name = &dentry->d_name;
struct posix_acl *default_acl, *acl;
error = 0;
if (file) {
if (S_ISREG(inode->i_mode))
- error = finish_open(file, dentry, gfs2_open_common, opened);
+ error = finish_open(file, dentry, gfs2_open_common);
else
error = finish_no_open(file, NULL);
}
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
if (file) {
- *opened |= FILE_CREATED;
- error = finish_open(file, dentry, gfs2_open_common, opened);
+ file->f_mode |= FMODE_CREATED;
+ error = finish_open(file, dentry, gfs2_open_common);
}
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
static int gfs2_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool excl)
{
- return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
+ return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
}
/**
* @dir: The directory inode
* @dentry: The dentry of the new inode
* @file: File to be opened
- * @opened: atomic_open flags
*
*
* Returns: errno
*/
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct file *file, int *opened)
+ struct file *file)
{
struct inode *inode;
struct dentry *d;
return d;
}
if (file && S_ISREG(inode->i_mode))
- error = finish_open(file, dentry, gfs2_open_common, opened);
+ error = finish_open(file, dentry, gfs2_open_common);
gfs2_glock_dq_uninit(&gh);
if (error) {
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
unsigned flags)
{
- return __gfs2_lookup(dir, dentry, NULL, NULL);
+ return __gfs2_lookup(dir, dentry, NULL);
}
/**
if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
return -ENAMETOOLONG;
- return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0, NULL);
+ return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
}
/**
static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
- return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0, NULL);
+ return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
}
/**
static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
dev_t dev)
{
- return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0, NULL);
+ return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
}
/**
* @file: The proposed new struct file
* @flags: open flags
* @mode: File mode
- * @opened: Flag to say whether the file has been opened or not
*
* Returns: error code or 0 for success
*/
static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags,
- umode_t mode, int *opened)
+ umode_t mode)
{
struct dentry *d;
bool excl = !!(flags & O_EXCL);
if (!d_in_lookup(dentry))
goto skip_lookup;
- d = __gfs2_lookup(dir, dentry, file, opened);
+ d = __gfs2_lookup(dir, dentry, file);
if (IS_ERR(d))
return PTR_ERR(d);
if (d != NULL)
dentry = d;
if (d_really_is_positive(dentry)) {
- if (!(*opened & FILE_OPENED))
+ if (!(file->f_mode & FMODE_OPENED))
return finish_no_open(file, d);
dput(d);
return 0;
if (!(flags & O_CREAT))
return -ENOENT;
- return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl, opened);
+ return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl);
}
/*
inode->i_mode &= ~hsb->s_file_umask;
inode->i_mode |= S_IFREG;
inode->i_ctime = inode->i_atime = inode->i_mtime =
- hfs_m_to_utime(rec->file.MdDat);
+ timespec_to_timespec64(hfs_m_to_utime(rec->file.MdDat));
inode->i_op = &hfs_file_inode_operations;
inode->i_fop = &hfs_file_operations;
inode->i_mapping->a_ops = &hfs_aops;
HFS_I(inode)->fs_blocks = 0;
inode->i_mode = S_IFDIR | (S_IRWXUGO & ~hsb->s_dir_umask);
inode->i_ctime = inode->i_atime = inode->i_mtime =
- hfs_m_to_utime(rec->dir.MdDat);
+ timespec_to_timespec64(hfs_m_to_utime(rec->dir.MdDat));
inode->i_op = &hfs_dir_inode_operations;
inode->i_fop = &hfs_dir_operations;
break;
HFS_I(inode)->rsrc_inode = dir;
HFS_I(dir)->rsrc_inode = inode;
igrab(dir);
- hlist_add_fake(&inode->i_hash);
+ inode_fake_hash(inode);
mark_inode_dirty(inode);
dont_mount(dentry);
out:
hfsplus_get_perms(inode, &folder->permissions, 1);
set_nlink(inode, 1);
inode->i_size = 2 + be32_to_cpu(folder->valence);
- inode->i_atime = hfsp_mt2ut(folder->access_date);
- inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
- inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
+ inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(folder->access_date));
+ inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(folder->content_mod_date));
+ inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(folder->attribute_mod_date));
HFSPLUS_I(inode)->create_date = folder->create_date;
HFSPLUS_I(inode)->fs_blocks = 0;
if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
init_special_inode(inode, inode->i_mode,
be32_to_cpu(file->permissions.dev));
}
- inode->i_atime = hfsp_mt2ut(file->access_date);
- inode->i_mtime = hfsp_mt2ut(file->content_mod_date);
- inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date);
+ inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(file->access_date));
+ inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(file->content_mod_date));
+ inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(file->attribute_mod_date));
HFSPLUS_I(inode)->create_date = file->create_date;
} else {
pr_err("bad catalog entry used to create inode\n");
set_nlink(ino, st.nlink);
i_uid_write(ino, st.uid);
i_gid_write(ino, st.gid);
- ino->i_atime = st.atime;
- ino->i_mtime = st.mtime;
- ino->i_ctime = st.ctime;
+ ino->i_atime = timespec_to_timespec64(st.atime);
+ ino->i_mtime = timespec_to_timespec64(st.mtime);
+ ino->i_ctime = timespec_to_timespec64(st.ctime);
ino->i_size = st.size;
ino->i_blocks = st.blocks;
return 0;
int err;
inode = hostfs_iget(ino->i_sb);
- if (IS_ERR(inode)) {
- err = PTR_ERR(inode);
+ if (IS_ERR(inode))
goto out;
- }
err = -ENOMEM;
name = dentry_name(dentry);
- if (name == NULL)
- goto out_put;
-
- err = read_name(inode, name);
-
- __putname(name);
- if (err == -ENOENT) {
+ if (name) {
+ err = read_name(inode, name);
+ __putname(name);
+ }
+ if (err) {
iput(inode);
- inode = NULL;
+ inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
}
- else if (err)
- goto out_put;
-
- d_add(dentry, inode);
- return NULL;
-
- out_put:
- iput(inode);
out:
- return ERR_PTR(err);
+ return d_splice_alias(inode, dentry);
}
static int hostfs_link(struct dentry *to, struct inode *ino,
}
if (attr->ia_valid & ATTR_ATIME) {
attrs.ia_valid |= HOSTFS_ATTR_ATIME;
- attrs.ia_atime = attr->ia_atime;
+ attrs.ia_atime = timespec64_to_timespec(attr->ia_atime);
}
if (attr->ia_valid & ATTR_MTIME) {
attrs.ia_valid |= HOSTFS_ATTR_MTIME;
- attrs.ia_mtime = attr->ia_mtime;
+ attrs.ia_mtime = timespec64_to_timespec(attr->ia_mtime);
}
if (attr->ia_valid & ATTR_CTIME) {
attrs.ia_valid |= HOSTFS_ATTR_CTIME;
- attrs.ia_ctime = attr->ia_ctime;
+ attrs.ia_ctime = timespec64_to_timespec(attr->ia_ctime);
}
if (attr->ia_valid & ATTR_ATIME_SET) {
attrs.ia_valid |= HOSTFS_ATTR_ATIME_SET;
result = iget_locked(dir->i_sb, ino);
if (!result) {
hpfs_error(dir->i_sb, "hpfs_lookup: can't get inode");
+ result = ERR_PTR(-ENOMEM);
goto bail1;
}
if (result->i_state & I_NEW) {
if (de->has_acl || de->has_xtd_perm) if (!sb_rdonly(dir->i_sb)) {
hpfs_error(result->i_sb, "ACLs or XPERM found. This is probably HPFS386. This driver doesn't support it now. Send me some info on these structures");
+ iput(result);
+ result = ERR_PTR(-EINVAL);
goto bail1;
}
}
}
+bail1:
hpfs_brelse4(&qbh);
/*
* Made it.
*/
- end:
- end_add:
+end:
+end_add:
hpfs_unlock(dir->i_sb);
- d_add(dentry, result);
- return NULL;
-
- /*
- * Didn't.
- */
- bail1:
-
- hpfs_brelse4(&qbh);
-
- /*bail:*/
-
- hpfs_unlock(dir->i_sb);
- return ERR_PTR(-ENOENT);
+ return d_splice_alias(result, dentry);
}
const struct file_operations hpfs_dir_ops =
bool truncate_op = (lend == LLONG_MAX);
memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+ vma_init(&pseudo_vma, current->mm);
pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
pagevec_init(&pvec);
next = start;
* as input to create an allocation policy.
*/
memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+ vma_init(&pseudo_vma, mm);
pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
pseudo_vma.vm_file = file;
return h - hstates;
}
-static const struct dentry_operations anon_ops = {
- .d_dname = simple_dname
-};
-
/*
* Note that size should be aligned to proper hugepage size in caller side,
* otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
vm_flags_t acctflag, struct user_struct **user,
int creat_flags, int page_size_log)
{
- struct file *file = ERR_PTR(-ENOMEM);
struct inode *inode;
- struct path path;
- struct super_block *sb;
- struct qstr quick_string;
+ struct vfsmount *mnt;
int hstate_idx;
+ struct file *file;
hstate_idx = get_hstate_idx(page_size_log);
if (hstate_idx < 0)
return ERR_PTR(-ENODEV);
*user = NULL;
- if (!hugetlbfs_vfsmount[hstate_idx])
+ mnt = hugetlbfs_vfsmount[hstate_idx];
+ if (!mnt)
return ERR_PTR(-ENOENT);
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
}
}
- sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
- quick_string.name = name;
- quick_string.len = strlen(quick_string.name);
- quick_string.hash = 0;
- path.dentry = d_alloc_pseudo(sb, &quick_string);
- if (!path.dentry)
- goto out_shm_unlock;
-
- d_set_d_op(path.dentry, &anon_ops);
- path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
file = ERR_PTR(-ENOSPC);
- inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
+ inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
- goto out_dentry;
+ goto out;
if (creat_flags == HUGETLB_SHMFS_INODE)
inode->i_flags |= S_PRIVATE;
- file = ERR_PTR(-ENOMEM);
- if (hugetlb_reserve_pages(inode, 0,
- size >> huge_page_shift(hstate_inode(inode)), NULL,
- acctflag))
- goto out_inode;
-
- d_instantiate(path.dentry, inode);
inode->i_size = size;
clear_nlink(inode);
- file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
- &hugetlbfs_file_operations);
- if (IS_ERR(file))
- goto out_dentry; /* inode is already attached */
-
- return file;
+ if (hugetlb_reserve_pages(inode, 0,
+ size >> huge_page_shift(hstate_inode(inode)), NULL,
+ acctflag))
+ file = ERR_PTR(-ENOMEM);
+ else
+ file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+ &hugetlbfs_file_operations);
+ if (!IS_ERR(file))
+ return file;
-out_inode:
iput(inode);
-out_dentry:
- path_put(&path);
-out_shm_unlock:
+out:
if (*user) {
user_shm_unlock(size, *user);
*user = NULL;
__wait_on_freeing_inode(inode);
goto repeat;
}
+ if (unlikely(inode->i_state & I_CREATING)) {
+ spin_unlock(&inode->i_lock);
+ return ERR_PTR(-ESTALE);
+ }
__iget(inode);
spin_unlock(&inode->i_lock);
return inode;
__wait_on_freeing_inode(inode);
goto repeat;
}
+ if (unlikely(inode->i_state & I_CREATING)) {
+ spin_unlock(&inode->i_lock);
+ return ERR_PTR(-ESTALE);
+ }
__iget(inode);
spin_unlock(&inode->i_lock);
return inode;
lockdep_annotate_inode_mutex_key(inode);
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
- inode->i_state &= ~I_NEW;
+ inode->i_state &= ~I_NEW & ~I_CREATING;
smp_mb();
wake_up_bit(&inode->i_state, __I_NEW);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);
+void discard_new_inode(struct inode *inode)
+{
+ lockdep_annotate_inode_mutex_key(inode);
+ spin_lock(&inode->i_lock);
+ WARN_ON(!(inode->i_state & I_NEW));
+ inode->i_state &= ~I_NEW;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_NEW);
+ spin_unlock(&inode->i_lock);
+ iput(inode);
+}
+EXPORT_SYMBOL(discard_new_inode);
+
/**
* lock_two_nondirectories - take two i_mutexes on non-directory objects
*
{
struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
struct inode *old;
+ bool creating = inode->i_state & I_CREATING;
again:
spin_lock(&inode_hash_lock);
* Use the old inode instead of the preallocated one.
*/
spin_unlock(&inode_hash_lock);
+ if (IS_ERR(old))
+ return NULL;
wait_on_inode(old);
if (unlikely(inode_unhashed(old))) {
iput(old);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
+ if (!creating)
+ inode_sb_list_add(inode);
unlock:
spin_unlock(&inode_hash_lock);
struct inode *inode = ilookup5(sb, hashval, test, data);
if (!inode) {
- struct inode *new = new_inode(sb);
+ struct inode *new = alloc_inode(sb);
if (new) {
+ new->i_state = 0;
inode = inode_insert5(new, hashval, test, set, data);
if (unlikely(inode != new))
- iput(new);
+ destroy_inode(new);
}
}
return inode;
inode = find_inode_fast(sb, head, ino);
spin_unlock(&inode_hash_lock);
if (inode) {
+ if (IS_ERR(inode))
+ return NULL;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
*/
spin_unlock(&inode_hash_lock);
destroy_inode(inode);
+ if (IS_ERR(old))
+ return NULL;
inode = old;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
inode = find_inode(sb, head, test, data);
spin_unlock(&inode_hash_lock);
- return inode;
+ return IS_ERR(inode) ? NULL : inode;
}
EXPORT_SYMBOL(ilookup5_nowait);
spin_unlock(&inode_hash_lock);
if (inode) {
+ if (IS_ERR(inode))
+ return NULL;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
}
if (likely(!old)) {
spin_lock(&inode->i_lock);
- inode->i_state |= I_NEW;
+ inode->i_state |= I_NEW | I_CREATING;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
return 0;
}
+ if (unlikely(old->i_state & I_CREATING)) {
+ spin_unlock(&old->i_lock);
+ spin_unlock(&inode_hash_lock);
+ return -EBUSY;
+ }
__iget(old);
spin_unlock(&old->i_lock);
spin_unlock(&inode_hash_lock);
int insert_inode_locked4(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
- struct inode *old = inode_insert5(inode, hashval, test, NULL, data);
+ struct inode *old;
+
+ inode->i_state |= I_CREATING;
+ old = inode_insert5(inode, hashval, test, NULL, data);
if (old != inode) {
iput(old);
if (upperdentry) {
struct inode *realinode = d_inode(upperdentry);
- if ((!timespec_equal(&inode->i_mtime, &realinode->i_mtime) ||
- !timespec_equal(&inode->i_ctime, &realinode->i_ctime))) {
+ if ((!timespec64_equal(&inode->i_mtime, &realinode->i_mtime) ||
+ !timespec64_equal(&inode->i_ctime, &realinode->i_ctime))) {
inode->i_mtime = realinode->i_mtime;
inode->i_ctime = realinode->i_ctime;
}
/*
* Is mtime younger than atime? If yes, update atime:
*/
- if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0)
+ if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0)
return 1;
/*
* Is ctime younger than atime? If yes, update atime:
*/
- if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0)
+ if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0)
return 1;
/*
return 0;
}
-int generic_update_time(struct inode *inode, struct timespec *time, int flags)
+int generic_update_time(struct inode *inode, struct timespec64 *time, int flags)
{
int iflags = I_DIRTY_TIME;
bool dirty = false;
* This does the actual work of updating an inodes time or version. Must have
* had called mnt_want_write() before calling this.
*/
-static int update_time(struct inode *inode, struct timespec *time, int flags)
+static int update_time(struct inode *inode, struct timespec64 *time, int flags)
{
- int (*update_time)(struct inode *, struct timespec *, int);
+ int (*update_time)(struct inode *, struct timespec64 *, int);
update_time = inode->i_op->update_time ? inode->i_op->update_time :
generic_update_time;
bool rcu)
{
struct vfsmount *mnt = path->mnt;
- struct timespec now;
+ struct timespec64 now;
if (inode->i_flags & S_NOATIME)
return false;
now = current_time(inode);
- if (!relatime_need_update(path, inode, now, rcu))
+ if (!relatime_need_update(path, inode, timespec64_to_timespec(now), rcu))
return false;
- if (timespec_equal(&inode->i_atime, &now))
+ if (timespec64_equal(&inode->i_atime, &now))
return false;
return true;
{
struct vfsmount *mnt = path->mnt;
struct inode *inode = d_inode(path->dentry);
- struct timespec now;
+ struct timespec64 now;
if (!__atime_needs_update(path, inode, false))
return;
int file_update_time(struct file *file)
{
struct inode *inode = file_inode(file);
- struct timespec now;
+ struct timespec64 now;
int sync_it = 0;
int ret;
return 0;
now = current_time(inode);
- if (!timespec_equal(&inode->i_mtime, &now))
+ if (!timespec64_equal(&inode->i_mtime, &now))
sync_it = S_MTIME;
- if (!timespec_equal(&inode->i_ctime, &now))
+ if (!timespec64_equal(&inode->i_ctime, &now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
inode->i_uid = current_fsuid();
if (dir && dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
+
+ /* Directories are special, and always inherit S_ISGID */
if (S_ISDIR(mode))
mode |= S_ISGID;
+ else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
+ !in_group_p(inode->i_gid) &&
+ !capable_wrt_inode_uidgid(dir, CAP_FSETID))
+ mode &= ~S_ISGID;
} else
inode->i_gid = current_fsgid();
inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_nohighmem);
+/**
+ * timespec64_trunc - Truncate timespec64 to a granularity
+ * @t: Timespec64
+ * @gran: Granularity in ns.
+ *
+ * Truncate a timespec64 to a granularity. Always rounds down. gran must
+ * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns).
+ */
+struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran)
+{
+ /* Avoid division in the common cases 1 ns and 1 s. */
+ if (gran == 1) {
+ /* nothing */
+ } else if (gran == NSEC_PER_SEC) {
+ t.tv_nsec = 0;
+ } else if (gran > 1 && gran < NSEC_PER_SEC) {
+ t.tv_nsec -= t.tv_nsec % gran;
+ } else {
+ WARN(1, "illegal file time granularity: %u", gran);
+ }
+ return t;
+}
+EXPORT_SYMBOL(timespec64_trunc);
+
/**
* current_time - Return FS time
* @inode: inode.
* Note that inode and inode->sb cannot be NULL.
* Otherwise, the function warns and returns time without truncation.
*/
-struct timespec current_time(struct inode *inode)
+struct timespec64 current_time(struct inode *inode)
{
- struct timespec now = current_kernel_time();
+ struct timespec64 now = current_kernel_time64();
if (unlikely(!inode->i_sb)) {
WARN(1, "current_time() called with uninitialized super_block in the inode");
return now;
}
- return timespec_trunc(now, inode->i_sb->s_time_gran);
+ return timespec64_trunc(now, inode->i_sb->s_time_gran);
}
EXPORT_SYMBOL(current_time);
/*
* file_table.c
*/
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(int, const struct cred *);
/*
* super.c
int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
int flag);
-extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
+extern int vfs_open(const struct path *, struct file *);
/*
* inode.c
const struct iomap_ops *ops)
{
struct inode *inode = mapping->host;
- loff_t pos = bno >> inode->i_blkbits;
+ loff_t pos = bno << inode->i_blkbits;
unsigned blocksize = i_blocksize(inode);
if (filemap_write_and_wait(mapping))
if (jh->b_transaction == transaction &&
jh->b_jlist != BJ_Metadata) {
jbd_lock_bh_state(bh);
+ if (jh->b_transaction == transaction &&
+ jh->b_jlist != BJ_Metadata)
+ pr_err("JBD2: assertion failure: h_type=%u "
+ "h_line_no=%u block_no=%llu jlist=%u\n",
+ handle->h_type, handle->h_line_no,
+ (unsigned long long) bh->b_blocknr,
+ jh->b_jlist);
J_ASSERT_JH(jh, jh->b_transaction != transaction ||
jh->b_jlist == BJ_Metadata);
jbd_unlock_bh_state(bh);
* of the transaction. This needs to be done
* once a transaction -bzzz
*/
- jh->b_modified = 1;
if (handle->h_buffer_credits <= 0) {
ret = -ENOSPC;
goto out_unlock_bh;
}
+ jh->b_modified = 1;
handle->h_buffer_credits--;
}
if (ret)
goto fail;
- dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime));
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
jffs2_free_raw_inode(ri);
if (dead_f->inocache)
set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink);
if (!ret)
- dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
return ret;
}
/***********************************************************************/
set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink);
mutex_unlock(&f->sem);
d_instantiate(dentry, d_inode(old_dentry));
- dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
ihold(d_inode(old_dentry));
}
return ret;
goto fail;
}
- dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
jffs2_free_raw_dirent(rd);
goto fail;
}
- dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
inc_nlink(dir_i);
jffs2_free_raw_dirent(rd);
ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
dentry->d_name.len, f, now);
if (!ret) {
- dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
clear_nlink(d_inode(dentry));
drop_nlink(dir_i);
}
goto fail;
}
- dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
+ dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
jffs2_free_raw_dirent(rd);
* caller won't do it on its own since we are returning an error.
*/
d_invalidate(new_dentry);
- new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
+ new_dir_i->i_mtime = new_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
return ret;
}
if (d_is_dir(old_dentry))
drop_nlink(old_dir_i);
- new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now);
+ new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
return 0;
}
inode->i_size = pos + writtenlen;
inode->i_blocks = (inode->i_size + 511) >> 9;
- inode->i_ctime = inode->i_mtime = ITIME(je32_to_cpu(ri->ctime));
+ inode->i_ctime = inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
}
}
return PTR_ERR(new_metadata);
}
/* It worked. Update the inode */
- inode->i_atime = ITIME(je32_to_cpu(ri->atime));
- inode->i_ctime = ITIME(je32_to_cpu(ri->ctime));
- inode->i_mtime = ITIME(je32_to_cpu(ri->mtime));
+ inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->atime)));
+ inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+ inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->mtime)));
inode->i_mode = jemode_to_cpu(ri->mode);
i_uid_write(inode, je16_to_cpu(ri->uid));
i_gid_write(inode, je16_to_cpu(ri->gid));
i_uid_write(inode, je16_to_cpu(latest_node.uid));
i_gid_write(inode, je16_to_cpu(latest_node.gid));
inode->i_size = je32_to_cpu(latest_node.isize);
- inode->i_atime = ITIME(je32_to_cpu(latest_node.atime));
- inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime));
- inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime));
+ inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.atime)));
+ inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.mtime)));
+ inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.ctime)));
set_nlink(inode, f->inocache->pino_nlink);
dxd_t _dxd; /* 16: */
union {
__le32 _rdev; /* 4: */
+ /*
+ * The fast symlink area
+ * is expected to overflow
+ * into _inlineea when
+ * needed (which will clear
+ * INLINEEA).
+ */
u8 _fastsymlink[128];
} _u;
u8 _inlineea[128];
/* release the page */
release_metapage(mp);
- /*
- * __mark_inode_dirty expects inodes to be hashed. Since we don't
- * want special inodes in the fileset inode space, we make them
- * appear hashed, but do not put on any lists. hlist_del()
- * will work fine and require no locking.
- */
- hlist_add_fake(&ip->i_hash);
+ inode_fake_hash(ip);
return (ip);
}
struct {
unchar _unused[16]; /* 16: */
dxd_t _dxd; /* 16: */
+ /* _inline may overflow into _inline_ea when needed */
unchar _inline[128]; /* 128: inline symlink */
/* _inline_ea may overlay the last part of
* file._xtroot if maxentry = XTROOTINITSLOT
inode = new_inode(sb);
if (!inode) {
jfs_warn("ialloc: new_inode returned NULL!");
- rc = -ENOMEM;
- goto fail;
+ return ERR_PTR(-ENOMEM);
}
jfs_inode = JFS_IP(inode);
rc = diAlloc(parent, S_ISDIR(mode), inode);
if (rc) {
jfs_warn("ialloc: diAlloc returned %d!", rc);
- if (rc == -EIO)
- make_bad_inode(inode);
goto fail_put;
}
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
clear_nlink(inode);
- unlock_new_inode(inode);
+ discard_new_inode(inode);
+ return ERR_PTR(rc);
+
fail_put:
iput(inode);
-fail:
return ERR_PTR(rc);
}
if (rc) {
free_ea_wmap(ip);
clear_nlink(ip);
- unlock_new_inode(ip);
- iput(ip);
+ discard_new_inode(ip);
} else {
d_instantiate_new(dentry, ip);
}
if (rc) {
free_ea_wmap(ip);
clear_nlink(ip);
- unlock_new_inode(ip);
- iput(ip);
+ discard_new_inode(ip);
} else {
d_instantiate_new(dentry, ip);
}
if (rc) {
free_ea_wmap(ip);
clear_nlink(ip);
- unlock_new_inode(ip);
- iput(ip);
+ discard_new_inode(ip);
} else {
d_instantiate_new(dentry, ip);
}
if (rc) {
free_ea_wmap(ip);
clear_nlink(ip);
- unlock_new_inode(ip);
- iput(ip);
+ discard_new_inode(ip);
} else {
d_instantiate_new(dentry, ip);
}
inode->i_ino = 0;
inode->i_size = i_size_read(sb->s_bdev->bd_inode);
inode->i_mapping->a_ops = &jfs_metapage_aops;
- hlist_add_fake(&inode->i_hash);
+ inode_fake_hash(inode);
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
sbi->direct_inode = inode;
jfs_inode_cachep =
kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
- offsetof(struct jfs_inode_info, i_inline),
- sizeof_field(struct jfs_inode_info, i_inline),
+ offsetof(struct jfs_inode_info, i_inline), IDATASIZE,
init_once);
if (jfs_inode_cachep == NULL)
return -ENOMEM;
if (size > PSIZE) {
/*
* To keep the rest of the code simple. Allocate a
- * contiguous buffer to work with
+ * contiguous buffer to work with. Make the buffer large
+ * enough to make use of the whole extent.
*/
- ea_buf->xattr = kmalloc(size, GFP_KERNEL);
+ ea_buf->max_size = (size + sb->s_blocksize - 1) &
+ ~(sb->s_blocksize - 1);
+
+ ea_buf->xattr = kmalloc(ea_buf->max_size, GFP_KERNEL);
if (ea_buf->xattr == NULL)
return -ENOMEM;
ea_buf->flag = EA_MALLOC;
- ea_buf->max_size = (size + sb->s_blocksize - 1) &
- ~(sb->s_blocksize - 1);
if (ea_size == 0)
return 0;
ps_iattr = parent->iattr;
if (ps_iattr) {
struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
- ktime_get_real_ts(&ps_iattrs->ia_ctime);
+ ktime_get_real_ts64(&ps_iattrs->ia_ctime);
ps_iattrs->ia_mtime = ps_iattrs->ia_ctime;
}
/* update timestamps on the parent */
if (ps_iattr) {
- ktime_get_real_ts(&ps_iattr->ia_iattr.ia_ctime);
+ ktime_get_real_ts64(&ps_iattr->ia_iattr.ia_ctime);
ps_iattr->ia_iattr.ia_mtime =
ps_iattr->ia_iattr.ia_ctime;
}
iattrs->ia_uid = GLOBAL_ROOT_UID;
iattrs->ia_gid = GLOBAL_ROOT_GID;
- ktime_get_real_ts(&iattrs->ia_atime);
+ ktime_get_real_ts64(&iattrs->ia_atime);
iattrs->ia_mtime = iattrs->ia_atime;
iattrs->ia_ctime = iattrs->ia_atime;
struct super_block *sb = inode->i_sb;
inode->i_uid = iattr->ia_uid;
inode->i_gid = iattr->ia_gid;
- inode->i_atime = timespec_trunc(iattr->ia_atime, sb->s_time_gran);
- inode->i_mtime = timespec_trunc(iattr->ia_mtime, sb->s_time_gran);
- inode->i_ctime = timespec_trunc(iattr->ia_ctime, sb->s_time_gran);
+ inode->i_atime = timespec64_trunc(iattr->ia_atime, sb->s_time_gran);
+ inode->i_mtime = timespec64_trunc(iattr->ia_mtime, sb->s_time_gran);
+ inode->i_ctime = timespec64_trunc(iattr->ia_ctime, sb->s_time_gran);
}
static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
* exclusive leases. The justification is that if someone has an
* exclusive lease, then they could be modifying it.
*/
-void lease_get_mtime(struct inode *inode, struct timespec *time)
+void lease_get_mtime(struct inode *inode, struct timespec64 *time)
{
bool has_lease = false;
struct file_lock_context *ctx;
{
int err;
+ if (IS_ERR(name))
+ return PTR_ERR(name);
while (*name=='/')
name++;
if (!*name)
}
}
+/* must be paired with terminate_walk() */
static const char *path_init(struct nameidata *nd, unsigned flags)
{
const char *s = nd->name->name;
if (!*s)
flags &= ~LOOKUP_RCU;
+ if (flags & LOOKUP_RCU)
+ rcu_read_lock();
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
- rcu_read_lock();
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
nd->m_seq = read_seqbegin(&mount_lock);
nd->m_seq = read_seqbegin(&mount_lock);
if (*s == '/') {
- if (flags & LOOKUP_RCU)
- rcu_read_lock();
set_root(nd);
if (likely(!nd_jump_root(nd)))
return s;
- nd->root.mnt = NULL;
- rcu_read_unlock();
return ERR_PTR(-ECHILD);
} else if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
- rcu_read_lock();
-
do {
seq = read_seqcount_begin(&fs->seq);
nd->path = fs->pwd;
dentry = f.file->f_path.dentry;
- if (*s) {
- if (!d_can_lookup(dentry)) {
- fdput(f);
- return ERR_PTR(-ENOTDIR);
- }
+ if (*s && unlikely(!d_can_lookup(dentry))) {
+ fdput(f);
+ return ERR_PTR(-ENOTDIR);
}
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
- rcu_read_lock();
nd->inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
const char *s = path_init(nd, flags);
int err;
- if (IS_ERR(s))
- return PTR_ERR(s);
-
- if (unlikely(flags & LOOKUP_DOWN)) {
+ if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
err = handle_lookup_down(nd);
- if (unlikely(err < 0)) {
- terminate_walk(nd);
- return err;
- }
+ if (unlikely(err < 0))
+ s = ERR_PTR(err);
}
while (!(err = link_path_walk(s, nd))
&& ((err = lookup_last(nd)) > 0)) {
s = trailing_symlink(nd);
- if (IS_ERR(s)) {
- err = PTR_ERR(s);
- break;
- }
}
if (!err)
err = complete_walk(nd);
struct path *parent)
{
const char *s = path_init(nd, flags);
- int err;
- if (IS_ERR(s))
- return PTR_ERR(s);
- err = link_path_walk(s, nd);
+ int err = link_path_walk(s, nd);
if (!err)
err = complete_walk(nd);
if (!err) {
return inode_permission(base->d_inode, MAY_EXEC);
}
+/**
+ * try_lookup_one_len - filesystem helper to lookup single pathname component
+ * @name: pathname component to lookup
+ * @base: base directory to lookup from
+ * @len: maximum length @len should be interpreted to
+ *
+ * Look up a dentry by name in the dcache, returning NULL if it does not
+ * currently exist. The function does not try to create a dentry.
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
+ */
+struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len)
+{
+ struct qstr this;
+ int err;
+
+ WARN_ON_ONCE(!inode_is_locked(base->d_inode));
+
+ err = lookup_one_len_common(name, base, len, &this);
+ if (err)
+ return ERR_PTR(err);
+
+ return lookup_dcache(&this, base, 0);
+}
+EXPORT_SYMBOL(try_lookup_one_len);
+
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
{
const char *s = path_init(nd, flags);
int err;
- if (IS_ERR(s))
- return PTR_ERR(s);
+
while (!(err = link_path_walk(s, nd)) &&
(err = mountpoint_last(nd)) > 0) {
s = trailing_symlink(nd);
- if (IS_ERR(s)) {
- err = PTR_ERR(s);
- break;
- }
}
if (!err) {
*path = nd->path;
* Returns 0 if successful. The file will have been created and attached to
* @file by the filesystem calling finish_open().
*
- * Returns 1 if the file was looked up only or didn't need creating. The
- * caller will need to perform the open themselves. @path will have been
- * updated to point to the new dentry. This may be negative.
+ * If the file was looked up only or didn't need creating, FMODE_OPENED won't
+ * be set. The caller will need to perform the open themselves. @path will
+ * have been updated to point to the new dentry. This may be negative.
*
* Returns an error code otherwise.
*/
static int atomic_open(struct nameidata *nd, struct dentry *dentry,
struct path *path, struct file *file,
const struct open_flags *op,
- int open_flag, umode_t mode,
- int *opened)
+ int open_flag, umode_t mode)
{
struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
struct inode *dir = nd->path.dentry->d_inode;
file->f_path.dentry = DENTRY_NOT_SET;
file->f_path.mnt = nd->path.mnt;
error = dir->i_op->atomic_open(dir, dentry, file,
- open_to_namei_flags(open_flag),
- mode, opened);
+ open_to_namei_flags(open_flag), mode);
d_lookup_done(dentry);
if (!error) {
- /*
- * We didn't have the inode before the open, so check open
- * permission here.
- */
- int acc_mode = op->acc_mode;
- if (*opened & FILE_CREATED) {
- WARN_ON(!(open_flag & O_CREAT));
- fsnotify_create(dir, dentry);
- acc_mode = 0;
- }
- error = may_open(&file->f_path, acc_mode, open_flag);
- if (WARN_ON(error > 0))
- error = -EINVAL;
- } else if (error > 0) {
- if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+ if (file->f_mode & FMODE_OPENED) {
+ /*
+ * We didn't have the inode before the open, so check open
+ * permission here.
+ */
+ int acc_mode = op->acc_mode;
+ if (file->f_mode & FMODE_CREATED) {
+ WARN_ON(!(open_flag & O_CREAT));
+ fsnotify_create(dir, dentry);
+ acc_mode = 0;
+ }
+ error = may_open(&file->f_path, acc_mode, open_flag);
+ if (WARN_ON(error > 0))
+ error = -EINVAL;
+ } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
error = -EIO;
} else {
if (file->f_path.dentry) {
dput(dentry);
dentry = file->f_path.dentry;
}
- if (*opened & FILE_CREATED)
+ if (file->f_mode & FMODE_CREATED)
fsnotify_create(dir, dentry);
if (unlikely(d_is_negative(dentry))) {
error = -ENOENT;
} else {
path->dentry = dentry;
path->mnt = nd->path.mnt;
- return 1;
+ return 0;
}
}
}
/*
* Look up and maybe create and open the last component.
*
- * Must be called with i_mutex held on parent.
- *
- * Returns 0 if the file was successfully atomically created (if necessary) and
- * opened. In this case the file will be returned attached to @file.
+ * Must be called with parent locked (exclusive in O_CREAT case).
*
- * Returns 1 if the file was not completely opened at this time, though lookups
- * and creations will have been performed and the dentry returned in @path will
- * be positive upon return if O_CREAT was specified. If O_CREAT wasn't
- * specified then a negative dentry may be returned.
+ * Returns 0 on success, that is, if
+ * the file was successfully atomically created (if necessary) and opened, or
+ * the file was not completely opened at this time, though lookups and
+ * creations were performed.
+ * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
+ * In the latter case dentry returned in @path might be negative if O_CREAT
+ * hadn't been specified.
*
- * An error code is returned otherwise.
- *
- * FILE_CREATE will be set in @*opened if the dentry was created and will be
- * cleared otherwise prior to returning.
+ * An error code is returned on failure.
*/
static int lookup_open(struct nameidata *nd, struct path *path,
struct file *file,
const struct open_flags *op,
- bool got_write, int *opened)
+ bool got_write)
{
struct dentry *dir = nd->path.dentry;
struct inode *dir_inode = dir->d_inode;
if (unlikely(IS_DEADDIR(dir_inode)))
return -ENOENT;
- *opened &= ~FILE_CREATED;
+ file->f_mode &= ~FMODE_CREATED;
dentry = d_lookup(dir, &nd->last);
for (;;) {
if (!dentry) {
if (dir_inode->i_op->atomic_open) {
error = atomic_open(nd, dentry, path, file, op, open_flag,
- mode, opened);
+ mode);
if (unlikely(error == -ENOENT) && create_error)
error = create_error;
return error;
/* Negative dentry, just create the file */
if (!dentry->d_inode && (open_flag & O_CREAT)) {
- *opened |= FILE_CREATED;
+ file->f_mode |= FMODE_CREATED;
audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
if (!dir_inode->i_op->create) {
error = -EACCES;
out_no_open:
path->dentry = dentry;
path->mnt = nd->path.mnt;
- return 1;
+ return 0;
out_dput:
dput(dentry);
* Handle the last step of open()
*/
static int do_last(struct nameidata *nd,
- struct file *file, const struct open_flags *op,
- int *opened)
+ struct file *file, const struct open_flags *op)
{
struct dentry *dir = nd->path.dentry;
int open_flag = op->open_flag;
inode_lock(dir->d_inode);
else
inode_lock_shared(dir->d_inode);
- error = lookup_open(nd, &path, file, op, got_write, opened);
+ error = lookup_open(nd, &path, file, op, got_write);
if (open_flag & O_CREAT)
inode_unlock(dir->d_inode);
else
inode_unlock_shared(dir->d_inode);
- if (error <= 0) {
- if (error)
- goto out;
+ if (error)
+ goto out;
- if ((*opened & FILE_CREATED) ||
+ if (file->f_mode & FMODE_OPENED) {
+ if ((file->f_mode & FMODE_CREATED) ||
!S_ISREG(file_inode(file)->i_mode))
will_truncate = false;
goto opened;
}
- if (*opened & FILE_CREATED) {
+ if (file->f_mode & FMODE_CREATED) {
/* Don't check for write permission, don't truncate */
open_flag &= ~O_TRUNC;
will_truncate = false;
error = may_open(&nd->path, acc_mode, open_flag);
if (error)
goto out;
- BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
- error = vfs_open(&nd->path, file, current_cred());
+ BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
+ error = vfs_open(&nd->path, file);
if (error)
goto out;
- *opened |= FILE_OPENED;
opened:
- error = open_check_o_direct(file);
- if (!error)
- error = ima_file_check(file, op->acc_mode, *opened);
+ error = ima_file_check(file, op->acc_mode);
if (!error && will_truncate)
error = handle_truncate(file);
out:
- if (unlikely(error) && (*opened & FILE_OPENED))
- fput(file);
if (unlikely(error > 0)) {
WARN_ON(1);
error = -EINVAL;
static int do_tmpfile(struct nameidata *nd, unsigned flags,
const struct open_flags *op,
- struct file *file, int *opened)
+ struct file *file)
{
struct dentry *child;
struct path path;
if (error)
goto out2;
file->f_path.mnt = path.mnt;
- error = finish_open(file, child, NULL, opened);
- if (error)
- goto out2;
- error = open_check_o_direct(file);
- if (error)
- fput(file);
+ error = finish_open(file, child, NULL);
out2:
mnt_drop_write(path.mnt);
out:
int error = path_lookupat(nd, flags, &path);
if (!error) {
audit_inode(nd->name, path.dentry, 0);
- error = vfs_open(&path, file, current_cred());
+ error = vfs_open(&path, file);
path_put(&path);
}
return error;
static struct file *path_openat(struct nameidata *nd,
const struct open_flags *op, unsigned flags)
{
- const char *s;
struct file *file;
- int opened = 0;
int error;
- file = get_empty_filp();
+ file = alloc_empty_file(op->open_flag, current_cred());
if (IS_ERR(file))
return file;
- file->f_flags = op->open_flag;
-
if (unlikely(file->f_flags & __O_TMPFILE)) {
- error = do_tmpfile(nd, flags, op, file, &opened);
- goto out2;
- }
-
- if (unlikely(file->f_flags & O_PATH)) {
+ error = do_tmpfile(nd, flags, op, file);
+ } else if (unlikely(file->f_flags & O_PATH)) {
error = do_o_path(nd, flags, file);
- if (!error)
- opened |= FILE_OPENED;
- goto out2;
- }
-
- s = path_init(nd, flags);
- if (IS_ERR(s)) {
- put_filp(file);
- return ERR_CAST(s);
- }
- while (!(error = link_path_walk(s, nd)) &&
- (error = do_last(nd, file, op, &opened)) > 0) {
- nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
- s = trailing_symlink(nd);
- if (IS_ERR(s)) {
- error = PTR_ERR(s);
- break;
+ } else {
+ const char *s = path_init(nd, flags);
+ while (!(error = link_path_walk(s, nd)) &&
+ (error = do_last(nd, file, op)) > 0) {
+ nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+ s = trailing_symlink(nd);
}
+ terminate_walk(nd);
}
- terminate_walk(nd);
-out2:
- if (!(opened & FILE_OPENED)) {
- BUG_ON(!error);
- put_filp(file);
+ if (likely(!error)) {
+ if (likely(file->f_mode & FMODE_OPENED))
+ return file;
+ WARN_ON(1);
+ error = -EINVAL;
}
- if (unlikely(error)) {
- if (error == -EOPENSTALE) {
- if (flags & LOOKUP_RCU)
- error = -ECHILD;
- else
- error = -ESTALE;
- }
- file = ERR_PTR(error);
+ fput(file);
+ if (error == -EOPENSTALE) {
+ if (flags & LOOKUP_RCU)
+ error = -ECHILD;
+ else
+ error = -ESTALE;
}
- return file;
+ return ERR_PTR(error);
}
struct file *do_filp_open(int dfd, struct filename *pathname,
return len;
}
-/*
- * A helper for ->readlink(). This should be used *ONLY* for symlinks that
- * have ->get_link() not calling nd_jump_link(). Using (or not using) it
- * for any given inode is up to filesystem.
- */
-static int generic_readlink(struct dentry *dentry, char __user *buffer,
- int buflen)
-{
- DEFINE_DELAYED_CALL(done);
- struct inode *inode = d_inode(dentry);
- const char *link = inode->i_link;
- int res;
-
- if (!link) {
- link = inode->i_op->get_link(dentry, inode, &done);
- if (IS_ERR(link))
- return PTR_ERR(link);
- }
- res = readlink_copy(buffer, buflen, link);
- do_delayed_call(&done);
- return res;
-}
-
/**
* vfs_readlink - copy symlink body into userspace buffer
* @dentry: dentry on which to get symbolic link
int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
struct inode *inode = d_inode(dentry);
+ DEFINE_DELAYED_CALL(done);
+ const char *link;
+ int res;
if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
if (unlikely(inode->i_op->readlink))
spin_unlock(&inode->i_lock);
}
- return generic_readlink(dentry, buffer, buflen);
+ link = inode->i_link;
+ if (!link) {
+ link = inode->i_op->get_link(dentry, inode, &done);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ }
+ res = readlink_copy(buffer, buflen, link);
+ do_delayed_call(&done);
+ return res;
}
EXPORT_SYMBOL(vfs_readlink);
return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
+ smp_mb(); // see mntput_no_expire()
if (likely(!read_seqretry(&mount_lock, seq)))
return 0;
if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
mnt_add_count(mnt, -1);
return 1;
}
+ lock_mount_hash();
+ if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+ mnt_add_count(mnt, -1);
+ unlock_mount_hash();
+ return 1;
+ }
+ unlock_mount_hash();
+ /* caller will mntput() */
return -1;
}
static void mntput_no_expire(struct mount *mnt)
{
rcu_read_lock();
- mnt_add_count(mnt, -1);
- if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+ if (likely(READ_ONCE(mnt->mnt_ns))) {
+ /*
+ * Since we don't do lock_mount_hash() here,
+ * ->mnt_ns can change under us. However, if it's
+ * non-NULL, then there's a reference that won't
+ * be dropped until after an RCU delay done after
+ * turning ->mnt_ns NULL. So if we observe it
+ * non-NULL under rcu_read_lock(), the reference
+ * we are dropping is not the final one.
+ */
+ mnt_add_count(mnt, -1);
rcu_read_unlock();
return;
}
lock_mount_hash();
+ /*
+ * make sure that if __legitimize_mnt() has not seen us grab
+ * mount_lock, we'll see their refcount increment here.
+ */
+ smp_mb();
+ mnt_add_count(mnt, -1);
if (mnt_get_count(mnt)) {
rcu_read_unlock();
unlock_mount_hash();
res->change_attr = delegation->change_attr;
if (nfs_have_writebacks(inode))
res->change_attr++;
- res->ctime = inode->i_ctime;
- res->mtime = inode->i_mtime;
+ res->ctime = timespec64_to_timespec(inode->i_ctime);
+ res->mtime = timespec64_to_timespec(inode->i_mtime);
res->bitmap[0] = (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) &
args->bitmap[0];
res->bitmap[1] = (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) &
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
res = nfs_delegation_find_inode_server(server, fhandle);
- if (res != ERR_PTR(-ENOENT))
+ if (res != ERR_PTR(-ENOENT)) {
+ rcu_read_unlock();
return res;
+ }
}
rcu_read_unlock();
return ERR_PTR(-ENOENT);
static int nfs_finish_open(struct nfs_open_context *ctx,
struct dentry *dentry,
- struct file *file, unsigned open_flags,
- int *opened)
+ struct file *file, unsigned open_flags)
{
int err;
- err = finish_open(file, dentry, do_open, opened);
+ err = finish_open(file, dentry, do_open);
if (err)
goto out;
if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned open_flags,
- umode_t mode, int *opened)
+ umode_t mode)
{
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
struct nfs_open_context *ctx;
struct inode *inode;
unsigned int lookup_flags = 0;
bool switched = false;
+ int created = 0;
int err;
/* Expect a negative dentry */
goto out;
trace_nfs_atomic_open_enter(dir, ctx, open_flags);
- inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
+ inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created);
+ if (created)
+ file->f_mode |= FMODE_CREATED;
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
goto out;
}
- err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+ err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
put_nfs_open_context(ctx);
out:
struct dentry *parent = dget_parent(dentry);
struct inode *dir = d_inode(parent);
struct inode *inode;
+ struct dentry *d;
int error = -EACCES;
d_drop(dentry);
goto out_error;
}
inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
- error = PTR_ERR(inode);
- if (IS_ERR(inode))
+ d = d_splice_alias(inode, dentry);
+ if (IS_ERR(d)) {
+ error = PTR_ERR(d);
goto out_error;
- d_add(dentry, inode);
+ }
+ dput(d);
out:
dput(parent);
return 0;
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
+ clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
if (ff_layout_choose_best_ds_for_read(hdr->lseg,
hdr->pgio_mirror_idx + 1,
&hdr->pgio_mirror_idx))
goto out_eagain;
- ff_layout_read_record_layoutstats_done(task, hdr);
- pnfs_read_resend_pnfs(hdr);
+ set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
- ff_layout_reset_read(hdr);
+ set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
return task->tk_status;
case -EAGAIN:
goto out_eagain;
struct nfs_pgio_header *hdr = data;
ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ pnfs_read_resend_pnfs(hdr);
+ else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ ff_layout_reset_read(hdr);
pnfs_generic_rw_release(data);
}
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
+ clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
- ff_layout_reset_write(hdr, true);
+ set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
- ff_layout_reset_write(hdr, false);
+ set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
return task->tk_status;
case -EAGAIN:
return -EAGAIN;
struct nfs_pgio_header *hdr = data;
ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ ff_layout_reset_write(hdr, true);
+ else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ ff_layout_reset_write(hdr, false);
pnfs_generic_rw_release(data);
}
return FSCACHE_CHECKAUX_OBSOLETE;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = nfsi->vfs_inode.i_mtime;
- auxdata.ctime = nfsi->vfs_inode.i_ctime;
+ auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
+ auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
return;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = nfsi->vfs_inode.i_mtime;
- auxdata.ctime = nfsi->vfs_inode.i_ctime;
+ auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
+ auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = nfsi->vfs_inode.i_mtime;
- auxdata.ctime = nfsi->vfs_inode.i_ctime;
+ auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
+ auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
fscache_relinquish_cookie(cookie, &auxdata, false);
nfsi->fscache = NULL;
}
return;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = nfsi->vfs_inode.i_mtime;
- auxdata.ctime = nfsi->vfs_inode.i_ctime;
+ auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
+ auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
if (inode_is_open_for_write(inode)) {
dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- inode->i_atime = fattr->atime;
+ inode->i_atime = timespec_to_timespec64(fattr->atime);
else if (nfs_server_capable(inode, NFS_CAP_ATIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
- inode->i_mtime = fattr->mtime;
+ inode->i_mtime = timespec_to_timespec64(fattr->mtime);
else if (nfs_server_capable(inode, NFS_CAP_MTIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = fattr->ctime;
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
else if (nfs_server_capable(inode, NFS_CAP_CTIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
if ((attr->ia_valid & ATTR_GID) != 0)
inode->i_gid = attr->ia_gid;
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = fattr->ctime;
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME
| NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- inode->i_atime = fattr->atime;
+ inode->i_atime = timespec_to_timespec64(fattr->atime);
else if (attr->ia_valid & ATTR_ATIME_SET)
inode->i_atime = attr->ia_atime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = fattr->ctime;
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME
| NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
- inode->i_mtime = fattr->mtime;
+ inode->i_mtime = timespec_to_timespec64(fattr->mtime);
else if (attr->ia_valid & ATTR_MTIME_SET)
inode->i_mtime = attr->ia_mtime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = fattr->ctime;
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
+ struct timespec ts;
+
if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
&& inode_eq_iversion_raw(inode, fattr->pre_change_attr)) {
nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
}
/* If we have atomic WCC data, we may update some attributes */
+ ts = timespec64_to_timespec(inode->i_ctime);
if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
- && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
- memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+ && timespec_equal(&ts, &fattr->pre_ctime)) {
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
}
+ ts = timespec64_to_timespec(inode->i_mtime);
if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
- && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
- memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
+ && timespec_equal(&ts, &fattr->pre_mtime)) {
+ inode->i_mtime = timespec_to_timespec64(fattr->mtime);
if (S_ISDIR(inode->i_mode))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
}
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_size, new_isize;
unsigned long invalid = 0;
-
+ struct timespec ts;
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
return 0;
invalid |= NFS_INO_INVALID_CHANGE
| NFS_INO_REVAL_PAGECACHE;
- if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
+ ts = timespec64_to_timespec(inode->i_mtime);
+ if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&ts, &fattr->mtime))
invalid |= NFS_INO_INVALID_MTIME;
- if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&inode->i_ctime, &fattr->ctime))
+ ts = timespec64_to_timespec(inode->i_ctime);
+ if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&ts, &fattr->ctime))
invalid |= NFS_INO_INVALID_CTIME;
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
invalid |= NFS_INO_INVALID_OTHER;
- if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime))
+ ts = timespec64_to_timespec(inode->i_atime);
+ if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&ts, &fattr->atime))
invalid |= NFS_INO_INVALID_ATIME;
if (invalid != 0)
}
if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
- memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
+ fattr->pre_ctime = timespec64_to_timespec(inode->i_ctime);
fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
- memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
+ fattr->pre_mtime = timespec64_to_timespec(inode->i_mtime);
fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
}
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
- memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
+ inode->i_mtime = timespec_to_timespec64(fattr->mtime);
} else if (server->caps & NFS_CAP_MTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_MTIME
}
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
- memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+ inode->i_ctime = timespec_to_timespec64(fattr->ctime);
} else if (server->caps & NFS_CAP_CTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_CTIME
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
+ inode->i_atime = timespec_to_timespec64(fattr->atime);
else if (server->caps & NFS_CAP_ATIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATIME
static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr)
{
+ struct timespec ts;
__be32 *p;
p = xdr_reserve_space(xdr, NFS_sattr_sz << 2);
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
- if (attr->ia_valid & ATTR_ATIME_SET)
- p = xdr_encode_time(p, &attr->ia_atime);
- else if (attr->ia_valid & ATTR_ATIME)
- p = xdr_encode_current_server_time(p, &attr->ia_atime);
- else
+ if (attr->ia_valid & ATTR_ATIME_SET) {
+ ts = timespec64_to_timespec(attr->ia_atime);
+ p = xdr_encode_time(p, &ts);
+ } else if (attr->ia_valid & ATTR_ATIME) {
+ ts = timespec64_to_timespec(attr->ia_atime);
+ p = xdr_encode_current_server_time(p, &ts);
+ } else
p = xdr_time_not_set(p);
- if (attr->ia_valid & ATTR_MTIME_SET)
- xdr_encode_time(p, &attr->ia_mtime);
- else if (attr->ia_valid & ATTR_MTIME)
- xdr_encode_current_server_time(p, &attr->ia_mtime);
- else
+ if (attr->ia_valid & ATTR_MTIME_SET) {
+ ts = timespec64_to_timespec(attr->ia_atime);
+ xdr_encode_time(p, &ts);
+ } else if (attr->ia_valid & ATTR_MTIME) {
+ ts = timespec64_to_timespec(attr->ia_mtime);
+ xdr_encode_current_server_time(p, &ts);
+ } else
xdr_time_not_set(p);
}
*/
static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr)
{
+ struct timespec ts;
u32 nbytes;
__be32 *p;
*p++ = xdr_zero;
if (attr->ia_valid & ATTR_ATIME_SET) {
+ struct timespec ts;
*p++ = xdr_two;
- p = xdr_encode_nfstime3(p, &attr->ia_atime);
+ ts = timespec64_to_timespec(attr->ia_atime);
+ p = xdr_encode_nfstime3(p, &ts);
} else if (attr->ia_valid & ATTR_ATIME) {
*p++ = xdr_one;
} else
if (attr->ia_valid & ATTR_MTIME_SET) {
*p++ = xdr_two;
- xdr_encode_nfstime3(p, &attr->ia_mtime);
+ ts = timespec64_to_timespec(attr->ia_mtime);
+ xdr_encode_nfstime3(p, &ts);
} else if (attr->ia_valid & ATTR_MTIME) {
*p = xdr_one;
} else
/* dir.c */
int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
- unsigned, umode_t, int *);
+ unsigned, umode_t);
/* super.c */
extern struct file_system_type nfs4_fs_type;
}
}
if (opened && opendata->file_created)
- *opened |= FILE_CREATED;
+ *opened = 1;
if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
*ctx_th = opendata->f_attr.mdsthreshold;
struct nfs4_closedata *calldata = data;
struct nfs4_state *state = calldata->state;
struct inode *inode = calldata->inode;
+ struct pnfs_layout_hdr *lo;
bool is_rdonly, is_wronly, is_rdwr;
int call_close = 0;
goto out_wait;
}
+ lo = calldata->arg.lr_args ? calldata->arg.lr_args->layout : NULL;
+ if (lo && !pnfs_layout_is_valid(lo)) {
+ calldata->arg.lr_args = NULL;
+ calldata->res.lr_res = NULL;
+ }
+
if (calldata->arg.fmode == 0)
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
{
struct nfs4_delegreturndata *d_data;
+ struct pnfs_layout_hdr *lo;
d_data = (struct nfs4_delegreturndata *)data;
if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
return;
+ lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL;
+ if (lo && !pnfs_layout_is_valid(lo)) {
+ d_data->args.lr_args = NULL;
+ d_data->res.lr_res = NULL;
+ }
+
nfs4_setup_sequence(d_data->res.server->nfs_client,
&d_data->args.seq_args,
&d_data->res.seq_res,
if (data->arg.new_lock && !data->cancelled) {
data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
- break;
+ goto out_restart;
}
-
if (data->arg.new_lock_owner != 0) {
nfs_confirm_seqid(&lsp->ls_seqid, 0);
nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid);
set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
- goto out_done;
- } else if (nfs4_update_lock_stateid(lsp, &data->res.stateid))
- goto out_done;
-
+ } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid))
+ goto out_restart;
break;
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_EXPIRED:
if (data->arg.new_lock_owner != 0) {
- if (nfs4_stateid_match(&data->arg.open_stateid,
+ if (!nfs4_stateid_match(&data->arg.open_stateid,
&lsp->ls_state->open_stateid))
- goto out_done;
- } else if (nfs4_stateid_match(&data->arg.lock_stateid,
+ goto out_restart;
+ } else if (!nfs4_stateid_match(&data->arg.lock_stateid,
&lsp->ls_stateid))
- goto out_done;
+ goto out_restart;
}
- if (!data->cancelled)
- rpc_restart_call_prepare(task);
out_done:
dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status);
+ return;
+out_restart:
+ if (!data->cancelled)
+ rpc_restart_call_prepare(task);
+ goto out_done;
}
static void nfs4_lock_release(void *calldata)
dprintk("%s: begin!\n", __func__);
nfs_free_seqid(data->arg.open_seqid);
- if (data->cancelled) {
+ if (data->cancelled && data->rpc_status == 0) {
struct rpc_task *task;
task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
data->arg.lock_seqid);
dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
+
switch (nfs4err) {
case 0:
goto out;
goto out;
}
- nfs4_sequence_free_slot(&lgp->res.seq_res);
err = nfs4_handle_exception(server, nfs4err, exception);
if (!status) {
if (exception->retry)
if (IS_ERR(task))
return ERR_CAST(task);
status = rpc_wait_for_completion_task(task);
- if (status == 0) {
+ if (status != 0)
+ goto out;
+
+ /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
+ if (task->tk_status < 0 || lgp->res.layoutp->len == 0) {
status = nfs4_layoutget_handle_exception(task, lgp, &exception);
*timeout = exception.timeout;
- }
-
+ } else
+ lseg = pnfs_layout_process(lgp);
+out:
trace_nfs4_layoutget(lgp->args.ctx,
&lgp->args.range,
&lgp->res.range,
&lgp->res.stateid,
status);
- /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
- if (status == 0 && lgp->res.layoutp->len)
- lseg = pnfs_layout_process(lgp);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
if (status)
&lrp->args.seq_args,
&lrp->res.seq_res,
task);
+ if (!pnfs_layout_is_valid(lrp->args.layout))
+ rpc_exit(task, 0);
}
static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
const struct nfs_server *server,
const uint32_t attrmask[])
{
+ struct timespec ts;
char owner_name[IDMAP_NAMESZ];
char owner_group[IDMAP_NAMESZ];
int owner_namelen = 0;
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
if (iap->ia_valid & ATTR_ATIME_SET) {
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- p = xdr_encode_nfstime4(p, &iap->ia_atime);
+ ts = timespec64_to_timespec(iap->ia_atime);
+ p = xdr_encode_nfstime4(p, &ts);
} else
*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
}
if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
if (iap->ia_valid & ATTR_MTIME_SET) {
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- p = xdr_encode_nfstime4(p, &iap->ia_mtime);
+ ts = timespec64_to_timespec(iap->ia_mtime);
+ p = xdr_encode_nfstime4(p, &ts);
} else
*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
}
{
}
+static inline bool pnfs_layout_is_valid(const struct pnfs_layout_hdr *lo)
+{
+ return false;
+}
+
#endif /* CONFIG_NFS_V4_1 */
#if IS_ENABLED(CONFIG_NFS_V4_2)
{
loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
+ struct timespec ts;
int error;
+ ts = timespec64_to_timespec(inode->i_mtime);
if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
- timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
- lcp->lc_mtime = current_time(inode);
+ timespec_compare(&lcp->lc_mtime, &ts) < 0)
+ lcp->lc_mtime = timespec64_to_timespec(current_time(inode));
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
- iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
+ iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = timespec_to_timespec64(lcp->lc_mtime);
if (new_size > i_size_read(inode)) {
iattr.ia_valid |= ATTR_SIZE;
encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
struct kstat *stat)
{
+ struct timespec ts;
*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
*p++ = htonl((u32) (stat->mode & S_IALLUGO));
*p++ = htonl((u32) stat->nlink);
*p++ = htonl((u32) MINOR(stat->rdev));
p = encode_fsid(p, fhp);
p = xdr_encode_hyper(p, stat->ino);
- p = encode_time3(p, &stat->atime);
- p = encode_time3(p, &stat->mtime);
- p = encode_time3(p, &stat->ctime);
+ ts = timespec64_to_timespec(stat->atime);
+ p = encode_time3(p, &ts);
+ ts = timespec64_to_timespec(stat->mtime);
+ p = encode_time3(p, &ts);
+ ts = timespec64_to_timespec(stat->ctime);
+ p = encode_time3(p, &ts);
return p;
}
stat.size = inode->i_size;
}
- fhp->fh_pre_mtime = stat.mtime;
- fhp->fh_pre_ctime = stat.ctime;
+ fhp->fh_pre_mtime = timespec64_to_timespec(stat.mtime);
+ fhp->fh_pre_ctime = timespec64_to_timespec(stat.ctime);
fhp->fh_pre_size = stat.size;
fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
fhp->fh_pre_saved = true;
struct iattr *iattr, struct nfs4_acl **acl,
struct xdr_netobj *label, int *umask)
{
+ struct timespec ts;
int expected_len, len = 0;
u32 dummy32;
char *buf;
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
len += 12;
- status = nfsd4_decode_time(argp, &iattr->ia_atime);
+ status = nfsd4_decode_time(argp, &ts);
+ iattr->ia_atime = timespec_to_timespec64(ts);
if (status)
return status;
iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
len += 12;
- status = nfsd4_decode_time(argp, &iattr->ia_mtime);
+ status = nfsd4_decode_time(argp, &ts);
+ iattr->ia_mtime = timespec_to_timespec64(ts);
if (status)
return status;
iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
{
struct dentry *dentry = fhp->fh_dentry;
int type;
- struct timespec time;
+ struct timespec64 time;
u32 f;
type = (stat->mode & S_IFMT);
goto out_nfserr;
}
- host_err = ima_file_check(file, may_flags, 0);
+ host_err = ima_file_check(file, may_flags);
if (host_err) {
fput(file);
goto out_nfserr;
*/
static int dnotify_handle_event(struct fsnotify_group *group,
struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info)
{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
struct dnotify_struct **prev;
if (!S_ISDIR(inode->i_mode))
return 0;
- BUG_ON(vfsmount_mark);
+ if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
+ return 0;
dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark);
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
} else {
- error = fsnotify_add_mark_locked(new_fsn_mark, inode, NULL, 0);
+ error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0);
if (error) {
mutex_unlock(&dnotify_group->mark_mutex);
goto out_err;
return ret;
}
-static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmnt_mark,
- u32 event_mask,
- const void *data, int data_type)
+static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info,
+ u32 event_mask, const void *data,
+ int data_type)
{
__u32 marks_mask = 0, marks_ignored_mask = 0;
const struct path *path = data;
+ struct fsnotify_mark *mark;
+ int type;
- pr_debug("%s: inode_mark=%p vfsmnt_mark=%p mask=%x data=%p"
- " data_type=%d\n", __func__, inode_mark, vfsmnt_mark,
- event_mask, data, data_type);
+ pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
+ __func__, iter_info->report_mask, event_mask, data, data_type);
/* if we don't have enough info to send an event to userspace say no */
if (data_type != FSNOTIFY_EVENT_PATH)
!d_can_lookup(path->dentry))
return false;
- /*
- * if the event is for a child and this inode doesn't care about
- * events on the child, don't send it!
- */
- if (inode_mark &&
- (!(event_mask & FS_EVENT_ON_CHILD) ||
- (inode_mark->mask & FS_EVENT_ON_CHILD))) {
- marks_mask |= inode_mark->mask;
- marks_ignored_mask |= inode_mark->ignored_mask;
- }
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ /*
+ * if the event is for a child and this inode doesn't care about
+ * events on the child, don't send it!
+ */
+ if (type == FSNOTIFY_OBJ_TYPE_INODE &&
+ (event_mask & FS_EVENT_ON_CHILD) &&
+ !(mark->mask & FS_EVENT_ON_CHILD))
+ continue;
- if (vfsmnt_mark) {
- marks_mask |= vfsmnt_mark->mask;
- marks_ignored_mask |= vfsmnt_mark->ignored_mask;
+ marks_mask |= mark->mask;
+ marks_ignored_mask |= mark->ignored_mask;
}
if (d_is_dir(path->dentry) &&
static int fanotify_handle_event(struct fsnotify_group *group,
struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *fanotify_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info)
BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
- if (!fanotify_should_send_event(inode_mark, fanotify_mark, mask, data,
- data_type))
+ if (!fanotify_should_send_event(iter_info, mask, data, data_type))
return 0;
pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
struct inotify_inode_mark *inode_mark;
struct inode *inode;
- if (!(mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE))
+ if (mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE)
return;
inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
- if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+ if (mark->connector->type == FSNOTIFY_OBJ_TYPE_INODE) {
inode = igrab(mark->connector->inode);
if (!inode)
return;
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
- } else if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
struct mount *mnt = real_mount(mark->connector->mnt);
seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
EXPORT_SYMBOL_GPL(__fsnotify_parent);
static int send_to_group(struct inode *to_tell,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
__u32 mask, const void *data,
int data_is, u32 cookie,
const unsigned char *file_name,
__u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
__u32 marks_mask = 0;
__u32 marks_ignored_mask = 0;
+ struct fsnotify_mark *mark;
+ int type;
- if (unlikely(!inode_mark && !vfsmount_mark)) {
- BUG();
+ if (WARN_ON(!iter_info->report_mask))
return 0;
- }
/* clear ignored on inode modification */
if (mask & FS_MODIFY) {
- if (inode_mark &&
- !(inode_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
- inode_mark->ignored_mask = 0;
- if (vfsmount_mark &&
- !(vfsmount_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
- vfsmount_mark->ignored_mask = 0;
- }
-
- /* does the inode mark tell us to do something? */
- if (inode_mark) {
- group = inode_mark->group;
- marks_mask |= inode_mark->mask;
- marks_ignored_mask |= inode_mark->ignored_mask;
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ if (mark &&
+ !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
+ mark->ignored_mask = 0;
+ }
}
- /* does the vfsmount_mark tell us to do something? */
- if (vfsmount_mark) {
- group = vfsmount_mark->group;
- marks_mask |= vfsmount_mark->mask;
- marks_ignored_mask |= vfsmount_mark->ignored_mask;
+ fsnotify_foreach_obj_type(type) {
+ if (!fsnotify_iter_should_report_type(iter_info, type))
+ continue;
+ mark = iter_info->marks[type];
+ /* does the object mark tell us to do something? */
+ if (mark) {
+ group = mark->group;
+ marks_mask |= mark->mask;
+ marks_ignored_mask |= mark->ignored_mask;
+ }
}
- pr_debug("%s: group=%p to_tell=%p mask=%x inode_mark=%p"
- " vfsmount_mark=%p marks_mask=%x marks_ignored_mask=%x"
+ pr_debug("%s: group=%p to_tell=%p mask=%x marks_mask=%x marks_ignored_mask=%x"
" data=%p data_is=%d cookie=%d\n",
- __func__, group, to_tell, mask, inode_mark, vfsmount_mark,
- marks_mask, marks_ignored_mask, data,
- data_is, cookie);
+ __func__, group, to_tell, mask, marks_mask, marks_ignored_mask,
+ data, data_is, cookie);
if (!(test_mask & marks_mask & ~marks_ignored_mask))
return 0;
- return group->ops->handle_event(group, to_tell, inode_mark,
- vfsmount_mark, mask, data, data_is,
+ return group->ops->handle_event(group, to_tell, mask, data, data_is,
file_name, cookie, iter_info);
}
return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}
+/*
+ * iter_info is a multi head priority queue of marks.
+ * Pick a subset of marks from queue heads, all with the
+ * same group and set the report_mask for selected subset.
+ * Returns the report_mask of the selected subset.
+ */
+static unsigned int fsnotify_iter_select_report_types(
+ struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_group *max_prio_group = NULL;
+ struct fsnotify_mark *mark;
+ int type;
+
+ /* Choose max prio group among groups of all queue heads */
+ fsnotify_foreach_obj_type(type) {
+ mark = iter_info->marks[type];
+ if (mark &&
+ fsnotify_compare_groups(max_prio_group, mark->group) > 0)
+ max_prio_group = mark->group;
+ }
+
+ if (!max_prio_group)
+ return 0;
+
+ /* Set the report mask for marks from same group as max prio group */
+ iter_info->report_mask = 0;
+ fsnotify_foreach_obj_type(type) {
+ mark = iter_info->marks[type];
+ if (mark &&
+ fsnotify_compare_groups(max_prio_group, mark->group) == 0)
+ fsnotify_iter_set_report_type(iter_info, type);
+ }
+
+ return iter_info->report_mask;
+}
+
+/*
+ * Pop from iter_info multi head queue, the marks that were iterated in the
+ * current iteration step.
+ */
+static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
+{
+ int type;
+
+ fsnotify_foreach_obj_type(type) {
+ if (fsnotify_iter_should_report_type(iter_info, type))
+ iter_info->marks[type] =
+ fsnotify_next_mark(iter_info->marks[type]);
+ }
+}
+
/*
* This is the main call to fsnotify. The VFS calls into hook specific functions
* in linux/fsnotify.h. Those functions then in turn call here. Here will call
if ((mask & FS_MODIFY) ||
(test_mask & to_tell->i_fsnotify_mask)) {
- iter_info.inode_mark =
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
fsnotify_first_mark(&to_tell->i_fsnotify_marks);
}
if (mnt && ((mask & FS_MODIFY) ||
(test_mask & mnt->mnt_fsnotify_mask))) {
- iter_info.inode_mark =
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
fsnotify_first_mark(&to_tell->i_fsnotify_marks);
- iter_info.vfsmount_mark =
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
}
* ignore masks are properly reflected for mount mark notifications.
* That's why this traversal is so complicated...
*/
- while (iter_info.inode_mark || iter_info.vfsmount_mark) {
- struct fsnotify_mark *inode_mark = iter_info.inode_mark;
- struct fsnotify_mark *vfsmount_mark = iter_info.vfsmount_mark;
-
- if (inode_mark && vfsmount_mark) {
- int cmp = fsnotify_compare_groups(inode_mark->group,
- vfsmount_mark->group);
- if (cmp > 0)
- inode_mark = NULL;
- else if (cmp < 0)
- vfsmount_mark = NULL;
- }
-
- ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
- data, data_is, cookie, file_name,
- &iter_info);
+ while (fsnotify_iter_select_report_types(&iter_info)) {
+ ret = send_to_group(to_tell, mask, data, data_is, cookie,
+ file_name, &iter_info);
if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
goto out;
- if (inode_mark)
- iter_info.inode_mark =
- fsnotify_next_mark(iter_info.inode_mark);
- if (vfsmount_mark)
- iter_info.vfsmount_mark =
- fsnotify_next_mark(iter_info.vfsmount_mark);
+ fsnotify_iter_next(&iter_info);
}
ret = 0;
out:
#include "../mount.h"
-struct fsnotify_iter_info {
- struct fsnotify_mark *inode_mark;
- struct fsnotify_mark *vfsmount_mark;
- int srcu_idx;
-};
-
/* destroy all events sitting in this groups notification queue */
extern void fsnotify_flush_notify(struct fsnotify_group *group);
fsnotify_group_stop_queueing(group);
/* Clear all marks for this group and queue them for destruction */
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES_MASK);
/*
* Some marks can still be pinned when waiting for response from
struct fsnotify_group *group);
extern int inotify_handle_event(struct fsnotify_group *group,
struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info);
int inotify_handle_event(struct fsnotify_group *group,
struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info)
{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
struct inotify_inode_mark *i_mark;
struct inotify_event_info *event;
struct fsnotify_event *fsn_event;
int len = 0;
int alloc_len = sizeof(struct inotify_event_info);
- BUG_ON(vfsmount_mark);
+ if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
+ return 0;
if ((inode_mark->mask & FS_EXCL_UNLINK) &&
(data_type == FSNOTIFY_EVENT_PATH)) {
struct fsnotify_group *group)
{
struct inotify_inode_mark *i_mark;
+ struct fsnotify_iter_info iter_info = { };
+
+ fsnotify_iter_set_report_type_mark(&iter_info, FSNOTIFY_OBJ_TYPE_INODE,
+ fsn_mark);
/* Queue ignore event for the watch */
- inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
- NULL, FSNOTIFY_EVENT_NONE, NULL, 0, NULL);
+ inotify_handle_event(group, NULL, FS_IN_IGNORED, NULL,
+ FSNOTIFY_EVENT_NONE, NULL, 0, &iter_info);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
/* remove this mark from the idr */
}
/* we are on the idr, now get on the inode */
- ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, inode, NULL, 0);
+ ret = fsnotify_add_inode_mark_locked(&tmp_i_mark->fsn_mark, inode, 0);
if (ret) {
/* we failed to get on the inode, get off the idr */
inotify_remove_from_idr(group, tmp_i_mark);
if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
new_mask |= mark->mask;
}
- if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
conn->inode->i_fsnotify_mask = new_mask;
- else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+ else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT)
real_mount(conn->mnt)->mnt_fsnotify_mask = new_mask;
}
spin_lock(&conn->lock);
__fsnotify_recalc_mask(conn);
spin_unlock(&conn->lock);
- if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
__fsnotify_update_child_dentry_flags(conn->inode);
}
{
struct inode *inode = NULL;
- if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+ if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
inode = conn->inode;
rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
inode->i_fsnotify_mask = 0;
conn->inode = NULL;
- conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
- } else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
+ } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
rcu_assign_pointer(real_mount(conn->mnt)->mnt_fsnotify_marks,
NULL);
real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
conn->mnt = NULL;
- conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
}
return inode;
bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info)
{
- /* This can fail if mark is being removed */
- if (!fsnotify_get_mark_safe(iter_info->inode_mark))
- return false;
- if (!fsnotify_get_mark_safe(iter_info->vfsmount_mark)) {
- fsnotify_put_mark_wake(iter_info->inode_mark);
- return false;
+ int type;
+
+ fsnotify_foreach_obj_type(type) {
+ /* This can fail if mark is being removed */
+ if (!fsnotify_get_mark_safe(iter_info->marks[type]))
+ goto fail;
}
/*
srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx);
return true;
+
+fail:
+ for (type--; type >= 0; type--)
+ fsnotify_put_mark_wake(iter_info->marks[type]);
+ return false;
}
void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
{
+ int type;
+
iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
- fsnotify_put_mark_wake(iter_info->inode_mark);
- fsnotify_put_mark_wake(iter_info->vfsmount_mark);
+ fsnotify_foreach_obj_type(type)
+ fsnotify_put_mark_wake(iter_info->marks[type]);
}
/*
spin_lock_init(&conn->lock);
INIT_HLIST_HEAD(&conn->list);
if (inode) {
- conn->flags = FSNOTIFY_OBJ_TYPE_INODE;
+ conn->type = FSNOTIFY_OBJ_TYPE_INODE;
conn->inode = igrab(inode);
} else {
- conn->flags = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ conn->type = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
conn->mnt = mnt;
}
/*
if (!conn)
goto out;
spin_lock(&conn->lock);
- if (!(conn->flags & (FSNOTIFY_OBJ_TYPE_INODE |
- FSNOTIFY_OBJ_TYPE_VFSMOUNT))) {
+ if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) {
spin_unlock(&conn->lock);
srcu_read_unlock(&fsnotify_mark_srcu, idx);
return NULL;
return NULL;
}
-/* Clear any marks in a group with given type */
+/* Clear any marks in a group with given type mask */
void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
- unsigned int type)
+ unsigned int type_mask)
{
struct fsnotify_mark *lmark, *mark;
LIST_HEAD(to_free);
struct list_head *head = &to_free;
/* Skip selection step if we want to clear all marks. */
- if (type == FSNOTIFY_OBJ_ALL_TYPES) {
+ if (type_mask == FSNOTIFY_OBJ_ALL_TYPES_MASK) {
head = &group->marks_list;
goto clear;
}
*/
mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
- if (mark->connector->flags & type)
+ if ((1U << mark->connector->type) & type_mask)
list_move(&mark->g_list, &to_free);
}
mutex_unlock(&group->mark_mutex);
* mtime is the last change of the data within the file. Not changed
* when only metadata is changed, e.g. a rename doesn't affect mtime.
*/
- vi->i_mtime = ntfs2utc(si->last_data_change_time);
+ vi->i_mtime = timespec_to_timespec64(ntfs2utc(si->last_data_change_time));
/*
* ctime is the last change of the metadata of the file. This obviously
* always changes, when mtime is changed. ctime can be changed on its
* own, mtime is then not changed, e.g. when a file is renamed.
*/
- vi->i_ctime = ntfs2utc(si->last_mft_change_time);
+ vi->i_ctime = timespec_to_timespec64(ntfs2utc(si->last_mft_change_time));
/*
* Last access to the data within the file. Not changed during a rename
* for example but changed whenever the file is written to.
*/
- vi->i_atime = ntfs2utc(si->last_access_time);
+ vi->i_atime = timespec_to_timespec64(ntfs2utc(si->last_access_time));
/* Find the attribute list attribute if present. */
ntfs_attr_reinit_search_ctx(ctx);
* for real.
*/
if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) {
- struct timespec now = current_time(VFS_I(base_ni));
+ struct timespec64 now = current_time(VFS_I(base_ni));
int sync_it = 0;
- if (!timespec_equal(&VFS_I(base_ni)->i_mtime, &now) ||
- !timespec_equal(&VFS_I(base_ni)->i_ctime, &now))
+ if (!timespec64_equal(&VFS_I(base_ni)->i_mtime, &now) ||
+ !timespec64_equal(&VFS_I(base_ni)->i_ctime, &now))
sync_it = 1;
VFS_I(base_ni)->i_mtime = now;
VFS_I(base_ni)->i_ctime = now;
}
}
if (ia_valid & ATTR_ATIME)
- vi->i_atime = timespec_trunc(attr->ia_atime,
- vi->i_sb->s_time_gran);
+ vi->i_atime = timespec64_trunc(attr->ia_atime,
+ vi->i_sb->s_time_gran);
if (ia_valid & ATTR_MTIME)
- vi->i_mtime = timespec_trunc(attr->ia_mtime,
- vi->i_sb->s_time_gran);
+ vi->i_mtime = timespec64_trunc(attr->ia_mtime,
+ vi->i_sb->s_time_gran);
if (ia_valid & ATTR_CTIME)
- vi->i_ctime = timespec_trunc(attr->ia_ctime,
- vi->i_sb->s_time_gran);
+ vi->i_ctime = timespec64_trunc(attr->ia_ctime,
+ vi->i_sb->s_time_gran);
mark_inode_dirty(vi);
out:
return err;
si = (STANDARD_INFORMATION*)((u8*)ctx->attr +
le16_to_cpu(ctx->attr->data.resident.value_offset));
/* Update the access times if they have changed. */
- nt = utc2ntfs(vi->i_mtime);
+ nt = utc2ntfs(timespec64_to_timespec(vi->i_mtime));
if (si->last_data_change_time != nt) {
ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, "
"new = 0x%llx", vi->i_ino, (long long)
si->last_data_change_time = nt;
modified = true;
}
- nt = utc2ntfs(vi->i_ctime);
+ nt = utc2ntfs(timespec64_to_timespec(vi->i_ctime));
if (si->last_mft_change_time != nt) {
ntfs_debug("Updating ctime for inode 0x%lx: old = 0x%llx, "
"new = 0x%llx", vi->i_ino, (long long)
si->last_mft_change_time = nt;
modified = true;
}
- nt = utc2ntfs(vi->i_atime);
+ nt = utc2ntfs(timespec64_to_timespec(vi->i_atime));
if (si->last_access_time != nt) {
ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, "
"new = 0x%llx", vi->i_ino,
struct ocfs2_inode_info *oi = OCFS2_I(inode);
struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
struct ocfs2_meta_lvb *lvb;
+ struct timespec ts;
lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
lvb->lvb_igid = cpu_to_be32(i_gid_read(inode));
lvb->lvb_imode = cpu_to_be16(inode->i_mode);
lvb->lvb_inlink = cpu_to_be16(inode->i_nlink);
+ ts = timespec64_to_timespec(inode->i_atime);
lvb->lvb_iatime_packed =
- cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime));
+ cpu_to_be64(ocfs2_pack_timespec(&ts));
+ ts = timespec64_to_timespec(inode->i_ctime);
lvb->lvb_ictime_packed =
- cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime));
+ cpu_to_be64(ocfs2_pack_timespec(&ts));
+ ts = timespec64_to_timespec(inode->i_mtime);
lvb->lvb_imtime_packed =
- cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
+ cpu_to_be64(ocfs2_pack_timespec(&ts));
lvb->lvb_iattr = cpu_to_be32(oi->ip_attr);
lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features);
lvb->lvb_igeneration = cpu_to_be32(inode->i_generation);
static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
{
+ struct timespec ts;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
struct ocfs2_meta_lvb *lvb;
i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
inode->i_mode = be16_to_cpu(lvb->lvb_imode);
set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
- ocfs2_unpack_timespec(&inode->i_atime,
+ ocfs2_unpack_timespec(&ts,
be64_to_cpu(lvb->lvb_iatime_packed));
- ocfs2_unpack_timespec(&inode->i_mtime,
+ inode->i_atime = timespec_to_timespec64(ts);
+ ocfs2_unpack_timespec(&ts,
be64_to_cpu(lvb->lvb_imtime_packed));
- ocfs2_unpack_timespec(&inode->i_ctime,
+ inode->i_mtime = timespec_to_timespec64(ts);
+ ocfs2_unpack_timespec(&ts,
be64_to_cpu(lvb->lvb_ictime_packed));
+ inode->i_ctime = timespec_to_timespec64(ts);
spin_unlock(&oi->ip_lock);
}
int ocfs2_should_update_atime(struct inode *inode,
struct vfsmount *vfsmnt)
{
- struct timespec now;
+ struct timespec64 now;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return 0;
if (vfsmnt->mnt_flags & MNT_RELATIME) {
- if ((timespec_compare(&inode->i_atime, &inode->i_mtime) <= 0) ||
- (timespec_compare(&inode->i_atime, &inode->i_ctime) <= 0))
+ if ((timespec64_compare(&inode->i_atime, &inode->i_mtime) <= 0) ||
+ (timespec64_compare(&inode->i_atime, &inode->i_ctime) <= 0))
return 1;
return 0;
return ksys_fchown(fd, user, group);
}
-int open_check_o_direct(struct file *f)
-{
- /* NB: we're sure to have correct a_ops only after f_op->open */
- if (f->f_flags & O_DIRECT) {
- if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
- return -EINVAL;
- }
- return 0;
-}
-
static int do_dentry_open(struct file *f,
struct inode *inode,
- int (*open)(struct inode *, struct file *),
- const struct cred *cred)
+ int (*open)(struct inode *, struct file *))
{
static const struct file_operations empty_fops = {};
int error;
- f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
- FMODE_PREAD | FMODE_PWRITE;
-
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
if (unlikely(f->f_flags & O_PATH)) {
- f->f_mode = FMODE_PATH;
+ f->f_mode = FMODE_PATH | FMODE_OPENED;
f->f_op = &empty_fops;
return 0;
}
goto cleanup_all;
}
- error = security_file_open(f, cred);
+ error = security_file_open(f);
if (error)
goto cleanup_all;
if (error)
goto cleanup_all;
+ /* normally all 3 are set; ->open() can clear them if needed */
+ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
if (!open)
open = f->f_op->open;
if (open) {
if (error)
goto cleanup_all;
}
+ f->f_mode |= FMODE_OPENED;
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
if ((f->f_mode & FMODE_READ) &&
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
+ /* NB: we're sure to have correct a_ops only after f_op->open */
+ if (f->f_flags & O_DIRECT) {
+ if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+ return -EINVAL;
+ }
return 0;
cleanup_all:
+ if (WARN_ON_ONCE(error > 0))
+ error = -EINVAL;
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITER) {
put_write_access(inode);
* Returns zero on success or -errno if the open failed.
*/
int finish_open(struct file *file, struct dentry *dentry,
- int (*open)(struct inode *, struct file *),
- int *opened)
+ int (*open)(struct inode *, struct file *))
{
- int error;
- BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+ BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
file->f_path.dentry = dentry;
- error = do_dentry_open(file, d_backing_inode(dentry), open,
- current_cred());
- if (!error)
- *opened |= FILE_OPENED;
-
- return error;
+ return do_dentry_open(file, d_backing_inode(dentry), open);
}
EXPORT_SYMBOL(finish_open);
* NB: unlike finish_open() this function does consume the dentry reference and
* the caller need not dput() it.
*
- * Returns "1" which must be the return value of ->atomic_open() after having
+ * Returns "0" which must be the return value of ->atomic_open() after having
* called this function.
*/
int finish_no_open(struct file *file, struct dentry *dentry)
{
file->f_path.dentry = dentry;
- return 1;
+ return 0;
}
EXPORT_SYMBOL(finish_no_open);
* @file: newly allocated file with f_flag initialized
* @cred: credentials to use
*/
-int vfs_open(const struct path *path, struct file *file,
- const struct cred *cred)
+int vfs_open(const struct path *path, struct file *file)
{
struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0);
return PTR_ERR(dentry);
file->f_path = *path;
- return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
+ return do_dentry_open(file, d_backing_inode(dentry), NULL);
}
struct file *dentry_open(const struct path *path, int flags,
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
- f = get_empty_filp();
+ f = alloc_empty_file(flags, cred);
if (!IS_ERR(f)) {
- f->f_flags = flags;
- error = vfs_open(path, f, cred);
- if (!error) {
- /* from now on we need fput() to dispose of f */
- error = open_check_o_direct(f);
- if (error) {
- fput(f);
- f = ERR_PTR(error);
- }
- } else {
- put_filp(f);
+ error = vfs_open(path, f);
+ if (error) {
+ fput(f);
f = ERR_PTR(error);
}
}
}
EXPORT_SYMBOL(file_open_root);
-struct file *filp_clone_open(struct file *oldfile)
-{
- struct file *file;
- int retval;
-
- file = get_empty_filp();
- if (IS_ERR(file))
- return file;
-
- file->f_flags = oldfile->f_flags;
- retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred);
- if (retval) {
- put_filp(file);
- return ERR_PTR(retval);
- }
-
- return file;
-}
-EXPORT_SYMBOL(filp_clone_open);
-
long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
struct open_flags op;
__s32 count;
};
-static unsigned long translate_dev_map26(unsigned long args, long *error)
-{
- struct ORANGEFS_dev_map_desc32 __user *p32 = (void __user *)args;
- /*
- * Depending on the architecture, allocate some space on the
- * user-call-stack based on our expected layout.
- */
- struct ORANGEFS_dev_map_desc __user *p =
- compat_alloc_user_space(sizeof(*p));
- compat_uptr_t addr;
-
- *error = 0;
- /* get the ptr from the 32 bit user-space */
- if (get_user(addr, &p32->ptr))
- goto err;
- /* try to put that into a 64-bit layout */
- if (put_user(compat_ptr(addr), &p->ptr))
- goto err;
- /* copy the remaining fields */
- if (copy_in_user(&p->total_size, &p32->total_size, sizeof(__s32)))
- goto err;
- if (copy_in_user(&p->size, &p32->size, sizeof(__s32)))
- goto err;
- if (copy_in_user(&p->count, &p32->count, sizeof(__s32)))
- goto err;
- return (unsigned long)p;
-err:
- *error = -EFAULT;
- return 0;
-}
-
/*
* 32 bit user-space apps' ioctl handlers when kernel modules
* is compiled as a 64 bit one
unsigned long args)
{
long ret;
- unsigned long arg = args;
/* Check for properly constructed commands */
ret = check_ioctl_command(cmd);
if (ret < 0)
return ret;
if (cmd == ORANGEFS_DEV_MAP) {
- /*
- * convert the arguments to what we expect internally
- * in kernel space
- */
- arg = translate_dev_map26(args, &ret);
- if (ret < 0) {
- gossip_err("Could not translate dev map\n");
- return ret;
- }
+ struct ORANGEFS_dev_map_desc desc;
+ struct ORANGEFS_dev_map_desc32 d32;
+
+ if (copy_from_user(&d32, (void __user *)args, sizeof(d32)))
+ return -EFAULT;
+
+ desc.ptr = compat_ptr(d32.ptr);
+ desc.total_size = d32.total_size;
+ desc.size = d32.size;
+ desc.count = d32.count;
+ return orangefs_bufmap_initialize(&desc);
}
/* no other ioctl requires translation */
- return dispatch_ioctl_command(cmd, arg);
+ return dispatch_ioctl_command(cmd, args);
}
#endif /* CONFIG_COMPAT is in .config */
return generic_permission(inode, mask);
}
-int orangefs_update_time(struct inode *inode, struct timespec *time, int flags)
+int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags)
{
struct iattr iattr;
gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_update_time: %pU\n",
int orangefs_permission(struct inode *inode, int mask);
-int orangefs_update_time(struct inode *, struct timespec *, int);
+int orangefs_update_time(struct inode *, struct timespec64 *, int);
/*
* defined in xattr.c
// SPDX-License-Identifier: GPL-2.0
/*
- * Documentation/ABI/stable/orangefs-sysfs:
+ * Documentation/ABI/stable/sysfs-fs-orangefs:
*
* What: /sys/fs/orangefs/perf_counter_reset
* Date: June 2015
return err;
}
-int ovl_update_time(struct inode *inode, struct timespec *ts, int flags)
+int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags)
{
if (flags & S_ATIME) {
struct ovl_fs *ofs = inode->i_sb->s_fs_info;
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
struct posix_acl *ovl_get_acl(struct inode *inode, int type);
int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
-int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
+int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags);
bool ovl_is_private_xattr(const char *name);
struct ovl_inode_params {
}
}
-static struct wait_queue_head *
-pipe_get_poll_head(struct file *filp, __poll_t events)
-{
- struct pipe_inode_info *pipe = filp->private_data;
-
- return &pipe->wait;
-}
-
/* No kernel lock held - fine */
-static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+static __poll_t
+pipe_poll(struct file *filp, poll_table *wait)
{
+ __poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- int nrbufs = pipe->nrbufs;
- __poll_t mask = 0;
+ int nrbufs;
+
+ poll_wait(filp, &pipe->wait, wait);
/* Reading only -- no need for acquiring the semaphore. */
+ nrbufs = pipe->nrbufs;
+ mask = 0;
if (filp->f_mode & FMODE_READ) {
mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
if (!pipe->writers && filp->f_version != pipe->w_counter)
int create_pipe_files(struct file **res, int flags)
{
- int err;
struct inode *inode = get_pipe_inode();
struct file *f;
- struct path path;
if (!inode)
return -ENFILE;
- err = -ENOMEM;
- path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
- if (!path.dentry)
- goto err_inode;
- path.mnt = mntget(pipe_mnt);
-
- d_instantiate(path.dentry, inode);
-
- f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+ f = alloc_file_pseudo(inode, pipe_mnt, "",
+ O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+ &pipefifo_fops);
if (IS_ERR(f)) {
- err = PTR_ERR(f);
- goto err_dentry;
+ free_pipe_info(inode->i_pipe);
+ iput(inode);
+ return PTR_ERR(f);
}
- f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
f->private_data = inode->i_pipe;
- res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+ res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
+ &pipefifo_fops);
if (IS_ERR(res[0])) {
- err = PTR_ERR(res[0]);
- goto err_file;
+ put_pipe_info(inode, inode->i_pipe);
+ fput(f);
+ return PTR_ERR(res[0]);
}
-
- path_get(&path);
res[0]->private_data = inode->i_pipe;
- res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
res[1] = f;
return 0;
-
-err_file:
- put_filp(f);
-err_dentry:
- free_pipe_info(inode->i_pipe);
- path_put(&path);
- return err;
-
-err_inode:
- free_pipe_info(inode->i_pipe);
- iput(inode);
- return err;
}
static int __do_pipe_flags(int *fd, struct file **files, int flags)
.llseek = no_llseek,
.read_iter = pipe_read,
.write_iter = pipe_write,
- .get_poll_head = pipe_get_poll_head,
- .poll_mask = pipe_poll_mask,
+ .poll = pipe_poll,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
if (env_start != arg_end || env_start >= env_end)
env_start = env_end = arg_end;
+ /* .. and limit it to a maximum of one page of slop */
+ if (env_end >= arg_end + PAGE_SIZE)
+ env_end = arg_end + PAGE_SIZE - 1;
+
/* We're not going to care if "*ppos" has high bits set */
pos = arg_start + *ppos;
while (count) {
int got;
size_t size = min_t(size_t, PAGE_SIZE, count);
+ long offset;
- got = access_remote_vm(mm, pos, page, size, FOLL_ANON);
- if (got <= 0)
+ /*
+ * Are we already starting past the official end?
+ * We always include the last byte that is *supposed*
+ * to be NUL
+ */
+ offset = (pos >= arg_end) ? pos - arg_end + 1 : 0;
+
+ got = access_remote_vm(mm, pos - offset, page, size + offset, FOLL_ANON);
+ if (got <= offset)
break;
+ got -= offset;
/* Don't walk past a NUL character once you hit arg_end */
if (pos + got >= arg_end) {
n = arg_end - pos - 1;
/* Cut off at first NUL after 'n' */
- got = n + strnlen(page+n, got-n);
- if (!got)
+ got = n + strnlen(page+n, offset+got-n);
+ if (got < offset)
break;
+ got -= offset;
+
+ /* Include the NUL if it existed */
+ if (got < size)
+ got++;
}
- got -= copy_to_user(buf, page, got);
+ got -= copy_to_user(buf, page+offset, got);
if (unlikely(!got)) {
if (!len)
len = -EFAULT;
for (p = ents; p < last; p++) {
if (p->len != dentry->d_name.len)
continue;
- if (!memcmp(dentry->d_name.name, p->name, p->len))
+ if (!memcmp(dentry->d_name.name, p->name, p->len)) {
+ res = proc_pident_instantiate(dentry, task, p);
break;
+ }
}
- if (p >= last)
- goto out;
-
- res = proc_pident_instantiate(dentry, task, p);
-out:
put_task_struct(task);
out_no_task:
return res;
if (!ent)
goto out;
- if (qstr.len + 1 <= sizeof(ent->inline_name)) {
+ if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) {
ent->name = ent->inline_name;
} else {
ent->name = kmalloc(qstr.len + 1, GFP_KERNEL);
return seq_open(file, de->seq_ops);
}
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *de = PDE(inode);
+
+ if (de->state_size)
+ return seq_release_private(inode, file);
+ return seq_release(inode, file);
+}
+
static const struct file_operations proc_seq_fops = {
.open = proc_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = proc_seq_release,
};
struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
return __PDE_DATA(inode);
}
EXPORT_SYMBOL(PDE_DATA);
+
+/*
+ * Pull a user buffer into memory and pass it to the file's write handler if
+ * one is supplied. The ->write() method is permitted to modify the
+ * kernel-side buffer.
+ */
+ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size,
+ loff_t *_pos)
+{
+ struct proc_dir_entry *pde = PDE(file_inode(f));
+ char *buf;
+ int ret;
+
+ if (!pde->write)
+ return -EACCES;
+ if (size == 0 || size > PAGE_SIZE - 1)
+ return -EINVAL;
+ buf = memdup_user_nul(ubuf, size);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+ ret = pde->write(f, buf, size);
+ kfree(buf);
+ return ret == 0 ? size : ret;
+}
kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0,
SLAB_ACCOUNT|SLAB_PANIC, NULL);
proc_dir_entry_cache = kmem_cache_create_usercopy(
- "proc_dir_entry", sizeof(struct proc_dir_entry), 0, SLAB_PANIC,
- offsetof(struct proc_dir_entry, inline_name),
- sizeof_field(struct proc_dir_entry, inline_name), NULL);
+ "proc_dir_entry", SIZEOF_PDE_SLOT, 0, SLAB_PANIC,
+ OFFSETOF_PDE_NAME, SIZEOF_PDE_INLINE_NAME, NULL);
}
static int proc_show_options(struct seq_file *seq, struct dentry *root)
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
};
+ proc_write_t write;
void *data;
unsigned int state_size;
unsigned int low_ino;
char *name;
umode_t mode;
u8 namelen;
-#ifdef CONFIG_64BIT
-#define SIZEOF_PDE_INLINE_NAME (192-155)
-#else
-#define SIZEOF_PDE_INLINE_NAME (128-95)
-#endif
- char inline_name[SIZEOF_PDE_INLINE_NAME];
+ char inline_name[];
} __randomize_layout;
+#define OFFSETOF_PDE_NAME offsetof(struct proc_dir_entry, inline_name)
+#define SIZEOF_PDE_SLOT \
+ (OFFSETOF_PDE_NAME + 34 <= 64 ? 64 : \
+ OFFSETOF_PDE_NAME + 34 <= 128 ? 128 : \
+ OFFSETOF_PDE_NAME + 34 <= 192 ? 192 : \
+ OFFSETOF_PDE_NAME + 34 <= 256 ? 256 : \
+ OFFSETOF_PDE_NAME + 34 <= 512 ? 512 : \
+ 0)
+
+#define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE_SLOT - OFFSETOF_PDE_NAME)
+
extern struct kmem_cache *proc_dir_entry_cache;
void pde_free(struct proc_dir_entry *pde);
{
return S_ISDIR(pde->mode) && !pde->proc_iops;
}
+extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *);
/*
* inode.c
WARN_ON_ONCE(state_size < sizeof(*p));
+ if (file->f_mode & FMODE_WRITE && !PDE(inode)->write)
+ return -EACCES;
+
net = get_proc_net(inode);
if (!net)
return -ENXIO;
static const struct file_operations proc_net_seq_fops = {
.open = seq_open_net,
.read = seq_read,
+ .write = proc_simple_write,
.llseek = seq_lseek,
.release = seq_release_net,
};
}
EXPORT_SYMBOL_GPL(proc_create_net_data);
+/**
+ * proc_create_net_data_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @ops: The seq_file ops with which to read the file.
+ * @write: The write method which which to 'modify' the file.
+ * @data: Data for retrieval by PDE_DATA().
+ *
+ * Create a network namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * series of elements and also provides for the file accepting writes that have
+ * some arbitrary effect.
+ *
+ * The functions in the @ops table are used to iterate over items to be
+ * presented and extract the readable content using the seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience. The buffer may be
+ * modified by the @write function. @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * PDE_DATA() on the file inode. The network namespace must be accessed by
+ * calling seq_file_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ const struct seq_operations *ops,
+ proc_write_t write,
+ unsigned int state_size, void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_net_seq_fops;
+ p->seq_ops = ops;
+ p->state_size = state_size;
+ p->write = write;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data_write);
+
static int single_open_net(struct inode *inode, struct file *file)
{
struct proc_dir_entry *de = PDE(inode);
static const struct file_operations proc_net_single_fops = {
.open = single_open_net,
.read = seq_read,
+ .write = proc_simple_write,
.llseek = seq_lseek,
.release = single_release_net,
};
}
EXPORT_SYMBOL_GPL(proc_create_net_single);
+/**
+ * proc_create_net_single_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @show: The seqfile show method with which to read the file.
+ * @write: The write method which which to 'modify' the file.
+ * @data: Data for retrieval by PDE_DATA().
+ *
+ * Create a network-namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * single element rather than a series and also provides for the file accepting
+ * writes that have some arbitrary effect.
+ *
+ * The @show function is called to extract the readable content via the
+ * seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience. The buffer may be
+ * modified by the @write function. @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * PDE_DATA() on the file inode. The network namespace must be accessed by
+ * calling seq_file_single_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *),
+ proc_write_t write,
+ void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_net_single_fops;
+ p->single_show = show;
+ p->write = write;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single_write);
+
static struct net *get_proc_task_net(struct inode *dir)
{
struct task_struct *task;
.proc_fops = &proc_root_operations,
.parent = &proc_root,
.subdir = RB_ROOT,
- .name = proc_root.inline_name,
- .inline_name = "/proc",
+ .name = "/proc",
};
int pid_ns_prepare_proc(struct pid_namespace *ns)
SEQ_PUT_DEC(" kB\nSwap: ", mss->swap);
SEQ_PUT_DEC(" kB\nSwapPss: ",
mss->swap_pss >> PSS_SHIFT);
- SEQ_PUT_DEC(" kB\nLocked: ", mss->pss >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nLocked: ",
+ mss->pss_locked >> PSS_SHIFT);
seq_puts(m, " kB\n");
}
if (!rollup_mode) {
static int uptime_proc_show(struct seq_file *m, void *v)
{
struct timespec uptime;
- struct timespec idle;
+ struct timespec64 idle;
u64 nsec;
u32 rem;
int i;
record->psi = psinfo;
/* Report zeroed timestamp if called before timekeeping has resumed. */
- record->time = ns_to_timespec(ktime_get_real_fast_ns());
+ record->time = ns_to_timespec64(ktime_get_real_fast_ns());
}
/*
return prz;
}
-static int ramoops_read_kmsg_hdr(char *buffer, struct timespec *time,
+static int ramoops_read_kmsg_hdr(char *buffer, struct timespec64 *time,
bool *compressed)
{
char data_type;
int header_length = 0;
- if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n%n", &time->tv_sec,
- &time->tv_nsec, &data_type, &header_length) == 3) {
+ if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lld.%lu-%c\n%n",
+ (time64_t *)&time->tv_sec, &time->tv_nsec, &data_type,
+ &header_length) == 3) {
if (data_type == 'C')
*compressed = true;
else
*compressed = false;
- } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu\n%n",
- &time->tv_sec, &time->tv_nsec, &header_length) == 2) {
- *compressed = false;
+ } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lld.%lu\n%n",
+ (time64_t *)&time->tv_sec, &time->tv_nsec,
+ &header_length) == 2) {
+ *compressed = false;
} else {
time->tv_sec = 0;
time->tv_nsec = 0;
char *hdr;
size_t len;
- hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n",
- record->time.tv_sec,
+ hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lld.%06lu-%c\n",
+ (time64_t)record->time.tv_sec,
record->time.tv_nsec / 1000,
record->compressed ? 'C' : 'D');
WARN_ON_ONCE(!hdr);
static unsigned long
dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- struct list_head *head;
struct dquot *dquot;
unsigned long freed = 0;
spin_lock(&dq_list_lock);
- head = free_dquots.prev;
- while (head != &free_dquots && sc->nr_to_scan) {
- dquot = list_entry(head, struct dquot, dq_free);
+ while (!list_empty(&free_dquots) && sc->nr_to_scan) {
+ dquot = list_first_entry(&free_dquots, struct dquot, dq_free);
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
sc->nr_to_scan--;
freed++;
- head = free_dquots.prev;
}
spin_unlock(&dq_list_lock);
return freed;
int jbegin_count;
umode_t old_inode_mode;
unsigned long savelink = 1;
- struct timespec ctime;
+ struct timespec64 ctime;
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
}
/* %k */
-static void sprintf_le_key(char *buf, struct reiserfs_key *key)
+static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key)
{
if (key)
- sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id),
- le32_to_cpu(key->k_objectid), le_offset(key),
- le_type(key));
+ return scnprintf(buf, size, "[%d %d %s %s]",
+ le32_to_cpu(key->k_dir_id),
+ le32_to_cpu(key->k_objectid), le_offset(key),
+ le_type(key));
else
- sprintf(buf, "[NULL]");
+ return scnprintf(buf, size, "[NULL]");
}
/* %K */
-static void sprintf_cpu_key(char *buf, struct cpu_key *key)
+static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key)
{
if (key)
- sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id,
- key->on_disk_key.k_objectid, reiserfs_cpu_offset(key),
- cpu_type(key));
+ return scnprintf(buf, size, "[%d %d %s %s]",
+ key->on_disk_key.k_dir_id,
+ key->on_disk_key.k_objectid,
+ reiserfs_cpu_offset(key), cpu_type(key));
else
- sprintf(buf, "[NULL]");
+ return scnprintf(buf, size, "[NULL]");
}
-static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh)
+static int scnprintf_de_head(char *buf, size_t size,
+ struct reiserfs_de_head *deh)
{
if (deh)
- sprintf(buf,
- "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
- deh_offset(deh), deh_dir_id(deh), deh_objectid(deh),
- deh_location(deh), deh_state(deh));
+ return scnprintf(buf, size,
+ "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
+ deh_offset(deh), deh_dir_id(deh),
+ deh_objectid(deh), deh_location(deh),
+ deh_state(deh));
else
- sprintf(buf, "[NULL]");
+ return scnprintf(buf, size, "[NULL]");
}
-static void sprintf_item_head(char *buf, struct item_head *ih)
+static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih)
{
if (ih) {
- strcpy(buf,
- (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*");
- sprintf_le_key(buf + strlen(buf), &(ih->ih_key));
- sprintf(buf + strlen(buf), ", item_len %d, item_location %d, "
- "free_space(entry_count) %d",
- ih_item_len(ih), ih_location(ih), ih_free_space(ih));
+ char *p = buf;
+ char * const end = buf + size;
+
+ p += scnprintf(p, end - p, "%s",
+ (ih_version(ih) == KEY_FORMAT_3_6) ?
+ "*3.6* " : "*3.5*");
+
+ p += scnprintf_le_key(p, end - p, &ih->ih_key);
+
+ p += scnprintf(p, end - p,
+ ", item_len %d, item_location %d, free_space(entry_count) %d",
+ ih_item_len(ih), ih_location(ih),
+ ih_free_space(ih));
+ return p - buf;
} else
- sprintf(buf, "[NULL]");
+ return scnprintf(buf, size, "[NULL]");
}
-static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de)
+static int scnprintf_direntry(char *buf, size_t size,
+ struct reiserfs_dir_entry *de)
{
char name[20];
memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen);
name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0;
- sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid);
+ return scnprintf(buf, size, "\"%s\"==>[%d %d]",
+ name, de->de_dir_id, de->de_objectid);
}
-static void sprintf_block_head(char *buf, struct buffer_head *bh)
+static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh)
{
- sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ",
- B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
+ return scnprintf(buf, size,
+ "level=%d, nr_items=%d, free_space=%d rdkey ",
+ B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
}
-static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
+static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh)
{
- sprintf(buf,
- "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
- bh->b_bdev, bh->b_size,
- (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
- bh->b_state, bh->b_page,
- buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
- buffer_dirty(bh) ? "DIRTY" : "CLEAN",
- buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
+ return scnprintf(buf, size,
+ "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+ bh->b_bdev, bh->b_size,
+ (unsigned long long)bh->b_blocknr,
+ atomic_read(&(bh->b_count)),
+ bh->b_state, bh->b_page,
+ buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
+ buffer_dirty(bh) ? "DIRTY" : "CLEAN",
+ buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
}
-static void sprintf_disk_child(char *buf, struct disk_child *dc)
+static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc)
{
- sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc),
- dc_size(dc));
+ return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]",
+ dc_block_number(dc), dc_size(dc));
}
static char *is_there_reiserfs_struct(char *fmt, int *what)
char *fmt1 = fmt_buf;
char *k;
char *p = error_buf;
+ char * const end = &error_buf[sizeof(error_buf)];
int what;
spin_lock(&error_lock);
- strcpy(fmt1, fmt);
+ if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) {
+ strscpy(error_buf, "format string too long", end - error_buf);
+ goto out_unlock;
+ }
while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) {
*k = 0;
- p += vsprintf(p, fmt1, args);
+ p += vscnprintf(p, end - p, fmt1, args);
switch (what) {
case 'k':
- sprintf_le_key(p, va_arg(args, struct reiserfs_key *));
+ p += scnprintf_le_key(p, end - p,
+ va_arg(args, struct reiserfs_key *));
break;
case 'K':
- sprintf_cpu_key(p, va_arg(args, struct cpu_key *));
+ p += scnprintf_cpu_key(p, end - p,
+ va_arg(args, struct cpu_key *));
break;
case 'h':
- sprintf_item_head(p, va_arg(args, struct item_head *));
+ p += scnprintf_item_head(p, end - p,
+ va_arg(args, struct item_head *));
break;
case 't':
- sprintf_direntry(p,
- va_arg(args,
- struct reiserfs_dir_entry *));
+ p += scnprintf_direntry(p, end - p,
+ va_arg(args, struct reiserfs_dir_entry *));
break;
case 'y':
- sprintf_disk_child(p,
- va_arg(args, struct disk_child *));
+ p += scnprintf_disk_child(p, end - p,
+ va_arg(args, struct disk_child *));
break;
case 'z':
- sprintf_block_head(p,
- va_arg(args, struct buffer_head *));
+ p += scnprintf_block_head(p, end - p,
+ va_arg(args, struct buffer_head *));
break;
case 'b':
- sprintf_buffer_head(p,
- va_arg(args, struct buffer_head *));
+ p += scnprintf_buffer_head(p, end - p,
+ va_arg(args, struct buffer_head *));
break;
case 'a':
- sprintf_de_head(p,
- va_arg(args,
- struct reiserfs_de_head *));
+ p += scnprintf_de_head(p, end - p,
+ va_arg(args, struct reiserfs_de_head *));
break;
}
- p += strlen(p);
fmt1 = k + 2;
}
- vsprintf(p, fmt1, args);
+ p += vscnprintf(p, end - p, fmt1, args);
+out_unlock:
spin_unlock(&error_lock);
}
static void update_ctime(struct inode *inode)
{
- struct timespec now = current_time(inode);
+ struct timespec64 now = current_time(inode);
if (inode_unhashed(inode) || !inode->i_nlink ||
- timespec_equal(&inode->i_ctime, &now))
+ timespec64_equal(&inode->i_ctime, &now))
return;
inode->i_ctime = current_time(inode);
#include <linux/uaccess.h>
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
-{
- if (file->f_op->poll) {
- return file->f_op->poll(file, pt);
- } else if (file_has_poll_mask(file)) {
- unsigned int events = poll_requested_events(pt);
- struct wait_queue_head *head;
-
- if (pt && pt->_qproc) {
- head = file->f_op->get_poll_head(file, events);
- if (!head)
- return DEFAULT_POLLMASK;
- if (IS_ERR(head))
- return EPOLLERR;
- pt->_qproc(file, head, pt);
- }
-
- return file->f_op->poll_mask(file, events);
- } else {
- return DEFAULT_POLLMASK;
- }
-}
-EXPORT_SYMBOL_GPL(vfs_poll);
/*
* Estimate expected accuracy in ns from a timeval.
.llseek = noop_llseek,
};
-static int do_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask,
- int flags)
+static int do_signalfd4(int ufd, sigset_t *mask, int flags)
{
- sigset_t sigmask;
struct signalfd_ctx *ctx;
/* Check the SFD_* constants for consistency. */
if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
return -EINVAL;
- if (sizemask != sizeof(sigset_t) ||
- copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
- return -EINVAL;
- sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
- signotset(&sigmask);
+ sigdelsetmask(mask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ signotset(mask);
if (ufd == -1) {
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
- ctx->sigmask = sigmask;
+ ctx->sigmask = *mask;
/*
* When we call this, the initialization must be complete, since
return -EINVAL;
}
spin_lock_irq(¤t->sighand->siglock);
- ctx->sigmask = sigmask;
+ ctx->sigmask = *mask;
spin_unlock_irq(¤t->sighand->siglock);
wake_up(¤t->sighand->signalfd_wqh);
SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
size_t, sizemask, int, flags)
{
- return do_signalfd4(ufd, user_mask, sizemask, flags);
+ sigset_t mask;
+
+ if (sizemask != sizeof(sigset_t) ||
+ copy_from_user(&mask, user_mask, sizeof(mask)))
+ return -EINVAL;
+ return do_signalfd4(ufd, &mask, flags);
}
SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask,
size_t, sizemask)
{
- return do_signalfd4(ufd, user_mask, sizemask, 0);
+ sigset_t mask;
+
+ if (sizemask != sizeof(sigset_t) ||
+ copy_from_user(&mask, user_mask, sizeof(mask)))
+ return -EINVAL;
+ return do_signalfd4(ufd, &mask, 0);
}
#ifdef CONFIG_COMPAT
static long do_compat_signalfd4(int ufd,
- const compat_sigset_t __user *sigmask,
+ const compat_sigset_t __user *user_mask,
compat_size_t sigsetsize, int flags)
{
- sigset_t tmp;
- sigset_t __user *ksigmask;
+ sigset_t mask;
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
- if (get_compat_sigset(&tmp, sigmask))
- return -EFAULT;
- ksigmask = compat_alloc_user_space(sizeof(sigset_t));
- if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
+ if (get_compat_sigset(&mask, user_mask))
return -EFAULT;
-
- return do_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags);
+ return do_signalfd4(ufd, &mask, flags);
}
COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd,
- const compat_sigset_t __user *, sigmask,
+ const compat_sigset_t __user *, user_mask,
compat_size_t, sigsetsize,
int, flags)
{
- return do_compat_signalfd4(ufd, sigmask, sigsetsize, flags);
+ return do_compat_signalfd4(ufd, user_mask, sigsetsize, flags);
}
COMPAT_SYSCALL_DEFINE3(signalfd, int, ufd,
- const compat_sigset_t __user *,sigmask,
+ const compat_sigset_t __user *, user_mask,
compat_size_t, sigsetsize)
{
- return do_compat_signalfd4(ufd, sigmask, sigsetsize, 0);
+ return do_compat_signalfd4(ufd, user_mask, sigsetsize, 0);
}
#endif
* For lack of a better implementation, implement vmsplice() to userspace
* as a simple copy of the pipes pages to the user iov.
*/
-static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
- unsigned long nr_segs, unsigned int flags)
+static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
+ unsigned int flags)
{
- struct pipe_inode_info *pipe;
- struct splice_desc sd;
- long ret;
- struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov = iovstack;
- struct iov_iter iter;
+ struct pipe_inode_info *pipe = get_pipe_info(file);
+ struct splice_desc sd = {
+ .total_len = iov_iter_count(iter),
+ .flags = flags,
+ .u.data = iter
+ };
+ long ret = 0;
- pipe = get_pipe_info(file);
if (!pipe)
return -EBADF;
- ret = import_iovec(READ, uiov, nr_segs,
- ARRAY_SIZE(iovstack), &iov, &iter);
- if (ret < 0)
- return ret;
-
- sd.total_len = iov_iter_count(&iter);
- sd.len = 0;
- sd.flags = flags;
- sd.u.data = &iter;
- sd.pos = 0;
-
if (sd.total_len) {
pipe_lock(pipe);
ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
pipe_unlock(pipe);
}
- kfree(iov);
return ret;
}
* as splice-from-memory, where the regular splice is splice-from-file (or
* to file). In both cases the output is a pipe, naturally.
*/
-static long vmsplice_to_pipe(struct file *file, const struct iovec __user *uiov,
- unsigned long nr_segs, unsigned int flags)
+static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
+ unsigned int flags)
{
struct pipe_inode_info *pipe;
- struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov = iovstack;
- struct iov_iter from;
- long ret;
+ long ret = 0;
unsigned buf_flag = 0;
if (flags & SPLICE_F_GIFT)
if (!pipe)
return -EBADF;
- ret = import_iovec(WRITE, uiov, nr_segs,
- ARRAY_SIZE(iovstack), &iov, &from);
- if (ret < 0)
- return ret;
-
pipe_lock(pipe);
ret = wait_for_space(pipe, flags);
if (!ret)
- ret = iter_to_pipe(&from, pipe, buf_flag);
+ ret = iter_to_pipe(iter, pipe, buf_flag);
pipe_unlock(pipe);
if (ret > 0)
wakeup_pipe_readers(pipe);
- kfree(iov);
return ret;
}
+static int vmsplice_type(struct fd f, int *type)
+{
+ if (!f.file)
+ return -EBADF;
+ if (f.file->f_mode & FMODE_WRITE) {
+ *type = WRITE;
+ } else if (f.file->f_mode & FMODE_READ) {
+ *type = READ;
+ } else {
+ fdput(f);
+ return -EBADF;
+ }
+ return 0;
+}
+
/*
* Note that vmsplice only really supports true splicing _from_ user memory
* to a pipe, not the other way around. Splicing from user memory is a simple
* Currently we punt and implement it as a normal copy, see pipe_to_user().
*
*/
-static long do_vmsplice(int fd, const struct iovec __user *iov,
- unsigned long nr_segs, unsigned int flags)
+static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags)
{
- struct fd f;
- long error;
-
if (unlikely(flags & ~SPLICE_F_ALL))
return -EINVAL;
- if (unlikely(nr_segs > UIO_MAXIOV))
- return -EINVAL;
- else if (unlikely(!nr_segs))
- return 0;
- error = -EBADF;
- f = fdget(fd);
- if (f.file) {
- if (f.file->f_mode & FMODE_WRITE)
- error = vmsplice_to_pipe(f.file, iov, nr_segs, flags);
- else if (f.file->f_mode & FMODE_READ)
- error = vmsplice_to_user(f.file, iov, nr_segs, flags);
-
- fdput(f);
- }
+ if (!iov_iter_count(iter))
+ return 0;
- return error;
+ if (iov_iter_rw(iter) == WRITE)
+ return vmsplice_to_pipe(f, iter, flags);
+ else
+ return vmsplice_to_user(f, iter, flags);
}
-SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov,
+SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
unsigned long, nr_segs, unsigned int, flags)
{
- return do_vmsplice(fd, iov, nr_segs, flags);
+ struct iovec iovstack[UIO_FASTIOV];
+ struct iovec *iov = iovstack;
+ struct iov_iter iter;
+ long error;
+ struct fd f;
+ int type;
+
+ f = fdget(fd);
+ error = vmsplice_type(f, &type);
+ if (error)
+ return error;
+
+ error = import_iovec(type, uiov, nr_segs,
+ ARRAY_SIZE(iovstack), &iov, &iter);
+ if (!error) {
+ error = do_vmsplice(f.file, &iter, flags);
+ kfree(iov);
+ }
+ fdput(f);
+ return error;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32,
unsigned int, nr_segs, unsigned int, flags)
{
- unsigned i;
- struct iovec __user *iov;
- if (nr_segs > UIO_MAXIOV)
- return -EINVAL;
- iov = compat_alloc_user_space(nr_segs * sizeof(struct iovec));
- for (i = 0; i < nr_segs; i++) {
- struct compat_iovec v;
- if (get_user(v.iov_base, &iov32[i].iov_base) ||
- get_user(v.iov_len, &iov32[i].iov_len) ||
- put_user(compat_ptr(v.iov_base), &iov[i].iov_base) ||
- put_user(v.iov_len, &iov[i].iov_len))
- return -EFAULT;
+ struct iovec iovstack[UIO_FASTIOV];
+ struct iovec *iov = iovstack;
+ struct iov_iter iter;
+ long error;
+ struct fd f;
+ int type;
+
+ f = fdget(fd);
+ error = vmsplice_type(f, &type);
+ if (error)
+ return error;
+
+ error = compat_import_iovec(type, iov32, nr_segs,
+ ARRAY_SIZE(iovstack), &iov, &iter);
+ if (!error) {
+ error = do_vmsplice(f.file, &iter, flags);
+ kfree(iov);
}
- return do_vmsplice(fd, iov, nr_segs, flags);
+ fdput(f);
+ return error;
}
#endif
}
if (compressed) {
+ if (!msblk->stream)
+ goto read_failure;
length = squashfs_decompress(msblk, bh, b, offset, length,
output);
if (length < 0)
TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset);
+ if (unlikely(length < 0))
+ return -EIO;
+
while (length) {
entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
if (entry->error) {
}
for (i = 0; i < blocks; i++) {
- int size = le32_to_cpu(blist[i]);
+ int size = squashfs_block_size(blist[i]);
+ if (size < 0) {
+ err = size;
+ goto failure;
+ }
block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size);
}
n -= blocks;
sizeof(size));
if (res < 0)
return res;
- return le32_to_cpu(size);
+ return squashfs_block_size(size);
+}
+
+void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail)
+{
+ int copied;
+ void *pageaddr;
+
+ pageaddr = kmap_atomic(page);
+ copied = squashfs_copy_data(pageaddr, buffer, offset, avail);
+ memset(pageaddr + copied, 0, PAGE_SIZE - copied);
+ kunmap_atomic(pageaddr);
+
+ flush_dcache_page(page);
+ if (copied == avail)
+ SetPageUptodate(page);
+ else
+ SetPageError(page);
}
/* Copy data into page cache */
{
struct inode *inode = page->mapping->host;
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
- void *pageaddr;
int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
int start_index = page->index & ~mask, end_index = start_index | mask;
if (PageUptodate(push_page))
goto skip_page;
- pageaddr = kmap_atomic(push_page);
- squashfs_copy_data(pageaddr, buffer, offset, avail);
- memset(pageaddr + avail, 0, PAGE_SIZE - avail);
- kunmap_atomic(pageaddr);
- flush_dcache_page(push_page);
- SetPageUptodate(push_page);
+ squashfs_fill_page(push_page, buffer, offset, avail);
skip_page:
unlock_page(push_page);
if (i != page->index)
}
/* Read datablock stored packed inside a fragment (tail-end packed block) */
-static int squashfs_readpage_fragment(struct page *page)
+static int squashfs_readpage_fragment(struct page *page, int expected)
{
struct inode *inode = page->mapping->host;
- struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb,
squashfs_i(inode)->fragment_block,
squashfs_i(inode)->fragment_size);
squashfs_i(inode)->fragment_block,
squashfs_i(inode)->fragment_size);
else
- squashfs_copy_cache(page, buffer, i_size_read(inode) &
- (msblk->block_size - 1),
+ squashfs_copy_cache(page, buffer, expected,
squashfs_i(inode)->fragment_offset);
squashfs_cache_put(buffer);
return res;
}
-static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
+static int squashfs_readpage_sparse(struct page *page, int expected)
{
- struct inode *inode = page->mapping->host;
- struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
- int bytes = index == file_end ?
- (i_size_read(inode) & (msblk->block_size - 1)) :
- msblk->block_size;
-
- squashfs_copy_cache(page, NULL, bytes, 0);
+ squashfs_copy_cache(page, NULL, expected, 0);
return 0;
}
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
int index = page->index >> (msblk->block_log - PAGE_SHIFT);
int file_end = i_size_read(inode) >> msblk->block_log;
+ int expected = index == file_end ?
+ (i_size_read(inode) & (msblk->block_size - 1)) :
+ msblk->block_size;
int res;
void *pageaddr;
goto error_out;
if (bsize == 0)
- res = squashfs_readpage_sparse(page, index, file_end);
+ res = squashfs_readpage_sparse(page, expected);
else
- res = squashfs_readpage_block(page, block, bsize);
+ res = squashfs_readpage_block(page, block, bsize, expected);
} else
- res = squashfs_readpage_fragment(page);
+ res = squashfs_readpage_fragment(page, expected);
if (!res)
return 0;
#include "squashfs.h"
/* Read separately compressed datablock and memcopy into page cache */
-int squashfs_readpage_block(struct page *page, u64 block, int bsize)
+int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected)
{
struct inode *i = page->mapping->host;
struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
ERROR("Unable to read page, block %llx, size %x\n", block,
bsize);
else
- squashfs_copy_cache(page, buffer, buffer->length, 0);
+ squashfs_copy_cache(page, buffer, expected, 0);
squashfs_cache_put(buffer);
return res;
#include "page_actor.h"
static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
- int pages, struct page **page);
+ int pages, struct page **page, int bytes);
/* Read separately compressed datablock directly into page cache */
-int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
+int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
+ int expected)
{
struct inode *inode = target_page->mapping->host;
* using an intermediate buffer.
*/
res = squashfs_read_cache(target_page, block, bsize, pages,
- page);
+ page, expected);
if (res < 0)
goto mark_errored;
if (res < 0)
goto mark_errored;
+ if (res != expected) {
+ res = -EIO;
+ goto mark_errored;
+ }
+
/* Last page may have trailing bytes not filled */
bytes = res % PAGE_SIZE;
if (bytes) {
static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
- int pages, struct page **page)
+ int pages, struct page **page, int bytes)
{
struct inode *i = target_page->mapping->host;
struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
block, bsize);
- int bytes = buffer->length, res = buffer->error, n, offset = 0;
- void *pageaddr;
+ int res = buffer->error, n, offset = 0;
if (res) {
ERROR("Unable to read page, block %llx, size %x\n", block,
if (page[n] == NULL)
continue;
- pageaddr = kmap_atomic(page[n]);
- squashfs_copy_data(pageaddr, buffer, offset, avail);
- memset(pageaddr + avail, 0, PAGE_SIZE - avail);
- kunmap_atomic(pageaddr);
- flush_dcache_page(page[n]);
- SetPageUptodate(page[n]);
+ squashfs_fill_page(page[n], buffer, offset, avail);
unlock_page(page[n]);
if (page[n] != target_page)
put_page(page[n]);
u64 *fragment_block)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- int block = SQUASHFS_FRAGMENT_INDEX(fragment);
- int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment);
- u64 start_block = le64_to_cpu(msblk->fragment_index[block]);
+ int block, offset, size;
struct squashfs_fragment_entry fragment_entry;
- int size;
+ u64 start_block;
+
+ if (fragment >= msblk->fragments)
+ return -EIO;
+ block = SQUASHFS_FRAGMENT_INDEX(fragment);
+ offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment);
+
+ start_block = le64_to_cpu(msblk->fragment_index[block]);
size = squashfs_read_metadata(sb, &fragment_entry, &start_block,
&offset, sizeof(fragment_entry));
return size;
*fragment_block = le64_to_cpu(fragment_entry.start_block);
- size = le32_to_cpu(fragment_entry.size);
-
- return size;
+ return squashfs_block_size(fragment_entry.size);
}
u64, u64, unsigned int);
/* file.c */
+void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int);
void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
int);
/* file_xxx.c */
-extern int squashfs_readpage_block(struct page *, u64, int);
+extern int squashfs_readpage_block(struct page *, u64, int, int);
/* id.c */
extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
#define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK))
+static inline int squashfs_block_size(__le32 raw)
+{
+ u32 size = le32_to_cpu(raw);
+ return (size >> 25) ? -EIO : size;
+}
+
/*
* Inode number ops. Inodes consist of a compressed block number, and an
* uncompressed offset within that block
unsigned short block_log;
long long bytes_used;
unsigned int inodes;
+ unsigned int fragments;
int xattr_ids;
};
#endif
msblk->inode_table = le64_to_cpu(sblk->inode_table_start);
msblk->directory_table = le64_to_cpu(sblk->directory_table_start);
msblk->inodes = le32_to_cpu(sblk->inodes);
+ msblk->fragments = le32_to_cpu(sblk->fragments);
flags = le16_to_cpu(sblk->flags);
TRACE("Found valid superblock on %pg\n", sb->s_bdev);
TRACE("Filesystem size %lld bytes\n", msblk->bytes_used);
TRACE("Block size %d\n", msblk->block_size);
TRACE("Number of inodes %d\n", msblk->inodes);
- TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments));
+ TRACE("Number of fragments %d\n", msblk->fragments);
TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids));
TRACE("sblk->inode_table_start %llx\n", msblk->inode_table);
TRACE("sblk->directory_table_start %llx\n", msblk->directory_table);
sb->s_export_op = &squashfs_export_ops;
handle_fragments:
- fragments = le32_to_cpu(sblk->fragments);
+ fragments = msblk->fragments;
if (fragments == 0)
goto check_directory_table;
spin_lock_irqsave(&ctx->wqh.lock, flags);
ctx->expired = 1;
ctx->ticks++;
- wake_up_locked(&ctx->wqh);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
}
if (ctx->moffs != moffs) {
ctx->moffs = KTIME_MAX;
ctx->ticks++;
- wake_up_locked(&ctx->wqh);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN);
}
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
}
kfree_rcu(ctx, rcu);
return 0;
}
-
-static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
- __poll_t eventmask)
+
+static __poll_t timerfd_poll(struct file *file, poll_table *wait)
{
struct timerfd_ctx *ctx = file->private_data;
+ __poll_t events = 0;
+ unsigned long flags;
- return &ctx->wqh;
-}
+ poll_wait(file, &ctx->wqh, wait);
-static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
-{
- struct timerfd_ctx *ctx = file->private_data;
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ if (ctx->ticks)
+ events |= EPOLLIN;
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
- return ctx->ticks ? EPOLLIN : 0;
+ return events;
}
static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
spin_lock_irq(&ctx->wqh.lock);
if (!timerfd_canceled(ctx)) {
ctx->ticks = ticks;
- wake_up_locked(&ctx->wqh);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN);
} else
ret = -ECANCELED;
spin_unlock_irq(&ctx->wqh.lock);
static const struct file_operations timerfd_fops = {
.release = timerfd_release,
- .get_poll_head = timerfd_get_poll_head,
- .poll_mask = timerfd_poll_mask,
+ .poll = timerfd_poll,
.read = timerfd_read,
.llseek = noop_llseek,
.show_fdinfo = timerfd_show,
}
SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
- const struct itimerspec __user *, utmr,
- struct itimerspec __user *, otmr)
+ const struct __kernel_itimerspec __user *, utmr,
+ struct __kernel_itimerspec __user *, otmr)
{
struct itimerspec64 new, old;
int ret;
return ret;
}
-SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr)
{
struct itimerspec64 kotmr;
int ret = do_timerfd_gettime(ufd, &kotmr);
return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
const struct compat_itimerspec __user *, utmr,
struct compat_itimerspec __user *, otmr)
.dirtied_ino = 3 };
struct ubifs_budget_req ino_req = { .dirtied_ino = 1,
.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
- struct timespec time;
+ struct timespec64 time;
unsigned int uninitialized_var(saved_nlink);
struct fscrypt_name old_nm, new_nm;
int sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir);
struct inode *fst_inode = d_inode(old_dentry);
struct inode *snd_inode = d_inode(new_dentry);
- struct timespec time;
+ struct timespec64 time;
int err;
struct fscrypt_name fst_nm, snd_nm;
if (attr->ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
if (attr->ia_valid & ATTR_ATIME)
- inode->i_atime = timespec_trunc(attr->ia_atime,
- inode->i_sb->s_time_gran);
+ inode->i_atime = timespec64_trunc(attr->ia_atime,
+ inode->i_sb->s_time_gran);
if (attr->ia_valid & ATTR_MTIME)
- inode->i_mtime = timespec_trunc(attr->ia_mtime,
- inode->i_sb->s_time_gran);
+ inode->i_mtime = timespec64_trunc(attr->ia_mtime,
+ inode->i_sb->s_time_gran);
if (attr->ia_valid & ATTR_CTIME)
- inode->i_ctime = timespec_trunc(attr->ia_ctime,
- inode->i_sb->s_time_gran);
+ inode->i_ctime = timespec64_trunc(attr->ia_ctime,
+ inode->i_sb->s_time_gran);
if (attr->ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
static inline int mctime_update_needed(const struct inode *inode,
const struct timespec *now)
{
- if (!timespec_equal(&inode->i_mtime, now) ||
- !timespec_equal(&inode->i_ctime, now))
+ struct timespec64 now64 = timespec_to_timespec64(*now);
+ if (!timespec64_equal(&inode->i_mtime, &now64) ||
+ !timespec64_equal(&inode->i_ctime, &now64))
return 1;
return 0;
}
*
* This function updates time of the inode.
*/
-int ubifs_update_time(struct inode *inode, struct timespec *time,
+int ubifs_update_time(struct inode *inode, struct timespec64 *time,
int flags)
{
struct ubifs_inode *ui = ubifs_inode(inode);
*/
static int update_mctime(struct inode *inode)
{
- struct timespec now = current_time(inode);
+ struct timespec now = timespec64_to_timespec(current_time(inode));
struct ubifs_inode *ui = ubifs_inode(inode);
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct ubifs_info *c = inode->i_sb->s_fs_info;
- struct timespec now = current_time(inode);
+ struct timespec now = timespec64_to_timespec(current_time(inode));
struct ubifs_budget_req req = { .new_page = 1 };
int err, update_time;
int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync);
int ubifs_setattr(struct dentry *dentry, struct iattr *attr);
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
-int ubifs_update_time(struct inode *inode, struct timespec *time, int flags);
+int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags);
#endif
/* dir.c */
udf_write_aext(table, &epos, &eloc,
(etype << 30) | elen, 1);
} else
- udf_delete_aext(table, epos, eloc,
- (etype << 30) | elen);
+ udf_delete_aext(table, epos);
} else {
alloc_count = 0;
}
if (goal_elen)
udf_write_aext(table, &goal_epos, &goal_eloc, goal_elen, 1);
else
- udf_delete_aext(table, goal_epos, goal_eloc, goal_elen);
+ udf_delete_aext(table, goal_epos);
brelse(goal_epos.bh);
udf_add_free_space(sb, partition, -1);
fibh->ebh->b_data,
sizeof(struct fileIdentDesc) + fibh->soffset);
- fi_len = (sizeof(struct fileIdentDesc) +
- cfi->lengthFileIdent +
- le16_to_cpu(cfi->lengthOfImpUse) + 3) & ~3;
-
+ fi_len = udf_dir_entry_len(cfi);
*nf_pos += fi_len - (fibh->eoffset - fibh->soffset);
fibh->eoffset = fibh->soffset + fi_len;
} else {
sizeof(struct fileIdentDesc));
}
}
+ /* Got last entry outside of dir size - fs is corrupted! */
+ if (*nf_pos > dir->i_size)
+ return NULL;
return fi;
}
iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
else
iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
- inode->i_mtime = inode->i_atime = inode->i_ctime =
- iinfo->i_crtime = current_time(inode);
+ inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+ iinfo->i_crtime = timespec64_to_timespec(inode->i_mtime);
if (unlikely(insert_inode_locked(inode) < 0)) {
make_bad_inode(inode);
iput(inode);
if (startnum > endnum) {
for (i = 0; i < (startnum - endnum); i++)
- udf_delete_aext(inode, *epos, laarr[i].extLocation,
- laarr[i].extLength);
+ udf_delete_aext(inode, *epos);
} else if (startnum < endnum) {
for (i = 0; i < (endnum - startnum); i++) {
udf_insert_aext(inode, *epos, laarr[i].extLocation,
struct udf_inode_info *iinfo = UDF_I(inode);
struct udf_sb_info *sbi = UDF_SB(inode->i_sb);
struct kernel_lb_addr *iloc = &iinfo->i_location;
+ struct timespec ts;
unsigned int link_count;
unsigned int indirections = 0;
int bs = inode->i_sb->s_blocksize;
inode->i_blocks = le64_to_cpu(fe->logicalBlocksRecorded) <<
(inode->i_sb->s_blocksize_bits - 9);
- if (!udf_disk_stamp_to_time(&inode->i_atime, fe->accessTime))
- inode->i_atime = sbi->s_record_time;
-
- if (!udf_disk_stamp_to_time(&inode->i_mtime,
- fe->modificationTime))
- inode->i_mtime = sbi->s_record_time;
-
- if (!udf_disk_stamp_to_time(&inode->i_ctime, fe->attrTime))
- inode->i_ctime = sbi->s_record_time;
+ udf_disk_stamp_to_time(&ts, fe->accessTime);
+ inode->i_atime = timespec_to_timespec64(ts);
+ udf_disk_stamp_to_time(&ts, fe->modificationTime);
+ inode->i_mtime = timespec_to_timespec64(ts);
+ udf_disk_stamp_to_time(&ts, fe->attrTime);
+ inode->i_ctime = timespec_to_timespec64(ts);
iinfo->i_unique = le64_to_cpu(fe->uniqueID);
iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr);
inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) <<
(inode->i_sb->s_blocksize_bits - 9);
- if (!udf_disk_stamp_to_time(&inode->i_atime, efe->accessTime))
- inode->i_atime = sbi->s_record_time;
-
- if (!udf_disk_stamp_to_time(&inode->i_mtime,
- efe->modificationTime))
- inode->i_mtime = sbi->s_record_time;
-
- if (!udf_disk_stamp_to_time(&iinfo->i_crtime, efe->createTime))
- iinfo->i_crtime = sbi->s_record_time;
-
- if (!udf_disk_stamp_to_time(&inode->i_ctime, efe->attrTime))
- inode->i_ctime = sbi->s_record_time;
+ udf_disk_stamp_to_time(&ts, efe->accessTime);
+ inode->i_atime = timespec_to_timespec64(ts);
+ udf_disk_stamp_to_time(&ts, efe->modificationTime);
+ inode->i_mtime = timespec_to_timespec64(ts);
+ udf_disk_stamp_to_time(&iinfo->i_crtime, efe->createTime);
+ udf_disk_stamp_to_time(&ts, efe->attrTime);
+ inode->i_ctime = timespec_to_timespec64(ts);
iinfo->i_unique = le64_to_cpu(efe->uniqueID);
iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr);
inode->i_sb->s_blocksize - sizeof(struct fileEntry));
fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
- udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime);
- udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime);
- udf_time_to_disk_stamp(&fe->attrTime, inode->i_ctime);
+ udf_time_to_disk_stamp(&fe->accessTime,
+ timespec64_to_timespec(inode->i_atime));
+ udf_time_to_disk_stamp(&fe->modificationTime,
+ timespec64_to_timespec(inode->i_mtime));
+ udf_time_to_disk_stamp(&fe->attrTime,
+ timespec64_to_timespec(inode->i_ctime));
memset(&(fe->impIdent), 0, sizeof(struct regid));
strcpy(fe->impIdent.ident, UDF_ID_DEVELOPER);
fe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
efe->objectSize = cpu_to_le64(inode->i_size);
efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
- udf_adjust_time(iinfo, inode->i_atime);
- udf_adjust_time(iinfo, inode->i_mtime);
- udf_adjust_time(iinfo, inode->i_ctime);
+ udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_atime));
+ udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_mtime));
+ udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_ctime));
- udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime);
- udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime);
+ udf_time_to_disk_stamp(&efe->accessTime,
+ timespec64_to_timespec(inode->i_atime));
+ udf_time_to_disk_stamp(&efe->modificationTime,
+ timespec64_to_timespec(inode->i_mtime));
udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime);
- udf_time_to_disk_stamp(&efe->attrTime, inode->i_ctime);
+ udf_time_to_disk_stamp(&efe->attrTime,
+ timespec64_to_timespec(inode->i_ctime));
memset(&(efe->impIdent), 0, sizeof(efe->impIdent));
strcpy(efe->impIdent.ident, UDF_ID_DEVELOPER);
return (nelen >> 30);
}
-int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
- struct kernel_lb_addr eloc, uint32_t elen)
+int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
{
struct extent_position oepos;
int adsize;
int8_t etype;
struct allocExtDesc *aed;
struct udf_inode_info *iinfo;
+ struct kernel_lb_addr eloc;
+ uint32_t elen;
if (epos.bh) {
get_bh(epos.bh);
loff_t f_pos;
loff_t size = udf_ext0_offset(dir) + dir->i_size;
int nfidlen;
- uint8_t lfi;
- uint16_t liu;
udf_pblk_t block;
struct kernel_lb_addr eloc;
uint32_t elen = 0;
namelen = 0;
}
- nfidlen = (sizeof(struct fileIdentDesc) + namelen + 3) & ~3;
+ nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD);
f_pos = udf_ext0_offset(dir);
goto out_err;
}
- liu = le16_to_cpu(cfi->lengthOfImpUse);
- lfi = cfi->lengthFileIdent;
-
if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) {
- if (((sizeof(struct fileIdentDesc) +
- liu + lfi + 3) & ~3) == nfidlen) {
+ if (udf_dir_entry_len(cfi) == nfidlen) {
cfi->descTag.tagSerialNum = cpu_to_le16(1);
cfi->fileVersionNum = cpu_to_le16(1);
cfi->fileCharacteristics = 0;
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (unlikely(!fi)) {
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return err;
}
cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err);
if (!fi) {
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
goto out;
}
set_nlink(inode, 2);
if (!fi) {
clear_nlink(inode);
mark_inode_dirty(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
goto out;
}
cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
out_no_entry:
up_write(&iinfo->i_data_sem);
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
goto out;
}
if (dir_fi) {
dir_fi->icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location);
- udf_update_tag((char *)dir_fi,
- (sizeof(struct fileIdentDesc) +
- le16_to_cpu(dir_fi->lengthOfImpUse) + 3) & ~3);
+ udf_update_tag((char *)dir_fi, udf_dir_entry_len(dir_fi));
if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
mark_inode_dirty(old_inode);
else
struct buffer_head *bh;
uint16_t ident;
int ret = -ENOMEM;
+#ifdef UDFFS_DEBUG
+ struct timestamp *ts;
+#endif
outstr = kmalloc(128, GFP_NOFS);
if (!outstr)
pvoldesc = (struct primaryVolDesc *)bh->b_data;
- if (udf_disk_stamp_to_time(&UDF_SB(sb)->s_record_time,
- pvoldesc->recordingDateAndTime)) {
+ udf_disk_stamp_to_time(&UDF_SB(sb)->s_record_time,
+ pvoldesc->recordingDateAndTime);
#ifdef UDFFS_DEBUG
- struct timestamp *ts = &pvoldesc->recordingDateAndTime;
- udf_debug("recording time %04u/%02u/%02u %02u:%02u (%x)\n",
- le16_to_cpu(ts->year), ts->month, ts->day, ts->hour,
- ts->minute, le16_to_cpu(ts->typeAndTimezone));
+ ts = &pvoldesc->recordingDateAndTime;
+ udf_debug("recording time %04u/%02u/%02u %02u:%02u (%x)\n",
+ le16_to_cpu(ts->year), ts->month, ts->day, ts->hour,
+ ts->minute, le16_to_cpu(ts->typeAndTimezone));
#endif
- }
+
ret = udf_dstrCS0toChar(sb, outstr, 31, pvoldesc->volIdent, 32);
if (ret < 0)
extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
struct fileIdentDesc *, struct udf_fileident_bh *,
uint8_t *, uint8_t *);
+static inline unsigned int udf_dir_entry_len(struct fileIdentDesc *cfi)
+{
+ return ALIGN(sizeof(struct fileIdentDesc) +
+ le16_to_cpu(cfi->lengthOfImpUse) + cfi->lengthFileIdent,
+ UDF_NAME_PAD);
+}
/* file.c */
extern long udf_ioctl(struct file *, unsigned int, unsigned long);
struct kernel_lb_addr *, uint32_t, int);
extern void udf_write_aext(struct inode *, struct extent_position *,
struct kernel_lb_addr *, uint32_t, int);
-extern int8_t udf_delete_aext(struct inode *, struct extent_position,
- struct kernel_lb_addr, uint32_t);
+extern int8_t udf_delete_aext(struct inode *, struct extent_position);
extern int8_t udf_next_aext(struct inode *, struct extent_position *,
struct kernel_lb_addr *, uint32_t *, int);
extern int8_t udf_current_aext(struct inode *, struct extent_position *,
extern struct short_ad *udf_get_fileshortad(uint8_t *, int, uint32_t *, int);
/* udftime.c */
-extern struct timespec *udf_disk_stamp_to_time(struct timespec *dest,
+extern void udf_disk_stamp_to_time(struct timespec *dest,
struct timestamp src);
-extern struct timestamp *udf_time_to_disk_stamp(struct timestamp *dest, struct timespec src);
+extern void udf_time_to_disk_stamp(struct timestamp *dest, struct timespec src);
#endif /* __UDF_DECL_H */
#include <linux/kernel.h>
#include <linux/time.h>
-struct timespec *
+void
udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src)
{
u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone);
* recorded with bogus sub-second values.
*/
dest->tv_nsec %= NSEC_PER_SEC;
- return dest;
}
-struct timestamp *
+void
udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts)
{
long seconds;
offset = -sys_tz.tz_minuteswest;
- if (!dest)
- return NULL;
-
dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF));
seconds = ts.tv_sec + offset * 60;
dest->centiseconds * 10000) / 100;
dest->microseconds = (ts.tv_nsec / 1000 - dest->centiseconds * 10000 -
dest->hundredsOfMicroseconds * 100);
- return dest;
}
/* EOF */
fail_remove_inode:
mutex_unlock(&sbi->s_lock);
clear_nlink(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
failed:
return 0;
}
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return err;
}
out_fail:
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return err;
}
out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput (inode);
+ discard_new_inode(inode);
out_dir:
inode_dec_link_count(dir);
return err;
unsigned long reason)
{
struct mm_struct *mm = ctx->mm;
- pte_t *pte;
+ pte_t *ptep, pte;
bool ret = true;
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
- pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
- if (!pte)
+ ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+
+ if (!ptep)
goto out;
ret = false;
+ pte = huge_ptep_get(ptep);
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us.
*/
- if (huge_pte_none(*pte))
+ if (huge_pte_none(pte))
ret = true;
- if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+ if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
ret = true;
out:
return ret;
/* the various vma->vm_userfaultfd_ctx still points to it */
down_write(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx)
+ if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+ vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ }
up_write(&mm->mmap_sem);
userfaultfd_ctx_put(release_new_ctx);
error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
resv->ar_reserved = 0;
resv->ar_asked = 0;
+ resv->ar_orig_reserved = 0;
if (error)
trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
struct xfs_mount *mp = pag->pag_mount;
struct xfs_ag_resv *resv;
int error;
- xfs_extlen_t reserved;
+ xfs_extlen_t hidden_space;
if (used > ask)
ask = used;
- reserved = ask - used;
- error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+ switch (type) {
+ case XFS_AG_RESV_RMAPBT:
+ /*
+ * Space taken by the rmapbt is not subtracted from fdblocks
+ * because the rmapbt lives in the free space. Here we must
+ * subtract the entire reservation from fdblocks so that we
+ * always have blocks available for rmapbt expansion.
+ */
+ hidden_space = ask;
+ break;
+ case XFS_AG_RESV_METADATA:
+ /*
+ * Space taken by all other metadata btrees are accounted
+ * on-disk as used space. We therefore only hide the space
+ * that is reserved but not used by the trees.
+ */
+ hidden_space = ask - used;
+ break;
+ default:
+ ASSERT(0);
+ return -EINVAL;
+ }
+ error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
resv = xfs_perag_resv(pag, type);
resv->ar_asked = ask;
- resv->ar_reserved = resv->ar_orig_reserved = reserved;
+ resv->ar_orig_reserved = hidden_space;
+ resv->ar_reserved = ask - used;
trace_xfs_ag_resv_init(pag, type, ask);
return 0;
error = xfs_btree_get_rec(cur, &rec, stat);
if (error || !(*stat))
return error;
- if (rec->alloc.ar_blockcount == 0)
- goto out_bad_rec;
*bno = be32_to_cpu(rec->alloc.ar_startblock);
*len = be32_to_cpu(rec->alloc.ar_blockcount);
+ if (*len == 0)
+ goto out_bad_rec;
+
/* check for valid extent range, including overflow */
if (!xfs_verify_agbno(mp, agno, *bno))
goto out_bad_rec;
return error;
}
+/* Make sure we won't be right-shifting an extent past the maximum bound. */
+int
+xfs_bmap_can_insert_extents(
+ struct xfs_inode *ip,
+ xfs_fileoff_t off,
+ xfs_fileoff_t shift)
+{
+ struct xfs_bmbt_irec got;
+ int is_empty;
+ int error = 0;
+
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ return -EIO;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty);
+ if (!error && !is_empty && got.br_startoff >= off &&
+ ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff)
+ error = -EINVAL;
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ return error;
+}
+
int
xfs_bmap_insert_extents(
struct xfs_trans *tp,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops);
+int xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
+ xfs_fileoff_t shift);
int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
XFS_DFORK_DSIZE(dip, mp) : \
XFS_DFORK_ASIZE(dip, mp))
+#define XFS_DFORK_MAXEXT(dip, mp, w) \
+ (XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))
+
/*
* Return pointers to the data or attribute forks.
*/
#define BMBT_STARTBLOCK_BITLEN 52
#define BMBT_BLOCKCOUNT_BITLEN 21
+#define BMBT_STARTOFF_MASK ((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+
typedef struct xfs_bmbt_rec {
__be64 l0, l1;
} xfs_bmbt_rec_t;
}
}
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+ struct xfs_dinode *dip,
+ struct xfs_mount *mp,
+ int whichfork)
+{
+ uint32_t di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+ switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * no local regular files yet
+ */
+ if (whichfork == XFS_DATA_FORK) {
+ if (S_ISREG(be16_to_cpu(dip->di_mode)))
+ return __this_address;
+ if (be64_to_cpu(dip->di_size) >
+ XFS_DFORK_SIZE(dip, mp, whichfork))
+ return __this_address;
+ }
+ if (di_nextents)
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (whichfork == XFS_ATTR_FORK) {
+ if (di_nextents > MAXAEXTNUM)
+ return __this_address;
+ } else if (di_nextents > MAXEXTNUM) {
+ return __this_address;
+ }
+ break;
+ default:
+ return __this_address;
+ }
+ return NULL;
+}
+
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
case S_IFREG:
case S_IFLNK:
case S_IFDIR:
- switch (dip->di_format) {
- case XFS_DINODE_FMT_LOCAL:
- /*
- * no local regular files yet
- */
- if (S_ISREG(mode))
- return __this_address;
- if (di_size > XFS_DFORK_DSIZE(dip, mp))
- return __this_address;
- if (dip->di_nextents)
- return __this_address;
- /* fall through */
- case XFS_DINODE_FMT_EXTENTS:
- case XFS_DINODE_FMT_BTREE:
- break;
- default:
- return __this_address;
- }
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+ if (fa)
+ return fa;
break;
case 0:
/* Uninitialized inode ok. */
}
if (XFS_DFORK_Q(dip)) {
- switch (dip->di_aformat) {
- case XFS_DINODE_FMT_LOCAL:
- if (dip->di_anextents)
- return __this_address;
- /* fall through */
- case XFS_DINODE_FMT_EXTENTS:
- case XFS_DINODE_FMT_BTREE:
- break;
- default:
- return __this_address;
- }
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+ if (fa)
+ return fa;
} else {
/*
* If there is no fork offset, this may be a freshly-made inode
if ((hint_flag || inherit_flag) && extsize == 0)
return __this_address;
- if (!(hint_flag || inherit_flag) && extsize != 0)
+ /* free inodes get flags set to zero but extsize remains */
+ if (mode && !(hint_flag || inherit_flag) && extsize != 0)
return __this_address;
if (extsize_bytes % blocksize_bytes)
if (hint_flag && cowextsize == 0)
return __this_address;
- if (!hint_flag && cowextsize != 0)
+ /* free inodes get flags set to zero but cowextsize remains */
+ if (mode && !hint_flag && cowextsize != 0)
return __this_address;
if (hint_flag && rt_flag)
if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
low_rec->ar_startext == high_rec->ar_startext)
return 0;
- if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
- high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
+ if (high_rec->ar_startext > mp->m_sb.sb_rextents)
+ high_rec->ar_startext = mp->m_sb.sb_rextents;
/* Iterate the bitmap, looking for discrepancies. */
rtstart = low_rec->ar_startext;
}
/*
- * dead simple method of punching delalyed allocation blocks from a range in
- * the inode. Walks a block at a time so will be slow, but is only executed in
- * rare error cases so the overhead is not critical. This will always punch out
- * both the start and end blocks, even if the ranges only partially overlap
- * them, so it is up to the caller to ensure that partial blocks are not
- * passed in.
+ * Dead simple method of punching delalyed allocation blocks from a range in
+ * the inode. This will always punch out both the start and end blocks, even
+ * if the ranges only partially overlap them, so it is up to the caller to
+ * ensure that partial blocks are not passed in.
*/
int
xfs_bmap_punch_delalloc_range(
xfs_fileoff_t start_fsb,
xfs_fileoff_t length)
{
- xfs_fileoff_t remaining = length;
+ struct xfs_ifork *ifp = &ip->i_df;
+ xfs_fileoff_t end_fsb = start_fsb + length;
+ struct xfs_bmbt_irec got, del;
+ struct xfs_iext_cursor icur;
int error = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- do {
- int done;
- xfs_bmbt_irec_t imap;
- int nimaps = 1;
- xfs_fsblock_t firstblock;
- struct xfs_defer_ops dfops;
+ if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+ error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+ if (error)
+ return error;
+ }
- /*
- * Map the range first and check that it is a delalloc extent
- * before trying to unmap the range. Otherwise we will be
- * trying to remove a real extent (which requires a
- * transaction) or a hole, which is probably a bad idea...
- */
- error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
- XFS_BMAPI_ENTIRE);
+ if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
+ return 0;
- if (error) {
- /* something screwed, just bail */
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- xfs_alert(ip->i_mount,
- "Failed delalloc mapping lookup ino %lld fsb %lld.",
- ip->i_ino, start_fsb);
- }
- break;
- }
- if (!nimaps) {
- /* nothing there */
- goto next_block;
- }
- if (imap.br_startblock != DELAYSTARTBLOCK) {
- /* been converted, ignore */
- goto next_block;
- }
- WARN_ON(imap.br_blockcount == 0);
+ while (got.br_startoff + got.br_blockcount > start_fsb) {
+ del = got;
+ xfs_trim_extent(&del, start_fsb, length);
/*
- * Note: while we initialise the firstblock/dfops pair, they
- * should never be used because blocks should never be
- * allocated or freed for a delalloc extent and hence we need
- * don't cancel or finish them after the xfs_bunmapi() call.
+ * A delete can push the cursor forward. Step back to the
+ * previous extent on non-delalloc or extents outside the
+ * target range.
*/
- xfs_defer_init(&dfops, &firstblock);
- error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
- &dfops, &done);
- if (error)
- break;
+ if (!del.br_blockcount ||
+ !isnullstartblock(del.br_startblock)) {
+ if (!xfs_iext_prev_extent(ifp, &icur, &got))
+ break;
+ continue;
+ }
- ASSERT(!xfs_defer_has_unfinished_work(&dfops));
-next_block:
- start_fsb++;
- remaining--;
- } while(remaining > 0);
+ error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
+ &got, &del);
+ if (error || !xfs_iext_get_extent(ifp, &icur, &got))
+ break;
+ }
return error;
}
return 0;
if (offset + len > XFS_ISIZE(ip))
len = XFS_ISIZE(ip) - offset;
- return iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+ error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+ if (error)
+ return error;
+
+ /*
+ * If we zeroed right up to EOF and EOF straddles a page boundary we
+ * must make sure that the post-EOF area is also zeroed because the
+ * page could be mmap'd and iomap_zero_range doesn't do that for us.
+ * Writeback of the eof page will do this, albeit clumsily.
+ */
+ if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+ error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+ (offset + len) & ~PAGE_MASK, LLONG_MAX);
+ }
+
+ return error;
}
/*
trace_xfs_insert_file_space(ip);
+ error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
+ if (error)
+ return error;
+
error = xfs_prepare_shift(ip, offset);
if (error)
return error;
struct xfs_trans *tp,
struct xfs_getfsmap_info *info)
{
- struct xfs_rtalloc_rec alow;
- struct xfs_rtalloc_rec ahigh;
+ struct xfs_rtalloc_rec alow = { 0 };
+ struct xfs_rtalloc_rec ahigh = { 0 };
int error;
xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
do {
free = percpu_counter_sum(&mp->m_fdblocks) -
mp->m_alloc_set_aside;
- if (!free)
+ if (free <= 0)
break;
delta = request - mp->m_resblks;
xfs_inode_t *ip;
uint flags;
int error;
- struct timespec tv;
+ struct timespec64 tv;
struct inode *inode;
/*
struct xfs_inode *cip;
int nr_found;
int clcount = 0;
- int bufwasdelwri;
int i;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
* inode buffer and shut down the filesystem.
*/
rcu_read_unlock();
- /*
- * Clean up the buffer. If it was delwri, just release it --
- * brelse can handle it with no problems. If not, shut down the
- * filesystem before releasing the buffer.
- */
- bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
- if (bufwasdelwri)
- xfs_buf_relse(bp);
-
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- if (!bufwasdelwri) {
- /*
- * Just like incore_relse: if we have b_iodone functions,
- * mark the buffer as an error and call them. Otherwise
- * mark it as stale and brelse.
- */
- if (bp->b_iodone) {
- bp->b_flags &= ~XBF_DONE;
- xfs_buf_stale(bp);
- xfs_buf_ioerror(bp, -EIO);
- xfs_buf_ioend(bp);
- } else {
- xfs_buf_stale(bp);
- xfs_buf_relse(bp);
- }
- }
-
/*
- * Unlocks the flush lock
+ * We'll always have an inode attached to the buffer for completion
+ * process by the time we are called from xfs_iflush(). Hence we have
+ * always need to do IO completion processing to abort the inodes
+ * attached to the buffer. handle them just like the shutdown case in
+ * xfs_buf_submit().
*/
+ ASSERT(bp->b_iodone);
+ bp->b_flags &= ~XBF_DONE;
+ xfs_buf_stale(bp);
+ xfs_buf_ioerror(bp, -EIO);
+ xfs_buf_ioend(bp);
+
+ /* abort the corrupt inode, as it was not attached to the buffer */
xfs_iflush_abort(cip, false);
kmem_free(cilist);
xfs_perag_put(pag);
xfs_log_force(mp, 0);
/*
- * inode clustering:
- * see if other inodes can be gathered into this write
+ * inode clustering: try to gather other inodes into this write
+ *
+ * Note: Any error during clustering will result in the filesystem
+ * being shut down and completion callbacks run on the cluster buffer.
+ * As we have already flushed and attached this inode to the buffer,
+ * it has already been aborted and released by xfs_iflush_cluster() and
+ * so we have no further error handling to do here.
*/
error = xfs_iflush_cluster(ip, bp);
if (error)
- goto cluster_corrupt_out;
+ return error;
*bpp = bp;
return 0;
if (bp)
xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-cluster_corrupt_out:
- error = -EFSCORRUPTED;
abort_out:
- /*
- * Unlocks the flush lock
- */
+ /* abort the corrupt inode, as it was not attached to the buffer */
xfs_iflush_abort(ip, false);
return error;
}
unsigned *lockmode)
{
unsigned mode = XFS_ILOCK_SHARED;
+ bool is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
/*
* COW writes may allocate delalloc space or convert unwritten COW
* extents, so we need to make sure to take the lock exclusively here.
*/
- if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+ if (xfs_is_reflink_inode(ip) && is_write) {
/*
* FIXME: It could still overwrite on unshared extents and not
* need allocation.
mode = XFS_ILOCK_EXCL;
}
+relock:
if (flags & IOMAP_NOWAIT) {
if (!xfs_ilock_nowait(ip, mode))
return -EAGAIN;
xfs_ilock(ip, mode);
}
+ /*
+ * The reflink iflag could have changed since the earlier unlocked
+ * check, so if we got ILOCK_SHARED for a write and but we're now a
+ * reflink inode we have to switch to ILOCK_EXCL and relock.
+ */
+ if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_reflink_inode(ip)) {
+ xfs_iunlock(ip, mode);
+ mode = XFS_ILOCK_EXCL;
+ goto relock;
+ }
+
*lockmode = mode;
return 0;
}
STATIC int
xfs_vn_update_time(
struct inode *inode,
- struct timespec *now,
+ struct timespec64 *now,
int flags)
{
struct xfs_inode *ip = XFS_I(inode);
inode_sb_list_add(inode);
/* make the inode look hashed for the writeback code */
- hlist_add_fake(&inode->i_hash);
+ inode_fake_hash(inode);
inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
if (!(flags & XFS_TRANS_NO_WRITECOUNT))
sb_start_intwrite(mp->m_super);
- WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+ /*
+ * Zero-reservation ("empty") transactions can't modify anything, so
+ * they're allowed to run while we're frozen.
+ */
+ WARN_ON(resp->tr_logres > 0 &&
+ mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
atomic_inc(&mp->m_active_trans);
tp = kmem_zone_zalloc(xfs_trans_zone,
int flags)
{
struct inode *inode = VFS_I(ip);
- struct timespec tv;
+ struct timespec64 tv;
ASSERT(tp);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
{
return;
}
-static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr,
+static inline void acpi_processor_ppc_has_changed(struct acpi_processor *pr,
int event_flag)
{
static unsigned int printout = 1;
"Consider compiling CPUfreq support into your kernel.\n");
printout = 0;
}
- return 0;
}
static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
{
}
#endif
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#ifdef arch_atomic_fetch_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
kasan_check_write(v, sizeof(*v));
- return __arch_atomic_add_unless(v, a, u);
+ return arch_atomic_fetch_add_unless(v, a, u);
}
+#endif
-
-static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+#ifdef arch_atomic64_fetch_add_unless
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
kasan_check_write(v, sizeof(*v));
- return arch_atomic64_add_unless(v, a, u);
+ return arch_atomic64_fetch_add_unless(v, a, u);
}
+#endif
+#ifdef arch_atomic_inc
+#define atomic_inc atomic_inc
static __always_inline void atomic_inc(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
arch_atomic_inc(v);
}
+#endif
+#ifdef arch_atomic64_inc
+#define atomic64_inc atomic64_inc
static __always_inline void atomic64_inc(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
arch_atomic64_inc(v);
}
+#endif
+#ifdef arch_atomic_dec
+#define atomic_dec atomic_dec
static __always_inline void atomic_dec(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
arch_atomic_dec(v);
}
+#endif
+#ifdef atch_atomic64_dec
+#define atomic64_dec
static __always_inline void atomic64_dec(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
arch_atomic64_dec(v);
}
+#endif
static __always_inline void atomic_add(int i, atomic_t *v)
{
arch_atomic64_xor(i, v);
}
+#ifdef arch_atomic_inc_return
+#define atomic_inc_return atomic_inc_return
static __always_inline int atomic_inc_return(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_inc_return(v);
}
+#endif
+#ifdef arch_atomic64_in_return
+#define atomic64_inc_return atomic64_inc_return
static __always_inline s64 atomic64_inc_return(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_inc_return(v);
}
+#endif
+#ifdef arch_atomic_dec_return
+#define atomic_dec_return atomic_dec_return
static __always_inline int atomic_dec_return(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_dec_return(v);
}
+#endif
+#ifdef arch_atomic64_dec_return
+#define atomic64_dec_return atomic64_dec_return
static __always_inline s64 atomic64_dec_return(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_dec_return(v);
}
+#endif
-static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+#ifdef arch_atomic64_inc_not_zero
+#define atomic64_inc_not_zero atomic64_inc_not_zero
+static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_inc_not_zero(v);
}
+#endif
+#ifdef arch_atomic64_dec_if_positive
+#define atomic64_dec_if_positive atomic64_dec_if_positive
static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_dec_if_positive(v);
}
+#endif
+#ifdef arch_atomic_dec_and_test
+#define atomic_dec_and_test atomic_dec_and_test
static __always_inline bool atomic_dec_and_test(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_dec_and_test(v);
}
+#endif
+#ifdef arch_atomic64_dec_and_test
+#define atomic64_dec_and_test atomic64_dec_and_test
static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_dec_and_test(v);
}
+#endif
+#ifdef arch_atomic_inc_and_test
+#define atomic_inc_and_test atomic_inc_and_test
static __always_inline bool atomic_inc_and_test(atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_inc_and_test(v);
}
+#endif
+#ifdef arch_atomic64_inc_and_test
+#define atomic64_inc_and_test atomic64_inc_and_test
static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_inc_and_test(v);
}
+#endif
static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return arch_atomic64_fetch_xor(i, v);
}
+#ifdef arch_atomic_sub_and_test
+#define atomic_sub_and_test atomic_sub_and_test
static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_sub_and_test(i, v);
}
+#endif
+#ifdef arch_atomic64_sub_and_test
+#define atomic64_sub_and_test atomic64_sub_and_test
static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_sub_and_test(i, v);
}
+#endif
+#ifdef arch_atomic_add_negative
+#define atomic_add_negative atomic_add_negative
static __always_inline bool atomic_add_negative(int i, atomic_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic_add_negative(i, v);
}
+#endif
+#ifdef arch_atomic64_add_negative
+#define atomic64_add_negative atomic64_add_negative
static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
{
kasan_check_write(v, sizeof(*v));
return arch_atomic64_add_negative(i, v);
}
+#endif
-static __always_inline unsigned long
-cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
- kasan_check_write(ptr, size);
- switch (size) {
- case 1:
- return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
- case 2:
- return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
- case 4:
- return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
- case 8:
- BUILD_BUG_ON(sizeof(unsigned long) != 8);
- return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
- }
- BUILD_BUG();
- return 0;
-}
+#define xchg(ptr, new) \
+({ \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_xchg(__ai_ptr, (new)); \
+})
#define cmpxchg(ptr, old, new) \
({ \
- ((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old), \
- (unsigned long)(new), sizeof(*(ptr)))); \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_cmpxchg(__ai_ptr, (old), (new)); \
})
-static __always_inline unsigned long
-sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
- int size)
-{
- kasan_check_write(ptr, size);
- switch (size) {
- case 1:
- return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
- case 2:
- return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
- case 4:
- return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
- case 8:
- BUILD_BUG_ON(sizeof(unsigned long) != 8);
- return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
- }
- BUILD_BUG();
- return 0;
-}
-
#define sync_cmpxchg(ptr, old, new) \
({ \
- ((__typeof__(*(ptr)))sync_cmpxchg_size((ptr), \
- (unsigned long)(old), (unsigned long)(new), \
- sizeof(*(ptr)))); \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_sync_cmpxchg(__ai_ptr, (old), (new)); \
})
-static __always_inline unsigned long
-cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
- int size)
-{
- kasan_check_write(ptr, size);
- switch (size) {
- case 1:
- return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
- case 2:
- return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
- case 4:
- return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
- case 8:
- BUILD_BUG_ON(sizeof(unsigned long) != 8);
- return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
- }
- BUILD_BUG();
- return 0;
-}
-
#define cmpxchg_local(ptr, old, new) \
({ \
- ((__typeof__(*(ptr)))cmpxchg_local_size((ptr), \
- (unsigned long)(old), (unsigned long)(new), \
- sizeof(*(ptr)))); \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_cmpxchg_local(__ai_ptr, (old), (new)); \
})
-static __always_inline u64
-cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
-{
- kasan_check_write(ptr, sizeof(*ptr));
- return arch_cmpxchg64(ptr, old, new);
-}
-
#define cmpxchg64(ptr, old, new) \
({ \
- ((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old), \
- (u64)(new))); \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_cmpxchg64(__ai_ptr, (old), (new)); \
})
-static __always_inline u64
-cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
-{
- kasan_check_write(ptr, sizeof(*ptr));
- return arch_cmpxchg64_local(ptr, old, new);
-}
-
#define cmpxchg64_local(ptr, old, new) \
({ \
- ((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old), \
- (u64)(new))); \
+ typeof(ptr) __ai_ptr = (ptr); \
+ kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \
+ arch_cmpxchg64_local(__ai_ptr, (old), (new)); \
})
-/*
- * Originally we had the following code here:
- * __typeof__(p1) ____p1 = (p1);
- * kasan_check_write(____p1, 2 * sizeof(*____p1));
- * arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
- * But it leads to compilation failures (see gcc issue 72873).
- * So for now it's left non-instrumented.
- * There are few callers of cmpxchg_double(), so it's not critical.
- */
#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
({ \
- arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2)); \
+ typeof(p1) __ai_p1 = (p1); \
+ kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \
+ arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \
})
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
-({ \
- arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2)); \
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
+({ \
+ typeof(p1) __ai_p1 = (p1); \
+ kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \
+ arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \
})
#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
#include <linux/irqflags.h>
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
- return atomic_add_return(i, v) < 0;
-}
-
static inline void atomic_add(int i, atomic_t *v)
{
atomic_add_return(i, v);
atomic_sub_return(i, v);
}
-static inline void atomic_inc(atomic_t *v)
-{
- atomic_add_return(1, v);
-}
-
-static inline void atomic_dec(atomic_t *v)
-{
- atomic_sub_return(1, v);
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
#define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v)))
#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#ifndef __atomic_add_unless
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
- c = old;
- return c;
-}
-#endif
-
#endif /* __ASM_GENERIC_ATOMIC_H */
*/
#ifndef _ASM_GENERIC_ATOMIC64_H
#define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
typedef struct {
long long counter;
#undef ATOMIC64_OP
extern long long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern int atomic64_add_unless(atomic64_t *v, long long a, long long u);
-
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v) atomic64_add(1LL, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v) atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
+extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
#endif /* _ASM_GENERIC_ATOMIC64_H */
#ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
#define _ASM_GENERIC_BITOPS_ATOMIC_H_
-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h> /* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-# define ATOMIC_HASH_SIZE 4
-# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do { \
- arch_spinlock_t *s = ATOMIC_HASH(l); \
- local_irq_save(f); \
- arch_spin_lock(s); \
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do { \
- arch_spinlock_t *s = ATOMIC_HASH(l); \
- arch_spin_unlock(s); \
- local_irq_restore(f); \
-} while(0)
-
-
-#else
-# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
/*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave(). So you can get NMI events occurring while a
- * *_bit function is holding a spin lock. If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
*/
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered. See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p |= mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
}
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered. However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p &= ~mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
}
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
{
- unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- *p ^= mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
}
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;
- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old | mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ if (READ_ONCE(*p) & mask)
+ return 1;
- return (old & mask) != 0;
+ old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;
- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old & ~mask;
- _atomic_spin_unlock_irqrestore(p, flags);
+ p += BIT_WORD(nr);
+ if (!(READ_ONCE(*p) & mask))
+ return 0;
- return (old & mask) != 0;
+ old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
{
+ long old;
unsigned long mask = BIT_MASK(nr);
- unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old;
- unsigned long flags;
-
- _atomic_spin_lock_irqsave(p, flags);
- old = *p;
- *p = old ^ mask;
- _atomic_spin_unlock_irqrestore(p, flags);
- return (old & mask) != 0;
+ p += BIT_WORD(nr);
+ old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+ return !!(old & mask);
}
#endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
#define _ASM_GENERIC_BITOPS_LOCK_H_
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
/**
* test_and_set_bit_lock - Set a bit and return its old value, for lock
* @nr: Bit to set
* the returned value is 0.
* It can be used to implement bit locks.
*/
-#define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr)
+static inline int test_and_set_bit_lock(unsigned int nr,
+ volatile unsigned long *p)
+{
+ long old;
+ unsigned long mask = BIT_MASK(nr);
+
+ p += BIT_WORD(nr);
+ if (READ_ONCE(*p) & mask)
+ return 1;
+
+ old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+ return !!(old & mask);
+}
+
/**
* clear_bit_unlock - Clear a bit in memory, for unlock
*
* This operation is atomic and provides release barrier semantics.
*/
-#define clear_bit_unlock(nr, addr) \
-do { \
- smp_mb__before_atomic(); \
- clear_bit(nr, addr); \
-} while (0)
+static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+{
+ p += BIT_WORD(nr);
+ atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+}
/**
* __clear_bit_unlock - Clear a bit in memory, for unlock
*
* See for example x86's implementation.
*/
-#define __clear_bit_unlock(nr, addr) \
-do { \
- smp_mb__before_atomic(); \
- clear_bit(nr, addr); \
-} while (0)
+static inline void __clear_bit_unlock(unsigned int nr,
+ volatile unsigned long *p)
+{
+ unsigned long old;
-#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+ p += BIT_WORD(nr);
+ old = READ_ONCE(*p);
+ old &= ~BIT_MASK(nr);
+ atomic_long_set_release((atomic_long_t *)p, old);
+}
+
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ * byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+#ifndef clear_bit_unlock_is_negative_byte
+static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
+ volatile unsigned long *p)
+{
+ long old;
+ unsigned long mask = BIT_MASK(nr);
+
+ p += BIT_WORD(nr);
+ old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+ return !!(old & BIT(7));
+}
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
-int pud_free_pmd_page(pud_t *pud);
-int pmd_free_pte_page(pmd_t *pmd);
+int pud_free_pmd_page(pud_t *pud, unsigned long addr);
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
{
return 0;
}
-static inline int pud_free_pmd_page(pud_t *pud)
+static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
return 0;
}
-static inline int pmd_free_pte_page(pmd_t *pmd)
+static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
return 0;
}
/*
* Initializier
*/
-#define __ARCH_SPIN_LOCK_UNLOCKED { .val = ATOMIC_INIT(0) }
+#define __ARCH_SPIN_LOCK_UNLOCKED { { .val = ATOMIC_INIT(0) } }
/*
* Bitfields in the atomic value:
* For now w.r.t page table cache, mark the range_size as PAGE_SIZE
*/
+#ifndef pte_free_tlb
#define pte_free_tlb(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
__pte_free_tlb(tlb, ptep, address); \
} while (0)
+#endif
+#ifndef pmd_free_tlb
#define pmd_free_tlb(tlb, pmdp, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
__pmd_free_tlb(tlb, pmdp, address); \
} while (0)
+#endif
#ifndef __ARCH_HAS_4LEVEL_HACK
+#ifndef pud_free_tlb
#define pud_free_tlb(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
+#endif
#ifndef __ARCH_HAS_5LEVEL_HACK
+#ifndef p4d_free_tlb
#define p4d_free_tlb(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
__p4d_free_tlb(tlb, pudp, address); \
} while (0)
#endif
+#endif
#define tlb_migrate_finish(mm) do {} while (0)
+/*
+ * Used to flush the TLB when page tables are removed, when lazy
+ * TLB mode may cause a CPU to retain intermediate translations
+ * pointing to about-to-be-freed page table memory.
+ */
+#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES
+#define tlb_flush_remove_tables(mm) do {} while (0)
+#define tlb_flush_remove_tables_local(mm) do {} while (0)
+#endif
+
#endif /* _ASM_GENERIC__TLB_H */
int offset, size_t size, int flags);
void af_alg_free_resources(struct af_alg_async_req *areq);
void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
unsigned int areqlen);
int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
#define IMX6UL_CLK_CSI_PODF 222
#define IMX6UL_CLK_PLL3_120M 223
#define IMX6UL_CLK_KPP 224
-#define IMX6UL_CLK_CKO1_SEL 225
-#define IMX6UL_CLK_CKO1_PODF 226
-#define IMX6UL_CLK_CKO1 227
-#define IMX6UL_CLK_CKO2_SEL 228
-#define IMX6UL_CLK_CKO2_PODF 229
-#define IMX6UL_CLK_CKO2 230
-#define IMX6UL_CLK_CKO 231
-
-/* For i.MX6ULL */
-#define IMX6ULL_CLK_ESAI_PRED 232
-#define IMX6ULL_CLK_ESAI_PODF 233
-#define IMX6ULL_CLK_ESAI_EXTAL 234
-#define IMX6ULL_CLK_ESAI_MEM 235
-#define IMX6ULL_CLK_ESAI_IPG 236
-#define IMX6ULL_CLK_DCP_CLK 237
-#define IMX6ULL_CLK_EPDC_PRE_SEL 238
-#define IMX6ULL_CLK_EPDC_SEL 239
-#define IMX6ULL_CLK_EPDC_PODF 240
-#define IMX6ULL_CLK_EPDC_ACLK 241
-#define IMX6ULL_CLK_EPDC_PIX 242
-#define IMX6ULL_CLK_ESAI_SEL 243
+#define IMX6ULL_CLK_ESAI_PRED 225
+#define IMX6ULL_CLK_ESAI_PODF 226
+#define IMX6ULL_CLK_ESAI_EXTAL 227
+#define IMX6ULL_CLK_ESAI_MEM 228
+#define IMX6ULL_CLK_ESAI_IPG 229
+#define IMX6ULL_CLK_DCP_CLK 230
+#define IMX6ULL_CLK_EPDC_PRE_SEL 231
+#define IMX6ULL_CLK_EPDC_SEL 232
+#define IMX6ULL_CLK_EPDC_PODF 233
+#define IMX6ULL_CLK_EPDC_ACLK 234
+#define IMX6ULL_CLK_EPDC_PIX 235
+#define IMX6ULL_CLK_ESAI_SEL 236
+#define IMX6UL_CLK_CKO1_SEL 237
+#define IMX6UL_CLK_CKO1_PODF 238
+#define IMX6UL_CLK_CKO1 239
+#define IMX6UL_CLK_CKO2_SEL 240
+#define IMX6UL_CLK_CKO2_PODF 241
+#define IMX6UL_CLK_CKO2 242
+#define IMX6UL_CLK_CKO 243
#define IMX6UL_CLK_END 244
#endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */
/* Asymmetric public-key cryptography key subtype
*
- * See Documentation/security/asymmetric-keys.txt
+ * See Documentation/crypto/asymmetric-keys.txt
*
* Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
/* Asymmetric Public-key cryptography key type interface
*
- * See Documentation/security/asymmetric-keys.txt
+ * See Documentation/crypto/asymmetric-keys.txt
*
* Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
int acpi_check_region(resource_size_t start, resource_size_t n,
const char *name);
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+ u32 level);
+
int acpi_resources_are_enforced(void);
#ifdef CONFIG_HIBERNATION
/* Generic associative array implementation.
*
- * See Documentation/assoc_array.txt for information.
+ * See Documentation/core-api/assoc_array.rst for information.
*
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
/* Private definitions for the generic associative array implementation.
*
- * See Documentation/assoc_array.txt for information.
+ * See Documentation/core-api/assoc_array.rst for information.
*
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
struct atm_skb_data {
struct atm_vcc *vcc; /* ATM VCC */
unsigned long atm_options; /* ATM layer options */
+ unsigned int acct_truesize; /* truesize accounted to vcc */
};
#define VCC_HTABLE_SIZE 32
void atm_dev_release_vccs(struct atm_dev *dev);
+static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ /*
+ * Because ATM skbs may not belong to a sock (and we don't
+ * necessarily want to), skb->truesize may be adjusted,
+ * escaping the hack in pskb_expand_head() which avoids
+ * doing so for some cases. So stash the value of truesize
+ * at the time we accounted it, and atm_pop_raw() can use
+ * that value later, in case it changes.
+ */
+ refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+ ATM_SKB(skb)->acct_truesize = skb->truesize;
+ ATM_SKB(skb)->atm_options = vcc->atm_options;
+}
static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
{
/* Atomic operations usable in machine independent code */
#ifndef _LINUX_ATOMIC_H
#define _LINUX_ATOMIC_H
+#include <linux/types.h>
+
#include <asm/atomic.h>
#include <asm/barrier.h>
* barriers on top of the relaxed variant. In the case where the relaxed
* variant is already fully ordered, no additional barriers are needed.
*
- * Besides, if an arch has a special barrier for acquire/release, it could
- * implement its own __atomic_op_* and use the same framework for building
- * variants
- *
- * If an architecture overrides __atomic_op_acquire() it will probably want
- * to define smp_mb__after_spinlock().
+ * If an architecture overrides __atomic_acquire_fence() it will probably
+ * want to define smp_mb__after_spinlock().
*/
-#ifndef __atomic_op_acquire
+#ifndef __atomic_acquire_fence
+#define __atomic_acquire_fence smp_mb__after_atomic
+#endif
+
+#ifndef __atomic_release_fence
+#define __atomic_release_fence smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_pre_full_fence
+#define __atomic_pre_full_fence smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_post_full_fence
+#define __atomic_post_full_fence smp_mb__after_atomic
+#endif
+
#define __atomic_op_acquire(op, args...) \
({ \
typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \
- smp_mb__after_atomic(); \
+ __atomic_acquire_fence(); \
__ret; \
})
-#endif
-#ifndef __atomic_op_release
#define __atomic_op_release(op, args...) \
({ \
- smp_mb__before_atomic(); \
+ __atomic_release_fence(); \
op##_relaxed(args); \
})
-#endif
-#ifndef __atomic_op_fence
#define __atomic_op_fence(op, args...) \
({ \
typeof(op##_relaxed(args)) __ret; \
- smp_mb__before_atomic(); \
+ __atomic_pre_full_fence(); \
__ret = op##_relaxed(args); \
- smp_mb__after_atomic(); \
+ __atomic_post_full_fence(); \
__ret; \
})
-#endif
/* atomic_add_return_relaxed */
#ifndef atomic_add_return_relaxed
#endif
#endif /* atomic_add_return_relaxed */
+#ifndef atomic_inc
+#define atomic_inc(v) atomic_add(1, (v))
+#endif
+
/* atomic_inc_return_relaxed */
#ifndef atomic_inc_return_relaxed
+
+#ifndef atomic_inc_return
+#define atomic_inc_return(v) atomic_add_return(1, (v))
+#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v) atomic_add_return_release(1, (v))
+#else /* atomic_inc_return */
#define atomic_inc_return_relaxed atomic_inc_return
#define atomic_inc_return_acquire atomic_inc_return
#define atomic_inc_return_release atomic_inc_return
+#endif /* atomic_inc_return */
#else /* atomic_inc_return_relaxed */
#endif
#endif /* atomic_sub_return_relaxed */
+#ifndef atomic_dec
+#define atomic_dec(v) atomic_sub(1, (v))
+#endif
+
/* atomic_dec_return_relaxed */
#ifndef atomic_dec_return_relaxed
+
+#ifndef atomic_dec_return
+#define atomic_dec_return(v) atomic_sub_return(1, (v))
+#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v))
+#else /* atomic_dec_return */
#define atomic_dec_return_relaxed atomic_dec_return
#define atomic_dec_return_acquire atomic_dec_return
#define atomic_dec_return_release atomic_dec_return
+#endif /* atomic_dec_return */
#else /* atomic_dec_return_relaxed */
#endif
#endif /* atomic_fetch_and_relaxed */
-#ifdef atomic_andnot
-/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_andnot
+#define atomic_andnot(i, v) atomic_and(~(int)(i), (v))
+#endif
+
#ifndef atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_relaxed atomic_fetch_andnot
-#define atomic_fetch_andnot_acquire atomic_fetch_andnot
-#define atomic_fetch_andnot_release atomic_fetch_andnot
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v))
+#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v))
+#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v))
+#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v))
+#else /* atomic_fetch_andnot */
+#define atomic_fetch_andnot_relaxed atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire atomic_fetch_andnot
+#define atomic_fetch_andnot_release atomic_fetch_andnot
+#endif /* atomic_fetch_andnot */
#else /* atomic_fetch_andnot_relaxed */
__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
#endif
#endif /* atomic_fetch_andnot_relaxed */
-#endif /* atomic_andnot */
/* atomic_fetch_xor_relaxed */
#ifndef atomic_fetch_xor_relaxed
#endif
#endif /* xchg_relaxed */
+/**
+ * atomic_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+ int c = atomic_read(v);
+
+ do {
+ if (unlikely(c == u))
+ break;
+ } while (!atomic_try_cmpxchg(v, &c, c + a));
+
+ return c;
+}
+#endif
+
/**
* atomic_add_unless - add unless the number is already a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline bool atomic_add_unless(atomic_t *v, int a, int u)
{
- return __atomic_add_unless(v, a, u) != u;
+ return atomic_fetch_add_unless(v, a, u) != u;
}
/**
* atomic_inc_not_zero - increment unless the number is zero
* @v: pointer of type atomic_t
*
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
*/
#ifndef atomic_inc_not_zero
#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
#endif
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
- atomic_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot(int i, atomic_t *v)
-{
- return atomic_fetch_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_inc_and_test
+static inline bool atomic_inc_and_test(atomic_t *v)
{
- return atomic_fetch_and_relaxed(~i, v);
+ return atomic_inc_return(v) == 0;
}
+#endif
-static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic_dec_and_test
+static inline bool atomic_dec_and_test(atomic_t *v)
{
- return atomic_fetch_and_acquire(~i, v);
+ return atomic_dec_return(v) == 0;
}
+#endif
-static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_sub_and_test
+static inline bool atomic_sub_and_test(int i, atomic_t *v)
{
- return atomic_fetch_and_release(~i, v);
+ return atomic_sub_return(i, v) == 0;
}
#endif
/**
- * atomic_inc_not_zero_hint - increment if not null
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
* @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
*
- * Returns: 0 if increment was not done, 1 otherwise.
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
*/
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
+#ifndef atomic_add_negative
+static inline bool atomic_add_negative(int i, atomic_t *v)
{
- int val, c = hint;
-
- /* sanity test, should be removed by compiler if hint is a constant */
- if (!hint)
- return atomic_inc_not_zero(v);
-
- do {
- val = atomic_cmpxchg(v, c, c + 1);
- if (val == c)
- return 1;
- c = val;
- } while (c);
-
- return 0;
+ return atomic_add_return(i, v) < 0;
}
#endif
#ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *v)
{
- int v, v1;
- for (v = 0; v >= 0; v = v1) {
- v1 = atomic_cmpxchg(p, v, v + 1);
- if (likely(v1 == v))
- return 1;
- }
- return 0;
+ int c = atomic_read(v);
+
+ do {
+ if (unlikely(c < 0))
+ return false;
+ } while (!atomic_try_cmpxchg(v, &c, c + 1));
+
+ return true;
}
#endif
#ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *v)
{
- int v, v1;
- for (v = 0; v <= 0; v = v1) {
- v1 = atomic_cmpxchg(p, v, v - 1);
- if (likely(v1 == v))
- return 1;
- }
- return 0;
+ int c = atomic_read(v);
+
+ do {
+ if (unlikely(c > 0))
+ return false;
+ } while (!atomic_try_cmpxchg(v, &c, c - 1));
+
+ return true;
}
#endif
#ifndef atomic_dec_if_positive
static inline int atomic_dec_if_positive(atomic_t *v)
{
- int c, old, dec;
- c = atomic_read(v);
- for (;;) {
+ int dec, c = atomic_read(v);
+
+ do {
dec = c - 1;
if (unlikely(dec < 0))
break;
- old = atomic_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
+ } while (!atomic_try_cmpxchg(v, &c, dec));
+
return dec;
}
#endif
#endif
#endif /* atomic64_add_return_relaxed */
+#ifndef atomic64_inc
+#define atomic64_inc(v) atomic64_add(1, (v))
+#endif
+
/* atomic64_inc_return_relaxed */
#ifndef atomic64_inc_return_relaxed
+
+#ifndef atomic64_inc_return
+#define atomic64_inc_return(v) atomic64_add_return(1, (v))
+#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v))
+#else /* atomic64_inc_return */
#define atomic64_inc_return_relaxed atomic64_inc_return
#define atomic64_inc_return_acquire atomic64_inc_return
#define atomic64_inc_return_release atomic64_inc_return
+#endif /* atomic64_inc_return */
#else /* atomic64_inc_return_relaxed */
#endif
#endif /* atomic64_sub_return_relaxed */
+#ifndef atomic64_dec
+#define atomic64_dec(v) atomic64_sub(1, (v))
+#endif
+
/* atomic64_dec_return_relaxed */
#ifndef atomic64_dec_return_relaxed
+
+#ifndef atomic64_dec_return
+#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
+#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v))
+#else /* atomic64_dec_return */
#define atomic64_dec_return_relaxed atomic64_dec_return
#define atomic64_dec_return_acquire atomic64_dec_return
#define atomic64_dec_return_release atomic64_dec_return
+#endif /* atomic64_dec_return */
#else /* atomic64_dec_return_relaxed */
#endif
#endif /* atomic64_fetch_and_relaxed */
-#ifdef atomic64_andnot
-/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_andnot
+#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v))
+#endif
+
#ifndef atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot
-#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot
-#define atomic64_fetch_andnot_release atomic64_fetch_andnot
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v))
+#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v))
+#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v))
+#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v))
+#else /* atomic64_fetch_andnot */
+#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release atomic64_fetch_andnot
+#endif /* atomic64_fetch_andnot */
#else /* atomic64_fetch_andnot_relaxed */
__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
#endif
#endif /* atomic64_fetch_andnot_relaxed */
-#endif /* atomic64_andnot */
/* atomic64_fetch_xor_relaxed */
#ifndef atomic64_fetch_xor_relaxed
#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg
#endif /* atomic64_try_cmpxchg */
-#ifndef atomic64_andnot
-static inline void atomic64_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic64_fetch_add_unless
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+ long long u)
{
- atomic64_and(~i, v);
+ long long c = atomic64_read(v);
+
+ do {
+ if (unlikely(c == u))
+ break;
+ } while (!atomic64_try_cmpxchg(v, &c, c + a));
+
+ return c;
}
+#endif
-static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
+ */
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
{
- return atomic64_fetch_and(~i, v);
+ return atomic64_fetch_add_unless(v, a, u) != u;
}
-static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+/**
+ * atomic64_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
+ */
+#ifndef atomic64_inc_not_zero
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+#endif
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_inc_and_test
+static inline bool atomic64_inc_and_test(atomic64_t *v)
{
- return atomic64_fetch_and_relaxed(~i, v);
+ return atomic64_inc_return(v) == 0;
}
+#endif
-static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic64_dec_and_test
+static inline bool atomic64_dec_and_test(atomic64_t *v)
{
- return atomic64_fetch_and_acquire(~i, v);
+ return atomic64_dec_return(v) == 0;
}
+#endif
-static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_sub_and_test
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+ return atomic64_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic64_add_negative
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
{
- return atomic64_fetch_and_release(~i, v);
+ return atomic64_add_return(i, v) < 0;
+}
+#endif
+
+#ifndef atomic64_inc_unless_negative
+static inline bool atomic64_inc_unless_negative(atomic64_t *v)
+{
+ long long c = atomic64_read(v);
+
+ do {
+ if (unlikely(c < 0))
+ return false;
+ } while (!atomic64_try_cmpxchg(v, &c, c + 1));
+
+ return true;
+}
+#endif
+
+#ifndef atomic64_dec_unless_positive
+static inline bool atomic64_dec_unless_positive(atomic64_t *v)
+{
+ long long c = atomic64_read(v);
+
+ do {
+ if (unlikely(c > 0))
+ return false;
+ } while (!atomic64_try_cmpxchg(v, &c, c - 1));
+
+ return true;
+}
+#endif
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic64 variable, v, was not decremented.
+ */
+#ifndef atomic64_dec_if_positive
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long long dec, c = atomic64_read(v);
+
+ do {
+ dec = c - 1;
+ if (unlikely(dec < 0))
+ break;
+ } while (!atomic64_try_cmpxchg(v, &c, dec));
+
+ return dec;
}
#endif
*/
enum wb_state {
WB_registered, /* bdi_register() was done */
- WB_shutting_down, /* wb_shutdown() in progress */
WB_writeback_running, /* Writeback is in progress */
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
WB_start_all, /* nr_pages == 0 (all) work pending */
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
+ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
#else
struct bdi_writeback_congested *wb_congested;
#endif
#ifndef _LINUX_BITOPS_H
#define _LINUX_BITOPS_H
#include <asm/types.h>
+#include <linux/bits.h>
-#ifdef __KERNEL__
-#define BIT(nr) (1UL << (nr))
-#define BIT_ULL(nr) (1ULL << (nr))
-#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
- (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
- (((~0ULL) - (1ULL << (l)) + 1) & \
- (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr) (1UL << (nr))
+#define BIT_ULL(nr) (1ULL << (nr))
+#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE 8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+ (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+ (((~0ULL) - (1ULL << (l)) + 1) & \
+ (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif /* __LINUX_BITS_H */
void blk_mq_freeze_queue_wait(struct request_queue *q);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout);
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
- int (reinit_request)(void *, struct request *));
int blk_mq_map_queues(struct blk_mq_tag_set *set);
void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
void blk_mq_quiesce_queue_nowait(struct request_queue *q);
+/**
+ * blk_mq_mark_complete() - Set request state to complete
+ * @rq: request to set to complete state
+ *
+ * Returns true if request state was successfully set to complete. If
+ * successful, the caller is responsibile for seeing this request is ended, as
+ * blk_mq_complete_request will not work again.
+ */
+static inline bool blk_mq_mark_complete(struct request *rq)
+{
+ return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) ==
+ MQ_RQ_IN_FLIGHT;
+}
+
/*
* Driver command data is immediately after the request. So subtract request
* size to get back to the original request, add request size to get the PDU.
#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
/* already slept for hybrid poll */
#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
+/* ->timeout has been called, don't expire again */
+#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21))
/* flags that prevent us from merging requests: */
#define RQF_NOMERGE_FLAGS \
unsigned int dma_alignment;
struct blk_queue_tag *queue_tags;
- struct list_head tag_busy_list;
unsigned int nr_sorted;
unsigned int in_flight[2];
if (!q->limits.chunk_sectors)
return q->limits.max_sectors;
- return q->limits.chunk_sectors -
- (offset & (q->limits.chunk_sectors - 1));
+ return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
+ (offset & (q->limits.chunk_sectors - 1))));
}
static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
extern void blk_queue_free_tags(struct request_queue *);
extern int blk_queue_resize_tags(struct request_queue *, int);
-extern void blk_queue_invalidate_tags(struct request_queue *);
extern struct blk_queue_tag *blk_init_tags(int, int);
extern void blk_free_tags(struct blk_queue_tag *);
#ifndef _BPF_CGROUP_H
#define _BPF_CGROUP_H
+#include <linux/errno.h>
#include <linux/jump_label.h>
#include <uapi/linux/bpf.h>
\
__ret; \
})
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
#else
+struct bpf_prog;
struct cgroup_bpf {};
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return -EINVAL;
+}
+
#define cgroup_bpf_enabled (0)
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
/* Map specifics */
struct xdp_buff;
+struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
return 0;
}
+struct sk_buff;
+
+static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ return 0;
+}
+
static inline
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog);
#else
static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
{
{
return -EOPNOTSUPP;
}
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
#endif
#if defined(CONFIG_XDP_SOCKETS)
#include <uapi/linux/bpf.h>
#ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int lirc_prog_detach(const union bpf_attr *attr);
int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
#else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+ struct bpf_prog *prog)
{
return -EINVAL;
}
#include <uapi/linux/bpfilter.h>
struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval,
- int *optlen);
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
+ int __user *optlen);
extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
char __user *optval,
unsigned int optlen, bool is_set);
CEPH_CAP_XATTR_SHARED)
#define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \
CEPH_CAP_FILE_RD)
+#define CEPH_STAT_RSTAT CEPH_CAP_FILE_WREXTEND
#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \
CEPH_CAP_LINK_SHARED | \
u64 r_tid; /* unique for this client */
struct rb_node r_node;
struct rb_node r_mc_node; /* map check */
+ struct work_struct r_complete_work;
struct ceph_osd *r_osd;
struct ceph_osd_request_target r_t;
struct timespec r_mtime; /* ditto */
u64 r_data_offset; /* ditto */
bool r_linger; /* don't resend on failure */
- bool r_abort_on_full; /* return ENOSPC when full */
/* internal */
unsigned long r_stamp; /* jiffies, send or check time */
struct rb_root linger_map_checks;
atomic_t num_requests;
atomic_t num_homeless;
+ bool abort_on_full; /* abort w/ ENOSPC when full */
+ int abort_err;
struct delayed_work timeout_work;
struct delayed_work osds_timeout_work;
#ifdef CONFIG_DEBUG_FS
struct ceph_msgpool msgpool_op_reply;
struct workqueue_struct *notify_wq;
+ struct workqueue_struct *completion_wq;
};
static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag)
extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
+void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err);
extern void osd_req_op_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode, u32 flags);
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
-extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
+extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
const char *class, const char *method);
extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
const struct ceph_osds *new_acting,
bool any_change);
-int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
- const struct ceph_object_id *oid,
- const struct ceph_object_locator *oloc,
- struct ceph_pg *raw_pgid);
+void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
+ const struct ceph_object_id *oid,
+ const struct ceph_object_locator *oloc,
+ struct ceph_pg *raw_pgid);
int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
const struct ceph_object_id *oid,
const struct ceph_object_locator *oloc,
/* SPDX-License-Identifier: GPL-2.0 */
/*
- * See Documentation/circular-buffers.txt for more information.
+ * See Documentation/core-api/circular-buffers.rst for more information.
*/
#ifndef _LINUX_CIRC_BUF_H
extern void clocksource_resume(void);
extern struct clocksource * __init clocksource_default_clock(void);
extern void clocksource_mark_unstable(struct clocksource *cs);
+extern void
+clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles);
+extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now);
extern u64
clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles);
*/
#ifndef COMPAT_SYSCALL_DEFINEx
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_compat_sys##name)))); \
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
- return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ return ret; \
} \
+ __diag_pop(); \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* COMPAT_SYSCALL_DEFINEx */
struct compat_sel_arg_struct;
struct rusage;
-struct compat_itimerspec {
- struct compat_timespec it_interval;
- struct compat_timespec it_value;
-};
-
struct compat_utimbuf {
compat_time_t actime;
compat_time_t modtime;
extern int compat_put_timespec(const struct timespec *, void __user *);
extern int compat_get_timeval(struct timeval *, const void __user *);
extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int get_compat_itimerspec64(struct itimerspec64 *its,
- const struct compat_itimerspec __user *uits);
-extern int put_compat_itimerspec64(const struct itimerspec64 *its,
- struct compat_itimerspec __user *uits);
struct compat_iovec {
compat_uptr_t iov_base;
s32 tv_usec;
};
+struct compat_itimerspec {
+ struct compat_timespec it_interval;
+ struct compat_timespec it_value;
+};
+
extern int compat_get_timespec64(struct timespec64 *, const void __user *);
extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+extern int get_compat_itimerspec64(struct itimerspec64 *its,
+ const struct compat_itimerspec __user *uits);
+extern int put_compat_itimerspec64(const struct itimerspec64 *its,
+ struct compat_itimerspec __user *uits);
#endif /* _LINUX_COMPAT_TIME_H */
#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
#endif
+/*
+ * Feature detection for gnu_inline (gnu89 extern inline semantics). Either
+ * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics,
+ * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not
+ * defined so the gnu89 semantics are the default.
+ */
+#ifdef __GNUC_STDC_INLINE__
+# define __gnu_inline __attribute__((gnu_inline))
+#else
+# define __gnu_inline
+#endif
+
/*
* Force always-inline if the user requests it so via the .config,
* or if gcc is too old.
* -Wunused-function. This turns out to avoid the need for complex #ifdef
* directives. Suppress the warning in clang as well by using "unused"
* function attribute, which is redundant but not harmful for gcc.
+ * Prefer gnu_inline, so that extern inline functions do not emit an
+ * externally visible function. This makes extern inline behave as per gnu89
+ * semantics rather than c99. This prevents multiple symbol definition errors
+ * of extern inline functions at link time.
+ * A lot of inline functions can cause havoc with function tracing.
*/
#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
!defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline inline __attribute__((always_inline,unused)) notrace
-#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace
-#define __inline __inline __attribute__((always_inline,unused)) notrace
+#define inline \
+ inline __attribute__((always_inline, unused)) notrace __gnu_inline
#else
-/* A lot of inline functions can cause havoc with function tracing */
-#define inline inline __attribute__((unused)) notrace
-#define __inline__ __inline__ __attribute__((unused)) notrace
-#define __inline __inline __attribute__((unused)) notrace
+#define inline inline __attribute__((unused)) notrace __gnu_inline
#endif
+#define __inline__ inline
+#define __inline inline
#define __always_inline inline __attribute__((always_inline))
#define noinline __attribute__((noinline))
#if GCC_VERSION >= 50100
#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
#endif
+
+/*
+ * Turn individual warnings and errors on and off locally, depending
+ * on version.
+ */
+#define __diag_GCC(version, severity, s) \
+ __diag_GCC_ ## version(__diag_GCC_ ## severity s)
+
+/* Severity used in pragma directives */
+#define __diag_GCC_ignore ignored
+#define __diag_GCC_warn warning
+#define __diag_GCC_error error
+
+/* Compilers before gcc-4.6 do not understand "#pragma GCC diagnostic push" */
+#if GCC_VERSION >= 40600
+#define __diag_str1(s) #s
+#define __diag_str(s) __diag_str1(s)
+#define __diag(s) _Pragma(__diag_str(GCC diagnostic s))
+#endif
+
+#if GCC_VERSION >= 80000
+#define __diag_GCC_8(s) __diag(s)
+#else
+#define __diag_GCC_8(s)
+#endif
# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
#endif
+#ifndef __diag
+#define __diag(string)
+#endif
+
+#ifndef __diag_GCC
+#define __diag_GCC(version, severity, string)
+#endif
+
+#define __diag_push() __diag(push)
+#define __diag_pop() __diag(pop)
+
+#define __diag_ignore(compiler, version, option, comment) \
+ __diag_ ## compiler(version, ignore, option)
+#define __diag_warn(compiler, version, option, comment) \
+ __diag_ ## compiler(version, warn, option)
+#define __diag_error(compiler, version, option, comment) \
+ __diag_ ## compiler(version, error, option)
+
#endif /* __LINUX_COMPILER_TYPES_H */
};
extern void boot_cpu_init(void);
-extern void boot_cpu_state_init(void);
+extern void boot_cpu_hotplug_init(void);
extern void cpu_init(void);
extern void trap_init(void);
CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
+ CPUHP_AP_WATCHDOG_ONLINE,
CPUHP_AP_WORKQUEUE_ONLINE,
CPUHP_AP_RCUTREE_ONLINE,
CPUHP_AP_ONLINE_DYN,
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
enum page_entry_size pe_size, pfn_t pfn);
extern void d_instantiate_new(struct dentry *, struct inode *);
extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
-extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
extern void __d_drop(struct dentry *dentry);
extern void d_drop(struct dentry *dentry);
extern void d_delete(struct dentry *);
extern void d_add(struct dentry *, struct inode *);
-extern void dentry_update_name_case(struct dentry *, const struct qstr *);
-
/* used for rename() and baskets */
extern void d_move(struct dentry *, struct dentry *);
extern void d_exchange(struct dentry *, struct dentry *);
static inline void delayacct_blkio_end(struct task_struct *p)
{
- if (current->delays)
+ if (p->delays)
__delayacct_blkio_end(p);
delayacct_clear_flag(DELAYACCT_PF_BLKIO);
}
* CMA should not be used by the device drivers directly. It is
* only a helper framework for dma-mapping subsystem.
*
- * For more information, see kernel-docs in drivers/base/dma-contiguous.c
+ * For more information, see kernel-docs in kernel/dma/contiguous.c
*/
#ifdef __KERNEL__
}
#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(struct device *dev);
+#else
+static inline void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
#endif /* _LINUX_DMA_NONCOHERENT_H */
void *flush;
} efi_file_handle_t;
+typedef struct {
+ u64 revision;
+ u32 open_volume;
+} efi_file_io_interface_32_t;
+
+typedef struct {
+ u64 revision;
+ u64 open_volume;
+} efi_file_io_interface_64_t;
+
typedef struct _efi_file_io_interface {
u64 revision;
int (*open_volume)(struct _efi_file_io_interface *,
extern void efi_gettimeofday (struct timespec64 *ts);
extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */
#ifdef CONFIG_X86
-extern void efi_late_init(void);
extern void efi_free_boot_services(void);
extern efi_status_t efi_query_variable_store(u32 attributes,
unsigned long size,
bool nonblocking);
extern void efi_find_mirror(void);
#else
-static inline void efi_late_init(void) {}
static inline void efi_free_boot_services(void) {}
static inline efi_status_t efi_query_variable_store(u32 attributes,
extern int efi_tpm_eventlog_init(void);
+/* Workqueue to queue EFI Runtime Services */
+extern struct workqueue_struct *efi_rts_wq;
+
#endif /* _LINUX_EFI_H */
#include <linux/fcntl.h>
#include <linux/wait.h>
+#include <linux/err.h>
/*
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
struct file_operations;
struct vfsmount;
struct dentry;
+struct inode;
struct path;
-extern struct file *alloc_file(const struct path *, fmode_t mode,
- const struct file_operations *fop);
+extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
+ const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_clone(struct file *, int flags,
+ const struct file_operations *);
static inline void fput_light(struct file *file, int fput_needed)
{
extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
extern void set_close_on_exec(unsigned int fd, int flag);
extern bool get_close_on_exec(unsigned int fd);
-extern void put_filp(struct file *);
extern int get_unused_fd_flags(unsigned flags);
extern void put_unused_fd(unsigned int fd);
#include <linux/cryptohash.h>
#include <linux/set_memory.h>
#include <linux/kallsyms.h>
+#include <linux/if_vlan.h>
#include <net/sch_generic.h>
};
struct bpf_binary_header {
- unsigned int pages;
- u8 image[];
+ u32 pages;
+ /* Some arches need word alignment for their instructions */
+ u8 image[] __aligned(4);
};
struct bpf_prog {
u16 pages; /* Number of allocated pages */
u16 jited:1, /* Is our filter JIT'ed? */
jit_requested:1,/* archs need to JIT the prog */
- locked:1, /* Program image locked? */
+ undo_set_mem:1, /* Passed set_memory_ro() checkpoint */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1, /* Do we need dst entry? */
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
-{
- fp->locked = 1;
- WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
-}
-
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
- if (fp->locked) {
- WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
- /* In case set_memory_rw() fails, we want to be the first
- * to crash here instead of some random place later on.
- */
- fp->locked = 0;
- }
-}
-
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
-{
- WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
- WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
-}
-#else
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
+ fp->undo_set_mem = 1;
+ set_memory_ro((unsigned long)fp, fp->pages);
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
+ if (fp->undo_set_mem)
+ set_memory_rw((unsigned long)fp, fp->pages);
}
static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
{
+ set_memory_ro((unsigned long)hdr, hdr->pages);
}
static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
{
+ set_memory_rw((unsigned long)hdr, hdr->pages);
}
-#endif /* CONFIG_ARCH_HAS_SET_MEMORY */
static inline struct bpf_binary_header *
bpf_jit_binary_hdr(const struct bpf_prog *fp)
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len);
+static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
+ unsigned int pktlen)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (pktlen > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
* same cpu context. Further for best results no more than a single map
* for the do_redirect/do_flush pair should be used. This limitation is
}
#endif /* CONFIG_BPF_JIT */
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
+
#define BPF_ANC BIT(15)
static inline bool bpf_needs_clear_a(const struct sock_filter *first)
/* Has write method(s) */
#define FMODE_CAN_WRITE ((__force fmode_t)0x40000)
+#define FMODE_OPENED ((__force fmode_t)0x80000)
+#define FMODE_CREATED ((__force fmode_t)0x100000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
kuid_t ia_uid;
kgid_t ia_gid;
loff_t ia_size;
- struct timespec ia_atime;
- struct timespec ia_mtime;
- struct timespec ia_ctime;
+ struct timespec64 ia_atime;
+ struct timespec64 ia_mtime;
+ struct timespec64 ia_ctime;
/*
* Not an attribute, but an auxiliary info for filesystems wanting to
/*
* Write life time hint values.
+ * Stored in struct inode as u8.
*/
enum rw_hint {
WRITE_LIFE_NOT_SET = 0,
};
dev_t i_rdev;
loff_t i_size;
- struct timespec i_atime;
- struct timespec i_mtime;
- struct timespec i_ctime;
+ struct timespec64 i_atime;
+ struct timespec64 i_mtime;
+ struct timespec64 i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
- unsigned int i_blkbits;
- enum rw_hint i_write_hint;
+ u8 i_blkbits;
+ u8 i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
return hlist_unhashed(&inode->i_hash);
}
+/*
+ * __mark_inode_dirty expects inodes to be hashed. Since we don't
+ * want special inodes in the fileset inode space, we make them
+ * appear hashed, but do not put on any lists. hlist_del()
+ * will work fine and require no locking.
+ */
+static inline void inode_fake_hash(struct inode *inode)
+{
+ hlist_add_fake(&inode->i_hash);
+}
+
/*
* inode->i_mutex nesting subclasses for the lock validator:
*
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
-extern void lease_get_mtime(struct inode *, struct timespec *time);
+extern void lease_get_mtime(struct inode *, struct timespec64 *time);
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
extern int lease_modify(struct file_lock *, int, struct list_head *);
return 0;
}
-static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
+static inline void lease_get_mtime(struct inode *inode,
+ struct timespec64 *time)
{
return;
}
inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
}
-extern struct timespec current_time(struct inode *inode);
+extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran);
+extern struct timespec64 current_time(struct inode *inode);
/*
* Snapshotting support.
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
- int (*update_time)(struct inode *, struct timespec *, int);
+ int (*update_time)(struct inode *, struct timespec64 *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
- umode_t create_mode, int *opened);
+ umode_t create_mode);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
int (*set_acl)(struct inode *, struct posix_acl *, int);
} ____cacheline_aligned;
* I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
* and work dirs among overlayfs mounts.
*
+ * I_CREATING New object's inode in the middle of setting up.
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
#define __I_DIRTY_TIME_EXPIRED 12
#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED)
#define I_WB_SWITCH (1 << 13)
-#define I_OVL_INUSE (1 << 14)
+#define I_OVL_INUSE (1 << 14)
+#define I_CREATING (1 << 15)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
-extern int generic_update_time(struct inode *, struct timespec *, int);
+extern int generic_update_time(struct inode *, struct timespec64 *, int);
/* /sys/fs */
extern struct kobject *fs_kobj;
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
const char *, int, umode_t);
extern struct file * dentry_open(const struct path *, int, const struct cred *);
+static inline struct file *file_clone_open(struct file *file)
+{
+ return dentry_open(&file->f_path, file->f_flags, file->f_cred);
+}
extern int filp_close(struct file *, fl_owner_t id);
extern struct filename *getname_flags(const char __user *, int, int *);
extern struct filename *getname_kernel(const char *);
extern void putname(struct filename *name);
-enum {
- FILE_CREATED = 1,
- FILE_OPENED = 2
-};
extern int finish_open(struct file *file, struct dentry *dentry,
- int (*open)(struct inode *, struct file *),
- int *opened);
+ int (*open)(struct inode *, struct file *));
extern int finish_no_open(struct file *file, struct dentry *dentry);
/* fs/ioctl.c */
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
loff_t lend);
-extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
- loff_t lend);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
#endif
extern void unlock_new_inode(struct inode *);
+extern void discard_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern void evict_inodes(struct super_block *sb);
#define __FSL_GUTS_H__
#include <linux/types.h>
+#include <linux/io.h>
/**
* Global Utility Registers.
struct fsnotify_ops {
int (*handle_event)(struct fsnotify_group *group,
struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info);
#define FSNOTIFY_EVENT_PATH 1
#define FSNOTIFY_EVENT_INODE 2
+enum fsnotify_obj_type {
+ FSNOTIFY_OBJ_TYPE_INODE,
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT,
+ FSNOTIFY_OBJ_TYPE_COUNT,
+ FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT
+};
+
+#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE)
+#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1)
+
+struct fsnotify_iter_info {
+ struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT];
+ unsigned int report_mask;
+ int srcu_idx;
+};
+
+static inline bool fsnotify_iter_should_report_type(
+ struct fsnotify_iter_info *iter_info, int type)
+{
+ return (iter_info->report_mask & (1U << type));
+}
+
+static inline void fsnotify_iter_set_report_type(
+ struct fsnotify_iter_info *iter_info, int type)
+{
+ iter_info->report_mask |= (1U << type);
+}
+
+static inline void fsnotify_iter_set_report_type_mark(
+ struct fsnotify_iter_info *iter_info, int type,
+ struct fsnotify_mark *mark)
+{
+ iter_info->marks[type] = mark;
+ iter_info->report_mask |= (1U << type);
+}
+
+#define FSNOTIFY_ITER_FUNCS(name, NAME) \
+static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
+ struct fsnotify_iter_info *iter_info) \
+{ \
+ return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \
+ iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \
+}
+
+FSNOTIFY_ITER_FUNCS(inode, INODE)
+FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT)
+
+#define fsnotify_foreach_obj_type(type) \
+ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++)
+
/*
* Inode / vfsmount point to this structure which tracks all marks attached to
* the inode / vfsmount. The reference to inode / vfsmount is held by this
*/
struct fsnotify_mark_connector {
spinlock_t lock;
-#define FSNOTIFY_OBJ_TYPE_INODE 0x01
-#define FSNOTIFY_OBJ_TYPE_VFSMOUNT 0x02
-#define FSNOTIFY_OBJ_ALL_TYPES (FSNOTIFY_OBJ_TYPE_INODE | \
- FSNOTIFY_OBJ_TYPE_VFSMOUNT)
- unsigned int flags; /* Type of object [lock] */
+ unsigned int type; /* Type of object [lock] */
union { /* Object pointer [lock] */
struct inode *inode;
struct vfsmount *mnt;
extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
struct vfsmount *mnt, int allow_dups);
extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
- struct inode *inode, struct vfsmount *mnt, int allow_dups);
+ struct inode *inode, struct vfsmount *mnt,
+ int allow_dups);
+/* attach the mark to the inode */
+static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
+ struct inode *inode,
+ int allow_dups)
+{
+ return fsnotify_add_mark(mark, inode, NULL, allow_dups);
+}
+static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
+ struct inode *inode,
+ int allow_dups)
+{
+ return fsnotify_add_mark_locked(mark, inode, NULL, allow_dups);
+}
/* given a group and a mark, flag mark to be freed when all references are dropped */
extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group);
/* run all the marks in a group, and clear all of the vfsmount marks */
static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL);
}
/* run all the marks in a group, and clear all of the inode marks */
static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
+ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL);
}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Ftrace header. For implementation details beyond the random comments
- * scattered below, see: Documentation/trace/ftrace-design.txt
+ * scattered below, see: Documentation/trace/ftrace-design.rst
*/
#ifndef _LINUX_FTRACE_H
*/
int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
-void clear_ftrace_function(void);
extern void ftrace_stub(unsigned long a0, unsigned long a1,
struct ftrace_ops *op, struct pt_regs *regs);
{
return 0;
}
-static inline void clear_ftrace_function(void) { }
static inline void ftrace_kill(void) { }
static inline void ftrace_free_init_mem(void) { }
static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
#define HID_STAT_ADDED BIT(0)
#define HID_STAT_PARSED BIT(1)
#define HID_STAT_DUP_DETECTED BIT(2)
+#define HID_STAT_REPROBED BIT(3)
struct hid_input {
struct list_head list;
bool battery_avoid_query;
#endif
- unsigned int status; /* see STAT flags above */
+ unsigned long status; /* see STAT flags above */
unsigned claimed; /* Claimed by hidinput, hiddev? */
unsigned quirks; /* Various quirks the device can pull on us */
bool io_started; /* If IO has started */
static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
{
- return -1;
+ return -EINVAL;
}
static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo)
{
- return -1;
+ return -EINVAL;
}
#endif
extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto);
extern int igmp_rcv(struct sk_buff *);
extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr);
+extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+ unsigned int mode);
extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr);
extern void ip_mc_drop_socket(struct sock *sk);
extern int ip_mc_source(int add, int omode, struct sock *sk,
char __user *user_buffer);
size_t iio_dma_buffer_data_available(struct iio_buffer *buffer);
int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd);
-int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length);
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length);
int iio_dma_buffer_request_update(struct iio_buffer *buffer);
int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
#ifdef CONFIG_IMA
extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask, int opened);
+extern int ima_file_check(struct file *file, int mask);
extern void ima_file_free(struct file *file);
extern int ima_file_mmap(struct file *file, unsigned long prot);
extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
return 0;
}
-static inline int ima_file_check(struct file *file, int mask, int opened)
+static inline int ima_file_check(struct file *file, int mask)
{
return 0;
}
return axis == ABS_MT_SLOT || input_is_mt_value(axis);
}
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
unsigned int tool_type, bool active);
void input_mt_report_finger_count(struct input_dev *dev, int count);
#define ecap_srs(e) ((e >> 31) & 0x1)
#define ecap_ers(e) ((e >> 30) & 0x1)
#define ecap_prs(e) ((e >> 29) & 0x1)
+#define ecap_broken_pasid(e) ((e >> 28) & 0x1)
#define ecap_dis(e) ((e >> 27) & 0x1)
#define ecap_nest(e) ((e >> 26) & 0x1)
#define ecap_mts(e) ((e >> 25) & 0x1)
* IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip
* IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask
* IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode
+ * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs
*/
enum {
IRQCHIP_SET_TYPE_MASKED = (1 << 0),
#define GICD_TYPER_MBIS (1U << 16)
#define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1)
#define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32)
#define GICD_IROUTER_SPI_MODE_ONE (0U << 31)
phys_addr_t phys_base;
} __percpu *rdist;
struct page *prop_page;
- int id_bits;
u64 flags;
+ u32 gicd_typer;
bool has_vlpis;
bool has_direct_lpi;
};
return desc->irq_common_data.handler_data;
}
-static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
-{
- return desc->irq_common_data.msi_desc;
-}
-
/*
* Architectures call this to let the generic IRQ layer
* handle an interrupt.
KCOV_MODE_TRACE_CMP = 3,
};
+#define KCOV_IN_CTXSW (1 << 30)
+
void kcov_task_init(struct task_struct *t);
void kcov_task_exit(struct task_struct *t);
+#define kcov_prepare_switch(t) \
+do { \
+ (t)->kcov_mode |= KCOV_IN_CTXSW; \
+} while (0)
+
+#define kcov_finish_switch(t) \
+do { \
+ (t)->kcov_mode &= ~KCOV_IN_CTXSW; \
+} while (0)
+
#else
static inline void kcov_task_init(struct task_struct *t) {}
static inline void kcov_task_exit(struct task_struct *t) {}
+static inline void kcov_prepare_switch(struct task_struct *t) {}
+static inline void kcov_finish_switch(struct task_struct *t) {}
#endif /* CONFIG_KCOV */
#endif /* _LINUX_KCOV_H */
* your code. (Extra memory is used for special buffers that are
* allocated when trace_printk() is used.)
*
- * A little optization trick is done here. If there's only one
+ * A little optimization trick is done here. If there's only one
* argument, there's no need to scan the string for printf formats.
* The trace_puts() will suffice. But how can we take advantage of
* using trace_puts() when trace_printk() has only one argument?
struct kretprobe;
struct kretprobe_instance;
typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
-typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
unsigned long flags);
typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
*/
kprobe_fault_handler_t fault_handler;
- /*
- * ... called if breakpoint trap occurs in probe handler.
- * Return 1 if it handled break, otherwise kernel will see it.
- */
- kprobe_break_handler_t break_handler;
-
/* Saved opcode (which has been replaced with breakpoint) */
kprobe_opcode_t opcode;
return p->flags & KPROBE_FLAG_FTRACE;
}
-/*
- * Special probe type that uses setjmp-longjmp type tricks to resume
- * execution at a specified entry with a matching prototype corresponding
- * to the probed function - a trick to enable arguments to become
- * accessible seamlessly by probe handling logic.
- * Note:
- * Because of the way compilers allocate stack space for local variables
- * etc upfront, regardless of sub-scopes within a function, this mirroring
- * principle currently works only for probes placed on function entry points.
- */
-struct jprobe {
- struct kprobe kp;
- void *entry; /* probe handling code to jump to */
-};
-
-/* For backward compatibility with old code using JPROBE_ENTRY() */
-#define JPROBE_ENTRY(handler) (handler)
-
/*
* Function-return probe -
* Note:
void unregister_kprobe(struct kprobe *p);
int register_kprobes(struct kprobe **kps, int num);
void unregister_kprobes(struct kprobe **kps, int num);
-int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
-int longjmp_break_handler(struct kprobe *, struct pt_regs *);
-void jprobe_return(void);
unsigned long arch_deref_entry_point(void *);
int register_kretprobe(struct kretprobe *rp);
static inline void unregister_kprobes(struct kprobe **kps, int num)
{
}
-static inline void jprobe_return(void)
-{
-}
static inline int register_kretprobe(struct kretprobe *rp)
{
return -ENOSYS;
return -ENOSYS;
}
#endif /* CONFIG_KPROBES */
-static inline int register_jprobe(struct jprobe *p)
-{
- return -ENOSYS;
-}
-static inline int register_jprobes(struct jprobe **jps, int num)
-{
- return -ENOSYS;
-}
-static inline void unregister_jprobe(struct jprobe *p)
-{
-}
-static inline void unregister_jprobes(struct jprobe **jps, int num)
-{
-}
static inline int disable_kretprobe(struct kretprobe *rp)
{
return disable_kprobe(&rp->kp);
{
return enable_kprobe(&rp->kp);
}
-static inline int disable_jprobe(struct jprobe *jp)
-{
- return -ENOSYS;
-}
-static inline int enable_jprobe(struct jprobe *jp)
-{
- return -ENOSYS;
-}
#ifndef CONFIG_KPROBES
static inline bool is_kprobe_insn_slot(unsigned long addr)
int kthread_park(struct task_struct *k);
void kthread_unpark(struct task_struct *k);
void kthread_parkme(void);
-void kthread_park_complete(struct task_struct *k);
int kthreadd(void *unused);
extern struct task_struct *kthreadd_task;
/* Map the ktime_t to timeval conversion to ns_to_timeval function */
#define ktime_to_timeval(kt) ns_to_timeval((kt))
-/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */
-#define ktime_to_ns(kt) (kt)
+/* Convert ktime_t to nanoseconds */
+static inline s64 ktime_to_ns(const ktime_t kt)
+{
+ return kt;
+}
/**
* ktime_compare - Compares two ktime_t variables for less, greater or equal
ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */
/* (doesn't imply presence) */
ATA_FLAG_SATA = (1 << 1),
+ ATA_FLAG_NO_LPM = (1 << 2), /* host not happy with LPM */
ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */
ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */
ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */
return tag < ATA_MAX_QUEUE || ata_tag_internal(tag);
}
+#define __ata_qc_for_each(ap, qc, tag, max_tag, fn) \
+ for ((tag) = 0; (tag) < (max_tag) && \
+ ({ qc = fn((ap), (tag)); 1; }); (tag)++) \
+
+/*
+ * Internal use only, iterate commands ignoring error handling and
+ * status of 'qc'.
+ */
+#define ata_qc_for_each_raw(ap, qc, tag) \
+ __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, __ata_qc_from_tag)
+
+/*
+ * Iterate all potential commands that can be queued
+ */
+#define ata_qc_for_each(ap, qc, tag) \
+ __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, ata_qc_from_tag)
+
+/*
+ * Like ata_qc_for_each, but with the internal tag included
+ */
+#define ata_qc_for_each_with_internal(ap, qc, tag) \
+ __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE + 1, ata_qc_from_tag)
+
/*
* device helpers
*/
int (*file_send_sigiotask)(struct task_struct *tsk,
struct fown_struct *fown, int sig);
int (*file_receive)(struct file *file);
- int (*file_open)(struct file *file, const struct cred *cred);
+ int (*file_open)(struct file *file);
int (*task_alloc)(struct task_struct *task, unsigned long clone_flags);
void (*task_free)(struct task_struct *task);
*/
#define MARVELL_PHY_ID_88E6390 0x01410f90
+#define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4)
+
/* struct phy_device dev_flags definitions */
#define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001
#define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002
MEMCG_HIGH,
MEMCG_MAX,
MEMCG_OOM,
+ MEMCG_OOM_KILL,
MEMCG_SWAP_MAX,
MEMCG_SWAP_FAIL,
MEMCG_NR_MEMORY_EVENTS,
rcu_read_lock();
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (likely(memcg)) {
+ if (likely(memcg))
count_memcg_events(memcg, idx, 1);
- if (idx == OOM_KILL)
- cgroup_file_notify(&memcg->events_file);
- }
rcu_read_unlock();
}
cgroup_file_notify(&memcg->events_file);
}
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+ enum memcg_memory_event event)
+{
+ struct mem_cgroup *memcg;
+
+ if (mem_cgroup_disabled())
+ return;
+
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (likely(memcg))
+ memcg_memory_event(memcg, event);
+ rcu_read_unlock();
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void mem_cgroup_split_huge_fixup(struct page *head);
#endif
{
}
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+ enum memcg_memory_event event)
+{
+}
+
static inline enum mem_cgroup_protection mem_cgroup_protected(
struct mem_cgroup *root, struct mem_cgroup *memcg)
{
int arch_get_memory_phys_device(unsigned long start_pfn);
unsigned long memory_block_size_bytes(void);
+int set_memory_block_size_order(unsigned int order);
/* These states are exposed to userspace as text strings in sysfs */
#define MEM_ONLINE (1<<0) /* exposed to userspace */
struct mlx5_frag_buf frag_buf;
u32 sz_m1;
u32 frag_sz_m1;
+ u32 strides_offset;
u8 log_sz;
u8 log_stride;
u8 log_frag_strides;
return key & 0xffffff00u;
}
-static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
- struct mlx5_frag_buf_ctrl *fbc)
+static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz,
+ u32 strides_offset,
+ struct mlx5_frag_buf_ctrl *fbc)
{
fbc->log_stride = log_stride;
fbc->log_sz = log_sz;
fbc->sz_m1 = (1 << fbc->log_sz) - 1;
fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1;
+ fbc->strides_offset = strides_offset;
+}
+
+static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+ struct mlx5_frag_buf_ctrl *fbc)
+{
+ mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc);
}
static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
u32 ix)
{
- unsigned int frag = (ix >> fbc->log_frag_strides);
+ unsigned int frag;
+
+ ix += fbc->strides_offset;
+ frag = ix >> fbc->log_frag_strides;
return fbc->frag_buf.frags[frag].buf +
((fbc->frag_sz_m1 & ix) << fbc->log_stride);
#include <linux/mlx5/driver.h>
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
enum {
SRIOV_NONE,
SRIOV_LEGACY,
u8 vnic_env_queue_counters[0x1];
u8 ets[0x1];
u8 nic_flow_table[0x1];
- u8 eswitch_flow_table[0x1];
+ u8 eswitch_manager[0x1];
u8 device_memory[0x1];
u8 mcam_reg[0x1];
u8 pcam_reg[0x1];
* mmap() functions).
*/
-extern struct kmem_cache *vm_area_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *);
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
+void vm_area_free(struct vm_area_struct *);
#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
unsigned long addr);
};
+static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
+{
+ static const struct vm_operations_struct dummy_vm_ops = {};
+
+ vma->vm_mm = mm;
+ vma->vm_ops = &dummy_vm_ops;
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
+}
+
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+ vma->vm_ops = NULL;
+}
+
+/* flush_tlb_range() takes a vma, not a mm, and can care about flags */
+#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) }
+
struct mmu_gather;
struct inode;
struct mminit_pfnnid_cache *state);
#endif
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
void zero_resv_unavail(void);
#else
static inline void zero_resv_unavail(void) {}
struct kioctx_table;
struct mm_struct {
- struct vm_area_struct *mmap; /* list of VMAs */
- struct rb_root mm_rb;
- u32 vmacache_seqnum; /* per-thread vmacache */
+ struct {
+ struct vm_area_struct *mmap; /* list of VMAs */
+ struct rb_root mm_rb;
+ u32 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU
- unsigned long (*get_unmapped_area) (struct file *filp,
+ unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
#endif
- unsigned long mmap_base; /* base of mmap area */
- unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
+ unsigned long mmap_base; /* base of mmap area */
+ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
- /* Base adresses for compatible mmap() */
- unsigned long mmap_compat_base;
- unsigned long mmap_compat_legacy_base;
+ /* Base adresses for compatible mmap() */
+ unsigned long mmap_compat_base;
+ unsigned long mmap_compat_legacy_base;
#endif
- unsigned long task_size; /* size of task vm space */
- unsigned long highest_vm_end; /* highest vma end address */
- pgd_t * pgd;
-
- /**
- * @mm_users: The number of users including userspace.
- *
- * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops
- * to 0 (i.e. when the task exits and there are no other temporary
- * reference holders), we also release a reference on @mm_count
- * (which may then free the &struct mm_struct if @mm_count also
- * drops to 0).
- */
- atomic_t mm_users;
-
- /**
- * @mm_count: The number of references to &struct mm_struct
- * (@mm_users count as 1).
- *
- * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
- * &struct mm_struct is freed.
- */
- atomic_t mm_count;
+ unsigned long task_size; /* size of task vm space */
+ unsigned long highest_vm_end; /* highest vma end address */
+ pgd_t * pgd;
+
+ /**
+ * @mm_users: The number of users including userspace.
+ *
+ * Use mmget()/mmget_not_zero()/mmput() to modify. When this
+ * drops to 0 (i.e. when the task exits and there are no other
+ * temporary reference holders), we also release a reference on
+ * @mm_count (which may then free the &struct mm_struct if
+ * @mm_count also drops to 0).
+ */
+ atomic_t mm_users;
+
+ /**
+ * @mm_count: The number of references to &struct mm_struct
+ * (@mm_users count as 1).
+ *
+ * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
+ * &struct mm_struct is freed.
+ */
+ atomic_t mm_count;
#ifdef CONFIG_MMU
- atomic_long_t pgtables_bytes; /* PTE page table pages */
+ atomic_long_t pgtables_bytes; /* PTE page table pages */
#endif
- int map_count; /* number of VMAs */
+ int map_count; /* number of VMAs */
- spinlock_t page_table_lock; /* Protects page tables and some counters */
- struct rw_semaphore mmap_sem;
+ spinlock_t page_table_lock; /* Protects page tables and some
+ * counters
+ */
+ struct rw_semaphore mmap_sem;
- struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung
- * together off init_mm.mmlist, and are protected
- * by mmlist_lock
- */
+ struct list_head mmlist; /* List of maybe swapped mm's. These
+ * are globally strung together off
+ * init_mm.mmlist, and are protected
+ * by mmlist_lock
+ */
- unsigned long hiwater_rss; /* High-watermark of RSS usage */
- unsigned long hiwater_vm; /* High-water virtual memory usage */
+ unsigned long hiwater_rss; /* High-watermark of RSS usage */
+ unsigned long hiwater_vm; /* High-water virtual memory usage */
- unsigned long total_vm; /* Total pages mapped */
- unsigned long locked_vm; /* Pages that have PG_mlocked set */
- unsigned long pinned_vm; /* Refcount permanently increased */
- unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
- unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
- unsigned long stack_vm; /* VM_STACK */
- unsigned long def_flags;
+ unsigned long total_vm; /* Total pages mapped */
+ unsigned long locked_vm; /* Pages that have PG_mlocked set */
+ unsigned long pinned_vm; /* Refcount permanently increased */
+ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+ unsigned long stack_vm; /* VM_STACK */
+ unsigned long def_flags;
- spinlock_t arg_lock; /* protect the below fields */
- unsigned long start_code, end_code, start_data, end_data;
- unsigned long start_brk, brk, start_stack;
- unsigned long arg_start, arg_end, env_start, env_end;
+ spinlock_t arg_lock; /* protect the below fields */
+ unsigned long start_code, end_code, start_data, end_data;
+ unsigned long start_brk, brk, start_stack;
+ unsigned long arg_start, arg_end, env_start, env_end;
- unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+ unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
- /*
- * Special counters, in some configurations protected by the
- * page_table_lock, in other configurations by being atomic.
- */
- struct mm_rss_stat rss_stat;
-
- struct linux_binfmt *binfmt;
+ /*
+ * Special counters, in some configurations protected by the
+ * page_table_lock, in other configurations by being atomic.
+ */
+ struct mm_rss_stat rss_stat;
- cpumask_var_t cpu_vm_mask_var;
+ struct linux_binfmt *binfmt;
- /* Architecture-specific MM context */
- mm_context_t context;
+ /* Architecture-specific MM context */
+ mm_context_t context;
- unsigned long flags; /* Must use atomic bitops to access the bits */
+ unsigned long flags; /* Must use atomic bitops to access */
- struct core_state *core_state; /* coredumping support */
+ struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_MEMBARRIER
- atomic_t membarrier_state;
+ atomic_t membarrier_state;
#endif
#ifdef CONFIG_AIO
- spinlock_t ioctx_lock;
- struct kioctx_table __rcu *ioctx_table;
+ spinlock_t ioctx_lock;
+ struct kioctx_table __rcu *ioctx_table;
#endif
#ifdef CONFIG_MEMCG
- /*
- * "owner" points to a task that is regarded as the canonical
- * user/owner of this mm. All of the following must be true in
- * order for it to be changed:
- *
- * current == mm->owner
- * current->mm != mm
- * new_owner->mm == mm
- * new_owner->alloc_lock is held
- */
- struct task_struct __rcu *owner;
+ /*
+ * "owner" points to a task that is regarded as the canonical
+ * user/owner of this mm. All of the following must be true in
+ * order for it to be changed:
+ *
+ * current == mm->owner
+ * current->mm != mm
+ * new_owner->mm == mm
+ * new_owner->alloc_lock is held
+ */
+ struct task_struct __rcu *owner;
#endif
- struct user_namespace *user_ns;
+ struct user_namespace *user_ns;
- /* store ref to file /proc/<pid>/exe symlink points to */
- struct file __rcu *exe_file;
+
/* store ref to file /proc/<pid>/exe symlink points to */
+ struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER
- struct mmu_notifier_mm *mmu_notifier_mm;
+ struct mmu_notifier_mm *mmu_notifier_mm;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
- pgtable_t pmd_huge_pte; /* protected by page_table_lock */
-#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
- struct cpumask cpumask_allocation;
+ pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_NUMA_BALANCING
- /*
- * numa_next_scan is the next time that the PTEs will be marked
- * pte_numa. NUMA hinting faults will gather statistics and migrate
- * pages to new nodes if necessary.
- */
- unsigned long numa_next_scan;
+ /*
+ * numa_next_scan is the next time that the PTEs will be marked
+ * pte_numa. NUMA hinting faults will gather statistics and
+ * migrate pages to new nodes if necessary.
+ */
+ unsigned long numa_next_scan;
- /* Restart point for scanning and setting pte_numa */
- unsigned long numa_scan_offset;
+ /* Restart point for scanning and setting pte_numa */
+ unsigned long numa_scan_offset;
- /* numa_scan_seq prevents two threads setting pte_numa */
- int numa_scan_seq;
+ /* numa_scan_seq prevents two threads setting pte_numa */
+ int numa_scan_seq;
#endif
- /*
- * An operation with batched TLB flushing is going on. Anything that
- * can move process memory needs to flush the TLB when moving a
- * PROT_NONE or PROT_NUMA mapped page.
- */
- atomic_t tlb_flush_pending;
+ /*
+ * An operation with batched TLB flushing is going on. Anything
+ * that can move process memory needs to flush the TLB when
+ * moving a PROT_NONE or PROT_NUMA mapped page.
+ */
+ atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
- /* See flush_tlb_batched_pending() */
- bool tlb_flush_batched;
+ /* See flush_tlb_batched_pending() */
+ bool tlb_flush_batched;
#endif
- struct uprobes_state uprobes_state;
+ struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE
- atomic_long_t hugetlb_usage;
+ atomic_long_t hugetlb_usage;
#endif
- struct work_struct async_put_work;
+ struct work_struct async_put_work;
#if IS_ENABLED(CONFIG_HMM)
- /* HMM needs to track a few things per mm */
- struct hmm *hmm;
+ /* HMM needs to track a few things per mm */
+ struct hmm *hmm;
#endif
-} __randomize_layout;
+ } __randomize_layout;
+
+ /*
+ * The mm_cpumask needs to be at the end of mm_struct, because it
+ * is dynamically sized based on nr_cpu_ids.
+ */
+ unsigned long cpu_bitmap[];
+};
extern struct mm_struct init_mm;
+/* Pointer magic because the dynamic array size confuses some compilers. */
static inline void mm_init_cpumask(struct mm_struct *mm)
{
-#ifdef CONFIG_CPUMASK_OFFSTACK
- mm->cpu_vm_mask_var = &mm->cpumask_allocation;
-#endif
- cpumask_clear(mm->cpu_vm_mask_var);
+ unsigned long cpu_bitmap = (unsigned long)mm;
+
+ cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
+ cpumask_clear((struct cpumask *)cpu_bitmap);
}
/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
{
- return mm->cpu_vm_mask_var;
+ return (struct cpumask *)&mm->cpu_bitmap;
}
struct mmu_gather;
DMI_PRODUCT_VERSION,
DMI_PRODUCT_SERIAL,
DMI_PRODUCT_UUID,
+ DMI_PRODUCT_SKU,
DMI_PRODUCT_FAMILY,
DMI_BOARD_VENDOR,
DMI_BOARD_NAME,
extern struct dentry *kern_path_locked(const char *, struct path *);
extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int);
+extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int);
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int peer);
- __poll_t (*poll_mask) (struct socket *sock, __poll_t events);
__poll_t (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
if (PTR_ERR(pp) != -EINPROGRESS)
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff **pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ if (PTR_ERR(pp) != -EINPROGRESS) {
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+ }
+}
#else
static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
{
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff **pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+}
#endif
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
rcu_read_lock();
nat_hook = rcu_dereference(nf_nat_hook);
- if (nat_hook->decode_session)
+ if (nat_hook && nat_hook->decode_session)
nat_hook->decode_session(skb, fl);
rcu_read_unlock();
#endif
/* Set is defined with timeout support: timeout value may be 0 */
#define IPSET_NO_TIMEOUT UINT_MAX
+/* Max timeout value, see msecs_to_jiffies() in jiffies.h */
+#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC
+
#define ip_set_adt_opt_timeout(opt, set) \
((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout)
unsigned int timeout = ip_set_get_h32(tb);
/* Normalize to fit into jiffies */
- if (timeout > UINT_MAX/MSEC_PER_SEC)
- timeout = UINT_MAX/MSEC_PER_SEC;
+ if (timeout > IPSET_MAX_TIMEOUT)
+ timeout = IPSET_MAX_TIMEOUT;
- /* Userspace supplied TIMEOUT parameter: adjust crazy size */
- return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout;
+ return timeout;
}
static inline bool
static inline u32
ip_set_timeout_get(const unsigned long *timeout)
{
- return *timeout == IPSET_ELEM_PERMANENT ? 0 :
- jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+ u32 t;
+
+ if (*timeout == IPSET_ELEM_PERMANENT)
+ return 0;
+
+ t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
+ /* Zero value in userspace means no timeout */
+ return t == 0 ? 1 : t;
}
#endif /* __KERNEL__ */
NFS_IOHDR_EOF,
NFS_IOHDR_REDO,
NFS_IOHDR_STAT,
+ NFS_IOHDR_RESEND_PNFS,
+ NFS_IOHDR_RESEND_MDS,
};
struct nfs_io_completion;
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned int softlockup_panic;
-#else
+
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
static inline void touch_softlockup_watchdog_sched(void) { }
static inline void touch_softlockup_watchdog(void) { }
static inline void touch_softlockup_watchdog_sync(void) { }
static inline void touch_all_softlockup_watchdogs(void) { }
-#endif
+
+#define lockup_detector_online_cpu NULL
+#define lockup_detector_offline_cpu NULL
+#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
#ifdef CONFIG_DETECT_HUNG_TASK
void reset_hung_task_detector(void);
unsigned int transparent:1; /* Subtractive decode bridge */
unsigned int multifunction:1; /* Multi-function device */
- unsigned int is_added:1;
unsigned int is_busmaster:1; /* Is busmaster */
unsigned int no_msi:1; /* May not use MSI */
unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */
unsigned long pci_address_to_pio(phys_addr_t addr);
phys_addr_t pci_pio_to_address(unsigned long pio);
int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+ phys_addr_t phys_addr);
void pci_unmap_iospace(struct resource *res);
void __iomem *devm_pci_remap_cfgspace(struct device *dev,
resource_size_t offset,
};
/**
- * enum perf_event_state - the states of a event
+ * enum perf_event_state - the states of an event:
*/
enum perf_event_state {
PERF_EVENT_STATE_DEAD = -4,
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
u32 max_stack, bool crosstask, bool add_mark);
+extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
extern int get_callchain_buffers(int max_stack);
extern void put_callchain_buffers(void);
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
- * For further information, see the Documentation/spi/sc18is602 file.
+ * For further information, see the Documentation/spi/spi-sc18is602 file.
*/
/**
#include <drm/drm_mode.h>
-struct sh_mobile_meram_cfg;
-struct sh_mobile_meram_info;
-
enum shmob_drm_clk_source {
SHMOB_DRM_CLK_BUS,
SHMOB_DRM_CLK_PERIPHERAL,
struct shmob_drm_interface_data iface;
struct shmob_drm_panel_data panel;
struct shmob_drm_backlight_data backlight;
- const struct sh_mobile_meram_cfg *meram;
};
#endif /* __SHMOB_DRM_H__ */
int of_genpd_parse_idle_states(struct device_node *dn,
struct genpd_power_state **states, int *n);
unsigned int of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node);
+ struct device_node *np);
int genpd_dev_pm_attach(struct device *dev);
struct device *genpd_dev_pm_attach_by_id(struct device *dev,
static inline unsigned int
of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node)
+ struct device_node *np)
{
- return -ENODEV;
+ return 0;
}
static inline int genpd_dev_pm_attach(struct device *dev)
pt->_key = ~(__poll_t)0; /* all events enabled */
}
-static inline bool file_has_poll_mask(struct file *file)
+static inline bool file_can_poll(struct file *file)
{
- return file->f_op->get_poll_head && file->f_op->poll_mask;
+ return file->f_op->poll;
}
-static inline bool file_can_poll(struct file *file)
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
{
- return file->f_op->poll || file_has_poll_mask(file);
+ if (unlikely(!file->f_op->poll))
+ return DEFAULT_POLLMASK;
+ return file->f_op->poll(file, pt);
}
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
-
struct poll_table_entry {
struct file *filp;
__poll_t key;
clockid_t it_clock;
timer_t it_id;
int it_active;
- int it_overrun;
- int it_overrun_last;
+ s64 it_overrun;
+ s64 it_overrun_last;
int it_requeue_pending;
int it_sigev_notify;
ktime_t it_interval;
#ifdef CONFIG_PROC_FS
+typedef int (*proc_write_t)(struct file *, char *, size_t);
+
extern void proc_root_init(void);
extern void proc_flush_task(struct task_struct *);
struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
struct proc_dir_entry *parent,
int (*show)(struct seq_file *, void *), void *data);
+struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ const struct seq_operations *ops,
+ proc_write_t write,
+ unsigned int state_size, void *data);
+struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *),
+ proc_write_t write,
+ void *data);
#else /* CONFIG_PROC_FS */
struct pstore_info *psi;
enum pstore_type_id type;
u64 id;
- struct timespec time;
+ struct timespec64 time;
char *buf;
ssize_t size;
ssize_t ecc_notice_size;
#include <asm/pti.h>
#else
static inline void pti_init(void) { }
+static inline void pti_finalize(void) { }
#endif
#endif
* @member: the name of the list_head within the struct.
*
* Continue to iterate over list of given type, continuing after
- * the current position.
+ * the current position which must have been in the list when the RCU read
+ * lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_from_rcu() except
+ * this starts after the given position and that one starts at the given
+ * position.
*/
#define list_for_each_entry_continue_rcu(pos, head, member) \
for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
*
* Iterate over the tail of a list starting from a given position,
* which must have been in the list when the RCU read lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_continue_rcu() except
+ * this starts from the given position and that one starts from the position
+ * after the given position.
*/
#define list_for_each_entry_from_rcu(pos, head, member) \
for (; &(pos)->member != (head); \
*
* The barrier() is needed to make sure compiler doesn't cache first element [1],
* as this loop can be restarted [2]
- * [1] Documentation/atomic_ops.txt around line 114
+ * [1] Documentation/core-api/atomic_ops.rst around line 114
* [2] Documentation/RCU/rculist_nulls.txt around line 146
*/
#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
void __rcu_read_lock(void);
void __rcu_read_unlock(void);
-void rcu_read_unlock_special(struct task_struct *t);
void synchronize_rcu(void);
/*
} while (0)
/*
- * Note a voluntary context switch for RCU-tasks benefit. This is a
- * macro rather than an inline function to avoid #include hell.
+ * Note a quasi-voluntary context switch for RCU-tasks's benefit.
+ * This is a macro rather than an inline function to avoid #include hell.
*/
#ifdef CONFIG_TASKS_RCU
-#define rcu_note_voluntary_context_switch_lite(t) \
+#define rcu_tasks_qs(t) \
do { \
if (READ_ONCE((t)->rcu_tasks_holdout)) \
WRITE_ONCE((t)->rcu_tasks_holdout, false); \
#define rcu_note_voluntary_context_switch(t) \
do { \
rcu_all_qs(); \
- rcu_note_voluntary_context_switch_lite(t); \
+ rcu_tasks_qs(t); \
} while (0)
void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
void synchronize_rcu_tasks(void);
void exit_tasks_rcu_start(void);
void exit_tasks_rcu_finish(void);
#else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_note_voluntary_context_switch_lite(t) do { } while (0)
+#define rcu_tasks_qs(t) do { } while (0)
#define rcu_note_voluntary_context_switch(t) rcu_all_qs()
#define call_rcu_tasks call_rcu_sched
#define synchronize_rcu_tasks synchronize_sched
*/
#define cond_resched_tasks_rcu_qs() \
do { \
- if (!cond_resched()) \
- rcu_note_voluntary_context_switch_lite(current); \
+ rcu_tasks_qs(current); \
+ cond_resched(); \
} while (0)
/*
* This is simply an identity function, but it documents where a pointer
* is handed off from RCU to some other synchronization mechanism, for
* example, reference counting or locking. In C11, it would map to
- * kill_dependency(). It could be used as follows:
- * ``
+ * kill_dependency(). It could be used as follows::
+ *
* rcu_read_lock();
* p = rcu_dereference(gp);
* long_lived = is_long_lived(p);
* p = rcu_pointer_handoff(p);
* }
* rcu_read_unlock();
- *``
*/
#define rcu_pointer_handoff(p) (p)
#define rcu_note_context_switch(preempt) \
do { \
rcu_sched_qs(); \
- rcu_note_voluntary_context_switch_lite(current); \
+ rcu_tasks_qs(current); \
} while (0)
static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
#define _LINUX_REFCOUNT_H
#include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock_types.h>
+
+struct mutex;
/**
* struct refcount_t - variant of atomic_t specialized for reference counts
return atomic_read(&r->refs);
}
+extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
+extern void refcount_add_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
+extern void refcount_inc_checked(refcount_t *r);
+
+extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
+extern void refcount_dec_checked(refcount_t *r);
+
#ifdef CONFIG_REFCOUNT_FULL
-extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r);
-extern void refcount_add(unsigned int i, refcount_t *r);
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+#define refcount_add_not_zero refcount_add_not_zero_checked
+#define refcount_add refcount_add_checked
+
+#define refcount_inc_not_zero refcount_inc_not_zero_checked
+#define refcount_inc refcount_inc_checked
-extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
+#define refcount_sub_and_test refcount_sub_and_test_checked
+
+#define refcount_dec_and_test refcount_dec_and_test_checked
+#define refcount_dec refcount_dec_checked
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
#else
# ifdef CONFIG_ARCH_HAS_REFCOUNT
# include <asm/refcount.h>
extern __must_check bool refcount_dec_not_one(refcount_t *r);
extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock);
extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock);
-
+extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r,
+ spinlock_t *lock,
+ unsigned long *flags);
#endif /* _LINUX_REFCOUNT_H */
void ring_buffer_record_off(struct ring_buffer *buffer);
void ring_buffer_record_on(struct ring_buffer *buffer);
int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
struct mutex irq_mutex;
struct input_dev *input;
+ struct irq_domain *irqdomain;
+
u8 pdt_props;
u8 num_rx_electrodes;
extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key);
extern void rt_mutex_destroy(struct rt_mutex *lock);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass);
+#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0)
+#else
extern void rt_mutex_lock(struct rt_mutex *lock);
+#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock)
+#endif
+
extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
extern int rt_mutex_timed_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *timeout);
#include <asm/io.h>
struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
- unsigned long sg_magic;
-#endif
unsigned long page_link;
unsigned int offset;
unsigned int length;
*
*/
-#define SG_MAGIC 0x87654321
#define SG_CHAIN 0x01UL
#define SG_END 0x02UL
*/
BUG_ON((unsigned long) page & (SG_CHAIN | SG_END));
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
sg->page_link = page_link | (unsigned long) page;
static inline struct page *sg_page(struct scatterlist *sg)
{
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END));
**/
static inline void sg_mark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
/*
* Set termination bit, clear potential chain bit
*/
**/
static inline void sg_unmark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
sg->page_link &= ~SG_END;
}
static inline void sg_init_marker(struct scatterlist *sgl,
unsigned int nents)
{
-#ifdef CONFIG_DEBUG_SG
- unsigned int i;
-
- for (i = 0; i < nents; i++)
- sgl[i].sg_magic = SG_MAGIC;
-#endif
sg_mark_end(&sgl[nents - 1]);
}
* the comment with set_special_state().
*/
#define is_special_task_state(state) \
- ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
#define __set_current_state(state_value) \
do { \
* need_sleep = false;
* wake_up_state(p, TASK_UNINTERRUPTIBLE);
*
- * Where wake_up_state() (and all other wakeup primitives) imply enough
- * barriers to order the store of the variable against wakeup.
+ * where wake_up_state() executes a full memory barrier before accessing the
+ * task state.
*
* Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
* once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
u64 last_sum_exec_runtime;
struct callback_head numa_work;
- struct list_head numa_entry;
struct numa_group *numa_group;
/*
#ifdef CONFIG_KCOV
/* Coverage collection mode enabled for this task (0 if disabled): */
- enum kcov_mode kcov_mode;
+ unsigned int kcov_mode;
/* Size of the kcov_area: */
unsigned int kcov_size;
set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}
-void __rseq_handle_notify_resume(struct pt_regs *regs);
+void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+ struct pt_regs *regs)
{
if (current->rseq)
- __rseq_handle_notify_resume(regs);
+ __rseq_handle_notify_resume(ksig, regs);
}
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+ struct pt_regs *regs)
{
preempt_disable();
__set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask);
preempt_enable();
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(ksig, regs);
}
/* rseq_preempt() requires preemption to be disabled. */
/*
* If parent process has a registered restartable sequences area, the
- * child inherits. Only applies when forking a process, not a thread. In
- * case a parent fork() in the middle of a restartable sequence, set the
- * resume notifier to force the child to retry.
+ * child inherits. Only applies when forking a process, not a thread.
*/
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
t->rseq_len = current->rseq_len;
t->rseq_sig = current->rseq_sig;
t->rseq_event_mask = current->rseq_event_mask;
- rseq_preempt(t);
}
}
static inline void rseq_set_notify_resume(struct task_struct *t)
{
}
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+ struct pt_regs *regs)
{
}
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+ struct pt_regs *regs)
{
}
static inline void rseq_preempt(struct task_struct *t)
#ifdef CONFIG_SCHED_DEBUG
extern __read_mostly unsigned int sysctl_sched_migration_cost;
extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-extern __read_mostly unsigned int sysctl_sched_time_avg;
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-extern long kernel_wait4(pid_t, int *, int, struct rusage *);
+extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
extern void free_task(struct task_struct *tsk);
#define LINUX_SCHED_CLOCK
#ifdef CONFIG_GENERIC_SCHED_CLOCK
-extern void sched_clock_postinit(void);
+extern void generic_sched_clock_init(void);
extern void sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate);
#else
-static inline void sched_clock_postinit(void) { }
+static inline void generic_sched_clock_init(void) { }
static inline void sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate)
{
- ;
}
#endif
int security_file_send_sigiotask(struct task_struct *tsk,
struct fown_struct *fown, int sig);
int security_file_receive(struct file *file);
-int security_file_open(struct file *file, const struct cred *cred);
+int security_file_open(struct file *file);
int security_task_alloc(struct task_struct *task, unsigned long clone_flags);
void security_task_free(struct task_struct *task);
int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
return 0;
}
-static inline int security_file_open(struct file *file,
- const struct cred *cred)
+static inline int security_file_open(struct file *file)
{
return 0;
}
* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
* @xmit_more: More SKBs are pending for this queue
+ * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
* @l4_hash: indicate hash is a canonical 4-tuple hash over transport
peeked:1,
head_frag:1,
xmit_more:1,
- __unused:1; /* one bit hole */
+ pfmemalloc:1;
/* fields enclosed in headers_start/headers_end are copied
* using a single memcpy() in __copy_skb_header()
__u8 __pkt_type_offset[0];
__u8 pkt_type:3;
- __u8 pfmemalloc:1;
__u8 ignore_df:1;
-
__u8 nf_trace:1;
__u8 ip_summed:2;
__u8 ooo_okay:1;
+
__u8 l4_hash:1;
__u8 sw_hash:1;
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
-
__u8 no_fcs:1;
/* Indicates the inner headers are valid in the skbuff. */
__u8 encapsulation:1;
__u8 encap_hdr_csum:1;
__u8 csum_valid:1;
+
__u8 csum_complete_sw:1;
__u8 csum_level:2;
__u8 csum_not_inet:1;
-
__u8 dst_pending_confirm:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
__u8 ipvs_property:1;
+
__u8 inner_protocol_type:1;
__u8 remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV
int *peeked, int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
int *err);
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
struct iov_iter *to, int size);
static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
struct memcg_cache_array __rcu *memcg_caches;
struct list_head __root_caches_node;
struct list_head children;
+ bool dying;
};
struct {
struct mem_cgroup *memcg;
#ifdef CONFIG_SYSFS
#define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_unlink(struct kmem_cache *);
void sysfs_slab_release(struct kmem_cache *);
#else
+static inline void sysfs_slab_unlink(struct kmem_cache *s)
+{
+}
static inline void sysfs_slab_release(struct kmem_cache *s)
{
}
* parked (cpu offline)
* @unpark: Optional unpark function, called when the thread is
* unparked (cpu online)
- * @cpumask: Internal state. To update which threads are unparked,
- * call smpboot_update_cpumask_percpu_thread().
* @selfparking: Thread is not parked by the park function.
* @thread_comm: The base name of the thread
*/
void (*cleanup)(unsigned int cpu, bool online);
void (*park)(unsigned int cpu);
void (*unpark)(unsigned int cpu);
- cpumask_var_t cpumask;
bool selfparking;
const char *thread_comm;
};
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *cpumask);
-
-static inline int
-smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
-{
- return smpboot_register_percpu_thread_cpumask(plug_thread,
- cpu_possible_mask);
-}
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *);
#endif
#endif /*arch_spin_is_contended*/
/*
- * This barrier must provide two things:
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
*
- * - it must guarantee a STORE before the spin_lock() is ordered against a
- * LOAD after it, see the comments at its two usage sites.
+ * This guarantees that the following two properties hold:
*
- * - it must ensure the critical section is RCsc.
+ * 1) Given the snippet:
*
- * The latter is important for cases where we observe values written by other
- * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ * { X = 0; Y = 0; }
*
- * CPU0 CPU1 CPU2
+ * CPU0 CPU1
*
- * for (;;) {
- * if (READ_ONCE(X))
- * break;
- * }
- * X=1
- * <sched-out>
- * <sched-in>
- * r = X;
+ * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1);
+ * spin_lock(S); smp_mb();
+ * smp_mb__after_spinlock(); r1 = READ_ONCE(X);
+ * r0 = READ_ONCE(Y);
+ * spin_unlock(S);
*
- * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
- * we get migrated and CPU2 sees X==0.
+ * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ * preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ * try_to_wake_up().
+ *
+ * 2) Given the snippet:
+ *
+ * { X = 0; Y = 0; }
+ *
+ * CPU0 CPU1 CPU2
+ *
+ * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y);
+ * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb();
+ * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X);
+ * WRITE_ONCE(Y, 1);
+ * spin_unlock(S);
+ *
+ * it is forbidden that CPU0's critical section executes before CPU1's
+ * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ * preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ * snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
*
* Since most load-store architectures implement ACQUIRE with an smp_mb() after
* the LL/SC loop, they need no further barriers. Similarly all our TSO
#define atomic_dec_and_lock(atomic, lock) \
__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
+extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags);
+#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
+ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+
int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
size_t max_size, unsigned int cpu_mult,
gfp_t gfp);
return retval;
}
+/* Used by tracing, cannot be traced and cannot invoke lockdep. */
+static inline notrace int
+srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp)
+{
+ int retval;
+
+ retval = __srcu_read_lock(sp);
+ return retval;
+}
+
/**
* srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
* @sp: srcu_struct in which to unregister the old reader.
__srcu_read_unlock(sp, idx);
}
+/* Used by tracing, cannot be traced and cannot call lockdep. */
+static inline notrace void
+srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp)
+{
+ __srcu_read_unlock(sp, idx);
+}
+
/**
* smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
*
kuid_t uid;
kgid_t gid;
loff_t size;
- struct timespec atime;
- struct timespec mtime;
- struct timespec ctime;
- struct timespec btime; /* File creation time */
+ struct timespec64 atime;
+ struct timespec64 mtime;
+ struct timespec64 ctime;
+ struct timespec64 btime; /* File creation time */
u64 blocks;
};
* wait-queues, but the semantics are actually completely different, and
* every single user we have ever had has been buggy (or pointless).
*
- * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what
* "wake_up()" does, and has led to problems. In other cases, it has
* been fine, because there's only ever one waiter (kvm), but in that
* case gthe whole "simple" wait-queue is just pointless to begin with,
* all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
* sleeper state.
*
- * - the exclusive mode; because this requires preserving the list order
- * and this is hard.
+ * - the !exclusive mode; because that leads to O(n) wakeups, everything is
+ * exclusive.
*
* - custom wake callback functions; because you cannot give any guarantees
* about random code. This also allows swait to be used in RT, such that
* CPU0 - waker CPU1 - waiter
*
* for (;;) {
- * @cond = true; prepare_to_swait(&wq_head, &wait, state);
+ * @cond = true; prepare_to_swait_exclusive(&wq_head, &wait, state);
* smp_mb(); // smp_mb() from set_current_state()
* if (swait_active(wq_head)) if (@cond)
* wake_up(wq_head); break;
return swait_active(wq);
}
-extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_one(struct swait_queue_head *q);
extern void swake_up_all(struct swait_queue_head *q);
extern void swake_up_locked(struct swait_queue_head *q);
-extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
-/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+/* as per ___wait_event() but for swait, therefore "exclusive == 1" */
#define ___swait_event(wq, condition, state, ret, cmd) \
({ \
+ __label__ __out; \
struct swait_queue __wait; \
long __ret = ret; \
\
\
if (___wait_is_interruptible(state) && __int) { \
__ret = __int; \
- break; \
+ goto __out; \
} \
\
cmd; \
} \
finish_swait(&wq, &__wait); \
- __ret; \
+__out: __ret; \
})
#define __swait_event(wq, condition) \
(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \
schedule())
-#define swait_event(wq, condition) \
+#define swait_event_exclusive(wq, condition) \
do { \
if (condition) \
break; \
TASK_UNINTERRUPTIBLE, timeout, \
__ret = schedule_timeout(__ret))
-#define swait_event_timeout(wq, condition, timeout) \
+#define swait_event_timeout_exclusive(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \
schedule())
-#define swait_event_interruptible(wq, condition) \
+#define swait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
TASK_INTERRUPTIBLE, timeout, \
__ret = schedule_timeout(__ret))
-#define swait_event_interruptible_timeout(wq, condition, timeout) \
+#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
/**
- * swait_event_idle - wait without system load contribution
+ * swait_event_idle_exclusive - wait without system load contribution
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* condition and doesn't want to contribute to system load. Signals are
* ignored.
*/
-#define swait_event_idle(wq, condition) \
+#define swait_event_idle_exclusive(wq, condition) \
do { \
if (condition) \
break; \
__ret = schedule_timeout(__ret))
/**
- * swait_event_idle_timeout - wait up to timeout without load contribution
+ * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout at which we'll give up in jiffies
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
-#define swait_event_idle_timeout(wq, condition, timeout) \
+#define swait_event_idle_timeout_exclusive(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
#ifndef _LINUX_SYSCALLS_H
#define _LINUX_SYSCALLS_H
+struct __aio_sigset;
struct epoll_event;
struct iattr;
struct inode;
*/
#ifndef __SYSCALL_DEFINEx
#define __SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_sys##name)))); \
ALLOW_ERROR_INJECTION(sys##name, ERRNO); \
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
return ret; \
} \
+ __diag_pop(); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* __SYSCALL_DEFINEx */
/* fs/timerfd.c */
asmlinkage long sys_timerfd_create(int clockid, int flags);
asmlinkage long sys_timerfd_settime(int ufd, int flags,
- const struct itimerspec __user *utmr,
- struct itimerspec __user *otmr);
-asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
+ const struct __kernel_itimerspec __user *utmr,
+ struct __kernel_itimerspec __user *otmr);
+asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr);
/* fs/utimes.c */
asmlinkage long sys_utimensat(int dfd, const char __user *filename,
struct sigevent __user *timer_event_spec,
timer_t __user * created_timer_id);
asmlinkage long sys_timer_gettime(timer_t timer_id,
- struct itimerspec __user *setting);
+ struct __kernel_itimerspec __user *setting);
asmlinkage long sys_timer_getoverrun(timer_t timer_id);
asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
- const struct itimerspec __user *new_setting,
+ const struct __kernel_itimerspec __user *new_setting,
struct itimerspec __user *old_setting);
asmlinkage long sys_timer_delete(timer_t timer_id);
asmlinkage long sys_clock_settime(clockid_t which_clock,
int put_timespec64(const struct timespec64 *ts,
struct __kernel_timespec __user *uts);
int get_itimerspec64(struct itimerspec64 *it,
- const struct itimerspec __user *uit);
+ const struct __kernel_itimerspec __user *uit);
int put_itimerspec64(const struct itimerspec64 *it,
- struct itimerspec __user *uit);
+ struct __kernel_itimerspec __user *uit);
extern time64_t mktime64(const unsigned int year, const unsigned int mon,
const unsigned int day, const unsigned int hour,
*/
#ifndef CONFIG_64BIT_TIME
#define __kernel_timespec timespec
+#define __kernel_itimerspec itimerspec
#endif
#include <uapi/linux/time.h>
extern bool timekeeping_rtc_skipsuspend(void);
extern bool timekeeping_rtc_skipresume(void);
-extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
+extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
/*
* struct system_time_snapshot - simultaneous raw/real time capture with
extern int persistent_clock_is_local;
extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock64(struct timespec64 *ts);
+void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock,
+ struct timespec64 *boot_offset);
extern int update_persistent_clock64(struct timespec64 now);
/*
long trs_count;
};
#define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 }
+#define DEFINE_TORTURE_RANDOM_PERCPU(name) \
+ DEFINE_PER_CPU(struct torture_random_state, name)
unsigned long torture_random(struct torture_random_state *trsp);
/* Task shuffler, which causes CPUs to occasionally go idle. */
int torture_stutter_init(int s);
/* Initialization and cleanup. */
-bool torture_init_begin(char *ttype, bool v);
+bool torture_init_begin(char *ttype, int v);
void torture_init_end(void);
bool torture_cleanup_begin(void);
void torture_cleanup_end(void);
/*
* Kernel Tracepoint API.
*
- * See Documentation/trace/tracepoints.txt.
+ * See Documentation/trace/tracepoints.rst.
*
* Copyright (C) 2008-2014 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
*
struct fasync_struct *async_queue;
wait_queue_head_t wait;
struct uio_info *info;
- spinlock_t info_lock;
+ struct mutex info_lock;
struct kobject *map_dir;
struct kobject *portio_dir;
};
if (weak_barriers)
virt_rmb();
else
- rmb();
+ dma_rmb();
}
static inline void virtio_wmb(bool weak_barriers)
if (weak_barriers)
virt_wmb();
else
- wmb();
+ dma_wmb();
}
static inline void virtio_store_mb(bool weak_barriers,
struct list_head pending_links;
struct list_head accept_queue;
bool rejected;
- struct delayed_work dwork;
+ struct delayed_work connect_work;
+ struct delayed_work pending_work;
struct delayed_work close_work;
bool close_work_scheduled;
u32 peer_shutdown;
s64 vsock_stream_has_data(struct vsock_sock *vsk);
s64 vsock_stream_has_space(struct vsock_sock *vsk);
-void vsock_pending_work(struct work_struct *work);
struct sock *__vsock_create(struct net *net,
struct socket *sock,
struct sock *parent,
int flags);
int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
+__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
int bt_sock_wait_ready(struct sock *sk, unsigned long flags);
/**
* cfg80211_rx_control_port - notification about a received control port frame
* @dev: The device the frame matched to
- * @buf: control port frame
- * @len: length of the frame data
- * @addr: The peer from which the frame was received
- * @proto: frame protocol, typically PAE or Pre-authentication
+ * @skb: The skbuf with the control port frame. It is assumed that the skbuf
+ * is 802.3 formatted (with 802.3 header). The skb can be non-linear.
+ * This function does not take ownership of the skb, so the caller is
+ * responsible for any cleanup. The caller must also ensure that
+ * skb->protocol is set appropriately.
* @unencrypted: Whether the frame was received unencrypted
*
* This function is used to inform userspace about a received control port
* Return: %true if the frame was passed to userspace
*/
bool cfg80211_rx_control_port(struct net_device *dev,
- const u8 *buf, size_t len,
- const u8 *addr, u16 proto, bool unencrypted);
+ struct sk_buff *skb, bool unencrypted);
/**
* cfg80211_cqm_rssi_notify - connection quality monitoring rssi event
unused:3;
struct fib6_nh fib6_nh;
+ struct rcu_head rcu;
};
struct rt6_info {
}
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
-void fib6_info_destroy(struct fib6_info *f6i);
+void fib6_info_destroy_rcu(struct rcu_head *head);
static inline void fib6_info_hold(struct fib6_info *f6i)
{
atomic_inc(&f6i->fib6_ref);
}
+static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
+{
+ return atomic_inc_not_zero(&f6i->fib6_ref);
+}
+
static inline void fib6_info_release(struct fib6_info *f6i)
{
if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
- fib6_info_destroy(f6i);
+ call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
enum fib6_walk_state {
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
+static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
+{
+ return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
+ RTF_GATEWAY;
+}
+
void ip6_route_input(struct sk_buff *skb);
struct dst_entry *ip6_route_input_lookup(struct net *net,
struct net_device *dev,
/* alternate persistence engine */
struct ip_vs_pe __rcu *pe;
+ int conntrack_afmask;
struct rcu_head rcu_head;
};
return false;
}
+static inline int ip_vs_register_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ int afmask = (svc->af == AF_INET6) ? 2 : 1;
+ int ret = 0;
+
+ if (!(svc->conntrack_afmask & afmask)) {
+ ret = nf_ct_netns_get(svc->ipvs->net, svc->af);
+ if (ret >= 0)
+ svc->conntrack_afmask |= afmask;
+ }
+ return ret;
+#else
+ return 0;
+#endif
+}
+
+static inline void ip_vs_unregister_conntrack(struct ip_vs_service *svc)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ int afmask = (svc->af == AF_INET6) ? 2 : 1;
+
+ if (svc->conntrack_afmask & afmask) {
+ nf_ct_netns_put(svc->ipvs->net, svc->af);
+ svc->conntrack_afmask &= ~afmask;
+ }
+#endif
+}
+
static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
struct ipv6_txoptions *opt,
int newtype,
- struct ipv6_opt_hdr __user *newopt,
- int newoptlen);
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk,
- struct ipv6_txoptions *opt,
- int newtype,
- struct ipv6_opt_hdr *newopt,
- int newoptlen);
+ struct ipv6_opt_hdr *newopt);
struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
struct ipv6_txoptions *opt);
* to minimize possbility that any useful information to an
* attacker is leaked. Only lower 20 bits are relevant.
*/
- rol32(hash, 16);
+ hash = rol32(hash, 16);
flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
int ipv6_sock_mc_join(struct sock *sk, int ifindex,
const struct in6_addr *addr);
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+ const struct in6_addr *addr, unsigned int mode);
int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
const struct in6_addr *addr);
#endif /* _NET_IPV6_H */
atomic_t autobind_name;
};
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
refcount_inc(&sap->refcnt);
}
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+ return refcount_inc_not_zero(&sap->refcnt);
+}
+
void llc_sap_close(struct llc_sap *sap);
static inline void llc_sap_put(struct llc_sap *sap)
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag nf_frag;
+ struct ctl_table_header *nf_frag_frags_hdr;
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
bool *addit);
bool nf_conncount_add(struct hlist_head *head,
- const struct nf_conntrack_tuple *tuple);
+ const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_zone *zone);
void nf_conncount_cache_free(struct hlist_head *hhead);
* @portid: netlink portID of the original message
* @seq: netlink sequence number
* @family: protocol family
+ * @level: depth of the chains
* @report: notify via unicast netlink message
*/
struct nft_ctx {
u32 portid;
u32 seq;
u8 family;
+ u8 level;
bool report;
};
* @table: table that this chain belongs to
* @handle: chain handle
* @use: number of jump references to this chain
- * @level: length of longest path to this chain
* @flags: bitmask of enum nft_chain_flags
* @name: name of the chain
*/
struct nft_table *table;
u64 handle;
u32 use;
- u16 level;
u8 flags:6,
genmask:2;
char *name;
u32 genmask:2,
use:30;
u64 handle;
- char *dev_name[NFT_FLOWTABLE_DEVICE_MAX];
/* runtime data below here */
struct nf_hook_ops *ops ____cacheline_aligned;
struct nf_flowtable data;
extern struct static_key_false nft_counters_enabled;
extern struct static_key_false nft_trace_enabled;
+extern struct nft_set_type nft_set_rhash_type;
+extern struct nft_set_type nft_set_hash_type;
+extern struct nft_set_type nft_set_hash_fast_type;
+extern struct nft_set_type nft_set_rbtree_type;
+extern struct nft_set_type nft_set_bitmap_type;
+
#endif /* _NET_NF_TABLES_CORE_H */
* belonging to established connections going through that one.
*/
struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
struct sock *sk);
struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
const u8 protocol,
const struct in6_addr *saddr, const struct in6_addr *daddr,
const __be16 sport, const __be16 dport,
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_DUP_H_
-#define _NFT_DUP_H_
-
-struct nft_dup_inet {
- enum nft_registers sreg_addr:8;
- enum nft_registers sreg_dev:8;
-};
-
-#endif /* _NFT_DUP_H_ */
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag {
- struct netns_sysctl_ipv6 sysctl;
struct netns_frags frags;
};
#endif
{
}
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+ return false;
+}
+
static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
{
return NULL;
int sctp_inet_listen(struct socket *sock, int backlog);
void sctp_write_space(struct sock *sk);
void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t sctp_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
void sctp_sock_rfree(struct sk_buff *skb);
void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
};
#define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0]))
+struct sctp_output_cb {
+ struct sk_buff *last;
+};
+#define SCTP_OUTPUT_CB(__skb) ((struct sctp_output_cb *)&((__skb)->cb[0]))
+
static inline const struct sk_buff *sctp_gso_headskb(const struct sk_buff *skb)
{
const struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
#include <linux/tc_act/tc_csum.h>
struct tcf_csum_params {
- int action;
u32 update_flags;
struct rcu_head rcu;
};
struct tcf_tunnel_key_params {
struct rcu_head rcu;
int tcft_action;
- int action;
struct metadata_dst *tcft_enc_metadata;
};
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
static inline void tcp_dec_quickack_mode(struct sock *sk,
const unsigned int pkts)
{
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t tcp_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname,
void tcp_send_active_reset(struct sock *sk, gfp_t priority);
int tcp_send_synack(struct sock *);
void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
void tcp_send_ack(struct sock *sk);
void tcp_send_delayed_ack(struct sock *sk);
void tcp_send_loss_probe(struct sock *sk);
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+ TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
#if IS_ENABLED(CONFIG_IPV6)
/* This is the variant of inet6_iif() that must be used by TCP,
* as TCP moves IP6CB into a different location in skb->cb[]
*/
static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+ return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
{
bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
- CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
- CA_EVENT_NON_DELAYED_ACK,
};
/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6);
bool zc;
/* Protects multiple processes in the control path */
struct mutex mutex;
+ /* Mutual exclusion of NAPI TX thread and sendmsg error paths
+ * in the SKB destructor callback.
+ */
+ spinlock_t tx_completion_lock;
u64 rx_dropped;
};
*
* Users can examine the cq structure to determine the actual CQ size.
*/
-struct ib_cq *ib_create_cq(struct ib_device *device,
- ib_comp_handler comp_handler,
- void (*event_handler)(struct ib_event *, void *),
- void *cq_context,
- const struct ib_cq_init_attr *cq_attr);
+struct ib_cq *__ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context,
+ const struct ib_cq_init_attr *cq_attr,
+ const char *caller);
+#define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \
+ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME)
/**
* ib_resize_cq - Modifies the capacity of the CQ.
* "cpuqs": CPU passes through a quiescent state.
* "cpuonl": CPU comes online.
* "cpuofl": CPU goes offline.
+ * "cpuofl-bgp": CPU goes offline while blocking a grace period.
* "reqwait": GP kthread sleeps waiting for grace-period request.
* "reqwaitsig": GP kthread awakened by signal from reqwait state.
* "fqswait": GP kthread waiting until time to force quiescent states.
*/
TRACE_EVENT(rcu_grace_period,
- TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
+ TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent),
- TP_ARGS(rcuname, gpnum, gpevent),
+ TP_ARGS(rcuname, gp_seq, gpevent),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(const char *, gpevent)
),
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->gpevent = gpevent;
),
TP_printk("%s %lu %s",
- __entry->rcuname, __entry->gpnum, __entry->gpevent)
+ __entry->rcuname, __entry->gp_seq, __entry->gpevent)
);
/*
*
* "Startleaf": Request a grace period based on leaf-node data.
* "Prestarted": Someone beat us to the request
- * "Startedleaf": Leaf-node start proved sufficient.
- * "Startedleafroot": Leaf-node start proved sufficient after checking root.
+ * "Startedleaf": Leaf node marked for future GP.
+ * "Startedleafroot": All nodes from leaf to root marked for future GP.
* "Startedroot": Requested a nocb grace period based on root-node data.
* "NoGPkthread": The RCU grace-period kthread has not yet started.
* "StartWait": Start waiting for the requested grace period.
*/
TRACE_EVENT(rcu_future_grace_period,
- TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
- unsigned long c, u8 level, int grplo, int grphi,
+ TP_PROTO(const char *rcuname, unsigned long gp_seq,
+ unsigned long gp_seq_req, u8 level, int grplo, int grphi,
const char *gpevent),
- TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
+ TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
- __field(unsigned long, completed)
- __field(unsigned long, c)
+ __field(unsigned long, gp_seq)
+ __field(unsigned long, gp_seq_req)
__field(u8, level)
__field(int, grplo)
__field(int, grphi)
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
- __entry->completed = completed;
- __entry->c = c;
+ __entry->gp_seq = gp_seq;
+ __entry->gp_seq_req = gp_seq_req;
__entry->level = level;
__entry->grplo = grplo;
__entry->grphi = grphi;
__entry->gpevent = gpevent;
),
- TP_printk("%s %lu %lu %lu %u %d %d %s",
- __entry->rcuname, __entry->gpnum, __entry->completed,
- __entry->c, __entry->level, __entry->grplo, __entry->grphi,
- __entry->gpevent)
+ TP_printk("%s %lu %lu %u %d %d %s",
+ __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level,
+ __entry->grplo, __entry->grphi, __entry->gpevent)
);
/*
*/
TRACE_EVENT(rcu_grace_period_init,
- TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
+ TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level,
int grplo, int grphi, unsigned long qsmask),
- TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+ TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(u8, level)
__field(int, grplo)
__field(int, grphi)
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->level = level;
__entry->grplo = grplo;
__entry->grphi = grphi;
),
TP_printk("%s %lu %u %d %d %lx",
- __entry->rcuname, __entry->gpnum, __entry->level,
+ __entry->rcuname, __entry->gp_seq, __entry->level,
__entry->grplo, __entry->grphi, __entry->qsmask)
);
*/
TRACE_EVENT(rcu_preempt_task,
- TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
+ TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq),
- TP_ARGS(rcuname, pid, gpnum),
+ TP_ARGS(rcuname, pid, gp_seq),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(int, pid)
),
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->pid = pid;
),
TP_printk("%s %lu %d",
- __entry->rcuname, __entry->gpnum, __entry->pid)
+ __entry->rcuname, __entry->gp_seq, __entry->pid)
);
/*
*/
TRACE_EVENT(rcu_unlock_preempted_task,
- TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
+ TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid),
- TP_ARGS(rcuname, gpnum, pid),
+ TP_ARGS(rcuname, gp_seq, pid),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(int, pid)
),
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->pid = pid;
),
- TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+ TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
);
/*
*/
TRACE_EVENT(rcu_quiescent_state_report,
- TP_PROTO(const char *rcuname, unsigned long gpnum,
+ TP_PROTO(const char *rcuname, unsigned long gp_seq,
unsigned long mask, unsigned long qsmask,
u8 level, int grplo, int grphi, int gp_tasks),
- TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+ TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(unsigned long, mask)
__field(unsigned long, qsmask)
__field(u8, level)
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->mask = mask;
__entry->qsmask = qsmask;
__entry->level = level;
),
TP_printk("%s %lu %lx>%lx %u %d %d %u",
- __entry->rcuname, __entry->gpnum,
+ __entry->rcuname, __entry->gp_seq,
__entry->mask, __entry->qsmask, __entry->level,
__entry->grplo, __entry->grphi, __entry->gp_tasks)
);
/*
* Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number that
- * was blocked by the CPU, the CPU itself, and the type of quiescent state,
- * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
- * when kicking a CPU that has been in dyntick-idle mode for too long, or
- * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
+ * These trace events include the type of RCU, the grace-period number
+ * that was blocked by the CPU, the CPU itself, and the type of quiescent
+ * state, which can be "dti" for dyntick-idle mode, "kick" when kicking
+ * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the
+ * CPU got a quiescent state via its rcu_qs_ctr.
*/
TRACE_EVENT(rcu_fqs,
- TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
+ TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent),
- TP_ARGS(rcuname, gpnum, cpu, qsevent),
+ TP_ARGS(rcuname, gp_seq, cpu, qsevent),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(unsigned long, gpnum)
+ __field(unsigned long, gp_seq)
__field(int, cpu)
__field(const char *, qsevent)
),
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->gpnum = gpnum;
+ __entry->gp_seq = gp_seq;
__entry->cpu = cpu;
__entry->qsevent = qsevent;
),
TP_printk("%s %lu %d %s",
- __entry->rcuname, __entry->gpnum,
+ __entry->rcuname, __entry->gp_seq,
__entry->cpu, __entry->qsevent)
);
#else /* #ifdef CONFIG_RCU_TRACE */
-#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
-#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
+#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
+#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \
level, grplo, grphi, event) \
do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \
qsmask) do { } while (0)
#define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
do { } while (0)
#define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
do { } while (0)
#define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
-#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
-#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
+#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \
grplo, grphi, gp_tasks) do { } \
while (0)
-#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
+#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0)
#define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0)
#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
#include <linux/types.h>
#include <linux/fs.h>
-#include <linux/signal.h>
#include <asm/byteorder.h>
typedef __kernel_ulong_t aio_context_t;
#undef IFBIG
#undef IFLITTLE
-struct __aio_sigset {
- sigset_t __user *sigmask;
- size_t sigsetsize;
-};
-
#endif /* __LINUX__AIO_ABI_H */
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
- * is set to metric from route (IPv4/IPv6 only).
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
- * Egress device index on success, 0 if packet needs to continue
- * up the stack for further processing or a negative error in case
- * of failure.
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
- __u32 ifindex; /* L3 device index for lookup */
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
union {
/* inputs to lookup */
*/
#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24)
#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff)
+#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff)
/* Attributes stored in the BTF_INT_ENCODING */
#define BTF_INT_SIGNED (1 << 0)
#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */
#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */
#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */
+#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */
+#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */
/* Note header in a PT_NOTE section */
typedef struct elf32_note {
ETHTOOL_TX_COPYBREAK,
ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
/*
- * Add your fresh new tubale attribute above and remember to update
+ * Add your fresh new tunable attribute above and remember to update
* tunable_strings[] in net/core/ethtool.c
*/
__ETHTOOL_TUNABLE_COUNT,
#define KVM_CAP_GET_MSR_FEATURES 153
#define KVM_CAP_HYPERV_EVENTFD 154
#define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
#ifdef KVM_CAP_IRQ_ROUTING
/* These are client behavior specific flags. */
#define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on
disconnect. */
+#define NBD_CFLAG_DISCONNECT_ON_CLOSE (1 << 1) /* disconnect the nbd device on
+ * close by last opener.
+ */
/* userspace doesn't need the nbd_device structure */
IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
- __IPS_MAX_BIT = 14,
+ __IPS_MAX_BIT = 15,
};
/* Connection tracking event types */
* @NFT_SET_INTERVAL: set contains intervals
* @NFT_SET_MAP: set is used as a dictionary
* @NFT_SET_TIMEOUT: set uses timeouts
- * @NFT_SET_EVAL: set contains expressions for evaluation
+ * @NFT_SET_EVAL: set can be updated from the evaluation path
* @NFT_SET_OBJECT: set contains stateful objects
*/
enum nft_set_flags {
* only the %NL80211_ATTR_IE data is used and updated with this command.
*
* @NL80211_CMD_SET_PMK: For offloaded 4-Way handshake, set the PMK or PMK-R0
- * for the given authenticator address (specified with &NL80211_ATTR_MAC).
- * When &NL80211_ATTR_PMKR0_NAME is set, &NL80211_ATTR_PMK specifies the
+ * for the given authenticator address (specified with %NL80211_ATTR_MAC).
+ * When %NL80211_ATTR_PMKR0_NAME is set, %NL80211_ATTR_PMK specifies the
* PMK-R0, otherwise it specifies the PMK.
* @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
* configured PMK for the authenticator address identified by
- * &NL80211_ATTR_MAC.
+ * %NL80211_ATTR_MAC.
* @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way
* handshake was completed successfully by the driver. The BSSID is
- * specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake
+ * specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake
* offload should send this event after indicating 802.11 association with
- * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed
- * &NL80211_CMD_DISCONNECT should be indicated instead.
+ * %NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed
+ * %NL80211_CMD_DISCONNECT should be indicated instead.
*
* @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
* and RX notification. This command is used both as a request to transmit
* initiated the connection through the connect request.
*
* @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's
- * ht opmode or vht opmode changes using any of &NL80211_ATTR_SMPS_MODE,
- * &NL80211_ATTR_CHANNEL_WIDTH,&NL80211_ATTR_NSS attributes with its
- * address(specified in &NL80211_ATTR_MAC).
+ * ht opmode or vht opmode changes using any of %NL80211_ATTR_SMPS_MODE,
+ * %NL80211_ATTR_CHANNEL_WIDTH,%NL80211_ATTR_NSS attributes with its
+ * address(specified in %NL80211_ATTR_MAC).
*
* @NL80211_CMD_MAX: highest used command number
* @__NL80211_CMD_AFTER_LAST: internal use
* @NL80211_ATTR_EXTERNAL_AUTH_ACTION: Identify the requested external
* authentication operation (u32 attribute with an
* &enum nl80211_external_auth_action value). This is used with the
- * &NL80211_CMD_EXTERNAL_AUTH request event.
+ * %NL80211_CMD_EXTERNAL_AUTH request event.
* @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user
* space supports external authentication. This attribute shall be used
* only with %NL80211_CMD_CONNECT request. The driver may offload
* @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated
* base on contiguous rules and wider channels will be allowed to cross
* multiple contiguous/overlapping frequency ranges.
- * @NL80211_RRF_IR_CONCURRENT: See &NL80211_FREQUENCY_ATTR_IR_CONCURRENT
+ * @NL80211_RRF_IR_CONCURRENT: See %NL80211_FREQUENCY_ATTR_IR_CONCURRENT
* @NL80211_RRF_NO_HT40MINUS: channels can't be used in HT40- operation
* @NL80211_RRF_NO_HT40PLUS: channels can't be used in HT40+ operation
* @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed
* @NL80211_NAN_SRF_INCLUDE: present if the include bit of the SRF set.
* This is a flag.
* @NL80211_NAN_SRF_BF: Bloom Filter. Present if and only if
- * &NL80211_NAN_SRF_MAC_ADDRS isn't present. This attribute is binary.
+ * %NL80211_NAN_SRF_MAC_ADDRS isn't present. This attribute is binary.
* @NL80211_NAN_SRF_BF_IDX: index of the Bloom Filter. Mandatory if
- * &NL80211_NAN_SRF_BF is present. This is a u8.
+ * %NL80211_NAN_SRF_BF is present. This is a u8.
* @NL80211_NAN_SRF_MAC_ADDRS: list of MAC addresses for the SRF. Present if
- * and only if &NL80211_NAN_SRF_BF isn't present. This is a nested
+ * and only if %NL80211_NAN_SRF_BF isn't present. This is a nested
* attribute. Each nested attribute is a MAC address.
* @NUM_NL80211_NAN_SRF_ATTR: internal
* @NL80211_NAN_SRF_ATTR_MAX: highest NAN SRF attribute
PERF_SAMPLE_PHYS_ADDR = 1U << 19,
PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
+
+ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63,
};
/*
* asking selinux for a specific new context (e.g. with runcon) will result
* in execve returning -EPERM.
*
- * See Documentation/prctl/no_new_privs.txt for more details.
+ * See Documentation/userspace-api/no_new_privs.rst for more details.
*/
#define PR_SET_NO_NEW_PRIVS 38
#define PR_GET_NO_NEW_PRIVS 39
* Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
*/
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <linux/types_32_64.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
enum rseq_cpu_id_state {
RSEQ_CPU_ID_UNINITIALIZED = -1,
__u32 version;
/* enum rseq_cs_flags */
__u32 flags;
- LINUX_FIELD_u32_u64(start_ip);
+ __u64 start_ip;
/* Offset from start_ip. */
- LINUX_FIELD_u32_u64(post_commit_offset);
- LINUX_FIELD_u32_u64(abort_ip);
+ __u64 post_commit_offset;
+ __u64 abort_ip;
} __attribute__((aligned(4 * sizeof(__u64))));
/*
struct rseq {
/*
* Restartable sequences cpu_id_start field. Updated by the
- * kernel, and read by user-space with single-copy atomicity
- * semantics. Aligned on 32-bit. Always contains a value in the
- * range of possible CPUs, although the value may not be the
- * actual current CPU (e.g. if rseq is not initialized). This
- * CPU number value should always be compared against the value
- * of the cpu_id field before performing a rseq commit or
- * returning a value read from a data structure indexed using
- * the cpu_id_start value.
+ * kernel. Read by user-space with single-copy atomicity
+ * semantics. This field should only be read by the thread which
+ * registered this data structure. Aligned on 32-bit. Always
+ * contains a value in the range of possible CPUs, although the
+ * value may not be the actual current CPU (e.g. if rseq is not
+ * initialized). This CPU number value should always be compared
+ * against the value of the cpu_id field before performing a rseq
+ * commit or returning a value read from a data structure indexed
+ * using the cpu_id_start value.
*/
__u32 cpu_id_start;
/*
- * Restartable sequences cpu_id field. Updated by the kernel,
- * and read by user-space with single-copy atomicity semantics.
- * Aligned on 32-bit. Values RSEQ_CPU_ID_UNINITIALIZED and
- * RSEQ_CPU_ID_REGISTRATION_FAILED have a special semantic: the
- * former means "rseq uninitialized", and latter means "rseq
- * initialization failed". This value is meant to be read within
- * rseq critical sections and compared with the cpu_id_start
- * value previously read, before performing the commit instruction,
- * or read and compared with the cpu_id_start value before returning
- * a value loaded from a data structure indexed using the
- * cpu_id_start value.
+ * Restartable sequences cpu_id field. Updated by the kernel.
+ * Read by user-space with single-copy atomicity semantics. This
+ * field should only be read by the thread which registered this
+ * data structure. Aligned on 32-bit. Values
+ * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+ * have a special semantic: the former means "rseq uninitialized",
+ * and latter means "rseq initialization failed". This value is
+ * meant to be read within rseq critical sections and compared
+ * with the cpu_id_start value previously read, before performing
+ * the commit instruction, or read and compared with the
+ * cpu_id_start value before returning a value loaded from a data
+ * structure indexed using the cpu_id_start value.
*/
__u32 cpu_id;
/*
* targeted by the rseq_cs. Also needs to be set to NULL by user-space
* before reclaiming memory that contains the targeted struct rseq_cs.
*
- * Read and set by the kernel with single-copy atomicity semantics.
- * Set by user-space with single-copy atomicity semantics. Aligned
- * on 64-bit.
+ * Read and set by the kernel. Set by user-space with single-copy
+ * atomicity semantics. This field should only be updated by the
+ * thread which registered this data structure. Aligned on 64-bit.
*/
- LINUX_FIELD_u32_u64(rseq_cs);
+ union {
+ __u64 ptr64;
+#ifdef __LP64__
+ __u64 ptr;
+#else
+ struct {
+#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN)
+ __u32 padding; /* Initialized to zero. */
+ __u32 ptr32;
+#else /* LITTLE */
+ __u32 ptr32;
+ __u32 padding; /* Initialized to zero. */
+#endif /* ENDIAN */
+ } ptr;
+#endif
+ } rseq_cs;
+
/*
- * - RSEQ_DISABLE flag:
+ * Restartable sequences flags field.
+ *
+ * This field should only be updated by the thread which
+ * registered this data structure. Read by the kernel.
+ * Mainly used for single-stepping through rseq critical sections
+ * with debuggers.
*
- * Fallback fast-track flag for single-stepping.
- * Set by user-space if lack of progress is detected.
- * Cleared by user-space after rseq finish.
- * Read by the kernel.
* - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
- * Inhibit instruction sequence block restart and event
- * counter increment on preemption for this thread.
+ * Inhibit instruction sequence block restart on preemption
+ * for this thread.
* - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
- * Inhibit instruction sequence block restart and event
- * counter increment on signal delivery for this thread.
+ * Inhibit instruction sequence block restart on signal
+ * delivery for this thread.
* - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
- * Inhibit instruction sequence block restart and event
- * counter increment on migration for this thread.
+ * Inhibit instruction sequence block restart on migration for
+ * this thread.
*/
__u32 flags;
} __attribute__((aligned(4 * sizeof(__u64))));
#define TCMU_MAILBOX_VERSION 2
#define ALIGN_SIZE 64 /* Should be enough for most CPUs */
#define TCMU_MAILBOX_FLAG_CAP_OOOC (1 << 0) /* Out-of-order completions */
+#define TCMU_MAILBOX_FLAG_CAP_READ_LEN (1 << 1) /* Read data length */
struct tcmu_mailbox {
__u16 version;
__u16 cmd_id;
__u8 kflags;
#define TCMU_UFLAG_UNKNOWN_OP 0x1
+#define TCMU_UFLAG_READ_LEN 0x2
__u8 uflags;
} __packed;
__u8 scsi_status;
__u8 __pad1;
__u16 __pad2;
- __u32 __pad3;
+ __u32 read_len;
char sense_buffer[TCMU_SENSE_BUFFERSIZE];
} rsp;
};
#define TCP_CM_INQ TCP_INQ
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF 0
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
struct tcp_repair_opt {
__u32 opt_code;
__u32 opt_val;
};
#endif
+#ifndef __kernel_itimerspec
+struct __kernel_itimerspec {
+ struct __kernel_timespec it_interval; /* timer period */
+ struct __kernel_timespec it_value; /* timer expiration */
+};
+#endif
+
/*
* legacy timeval structure, only embedded in structures that
* traditionally used 'timeval' to pass time intervals (not absolute
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_TYPES_32_64_H
-#define _UAPI_LINUX_TYPES_32_64_H
-
-/*
- * linux/types_32_64.h
- *
- * Integer type declaration for pointers across 32-bit and 64-bit systems.
- *
- * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- */
-
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <asm/byteorder.h>
-
-#ifdef __BYTE_ORDER
-# if (__BYTE_ORDER == __BIG_ENDIAN)
-# define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-# define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#else
-# ifdef __BIG_ENDIAN
-# define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-# define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#endif
-
-#ifdef __LP64__
-# define LINUX_FIELD_u32_u64(field) __u64 field
-# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) field = (intptr_t)v
-#else
-# ifdef LINUX_BYTE_ORDER_BIG_ENDIAN
-# define LINUX_FIELD_u32_u64(field) __u32 field ## _padding, field
-# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) \
- field ## _padding = 0, field = (intptr_t)v
-# else
-# define LINUX_FIELD_u32_u64(field) __u32 field, field ## _padding
-# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) \
- field = (intptr_t)v, field ## _padding = 0
-# endif
-#endif
-
-#endif /* _UAPI_LINUX_TYPES_32_64_H */
#define UAC_OUTPUT_TERMINAL_COMMUNICATION_SPEAKER 0x306
#define UAC_OUTPUT_TERMINAL_LOW_FREQ_EFFECTS_SPEAKER 0x307
+/* Terminals - 2.4 Bi-directional Terminal Types */
+#define UAC_BIDIR_TERMINAL_UNDEFINED 0x400
+#define UAC_BIDIR_TERMINAL_HANDSET 0x401
+#define UAC_BIDIR_TERMINAL_HEADSET 0x402
+#define UAC_BIDIR_TERMINAL_SPEAKER_PHONE 0x403
+#define UAC_BIDIR_TERMINAL_ECHO_SUPPRESSING 0x404
+#define UAC_BIDIR_TERMINAL_ECHO_CANCELING 0x405
+
/* Set bControlSize = 2 as default setting */
#define UAC_DT_FEATURE_UNIT_SIZE(ch) (7 + ((ch) + 1) * 2)
/* We've given up on this device. */
#define VIRTIO_CONFIG_S_FAILED 0x80
-/* Some virtio feature bits (currently bits 28 through 32) are reserved for the
- * transport being used (eg. virtio_ring), the rest are per-device feature
- * bits. */
+/*
+ * Virtio feature bits VIRTIO_TRANSPORT_F_START through
+ * VIRTIO_TRANSPORT_F_END are reserved for the transport
+ * being used (e.g. virtio_ring, virtio_pci etc.), the
+ * rest are per-device feature bits.
+ */
#define VIRTIO_TRANSPORT_F_START 28
-#define VIRTIO_TRANSPORT_F_END 34
+#define VIRTIO_TRANSPORT_F_END 38
#ifndef VIRTIO_CONFIG_NO_LEGACY
/* Do we get callbacks when the ring is completely used, even if we've
* this is for compatibility with legacy systems.
*/
#define VIRTIO_F_IOMMU_PLATFORM 33
+
+/*
+ * Does the device support Single Root I/O Virtualization?
+ */
+#define VIRTIO_F_SR_IOV 37
#endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
+++ /dev/null
-/*
- * Definitions for AUO-K190X framebuffer drivers
- *
- * Copyright (C) 2012 Heiko Stuebner <heiko@sntech.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _LINUX_VIDEO_AUO_K190XFB_H_
-#define _LINUX_VIDEO_AUO_K190XFB_H_
-
-/* Controller standby command needs a param */
-#define AUOK190X_QUIRK_STANDBYPARAM (1 << 0)
-
-/* Controller standby is completely broken */
-#define AUOK190X_QUIRK_STANDBYBROKEN (1 << 1)
-
-/*
- * Resolutions for the displays
- */
-#define AUOK190X_RESOLUTION_800_600 0
-#define AUOK190X_RESOLUTION_1024_768 1
-#define AUOK190X_RESOLUTION_600_800 4
-#define AUOK190X_RESOLUTION_768_1024 5
-
-/*
- * struct used by auok190x. board specific stuff comes from *board
- */
-struct auok190xfb_par {
- struct fb_info *info;
- struct auok190x_board *board;
-
- struct regulator *regulator;
-
- struct mutex io_lock;
- struct delayed_work work;
- wait_queue_head_t waitq;
- int resolution;
- int rotation;
- int consecutive_threshold;
- int update_cnt;
-
- /* panel and controller informations */
- int epd_type;
- int panel_size_int;
- int panel_size_float;
- int panel_model;
- int tcon_version;
- int lut_version;
-
- /* individual controller callbacks */
- void (*update_partial)(struct auok190xfb_par *par, u16 y1, u16 y2);
- void (*update_all)(struct auok190xfb_par *par);
- bool (*need_refresh)(struct auok190xfb_par *par);
- void (*init)(struct auok190xfb_par *par);
- void (*recover)(struct auok190xfb_par *par);
-
- int update_mode; /* mode to use for updates */
- int last_mode; /* update mode last used */
- int flash;
-
- /* power management */
- int autosuspend_delay;
- bool standby;
- bool manual_standby;
-};
-
-/**
- * Board specific platform-data
- * @init: initialize the controller interface
- * @cleanup: cleanup the controller interface
- * @wait_for_rdy: wait until the controller is not busy anymore
- * @set_ctl: change an interface control
- * @set_hdb: write a value to the data register
- * @get_hdb: read a value from the data register
- * @setup_irq: method to setup the irq handling on the busy gpio
- * @gpio_nsleep: sleep gpio
- * @gpio_nrst: reset gpio
- * @gpio_nbusy: busy gpio
- * @resolution: one of the AUOK190X_RESOLUTION constants
- * @rotation: rotation of the framebuffer
- * @quirks: controller quirks to honor
- * @fps: frames per second for defio
- */
-struct auok190x_board {
- int (*init)(struct auok190xfb_par *);
- void (*cleanup)(struct auok190xfb_par *);
- int (*wait_for_rdy)(struct auok190xfb_par *);
-
- void (*set_ctl)(struct auok190xfb_par *, unsigned char, u8);
- void (*set_hdb)(struct auok190xfb_par *, u16);
- u16 (*get_hdb)(struct auok190xfb_par *);
-
- int (*setup_irq)(struct fb_info *);
-
- int gpio_nsleep;
- int gpio_nrst;
- int gpio_nbusy;
-
- int resolution;
- int quirks;
- int fps;
-};
-
-#endif
#define __ASM_SH_MOBILE_LCDC_H__
#include <linux/fb.h>
-#include <video/sh_mobile_meram.h>
/* Register definitions */
#define _LDDCKR 0x410
struct sh_mobile_lcdc_panel_cfg panel_cfg;
struct sh_mobile_lcdc_bl_info bl_info;
struct sh_mobile_lcdc_sys_bus_cfg sys_bus_cfg; /* only for SYSn I/F */
- const struct sh_mobile_meram_cfg *meram_cfg;
struct platform_device *tx_dev; /* HDMI/DSI transmitter device */
};
int clock_source;
struct sh_mobile_lcdc_chan_cfg ch[2];
struct sh_mobile_lcdc_overlay_cfg overlays[4];
- struct sh_mobile_meram_info *meram_dev;
};
#endif /* __ASM_SH_MOBILE_LCDC_H__ */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __VIDEO_SH_MOBILE_MERAM_H__
-#define __VIDEO_SH_MOBILE_MERAM_H__
-
-/* For sh_mobile_meram_info.addr_mode */
-enum {
- SH_MOBILE_MERAM_MODE0 = 0,
- SH_MOBILE_MERAM_MODE1
-};
-
-enum {
- SH_MOBILE_MERAM_PF_NV = 0,
- SH_MOBILE_MERAM_PF_RGB,
- SH_MOBILE_MERAM_PF_NV24
-};
-
-
-struct sh_mobile_meram_priv;
-
-/*
- * struct sh_mobile_meram_info - MERAM platform data
- * @reserved_icbs: Bitmask of reserved ICBs (for instance used through UIO)
- */
-struct sh_mobile_meram_info {
- int addr_mode;
- u32 reserved_icbs;
- struct sh_mobile_meram_priv *priv;
- struct platform_device *pdev;
-};
-
-/* icb config */
-struct sh_mobile_meram_icb_cfg {
- unsigned int meram_size; /* MERAM Buffer Size to use */
-};
-
-struct sh_mobile_meram_cfg {
- struct sh_mobile_meram_icb_cfg icb[2];
-};
-
-#if defined(CONFIG_FB_SH_MOBILE_MERAM) || \
- defined(CONFIG_FB_SH_MOBILE_MERAM_MODULE)
-unsigned long sh_mobile_meram_alloc(struct sh_mobile_meram_info *meram_dev,
- size_t size);
-void sh_mobile_meram_free(struct sh_mobile_meram_info *meram_dev,
- unsigned long mem, size_t size);
-void *sh_mobile_meram_cache_alloc(struct sh_mobile_meram_info *dev,
- const struct sh_mobile_meram_cfg *cfg,
- unsigned int xres, unsigned int yres,
- unsigned int pixelformat,
- unsigned int *pitch);
-void sh_mobile_meram_cache_free(struct sh_mobile_meram_info *dev, void *data);
-void sh_mobile_meram_cache_update(struct sh_mobile_meram_info *dev, void *data,
- unsigned long base_addr_y,
- unsigned long base_addr_c,
- unsigned long *icb_addr_y,
- unsigned long *icb_addr_c);
-#else
-static inline unsigned long
-sh_mobile_meram_alloc(struct sh_mobile_meram_info *meram_dev, size_t size)
-{
- return 0;
-}
-
-static inline void
-sh_mobile_meram_free(struct sh_mobile_meram_info *meram_dev,
- unsigned long mem, size_t size)
-{
-}
-
-static inline void *
-sh_mobile_meram_cache_alloc(struct sh_mobile_meram_info *dev,
- const struct sh_mobile_meram_cfg *cfg,
- unsigned int xres, unsigned int yres,
- unsigned int pixelformat,
- unsigned int *pitch)
-{
- return ERR_PTR(-ENODEV);
-}
-
-static inline void
-sh_mobile_meram_cache_free(struct sh_mobile_meram_info *dev, void *data)
-{
-}
-
-static inline void
-sh_mobile_meram_cache_update(struct sh_mobile_meram_info *dev, void *data,
- unsigned long base_addr_y,
- unsigned long base_addr_c,
- unsigned long *icb_addr_y,
- unsigned long *icb_addr_c)
-{
-}
-#endif
-
-#endif /* __VIDEO_SH_MOBILE_MERAM_H__ */
* Linux [2] and Windows [3] multi-touch support.
*
* [1] https://cgit.freedesktop.org/wayland/wayland/tree/protocol/wayland.xml
- * [2] https://www.kernel.org/doc/Documentation/input/multi-touch-protocol.txt
+ * [2] https://www.kernel.org/doc/Documentation/input/multi-touch-protocol.rst
* [3] https://msdn.microsoft.com/en-us/library/jj151564(v=vs.85).aspx
*
*
#define xen_hvm_domain() (xen_domain_type == XEN_HVM_DOMAIN)
#define xen_pvh_domain() (xen_pvh)
+#include <linux/types.h>
+
+extern uint32_t xen_start_flags;
+
#ifdef CONFIG_XEN_DOM0
#include <xen/interface/xen.h>
#include <asm/xen/hypervisor.h>
#define xen_initial_domain() (xen_domain() && \
- xen_start_info && xen_start_info->flags & SIF_INITDOMAIN)
+ (xen_start_flags & SIF_INITDOMAIN))
#else /* !CONFIG_XEN_DOM0 */
#define xen_initial_domain() (0)
#endif /* CONFIG_XEN_DOM0 */
config HAVE_KERNEL_LZ4
bool
+config HAVE_KERNEL_UNCOMPRESSED
+ bool
+
choice
prompt "Kernel compression mode"
default KERNEL_GZIP
- depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
+ depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
help
The linux kernel is a kind of self-extracting executable.
Several compression algorithms are available, which differ
is about 8% bigger than LZO. But the decompression speed is
faster than LZO.
+config KERNEL_UNCOMPRESSED
+ bool "None"
+ depends on HAVE_KERNEL_UNCOMPRESSED
+ help
+ Produce uncompressed kernel image. This option is usually not what
+ you want. It is useful for debugging the kernel in slow simulation
+ environments, where decompressing and moving the kernel is awfully
+ slow. This option allows early boot code to skip the decompressor
+ and jump right at uncompressed kernel image.
+
endchoice
config DEFAULT_HOSTNAME
depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
depends on EXPERT
help
- Select this if the architecture wants to do dead code and
- data elimination with the linker by compiling with
- -ffunction-sections -fdata-sections, and linking with
- --gc-sections.
+ Enable this if you want to do dead code and data elimination with
+ the linker by compiling with -ffunction-sections -fdata-sections,
+ and linking with --gc-sections.
This can reduce on disk and in-memory size of the kernel
code and static data, particularly for small configs and
endmenu # General setup
-config HAVE_GENERIC_DMA_COHERENT
- bool
- default n
-
config RT_MUTEXES
bool
#include <linux/pti.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
-#include <linux/sched_clock.h>
+#include <linux/sched/clock.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/context_tracking.h>
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
- boot_cpu_state_init();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
+ boot_cpu_hotplug_init();
build_all_zonelists(NULL);
page_alloc_init();
softirq_init();
timekeeping_init();
time_init();
- sched_clock_postinit();
printk_safe_init();
perf_event_init();
profile_init();
acpi_early_init();
if (late_time_init)
late_time_init();
+ sched_clock_init();
calibrate_delay();
pid_idr_init();
anon_vma_init();
jump_label_invalidate_initmem();
free_initmem();
mark_readonly();
+
+ /*
+ * Kernel mappings are now finalized - update the userspace page-table
+ * to finalize PTI.
+ */
+ pti_finalize();
+
system_state = SYSTEM_RUNNING;
numa_default_policy();
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>
#include <linux/sched/wake_q.h>
+#include <linux/nospec.h>
#include <linux/uaccess.h>
#include "util.h"
int nsops)
{
struct sem *sem;
+ int idx;
if (nsops != 1) {
/* Complex operation - acquire a full lock */
*
* Both facts are tracked by use_global_mode.
*/
- sem = &sma->sems[sops->sem_num];
+ idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
+ sem = &sma->sems[idx];
/*
* Initial check for use_global_lock. Just an optimization,
un = q->undo;
for (sop = sops; sop < sops + nsops; sop++) {
- curr = &sma->sems[sop->sem_num];
+ int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
+ curr = &sma->sems[idx];
sem_op = sop->sem_op;
result = curr->semval;
* until the operations can go through.
*/
for (sop = sops; sop < sops + nsops; sop++) {
- curr = &sma->sems[sop->sem_num];
+ int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
+
+ curr = &sma->sems[idx];
sem_op = sop->sem_op;
result = curr->semval;
return -EIDRM;
}
+ semnum = array_index_nospec(semnum, sma->sem_nsems);
curr = &sma->sems[semnum];
ipc_assert_locked_object(&sma->sem_perm);
err = -EIDRM;
goto out_unlock;
}
+
+ semnum = array_index_nospec(semnum, nsems);
curr = &sma->sems[semnum];
switch (cmd) {
*/
if (nsops == 1) {
struct sem *curr;
- curr = &sma->sems[sops->sem_num];
+ int idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
+ curr = &sma->sems[idx];
if (alter) {
if (sma->complex_count) {
}
do {
- queue.status = -EINTR;
+ WRITE_ONCE(queue.status, -EINTR);
queue.sleeper = current;
__set_current_state(TASK_INTERRUPTIBLE);
up_write(&shm_ids(ns).rwsem);
}
-static int shm_fault(struct vm_fault *vmf)
+static vm_fault_t shm_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
return 0;
}
+static unsigned long shm_pagesize(struct vm_area_struct *vma)
+{
+ struct file *file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
+
+ if (sfd->vm_ops->pagesize)
+ return sfd->vm_ops->pagesize(vma);
+
+ return PAGE_SIZE;
+}
+
#ifdef CONFIG_NUMA
static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
{
.close = shm_close, /* callback for when the vm-area is released */
.fault = shm_fault,
.split = shm_split,
+ .pagesize = shm_pagesize,
#if defined(CONFIG_NUMA)
.set_policy = shm_set_policy,
.get_policy = shm_get_policy,
struct shmid_kernel *shp;
unsigned long addr = (unsigned long)shmaddr;
unsigned long size;
- struct file *file;
+ struct file *file, *base;
int err;
unsigned long flags = MAP_SHARED;
unsigned long prot;
int acc_mode;
struct ipc_namespace *ns;
struct shm_file_data *sfd;
- struct path path;
- fmode_t f_mode;
+ int f_flags;
unsigned long populate = 0;
err = -EINVAL;
if (shmflg & SHM_RDONLY) {
prot = PROT_READ;
acc_mode = S_IRUGO;
- f_mode = FMODE_READ;
+ f_flags = O_RDONLY;
} else {
prot = PROT_READ | PROT_WRITE;
acc_mode = S_IRUGO | S_IWUGO;
- f_mode = FMODE_READ | FMODE_WRITE;
+ f_flags = O_RDWR;
}
if (shmflg & SHM_EXEC) {
prot |= PROT_EXEC;
goto out_unlock;
}
- path = shp->shm_file->f_path;
- path_get(&path);
+ /*
+ * We need to take a reference to the real shm file to prevent the
+ * pointer from becoming stale in cases where the lifetime of the outer
+ * file extends beyond that of the shm segment. It's not usually
+ * possible, but it can happen during remap_file_pages() emulation as
+ * that unmaps the memory, then does ->mmap() via file reference only.
+ * We'll deny the ->mmap() if the shm segment was since removed, but to
+ * detect shm ID reuse we need to compare the file pointers.
+ */
+ base = get_file(shp->shm_file);
shp->shm_nattch++;
- size = i_size_read(d_inode(path.dentry));
+ size = i_size_read(file_inode(base));
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
if (!sfd) {
- path_put(&path);
+ fput(base);
goto out_nattch;
}
- file = alloc_file(&path, f_mode,
- is_file_hugepages(shp->shm_file) ?
+ file = alloc_file_clone(base, f_flags,
+ is_file_hugepages(base) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
if (IS_ERR(file)) {
kfree(sfd);
- path_put(&path);
+ fput(base);
goto out_nattch;
}
- file->private_data = sfd;
- file->f_mapping = shp->shm_file->f_mapping;
sfd->id = shp->shm_perm.id;
sfd->ns = get_ipc_ns(ns);
- /*
- * We need to take a reference to the real shm file to prevent the
- * pointer from becoming stale in cases where the lifetime of the outer
- * file extends beyond that of the shm segment. It's not usually
- * possible, but it can happen during remap_file_pages() emulation as
- * that unmaps the memory, then does ->mmap() via file reference only.
- * We'll deny the ->mmap() if the shm segment was since removed, but to
- * detect shm ID reuse we need to compare the file pointers.
- */
- sfd->file = get_file(shp->shm_file);
+ sfd->file = base;
sfd->vm_ops = NULL;
+ file->private_data = sfd;
err = security_mmap_file(file, prot, flags);
if (err)
obj-y += irq/
obj-y += rcu/
obj-y += livepatch/
+obj-y += dma/
obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
obj-$(CONFIG_FREEZER) += freezer.o
audit_update_mark(audit_mark, dentry->d_inode);
audit_mark->rule = krule;
- ret = fsnotify_add_mark(&audit_mark->mark, inode, NULL, true);
+ ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
if (ret < 0) {
fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
/* Update mark data in audit rules based on fsnotify events. */
static int audit_mark_handle_event(struct fsnotify_group *group,
struct inode *to_tell,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *dname, u32 cookie,
struct fsnotify_iter_info *iter_info)
{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
struct audit_fsnotify_mark *audit_mark;
const struct inode *inode = NULL;
if (!new)
goto Fallback;
- if (fsnotify_add_mark_locked(&new->mark, entry->connector->inode,
- NULL, 1)) {
+ if (fsnotify_add_inode_mark_locked(&new->mark, entry->connector->inode,
+ 1)) {
fsnotify_put_mark(&new->mark);
goto Fallback;
}
return -ENOMEM;
entry = &chunk->mark;
- if (fsnotify_add_mark(entry, inode, NULL, 0)) {
+ if (fsnotify_add_inode_mark(entry, inode, 0)) {
fsnotify_put_mark(entry);
return -ENOSPC;
}
return -ENOENT;
}
- if (fsnotify_add_mark_locked(chunk_entry,
- old_entry->connector->inode, NULL, 1)) {
+ if (fsnotify_add_inode_mark_locked(chunk_entry,
+ old_entry->connector->inode, 1)) {
spin_unlock(&old_entry->lock);
mutex_unlock(&old_entry->group->mark_mutex);
fsnotify_put_mark(chunk_entry);
static int audit_tree_handle_event(struct fsnotify_group *group,
struct inode *to_tell,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info)
fsnotify_init_mark(&parent->mark, audit_watch_group);
parent->mark.mask = AUDIT_FS_WATCH;
- ret = fsnotify_add_mark(&parent->mark, inode, NULL, 0);
+ ret = fsnotify_add_inode_mark(&parent->mark, inode, 0);
if (ret < 0) {
audit_free_parent(parent);
return ERR_PTR(ret);
/* Update watch data in audit rules based on fsnotify events. */
static int audit_watch_handle_event(struct fsnotify_group *group,
struct inode *to_tell,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
u32 mask, const void *data, int data_type,
const unsigned char *dname, u32 cookie,
struct fsnotify_iter_info *iter_info)
{
+ struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
const struct inode *inode;
struct audit_parent *parent;
break;
case AUDIT_KERN_MODULE:
audit_log_format(ab, "name=");
- audit_log_untrustedstring(ab, context->module.name);
- kfree(context->module.name);
+ if (context->module.name) {
+ audit_log_untrustedstring(ab, context->module.name);
+ kfree(context->module.name);
+ } else
+ audit_log_format(ab, "(null)");
+
break;
}
audit_log_end(ab);
{
struct audit_context *context = audit_context();
- context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
- strcpy(context->module.name, name);
+ context->module.name = kstrdup(name, GFP_KERNEL);
+ if (!context->module.name)
+ audit_log_lost("out of memory in __audit_log_kern_module");
context->type = AUDIT_KERN_MODULE;
}
return -EINVAL;
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
- if (!value_type || value_size > map->value_size)
+ if (!value_type || value_size != map->value_size)
return -EINVAL;
return 0;
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
-
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u64_num >>= bits_offset;
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
+ u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
- u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
btf_verifier_log_type(env, t, NULL);
+ last_offset = 0;
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
return -EINVAL;
}
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
}
btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
}
return meta_needed;
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
return prog_adj;
}
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
return 0;
}
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
- fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
- fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+ bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
if (*err)
return fp;
}
+
+finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq);
+ struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
/* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, false);
}
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq)
+ struct xdp_bulk_queue *bq, bool in_napi_ctx)
{
unsigned int processed = 0, drops = 0;
const int to_cpu = rcpu->cpu;
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
}
processed++;
}
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
/* Flush all frames in bulkq to real queue */
bq = this_cpu_ptr(rcpu->bulkq);
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(rcpu->kthread);
}
static int bq_xmit_all(struct bpf_dtab_netdev *obj,
- struct xdp_bulk_queue *bq, u32 flags)
+ struct xdp_bulk_queue *bq, u32 flags,
+ bool in_napi_ctx)
{
struct net_device *dev = obj->dev;
int sent = 0, drops = 0, err = 0;
struct xdp_frame *xdpf = bq->q[i];
/* RX path under NAPI protection, can return frames faster */
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
drops++;
}
goto out;
__clear_bit(bit, bitmap);
bq = this_cpu_ptr(dev->bulkq);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
}
}
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
- bq_xmit_all(obj, bq, 0);
+ bq_xmit_all(obj, bq, 0, true);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
+ int err;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
return bq_enqueue(dst, xdpf, dev_rx);
}
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ int err;
+
+ err = xdp_ok_fwd_dev(dst->dev, skb->len);
+ if (unlikely(err))
+ return err;
+ skb->dev = dst->dev;
+ generic_xdp_tx(skb, xdp_prog);
+
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
__clear_bit(dev->bit, bitmap);
bq = per_cpu_ptr(dev->bulkq, cpu);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
}
}
}
* old element will be freed immediately.
* Otherwise return an error
*/
- atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
}
l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
htab->map.numa_node);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
}
memcpy(l_new->key, key, key_size);
GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
- return ERR_PTR(-ENOMEM);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
}
}
l_new->hash = hash;
return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
}
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
.release = bpffs_map_release,
};
+static int bpffs_obj_open(struct inode *inode, struct file *file)
+{
+ return -EIO;
+}
+
+static const struct file_operations bpffs_obj_fops = {
+ .open = bpffs_obj_open,
+};
+
static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
const struct inode_operations *iops,
const struct file_operations *fops)
static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
{
- return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, NULL);
+ return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops,
+ &bpffs_obj_fops);
}
static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
struct bpf_map *map = arg;
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
- map->btf ? &bpffs_map_fops : NULL);
+ map->btf ? &bpffs_map_fops : &bpffs_obj_fops);
}
static struct dentry *
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
+ lock_sock(sk);
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
+ release_sock(sk);
return sk->sk_prot->close(sk, timeout);
}
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
+ release_sock(sk);
close_fun(sk, timeout);
}
while (sg[i].length) {
free += sg[i].length;
sk_mem_uncharge(sk, sg[i].length);
- put_page(sg_page(&sg[i]));
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
sg[i].length = 0;
sg[i].page_link = 0;
sg[i].offset = 0;
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ if (md->skb)
+ consume_skb(md->skb);
return free;
}
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
while (msg_data_left(msg)) {
- struct sk_msg_buff *m;
+ struct sk_msg_buff *m = NULL;
bool enospc = false;
int copy;
if (sk->sk_err) {
- err = sk->sk_err;
+ err = -sk->sk_err;
goto out_err;
}
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
err = sk_stream_wait_memory(sk, &timeo);
- if (err)
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m);
goto out_err;
+ }
}
out_err:
if (err < 0)
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
*/
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
if (!e) {
err = -ENOMEM;
- goto out_progs;
+ goto out_free;
}
}
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
return -EOPNOTSUPP;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
if (err)
goto err;
- /* bpf_map_update_elem() can be called in_irq() */
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
raw_spin_lock_bh(&b->lock);
l_old = lookup_elem_raw(head, hash, key, key_size);
if (l_old && map_flags == BPF_NOEXIST) {
goto bucket_err;
}
- psock = smap_psock_sk(sock);
- if (unlikely(!psock)) {
- err = -EINVAL;
- goto bucket_err;
- }
-
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
raw_spin_unlock_bh(&b->lock);
return 0;
bucket_err:
+ smap_release_sock(psock, sock);
raw_spin_unlock_bh(&b->lock);
err:
kfree(e);
- psock = smap_psock_sk(sock);
- if (psock)
- smap_release_sock(psock, sock);
return err;
}
return -EINVAL;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
b = __select_bucket(htab, hash);
head = &b->head;
- raw_spin_lock_bh(&b->lock);
l = lookup_elem_raw(head, hash, key, key_size);
sk = l ? l->sk : NULL;
- raw_spin_unlock_bh(&b->lock);
return sk;
}
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
{
int refold;
- refold = __atomic_add_unless(&map->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
- int i;
-
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
-
- for (i = 0; i < prog->aux->func_cnt; i++)
- bpf_prog_kallsyms_del(prog->aux->func[i]);
- bpf_prog_kallsyms_del(prog);
+ bpf_prog_kallsyms_del_all(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
{
int refold;
- refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
if (err < 0)
goto free_used_maps;
- /* eBPF program is ready to be JITed */
- if (!prog->bpf_func)
- prog = bpf_prog_select_runtime(prog, &err);
+ prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
goto free_used_maps;
return err;
free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
- return -ENOMEM;
+ goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
- err = -EFAULT;
+ err = -ENOTSUPP;
goto out_free;
}
cond_resched();
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
+out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
err = jit_subprogs(env);
if (err == 0)
return 0;
+ if (err == -EFAULT)
+ return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
* load balancing domains (sched domains) as specified by that partial
* partition.
*
- * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt
+ * See "What is sched_load_balance" in Documentation/cgroup-v1/cpusets.txt
* for a background explanation of this.
*
* Does not return errors, on the theory that the callers of this
return ret;
}
-/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
- * are moved to kernel/time/time.c .
- */
-extern int __compat_get_timespec64(struct timespec64 *ts64,
- const struct compat_timespec __user *cts);
-extern int __compat_put_timespec64(const struct timespec64 *ts64,
- struct compat_timespec __user *cts);
-
-int get_compat_itimerspec64(struct itimerspec64 *its,
- const struct compat_itimerspec __user *uits)
-{
-
- if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
- __compat_get_timespec64(&its->it_value, &uits->it_value))
- return -EFAULT;
- return 0;
-}
-EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
-
-int put_compat_itimerspec64(const struct itimerspec64 *its,
- struct compat_itimerspec __user *uits)
-{
- if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
- __compat_put_timespec64(&its->it_value, &uits->it_value))
- return -EFAULT;
- return 0;
-}
-EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-
/*
* We currently only need the following fields from the sigevent
* structure: sigev_value, sigev_signo, sig_notify and (sometimes
# CONFIG_SLAB is not set
# CONFIG_SLUB is not set
CONFIG_SLOB=y
-CONFIG_CC_STACKPROTECTOR_NONE=y
-# CONFIG_CC_STACKPROTECTOR_REGULAR is not set
-# CONFIG_CC_STACKPROTECTOR_STRONG is not set
-# CONFIG_CC_STACKPROTECTOR_AUTO is not set
* otherwise a RCU stall occurs.
*/
[CPUHP_TIMERS_PREPARE] = {
- .name = "timers:dead",
+ .name = "timers:prepare",
.startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
.startup.single = perf_event_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
+ [CPUHP_AP_WATCHDOG_ONLINE] = {
+ .name = "lockup_detector:online",
+ .startup.single = lockup_detector_online_cpu,
+ .teardown.single = lockup_detector_offline_cpu,
+ },
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
.startup.single = workqueue_online_cpu,
/*
* Must be called _AFTER_ setting up the per_cpu areas
*/
-void __init boot_cpu_state_init(void)
+void __init boot_cpu_hotplug_init(void)
{
per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
}
--- /dev/null
+
+config HAS_DMA
+ bool
+ depends on !NO_DMA
+ default y
+
+config NEED_SG_DMA_LENGTH
+ bool
+
+config NEED_DMA_MAP_STATE
+ bool
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config HAVE_GENERIC_DMA_COHERENT
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+ bool
+ select NEED_DMA_MAP_STATE
+
+config DMA_DIRECT_OPS
+ bool
+ depends on HAS_DMA
+
+config DMA_NONCOHERENT_OPS
+ bool
+ depends on HAS_DMA
+ select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_VIRT_OPS
+ bool
+ depends on HAS_DMA
+
+config SWIOTLB
+ bool
+ select DMA_DIRECT_OPS
+ select NEED_DMA_MAP_STATE
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_HAS_DMA) += mapping.o
+obj-$(CONFIG_DMA_CMA) += contiguous.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o
+obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o
+obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o
+obj-$(CONFIG_DMA_VIRT_OPS) += virt.o
+obj-$(CONFIG_DMA_API_DEBUG) += debug.o
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
+
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+ void *virt_base;
+ dma_addr_t device_base;
+ unsigned long pfn_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+ spinlock_t spinlock;
+ bool use_dev_dma_pfn_offset;
+};
+
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
+{
+ if (dev && dev->dma_mem)
+ return dev->dma_mem;
+ return NULL;
+}
+
+static inline dma_addr_t dma_get_device_base(struct device *dev,
+ struct dma_coherent_mem * mem)
+{
+ if (mem->use_dev_dma_pfn_offset)
+ return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
+ else
+ return mem->device_base;
+}
+
+static int dma_init_coherent_memory(
+ phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
+ struct dma_coherent_mem **mem)
+{
+ struct dma_coherent_mem *dma_mem = NULL;
+ void __iomem *mem_base = NULL;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+ int ret;
+
+ if (!size) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mem_base = memremap(phys_addr, size, MEMREMAP_WC);
+ if (!mem_base) {
+ ret = -EINVAL;
+ goto out;
+ }
+ dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dma_mem) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!dma_mem->bitmap) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dma_mem->virt_base = mem_base;
+ dma_mem->device_base = device_addr;
+ dma_mem->pfn_base = PFN_DOWN(phys_addr);
+ dma_mem->size = pages;
+ dma_mem->flags = flags;
+ spin_lock_init(&dma_mem->spinlock);
+
+ *mem = dma_mem;
+ return 0;
+
+out:
+ kfree(dma_mem);
+ if (mem_base)
+ memunmap(mem_base);
+ return ret;
+}
+
+static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
+{
+ if (!mem)
+ return;
+
+ memunmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+
+static int dma_assign_coherent_memory(struct device *dev,
+ struct dma_coherent_mem *mem)
+{
+ if (!dev)
+ return -ENODEV;
+
+ if (dev->dma_mem)
+ return -EBUSY;
+
+ dev->dma_mem = mem;
+ return 0;
+}
+
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ struct dma_coherent_mem *mem;
+ int ret;
+
+ ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags, &mem);
+ if (ret)
+ return ret;
+
+ ret = dma_assign_coherent_memory(dev, mem);
+ if (ret)
+ dma_release_coherent_memory(mem);
+ return ret;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if (!mem)
+ return;
+ dma_release_coherent_memory(mem);
+ dev->dma_mem = NULL;
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ unsigned long flags;
+ int pos, err;
+
+ size += device_addr & ~PAGE_MASK;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+ pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
+ ssize_t size, dma_addr_t *dma_handle)
+{
+ int order = get_order(size);
+ unsigned long flags;
+ int pageno;
+ void *ret;
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+
+ if (unlikely(size > (mem->size << PAGE_SHIFT)))
+ goto err;
+
+ pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+ if (unlikely(pageno < 0))
+ goto err;
+
+ /*
+ * Memory was found in the coherent area.
+ */
+ *dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+ ret = mem->virt_base + (pageno << PAGE_SHIFT);
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ memset(ret, 0, size);
+ return ret;
+err:
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ return NULL;
+}
+
+/**
+ * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool
+ * @dev: device from which we allocate memory
+ * @size: size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret: This pointer will be filled with the virtual address
+ * to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+ dma_addr_t *dma_handle, void **ret)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ if (!mem)
+ return 0;
+
+ *ret = __dma_alloc_from_coherent(mem, size, dma_handle);
+ if (*ret)
+ return 1;
+
+ /*
+ * In the case where the allocation can not be satisfied from the
+ * per-device area, try to fall back to generic memory if the
+ * constraints allow it.
+ */
+ return mem->flags & DMA_MEMORY_EXCLUSIVE;
+}
+EXPORT_SYMBOL(dma_alloc_from_dev_coherent);
+
+void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle)
+{
+ if (!dma_coherent_default_memory)
+ return NULL;
+
+ return __dma_alloc_from_coherent(dma_coherent_default_memory, size,
+ dma_handle);
+}
+
+static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
+ int order, void *vaddr)
+{
+ if (mem && vaddr >= mem->virt_base && vaddr <
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+ bitmap_release_region(mem->bitmap, page, order);
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dma_release_from_dev_coherent() - free memory to device coherent memory pool
+ * @dev: device from which the memory was allocated
+ * @order: the order of pages allocated
+ * @vaddr: virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if the caller should
+ * proceed with releasing memory from generic pools.
+ */
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ return __dma_release_from_coherent(mem, order, vaddr);
+}
+EXPORT_SYMBOL(dma_release_from_dev_coherent);
+
+int dma_release_from_global_coherent(int order, void *vaddr)
+{
+ if (!dma_coherent_default_memory)
+ return 0;
+
+ return __dma_release_from_coherent(dma_coherent_default_memory, order,
+ vaddr);
+}
+
+static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
+ struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
+{
+ if (mem && vaddr >= mem->virt_base && vaddr + size <=
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ unsigned long off = vma->vm_pgoff;
+ int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+ int user_count = vma_pages(vma);
+ int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ *ret = -ENXIO;
+ if (off < count && user_count <= count - off) {
+ unsigned long pfn = mem->pfn_base + start + off;
+ *ret = remap_pfn_range(vma, vma->vm_start, pfn,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool
+ * @dev: device from which the memory was allocated
+ * @vma: vm_area for the userspace memory
+ * @vaddr: cpu address returned by dma_alloc_from_dev_coherent
+ * @size: size of the memory buffer allocated
+ * @ret: result from remap_pfn_range()
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
+ */
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+ void *vaddr, size_t size, int *ret)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
+}
+EXPORT_SYMBOL(dma_mmap_from_dev_coherent);
+
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
+ size_t size, int *ret)
+{
+ if (!dma_coherent_default_memory)
+ return 0;
+
+ return __dma_mmap_from_coherent(dma_coherent_default_memory, vma,
+ vaddr, size, ret);
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+static struct reserved_mem *dma_reserved_default_memory __initdata;
+
+static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+ struct dma_coherent_mem *mem = rmem->priv;
+ int ret;
+
+ if (!mem) {
+ ret = dma_init_coherent_memory(rmem->base, rmem->base,
+ rmem->size,
+ DMA_MEMORY_EXCLUSIVE, &mem);
+ if (ret) {
+ pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return ret;
+ }
+ }
+ mem->use_dev_dma_pfn_offset = true;
+ rmem->priv = mem;
+ dma_assign_coherent_memory(dev, mem);
+ return 0;
+}
+
+static void rmem_dma_device_release(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ if (dev)
+ dev->dma_mem = NULL;
+}
+
+static const struct reserved_mem_ops rmem_dma_ops = {
+ .device_init = rmem_dma_device_init,
+ .device_release = rmem_dma_device_release,
+};
+
+static int __init rmem_dma_setup(struct reserved_mem *rmem)
+{
+ unsigned long node = rmem->fdt_node;
+
+ if (of_get_flat_dt_prop(node, "reusable", NULL))
+ return -EINVAL;
+
+#ifdef CONFIG_ARM
+ if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
+ pr_err("Reserved memory: regions without no-map are not yet supported\n");
+ return -EINVAL;
+ }
+
+ if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
+ WARN(dma_reserved_default_memory,
+ "Reserved memory: region for default DMA coherent area is redefined\n");
+ dma_reserved_default_memory = rmem;
+ }
+#endif
+
+ rmem->ops = &rmem_dma_ops;
+ pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return 0;
+}
+
+static int __init dma_init_reserved_memory(void)
+{
+ const struct reserved_mem_ops *ops;
+ int ret;
+
+ if (!dma_reserved_default_memory)
+ return -ENOMEM;
+
+ ops = dma_reserved_default_memory->ops;
+
+ /*
+ * We rely on rmem_dma_device_init() does not propagate error of
+ * dma_assign_coherent_memory() for "NULL" device.
+ */
+ ret = ops->device_init(dma_reserved_default_memory, NULL);
+
+ if (!ret) {
+ dma_coherent_default_memory = dma_reserved_default_memory->priv;
+ pr_info("DMA: default coherent area is set\n");
+ }
+
+ return ret;
+}
+
+core_initcall(dma_init_reserved_memory);
+
+RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
+#endif
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ * Marek Szyprowski <m.szyprowski@samsung.com>
+ * Michal Nazarewicz <mina86@mina86.com>
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+# define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/sizes.h>
+#include <linux/dma-contiguous.h>
+#include <linux/cma.h>
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+struct cma *dma_contiguous_default_area;
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is useful mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+static phys_addr_t size_cmdline = -1;
+static phys_addr_t base_cmdline;
+static phys_addr_t limit_cmdline;
+
+static int __init early_cma(char *p)
+{
+ pr_debug("%s(%s)\n", __func__, p);
+ size_cmdline = memparse(p, &p);
+ if (*p != '@')
+ return 0;
+ base_cmdline = memparse(p + 1, &p);
+ if (*p != '-') {
+ limit_cmdline = base_cmdline + size_cmdline;
+ return 0;
+ }
+ limit_cmdline = memparse(p + 1, &p);
+
+ return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
+{
+ struct memblock_region *reg;
+ unsigned long total_pages = 0;
+
+ /*
+ * We cannot use memblock_phys_mem_size() here, because
+ * memblock_analyze() has not been called yet.
+ */
+ for_each_memblock(memory, reg)
+ total_pages += memblock_region_memory_end_pfn(reg) -
+ memblock_region_memory_base_pfn(reg);
+
+ return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
+{
+ return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+ phys_addr_t selected_size = 0;
+ phys_addr_t selected_base = 0;
+ phys_addr_t selected_limit = limit;
+ bool fixed = false;
+
+ pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+ if (size_cmdline != -1) {
+ selected_size = size_cmdline;
+ selected_base = base_cmdline;
+ selected_limit = min_not_zero(limit_cmdline, limit);
+ if (base_cmdline + size_cmdline == limit_cmdline)
+ fixed = true;
+ } else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+ selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+ selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+ selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+ selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+ }
+
+ if (selected_size && !dma_contiguous_default_area) {
+ pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+ (unsigned long)selected_size / SZ_1M);
+
+ dma_contiguous_reserve_area(selected_size, selected_base,
+ selected_limit,
+ &dma_contiguous_default_area,
+ fixed);
+ }
+}
+
+/**
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
+ * @fixed: hint about where to place the reserved area
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
+ *
+ * If @fixed is true, reserve contiguous area at exactly @base. If false,
+ * reserve in range from @base to @limit.
+ */
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+ phys_addr_t limit, struct cma **res_cma,
+ bool fixed)
+{
+ int ret;
+
+ ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
+ "reserved", res_cma);
+ if (ret)
+ return ret;
+
+ /* Architecture specific contiguous memory fixup. */
+ dma_contiguous_early_fixup(cma_get_base(*res_cma),
+ cma_get_size(*res_cma));
+
+ return 0;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev: Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ * @gfp_mask: GFP flags to use for this allocation.
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific dev_get_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+ unsigned int align, gfp_t gfp_mask)
+{
+ if (align > CONFIG_CMA_ALIGNMENT)
+ align = CONFIG_CMA_ALIGNMENT;
+
+ return cma_alloc(dev_get_cma_area(dev), count, align, gfp_mask);
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev: Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+ int count)
+{
+ return cma_release(dev_get_cma_area(dev), pages, count);
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+ dev_set_cma_area(dev, rmem->priv);
+ return 0;
+}
+
+static void rmem_cma_device_release(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ dev_set_cma_area(dev, NULL);
+}
+
+static const struct reserved_mem_ops rmem_cma_ops = {
+ .device_init = rmem_cma_device_init,
+ .device_release = rmem_cma_device_release,
+};
+
+static int __init rmem_cma_setup(struct reserved_mem *rmem)
+{
+ phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+ phys_addr_t mask = align - 1;
+ unsigned long node = rmem->fdt_node;
+ struct cma *cma;
+ int err;
+
+ if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
+ of_get_flat_dt_prop(node, "no-map", NULL))
+ return -EINVAL;
+
+ if ((rmem->base & mask) || (rmem->size & mask)) {
+ pr_err("Reserved memory: incorrect alignment of CMA region\n");
+ return -EINVAL;
+ }
+
+ err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma);
+ if (err) {
+ pr_err("Reserved memory: unable to setup CMA region\n");
+ return err;
+ }
+ /* Architecture specific contiguous memory fixup. */
+ dma_contiguous_early_fixup(rmem->base, rmem->size);
+
+ if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+ dma_contiguous_set_default(cma);
+
+ rmem->ops = &rmem_cma_ops;
+ rmem->priv = cma;
+
+ pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+
+ return 0;
+}
+RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
+#endif
--- /dev/null
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/sched/task_stack.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/sched/task.h>
+#include <linux/stacktrace.h>
+#include <linux/dma-debug.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include <asm/sections.h>
+
+#define HASH_SIZE 1024ULL
+#define HASH_FN_SHIFT 13
+#define HASH_FN_MASK (HASH_SIZE - 1)
+
+/* allow architectures to override this if absolutely required */
+#ifndef PREALLOC_DMA_DEBUG_ENTRIES
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+#endif
+
+enum {
+ dma_debug_single,
+ dma_debug_page,
+ dma_debug_sg,
+ dma_debug_coherent,
+ dma_debug_resource,
+};
+
+enum map_err_types {
+ MAP_ERR_CHECK_NOT_APPLICABLE,
+ MAP_ERR_NOT_CHECKED,
+ MAP_ERR_CHECKED,
+};
+
+#define DMA_DEBUG_STACKTRACE_ENTRIES 5
+
+/**
+ * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
+ * @list: node on pre-allocated free_entries list
+ * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
+ * @type: single, page, sg, coherent
+ * @pfn: page frame of the start address
+ * @offset: offset of mapping relative to pfn
+ * @size: length of the mapping
+ * @direction: enum dma_data_direction
+ * @sg_call_ents: 'nents' from dma_map_sg
+ * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
+ * @map_err_type: track whether dma_mapping_error() was checked
+ * @stacktrace: support backtraces when a violation is detected
+ */
+struct dma_debug_entry {
+ struct list_head list;
+ struct device *dev;
+ int type;
+ unsigned long pfn;
+ size_t offset;
+ u64 dev_addr;
+ u64 size;
+ int direction;
+ int sg_call_ents;
+ int sg_mapped_ents;
+ enum map_err_types map_err_type;
+#ifdef CONFIG_STACKTRACE
+ struct stack_trace stacktrace;
+ unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+#endif
+};
+
+typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
+
+struct hash_bucket {
+ struct list_head list;
+ spinlock_t lock;
+} ____cacheline_aligned_in_smp;
+
+/* Hash list to save the allocated dma addresses */
+static struct hash_bucket dma_entry_hash[HASH_SIZE];
+/* List of pre-allocated dma_debug_entry's */
+static LIST_HEAD(free_entries);
+/* Lock for the list above */
+static DEFINE_SPINLOCK(free_entries_lock);
+
+/* Global disable flag - will be set in case of an error */
+static bool global_disable __read_mostly;
+
+/* Early initialization disable flag, set at the end of dma_debug_init */
+static bool dma_debug_initialized __read_mostly;
+
+static inline bool dma_debug_disabled(void)
+{
+ return global_disable || !dma_debug_initialized;
+}
+
+/* Global error count */
+static u32 error_count;
+
+/* Global error show enable*/
+static u32 show_all_errors __read_mostly;
+/* Number of errors to show */
+static u32 show_num_errors = 1;
+
+static u32 num_free_entries;
+static u32 min_free_entries;
+static u32 nr_total_entries;
+
+/* number of preallocated entries requested by kernel cmdline */
+static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+
+/* debugfs dentry's for the stuff above */
+static struct dentry *dma_debug_dent __read_mostly;
+static struct dentry *global_disable_dent __read_mostly;
+static struct dentry *error_count_dent __read_mostly;
+static struct dentry *show_all_errors_dent __read_mostly;
+static struct dentry *show_num_errors_dent __read_mostly;
+static struct dentry *num_free_entries_dent __read_mostly;
+static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN 64
+
+static char current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
+
+static const char *const maperr2str[] = {
+ [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
+ [MAP_ERR_NOT_CHECKED] = "dma map error not checked",
+ [MAP_ERR_CHECKED] = "dma map error checked",
+};
+
+static const char *type2name[5] = { "single", "page",
+ "scather-gather", "coherent",
+ "resource" };
+
+static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
+ "DMA_FROM_DEVICE", "DMA_NONE" };
+
+/*
+ * The access to some variables in this macro is racy. We can't use atomic_t
+ * here because all these variables are exported to debugfs. Some of them even
+ * writeable. This is also the reason why a lock won't help much. But anyway,
+ * the races are no big deal. Here is why:
+ *
+ * error_count: the addition is racy, but the worst thing that can happen is
+ * that we don't count some errors
+ * show_num_errors: the subtraction is racy. Also no big deal because in
+ * worst case this will result in one warning more in the
+ * system log than the user configured. This variable is
+ * writeable via debugfs.
+ */
+static inline void dump_entry_trace(struct dma_debug_entry *entry)
+{
+#ifdef CONFIG_STACKTRACE
+ if (entry) {
+ pr_warning("Mapped at:\n");
+ print_stack_trace(&entry->stacktrace, 0);
+ }
+#endif
+}
+
+static bool driver_filter(struct device *dev)
+{
+ struct device_driver *drv;
+ unsigned long flags;
+ bool ret;
+
+ /* driver filter off */
+ if (likely(!current_driver_name[0]))
+ return true;
+
+ /* driver filter on and initialized */
+ if (current_driver && dev && dev->driver == current_driver)
+ return true;
+
+ /* driver filter on, but we can't filter on a NULL device... */
+ if (!dev)
+ return false;
+
+ if (current_driver || !current_driver_name[0])
+ return false;
+
+ /* driver filter on but not yet initialized */
+ drv = dev->driver;
+ if (!drv)
+ return false;
+
+ /* lock to protect against change of current_driver_name */
+ read_lock_irqsave(&driver_name_lock, flags);
+
+ ret = false;
+ if (drv->name &&
+ strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+ current_driver = drv;
+ ret = true;
+ }
+
+ read_unlock_irqrestore(&driver_name_lock, flags);
+
+ return ret;
+}
+
+#define err_printk(dev, entry, format, arg...) do { \
+ error_count += 1; \
+ if (driver_filter(dev) && \
+ (show_all_errors || show_num_errors > 0)) { \
+ WARN(1, "%s %s: " format, \
+ dev ? dev_driver_string(dev) : "NULL", \
+ dev ? dev_name(dev) : "NULL", ## arg); \
+ dump_entry_trace(entry); \
+ } \
+ if (!show_all_errors && show_num_errors > 0) \
+ show_num_errors -= 1; \
+ } while (0);
+
+/*
+ * Hash related functions
+ *
+ * Every DMA-API request is saved into a struct dma_debug_entry. To
+ * have quick access to these structs they are stored into a hash.
+ */
+static int hash_fn(struct dma_debug_entry *entry)
+{
+ /*
+ * Hash function is based on the dma address.
+ * We use bits 20-27 here as the index into the hash
+ */
+ return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK;
+}
+
+/*
+ * Request exclusive access to a hash bucket for a given dma_debug_entry.
+ */
+static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
+ unsigned long *flags)
+ __acquires(&dma_entry_hash[idx].lock)
+{
+ int idx = hash_fn(entry);
+ unsigned long __flags;
+
+ spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags);
+ *flags = __flags;
+ return &dma_entry_hash[idx];
+}
+
+/*
+ * Give up exclusive access to the hash bucket
+ */
+static void put_hash_bucket(struct hash_bucket *bucket,
+ unsigned long *flags)
+ __releases(&bucket->lock)
+{
+ unsigned long __flags = *flags;
+
+ spin_unlock_irqrestore(&bucket->lock, __flags);
+}
+
+static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
+{
+ return ((a->dev_addr == b->dev_addr) &&
+ (a->dev == b->dev)) ? true : false;
+}
+
+static bool containing_match(struct dma_debug_entry *a,
+ struct dma_debug_entry *b)
+{
+ if (a->dev != b->dev)
+ return false;
+
+ if ((b->dev_addr <= a->dev_addr) &&
+ ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
+ return true;
+
+ return false;
+}
+
+/*
+ * Search a given entry in the hash bucket list
+ */
+static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
+ struct dma_debug_entry *ref,
+ match_fn match)
+{
+ struct dma_debug_entry *entry, *ret = NULL;
+ int matches = 0, match_lvl, last_lvl = -1;
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!match(ref, entry))
+ continue;
+
+ /*
+ * Some drivers map the same physical address multiple
+ * times. Without a hardware IOMMU this results in the
+ * same device addresses being put into the dma-debug
+ * hash multiple times too. This can result in false
+ * positives being reported. Therefore we implement a
+ * best-fit algorithm here which returns the entry from
+ * the hash which fits best to the reference value
+ * instead of the first-fit.
+ */
+ matches += 1;
+ match_lvl = 0;
+ entry->size == ref->size ? ++match_lvl : 0;
+ entry->type == ref->type ? ++match_lvl : 0;
+ entry->direction == ref->direction ? ++match_lvl : 0;
+ entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
+
+ if (match_lvl == 4) {
+ /* perfect-fit - return the result */
+ return entry;
+ } else if (match_lvl > last_lvl) {
+ /*
+ * We found an entry that fits better then the
+ * previous one or it is the 1st match.
+ */
+ last_lvl = match_lvl;
+ ret = entry;
+ }
+ }
+
+ /*
+ * If we have multiple matches but no perfect-fit, just return
+ * NULL.
+ */
+ ret = (matches == 1) ? ret : NULL;
+
+ return ret;
+}
+
+static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
+ struct dma_debug_entry *ref)
+{
+ return __hash_bucket_find(bucket, ref, exact_match);
+}
+
+static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
+ struct dma_debug_entry *ref,
+ unsigned long *flags)
+{
+
+ unsigned int max_range = dma_get_max_seg_size(ref->dev);
+ struct dma_debug_entry *entry, index = *ref;
+ unsigned int range = 0;
+
+ while (range <= max_range) {
+ entry = __hash_bucket_find(*bucket, ref, containing_match);
+
+ if (entry)
+ return entry;
+
+ /*
+ * Nothing found, go back a hash bucket
+ */
+ put_hash_bucket(*bucket, flags);
+ range += (1 << HASH_FN_SHIFT);
+ index.dev_addr -= (1 << HASH_FN_SHIFT);
+ *bucket = get_hash_bucket(&index, flags);
+ }
+
+ return NULL;
+}
+
+/*
+ * Add an entry to a hash bucket
+ */
+static void hash_bucket_add(struct hash_bucket *bucket,
+ struct dma_debug_entry *entry)
+{
+ list_add_tail(&entry->list, &bucket->list);
+}
+
+/*
+ * Remove entry from a hash bucket list
+ */
+static void hash_bucket_del(struct dma_debug_entry *entry)
+{
+ list_del(&entry->list);
+}
+
+static unsigned long long phys_addr(struct dma_debug_entry *entry)
+{
+ if (entry->type == dma_debug_resource)
+ return __pfn_to_phys(entry->pfn) + entry->offset;
+
+ return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
+}
+
+/*
+ * Dump mapping entries for debugging purposes
+ */
+void debug_dma_dump_mappings(struct device *dev)
+{
+ int idx;
+
+ for (idx = 0; idx < HASH_SIZE; idx++) {
+ struct hash_bucket *bucket = &dma_entry_hash[idx];
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+
+ spin_lock_irqsave(&bucket->lock, flags);
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!dev || dev == entry->dev) {
+ dev_info(entry->dev,
+ "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n",
+ type2name[entry->type], idx,
+ phys_addr(entry), entry->pfn,
+ entry->dev_addr, entry->size,
+ dir2name[entry->direction],
+ maperr2str[entry->map_err_type]);
+ }
+ }
+
+ spin_unlock_irqrestore(&bucket->lock, flags);
+ }
+}
+
+/*
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
+ * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If
+ * the entry already exists at insertion time add a tag as a reference
+ * count for the overlapping mappings. For now, the overlap tracking
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
+ *
+ * Memory usage is mostly constrained by the maximum number of available
+ * dma-debug entries in that we need a free dma_debug_entry before
+ * inserting into the tree. In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event. dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
+ *
+ * At any time debug_dma_assert_idle() can be called to trigger a
+ * warning if any cachelines in the given page are in the active set.
+ */
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
+static DEFINE_SPINLOCK(radix_lock);
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
+
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+ return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+ (entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
+{
+ int overlap = 0, i;
+
+ for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+ if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
+ overlap |= 1 << i;
+ return overlap;
+}
+
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
+{
+ int i;
+
+ if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
+ return overlap;
+
+ for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+ if (overlap & 1 << i)
+ radix_tree_tag_set(&dma_active_cacheline, cln, i);
+ else
+ radix_tree_tag_clear(&dma_active_cacheline, cln, i);
+
+ return overlap;
+}
+
+static void active_cacheline_inc_overlap(phys_addr_t cln)
+{
+ int overlap = active_cacheline_read_overlap(cln);
+
+ overlap = active_cacheline_set_overlap(cln, ++overlap);
+
+ /* If we overflowed the overlap counter then we're potentially
+ * leaking dma-mappings. Otherwise, if maps and unmaps are
+ * balanced then this overflow may cause false negatives in
+ * debug_dma_assert_idle() as the cacheline may be marked idle
+ * prematurely.
+ */
+ WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+ "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+ ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
+}
+
+static int active_cacheline_dec_overlap(phys_addr_t cln)
+{
+ int overlap = active_cacheline_read_overlap(cln);
+
+ return active_cacheline_set_overlap(cln, --overlap);
+}
+
+static int active_cacheline_insert(struct dma_debug_entry *entry)
+{
+ phys_addr_t cln = to_cacheline_number(entry);
+ unsigned long flags;
+ int rc;
+
+ /* If the device is not writing memory then we don't have any
+ * concerns about the cpu consuming stale data. This mitigates
+ * legitimate usages of overlapping mappings.
+ */
+ if (entry->direction == DMA_TO_DEVICE)
+ return 0;
+
+ spin_lock_irqsave(&radix_lock, flags);
+ rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
+ if (rc == -EEXIST)
+ active_cacheline_inc_overlap(cln);
+ spin_unlock_irqrestore(&radix_lock, flags);
+
+ return rc;
+}
+
+static void active_cacheline_remove(struct dma_debug_entry *entry)
+{
+ phys_addr_t cln = to_cacheline_number(entry);
+ unsigned long flags;
+
+ /* ...mirror the insert case */
+ if (entry->direction == DMA_TO_DEVICE)
+ return;
+
+ spin_lock_irqsave(&radix_lock, flags);
+ /* since we are counting overlaps the final put of the
+ * cacheline will occur when the overlap count is 0.
+ * active_cacheline_dec_overlap() returns -1 in that case
+ */
+ if (active_cacheline_dec_overlap(cln) < 0)
+ radix_tree_delete(&dma_active_cacheline, cln);
+ spin_unlock_irqrestore(&radix_lock, flags);
+}
+
+/**
+ * debug_dma_assert_idle() - assert that a page is not undergoing dma
+ * @page: page to lookup in the dma_active_cacheline tree
+ *
+ * Place a call to this routine in cases where the cpu touching the page
+ * before the dma completes (page is dma_unmapped) will lead to data
+ * corruption.
+ */
+void debug_dma_assert_idle(struct page *page)
+{
+ static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+ struct dma_debug_entry *entry = NULL;
+ void **results = (void **) &ents;
+ unsigned int nents, i;
+ unsigned long flags;
+ phys_addr_t cln;
+
+ if (dma_debug_disabled())
+ return;
+
+ if (!page)
+ return;
+
+ cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
+ spin_lock_irqsave(&radix_lock, flags);
+ nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+ CACHELINES_PER_PAGE);
+ for (i = 0; i < nents; i++) {
+ phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+ if (ent_cln == cln) {
+ entry = ents[i];
+ break;
+ } else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+ break;
+ }
+ spin_unlock_irqrestore(&radix_lock, flags);
+
+ if (!entry)
+ return;
+
+ cln = to_cacheline_number(entry);
+ err_printk(entry->dev, entry,
+ "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+ &cln);
+}
+
+/*
+ * Wrapper function for adding an entry to the hash.
+ * This function takes care of locking itself.
+ */
+static void add_dma_entry(struct dma_debug_entry *entry)
+{
+ struct hash_bucket *bucket;
+ unsigned long flags;
+ int rc;
+
+ bucket = get_hash_bucket(entry, &flags);
+ hash_bucket_add(bucket, entry);
+ put_hash_bucket(bucket, &flags);
+
+ rc = active_cacheline_insert(entry);
+ if (rc == -ENOMEM) {
+ pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
+ global_disable = true;
+ }
+
+ /* TODO: report -EEXIST errors here as overlapping mappings are
+ * not supported by the DMA API
+ */
+}
+
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+ struct dma_debug_entry *entry;
+
+ entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+ list_del(&entry->list);
+ memset(entry, 0, sizeof(*entry));
+
+ num_free_entries -= 1;
+ if (num_free_entries < min_free_entries)
+ min_free_entries = num_free_entries;
+
+ return entry;
+}
+
+/* struct dma_entry allocator
+ *
+ * The next two functions implement the allocator for
+ * struct dma_debug_entries.
+ */
+static struct dma_debug_entry *dma_entry_alloc(void)
+{
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ if (list_empty(&free_entries)) {
+ global_disable = true;
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+ pr_err("DMA-API: debugging out of memory - disabling\n");
+ return NULL;
+ }
+
+ entry = __dma_entry_alloc();
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+#ifdef CONFIG_STACKTRACE
+ entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
+ entry->stacktrace.entries = entry->st_entries;
+ entry->stacktrace.skip = 2;
+ save_stack_trace(&entry->stacktrace);
+#endif
+
+ return entry;
+}
+
+static void dma_entry_free(struct dma_debug_entry *entry)
+{
+ unsigned long flags;
+
+ active_cacheline_remove(entry);
+
+ /*
+ * add to beginning of the list - this way the entries are
+ * more likely cache hot when they are reallocated.
+ */
+ spin_lock_irqsave(&free_entries_lock, flags);
+ list_add(&entry->list, &free_entries);
+ num_free_entries += 1;
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+}
+
+int dma_debug_resize_entries(u32 num_entries)
+{
+ int i, delta, ret = 0;
+ unsigned long flags;
+ struct dma_debug_entry *entry;
+ LIST_HEAD(tmp);
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ if (nr_total_entries < num_entries) {
+ delta = num_entries - nr_total_entries;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ for (i = 0; i < delta; i++) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ break;
+
+ list_add_tail(&entry->list, &tmp);
+ }
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ list_splice(&tmp, &free_entries);
+ nr_total_entries += i;
+ num_free_entries += i;
+ } else {
+ delta = nr_total_entries - num_entries;
+
+ for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+ entry = __dma_entry_alloc();
+ kfree(entry);
+ }
+
+ nr_total_entries -= i;
+ }
+
+ if (nr_total_entries != num_entries)
+ ret = 1;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ return ret;
+}
+
+/*
+ * DMA-API debugging init code
+ *
+ * The init code does two things:
+ * 1. Initialize core data structures
+ * 2. Preallocate a given number of dma_debug_entry structs
+ */
+
+static int prealloc_memory(u32 num_entries)
+{
+ struct dma_debug_entry *entry, *next_entry;
+ int i;
+
+ for (i = 0; i < num_entries; ++i) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ goto out_err;
+
+ list_add_tail(&entry->list, &free_entries);
+ }
+
+ num_free_entries = num_entries;
+ min_free_entries = num_entries;
+
+ pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
+
+ return 0;
+
+out_err:
+
+ list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+
+ return -ENOMEM;
+}
+
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN + 1];
+ unsigned long flags;
+ int len;
+
+ if (!current_driver_name[0])
+ return 0;
+
+ /*
+ * We can't copy to userspace directly because current_driver_name can
+ * only be read under the driver_name_lock with irqs disabled. So
+ * create a temporary copy first.
+ */
+ read_lock_irqsave(&driver_name_lock, flags);
+ len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+ read_unlock_irqrestore(&driver_name_lock, flags);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN];
+ unsigned long flags;
+ size_t len;
+ int i;
+
+ /*
+ * We can't copy from userspace directly. Access to
+ * current_driver_name is protected with a write_lock with irqs
+ * disabled. Since copy_from_user can fault and may sleep we
+ * need to copy to temporary buffer first
+ */
+ len = min(count, (size_t)(NAME_MAX_LEN - 1));
+ if (copy_from_user(buf, userbuf, len))
+ return -EFAULT;
+
+ buf[len] = 0;
+
+ write_lock_irqsave(&driver_name_lock, flags);
+
+ /*
+ * Now handle the string we got from userspace very carefully.
+ * The rules are:
+ * - only use the first token we got
+ * - token delimiter is everything looking like a space
+ * character (' ', '\n', '\t' ...)
+ *
+ */
+ if (!isalnum(buf[0])) {
+ /*
+ * If the first character userspace gave us is not
+ * alphanumerical then assume the filter should be
+ * switched off.
+ */
+ if (current_driver_name[0])
+ pr_info("DMA-API: switching off dma-debug driver filter\n");
+ current_driver_name[0] = 0;
+ current_driver = NULL;
+ goto out_unlock;
+ }
+
+ /*
+ * Now parse out the first token and use it as the name for the
+ * driver to filter for.
+ */
+ for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
+ current_driver_name[i] = buf[i];
+ if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+ break;
+ }
+ current_driver_name[i] = 0;
+ current_driver = NULL;
+
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+out_unlock:
+ write_unlock_irqrestore(&driver_name_lock, flags);
+
+ return count;
+}
+
+static const struct file_operations filter_fops = {
+ .read = filter_read,
+ .write = filter_write,
+ .llseek = default_llseek,
+};
+
+static int dma_debug_fs_init(void)
+{
+ dma_debug_dent = debugfs_create_dir("dma-api", NULL);
+ if (!dma_debug_dent) {
+ pr_err("DMA-API: can not create debugfs directory\n");
+ return -ENOMEM;
+ }
+
+ global_disable_dent = debugfs_create_bool("disabled", 0444,
+ dma_debug_dent,
+ &global_disable);
+ if (!global_disable_dent)
+ goto out_err;
+
+ error_count_dent = debugfs_create_u32("error_count", 0444,
+ dma_debug_dent, &error_count);
+ if (!error_count_dent)
+ goto out_err;
+
+ show_all_errors_dent = debugfs_create_u32("all_errors", 0644,
+ dma_debug_dent,
+ &show_all_errors);
+ if (!show_all_errors_dent)
+ goto out_err;
+
+ show_num_errors_dent = debugfs_create_u32("num_errors", 0644,
+ dma_debug_dent,
+ &show_num_errors);
+ if (!show_num_errors_dent)
+ goto out_err;
+
+ num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444,
+ dma_debug_dent,
+ &num_free_entries);
+ if (!num_free_entries_dent)
+ goto out_err;
+
+ min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444,
+ dma_debug_dent,
+ &min_free_entries);
+ if (!min_free_entries_dent)
+ goto out_err;
+
+ filter_dent = debugfs_create_file("driver_filter", 0644,
+ dma_debug_dent, NULL, &filter_fops);
+ if (!filter_dent)
+ goto out_err;
+
+ return 0;
+
+out_err:
+ debugfs_remove_recursive(dma_debug_dent);
+
+ return -ENOMEM;
+}
+
+static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
+{
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+ int count = 0, i;
+
+ for (i = 0; i < HASH_SIZE; ++i) {
+ spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
+ list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+ if (entry->dev == dev) {
+ count += 1;
+ *out_entry = entry;
+ }
+ }
+ spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
+ }
+
+ return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
+{
+ struct device *dev = data;
+ struct dma_debug_entry *uninitialized_var(entry);
+ int count;
+
+ if (dma_debug_disabled())
+ return 0;
+
+ switch (action) {
+ case BUS_NOTIFY_UNBOUND_DRIVER:
+ count = device_dma_allocations(dev, &entry);
+ if (count == 0)
+ break;
+ err_printk(dev, entry, "DMA-API: device driver has pending "
+ "DMA allocations while released from device "
+ "[count=%d]\n"
+ "One of leaked entries details: "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [mapped as %s]\n",
+ count, entry->dev_addr, entry->size,
+ dir2name[entry->direction], type2name[entry->type]);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+void dma_debug_add_bus(struct bus_type *bus)
+{
+ struct notifier_block *nb;
+
+ if (dma_debug_disabled())
+ return;
+
+ nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+ if (nb == NULL) {
+ pr_err("dma_debug_add_bus: out of memory\n");
+ return;
+ }
+
+ nb->notifier_call = dma_debug_device_change;
+
+ bus_register_notifier(bus, nb);
+}
+
+static int dma_debug_init(void)
+{
+ int i;
+
+ /* Do not use dma_debug_initialized here, since we really want to be
+ * called to set dma_debug_initialized
+ */
+ if (global_disable)
+ return 0;
+
+ for (i = 0; i < HASH_SIZE; ++i) {
+ INIT_LIST_HEAD(&dma_entry_hash[i].list);
+ spin_lock_init(&dma_entry_hash[i].lock);
+ }
+
+ if (dma_debug_fs_init() != 0) {
+ pr_err("DMA-API: error creating debugfs entries - disabling\n");
+ global_disable = true;
+
+ return 0;
+ }
+
+ if (prealloc_memory(nr_prealloc_entries) != 0) {
+ pr_err("DMA-API: debugging out of memory error - disabled\n");
+ global_disable = true;
+
+ return 0;
+ }
+
+ nr_total_entries = num_free_entries;
+
+ dma_debug_initialized = true;
+
+ pr_info("DMA-API: debugging enabled by kernel config\n");
+ return 0;
+}
+core_initcall(dma_debug_init);
+
+static __init int dma_debug_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (strncmp(str, "off", 3) == 0) {
+ pr_info("DMA-API: debugging disabled on kernel command line\n");
+ global_disable = true;
+ }
+
+ return 0;
+}
+
+static __init int dma_debug_entries_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+ if (!get_option(&str, &nr_prealloc_entries))
+ nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+ return 0;
+}
+
+__setup("dma_debug=", dma_debug_cmdline);
+__setup("dma_debug_entries=", dma_debug_entries_cmdline);
+
+static void check_unmap(struct dma_debug_entry *ref)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ bucket = get_hash_bucket(ref, &flags);
+ entry = bucket_find_exact(bucket, ref);
+
+ if (!entry) {
+ /* must drop lock before calling dma_mapping_error */
+ put_hash_bucket(bucket, &flags);
+
+ if (dma_mapping_error(ref->dev, ref->dev_addr)) {
+ err_printk(ref->dev, NULL,
+ "DMA-API: device driver tries to free an "
+ "invalid DMA memory address\n");
+ } else {
+ err_printk(ref->dev, NULL,
+ "DMA-API: device driver tries to free DMA "
+ "memory it has not allocated [device "
+ "address=0x%016llx] [size=%llu bytes]\n",
+ ref->dev_addr, ref->size);
+ }
+ return;
+ }
+
+ if (ref->size != entry->size) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different size "
+ "[device address=0x%016llx] [map size=%llu bytes] "
+ "[unmap size=%llu bytes]\n",
+ ref->dev_addr, entry->size, ref->size);
+ }
+
+ if (ref->type != entry->type) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with wrong function "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped as %s] [unmapped as %s]\n",
+ ref->dev_addr, ref->size,
+ type2name[entry->type], type2name[ref->type]);
+ } else if ((entry->type == dma_debug_coherent) &&
+ (phys_addr(ref) != phys_addr(entry))) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different CPU address "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[cpu alloc address=0x%016llx] "
+ "[cpu free address=0x%016llx]",
+ ref->dev_addr, ref->size,
+ phys_addr(entry),
+ phys_addr(ref));
+ }
+
+ if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+ ref->sg_call_ents != entry->sg_call_ents) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA sg list with different entry count "
+ "[map count=%d] [unmap count=%d]\n",
+ entry->sg_call_ents, ref->sg_call_ents);
+ }
+
+ /*
+ * This may be no bug in reality - but most implementations of the
+ * DMA API don't handle this properly, so check for it here
+ */
+ if (ref->direction != entry->direction) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different direction "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [unmapped with %s]\n",
+ ref->dev_addr, ref->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+ }
+
+ /*
+ * Drivers should use dma_mapping_error() to check the returned
+ * addresses of dma_map_single() and dma_map_page().
+ * If not, print this warning message. See Documentation/DMA-API.txt.
+ */
+ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+ err_printk(ref->dev, entry,
+ "DMA-API: device driver failed to check map error"
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped as %s]",
+ ref->dev_addr, ref->size,
+ type2name[entry->type]);
+ }
+
+ hash_bucket_del(entry);
+ dma_entry_free(entry);
+
+ put_hash_bucket(bucket, &flags);
+}
+
+static void check_for_stack(struct device *dev,
+ struct page *page, size_t offset)
+{
+ void *addr;
+ struct vm_struct *stack_vm_area = task_stack_vm_area(current);
+
+ if (!stack_vm_area) {
+ /* Stack is direct-mapped. */
+ if (PageHighMem(page))
+ return;
+ addr = page_address(page) + offset;
+ if (object_is_on_stack(addr))
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
+ } else {
+ /* Stack is vmalloced. */
+ int i;
+
+ for (i = 0; i < stack_vm_area->nr_pages; i++) {
+ if (page != stack_vm_area->pages[i])
+ continue;
+
+ addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
+ break;
+ }
+ }
+}
+
+static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
+{
+ unsigned long a1 = (unsigned long)addr;
+ unsigned long b1 = a1 + len;
+ unsigned long a2 = (unsigned long)start;
+ unsigned long b2 = (unsigned long)end;
+
+ return !(b1 <= a2 || a1 >= b2);
+}
+
+static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
+{
+ if (overlap(addr, len, _stext, _etext) ||
+ overlap(addr, len, __start_rodata, __end_rodata))
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
+}
+
+static void check_sync(struct device *dev,
+ struct dma_debug_entry *ref,
+ bool to_cpu)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ bucket = get_hash_bucket(ref, &flags);
+
+ entry = bucket_find_contain(&bucket, ref, &flags);
+
+ if (!entry) {
+ err_printk(dev, NULL, "DMA-API: device driver tries "
+ "to sync DMA memory it has not allocated "
+ "[device address=0x%016llx] [size=%llu bytes]\n",
+ (unsigned long long)ref->dev_addr, ref->size);
+ goto out;
+ }
+
+ if (ref->size > entry->size) {
+ err_printk(dev, entry, "DMA-API: device driver syncs"
+ " DMA memory outside allocated range "
+ "[device address=0x%016llx] "
+ "[allocation size=%llu bytes] "
+ "[sync offset+size=%llu]\n",
+ entry->dev_addr, entry->size,
+ ref->size);
+ }
+
+ if (entry->direction == DMA_BIDIRECTIONAL)
+ goto out;
+
+ if (ref->direction != entry->direction) {
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "DMA memory with different direction "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+ }
+
+ if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
+ !(ref->direction == DMA_TO_DEVICE))
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "device read-only DMA memory for cpu "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+
+ if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
+ !(ref->direction == DMA_FROM_DEVICE))
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "device write-only DMA memory to device "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+
+ if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+ ref->sg_call_ents != entry->sg_call_ents) {
+ err_printk(ref->dev, entry, "DMA-API: device driver syncs "
+ "DMA sg list with different entry count "
+ "[map count=%d] [sync count=%d]\n",
+ entry->sg_call_ents, ref->sg_call_ents);
+ }
+
+out:
+ put_hash_bucket(bucket, &flags);
+}
+
+static void check_sg_segment(struct device *dev, struct scatterlist *sg)
+{
+#ifdef CONFIG_DMA_API_DEBUG_SG
+ unsigned int max_seg = dma_get_max_seg_size(dev);
+ u64 start, end, boundary = dma_get_seg_boundary(dev);
+
+ /*
+ * Either the driver forgot to set dma_parms appropriately, or
+ * whoever generated the list forgot to check them.
+ */
+ if (sg->length > max_seg)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+ sg->length, max_seg);
+ /*
+ * In some cases this could potentially be the DMA API
+ * implementation's fault, but it would usually imply that
+ * the scatterlist was built inappropriately to begin with.
+ */
+ start = sg_dma_address(sg);
+ end = start + sg_dma_len(sg) - 1;
+ if ((start ^ end) & ~boundary)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+ start, end, boundary);
+#endif
+}
+
+void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
+ size_t size, int direction, dma_addr_t dma_addr,
+ bool map_single)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (dma_mapping_error(dev, dma_addr))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->dev = dev;
+ entry->type = dma_debug_page;
+ entry->pfn = page_to_pfn(page);
+ entry->offset = offset,
+ entry->dev_addr = dma_addr;
+ entry->size = size;
+ entry->direction = direction;
+ entry->map_err_type = MAP_ERR_NOT_CHECKED;
+
+ if (map_single)
+ entry->type = dma_debug_single;
+
+ check_for_stack(dev, page, offset);
+
+ if (!PageHighMem(page)) {
+ void *addr = page_address(page) + offset;
+
+ check_for_illegal_area(dev, addr, size);
+ }
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_page);
+
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ struct dma_debug_entry ref;
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.dev = dev;
+ ref.dev_addr = dma_addr;
+ bucket = get_hash_bucket(&ref, &flags);
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!exact_match(&ref, entry))
+ continue;
+
+ /*
+ * The same physical address can be mapped multiple
+ * times. Without a hardware IOMMU this results in the
+ * same device addresses being put into the dma-debug
+ * hash multiple times too. This can result in false
+ * positives being reported. Therefore we implement a
+ * best-fit algorithm here which updates the first entry
+ * from the hash which fits the reference value and is
+ * not currently listed as being checked.
+ */
+ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+ entry->map_err_type = MAP_ERR_CHECKED;
+ break;
+ }
+ }
+
+ put_hash_bucket(bucket, &flags);
+}
+EXPORT_SYMBOL(debug_dma_mapping_error);
+
+void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, int direction, bool map_single)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_page,
+ .dev = dev,
+ .dev_addr = addr,
+ .size = size,
+ .direction = direction,
+ };
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (map_single)
+ ref.type = dma_debug_single;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_page);
+
+void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+ int nents, int mapped_ents, int direction)
+{
+ struct dma_debug_entry *entry;
+ struct scatterlist *s;
+ int i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, mapped_ents, i) {
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_sg;
+ entry->dev = dev;
+ entry->pfn = page_to_pfn(sg_page(s));
+ entry->offset = s->offset,
+ entry->size = sg_dma_len(s);
+ entry->dev_addr = sg_dma_address(s);
+ entry->direction = direction;
+ entry->sg_call_ents = nents;
+ entry->sg_mapped_ents = mapped_ents;
+
+ check_for_stack(dev, sg_page(s), s->offset);
+
+ if (!PageHighMem(sg_page(s))) {
+ check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
+ }
+
+ check_sg_segment(dev, s);
+
+ add_dma_entry(entry);
+ }
+}
+EXPORT_SYMBOL(debug_dma_map_sg);
+
+static int get_nr_mapped_entries(struct device *dev,
+ struct dma_debug_entry *ref)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+ int mapped_ents;
+
+ bucket = get_hash_bucket(ref, &flags);
+ entry = bucket_find_exact(bucket, ref);
+ mapped_ents = 0;
+
+ if (entry)
+ mapped_ents = entry->sg_mapped_ents;
+ put_hash_bucket(bucket, &flags);
+
+ return mapped_ents;
+}
+
+void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+ int nelems, int dir)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sglist, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = dir,
+ .sg_call_ents = nelems,
+ };
+
+ if (mapped_ents && i >= mapped_ents)
+ break;
+
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ check_unmap(&ref);
+ }
+}
+EXPORT_SYMBOL(debug_dma_unmap_sg);
+
+void debug_dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t dma_addr, void *virt)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (unlikely(virt == NULL))
+ return;
+
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_coherent;
+ entry->dev = dev;
+ entry->offset = offset_in_page(virt);
+ entry->size = size;
+ entry->dev_addr = dma_addr;
+ entry->direction = DMA_BIDIRECTIONAL;
+
+ if (is_vmalloc_addr(virt))
+ entry->pfn = vmalloc_to_pfn(virt);
+ else
+ entry->pfn = page_to_pfn(virt_to_page(virt));
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_alloc_coherent);
+
+void debug_dma_free_coherent(struct device *dev, size_t size,
+ void *virt, dma_addr_t addr)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_coherent,
+ .dev = dev,
+ .offset = offset_in_page(virt),
+ .dev_addr = addr,
+ .size = size,
+ .direction = DMA_BIDIRECTIONAL,
+ };
+
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+ return;
+
+ if (is_vmalloc_addr(virt))
+ ref.pfn = vmalloc_to_pfn(virt);
+ else
+ ref.pfn = page_to_pfn(virt_to_page(virt));
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_free_coherent);
+
+void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
+ int direction, dma_addr_t dma_addr)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_resource;
+ entry->dev = dev;
+ entry->pfn = PHYS_PFN(addr);
+ entry->offset = offset_in_page(addr);
+ entry->size = size;
+ entry->dev_addr = dma_addr;
+ entry->direction = direction;
+ entry->map_err_type = MAP_ERR_NOT_CHECKED;
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_resource);
+
+void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_resource,
+ .dev = dev,
+ .dev_addr = dma_addr,
+ .size = size,
+ .direction = direction,
+ };
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_resource);
+
+void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
+
+void debug_dma_sync_single_for_device(struct device *dev,
+ dma_addr_t dma_handle, size_t size,
+ int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_device);
+
+void debug_dma_sync_single_range_for_cpu(struct device *dev,
+ dma_addr_t dma_handle,
+ unsigned long offset, size_t size,
+ int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = offset + size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
+
+void debug_dma_sync_single_range_for_device(struct device *dev,
+ dma_addr_t dma_handle,
+ unsigned long offset,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = offset + size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
+
+void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = direction,
+ .sg_call_ents = nelems,
+ };
+
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, &ref, true);
+ }
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
+
+void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = direction,
+ .sg_call_ents = nelems,
+ };
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, &ref, false);
+ }
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
+
+static int __init dma_debug_driver_setup(char *str)
+{
+ int i;
+
+ for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+ current_driver_name[i] = *str;
+ if (*str == 0)
+ break;
+ }
+
+ if (current_driver_name[0])
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+
+ return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMA operations that map physical memory directly without using an IOMMU or
+ * flushing caches.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-contiguous.h>
+#include <linux/pfn.h>
+#include <linux/set_memory.h>
+
+#define DIRECT_MAPPING_ERROR 0
+
+/*
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but
+ * some use it for entirely different regions:
+ */
+#ifndef ARCH_ZONE_DMA_BITS
+#define ARCH_ZONE_DMA_BITS 24
+#endif
+
+/*
+ * For AMD SEV all DMA must be to unencrypted addresses.
+ */
+static inline bool force_dma_unencrypted(void)
+{
+ return sev_active();
+}
+
+static bool
+check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
+ const char *caller)
+{
+ if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+ if (!dev->dma_mask) {
+ dev_err(dev,
+ "%s: call on device without dma_mask\n",
+ caller);
+ return false;
+ }
+
+ if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
+ dev_err(dev,
+ "%s: overflow %pad+%zu of device mask %llx\n",
+ caller, &dma_addr, size, *dev->dma_mask);
+ }
+ return false;
+ }
+ return true;
+}
+
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+{
+ dma_addr_t addr = force_dma_unencrypted() ?
+ __phys_to_dma(dev, phys) : phys_to_dma(dev, phys);
+ return addr + size - 1 <= dev->coherent_dma_mask;
+}
+
+void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ int page_order = get_order(size);
+ struct page *page = NULL;
+ void *ret;
+
+ /* we always manually zero the memory once we are done: */
+ gfp &= ~__GFP_ZERO;
+
+ /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ gfp |= GFP_DMA;
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
+ gfp |= GFP_DMA32;
+
+again:
+ /* CMA can be used only in the context which permits sleeping */
+ if (gfpflags_allow_blocking(gfp)) {
+ page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
+ if (!page)
+ page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
+
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ __free_pages(page, page_order);
+ page = NULL;
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
+ !(gfp & (GFP_DMA32 | GFP_DMA))) {
+ gfp |= GFP_DMA32;
+ goto again;
+ }
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ !(gfp & GFP_DMA)) {
+ gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
+ goto again;
+ }
+ }
+
+ if (!page)
+ return NULL;
+ ret = page_address(page);
+ if (force_dma_unencrypted()) {
+ set_memory_decrypted((unsigned long)ret, 1 << page_order);
+ *dma_handle = __phys_to_dma(dev, page_to_phys(page));
+ } else {
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+ }
+ memset(ret, 0, size);
+ return ret;
+}
+
+/*
+ * NOTE: this function must never look at the dma_addr argument, because we want
+ * to be able to use it as a helper for iommu implementations as well.
+ */
+void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned int page_order = get_order(size);
+
+ if (force_dma_unencrypted())
+ set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
+ if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
+ free_pages((unsigned long)cpu_addr, page_order);
+}
+
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset;
+
+ if (!check_addr(dev, dma_addr, size, __func__))
+ return DIRECT_MAPPING_ERROR;
+ return dma_addr;
+}
+
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ BUG_ON(!sg_page(sg));
+
+ sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
+ if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
+ return 0;
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nents;
+}
+
+int dma_direct_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_ZONE_DMA
+ if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ return 0;
+#else
+ /*
+ * Because 32-bit DMA masks are so common we expect every architecture
+ * to be able to satisfy them - either by not supporting more physical
+ * memory, or by providing a ZONE_DMA32. If neither is the case, the
+ * architecture needs to use an IOMMU instead of the direct mapping.
+ */
+ if (mask < DMA_BIT_MASK(32))
+ return 0;
+#endif
+ /*
+ * Various PCI/PCIe bridges have broken support for > 32bit DMA even
+ * if the device itself might support it.
+ */
+ if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+ return 0;
+ return 1;
+}
+
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr == DIRECT_MAPPING_ERROR;
+}
+
+const struct dma_map_ops dma_direct_ops = {
+ .alloc = dma_direct_alloc,
+ .free = dma_direct_free,
+ .map_page = dma_direct_map_page,
+ .map_sg = dma_direct_map_sg,
+ .dma_supported = dma_direct_supported,
+ .mapping_error = dma_direct_mapping_error,
+};
+EXPORT_SYMBOL(dma_direct_ops);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch-independent dma-mapping routines
+ *
+ * Copyright (c) 2006 SUSE Linux Products GmbH
+ * Copyright (c) 2006 Tejun Heo <teheo@suse.de>
+ */
+
+#include <linux/acpi.h>
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/*
+ * Managed DMA API
+ */
+struct dma_devres {
+ size_t size;
+ void *vaddr;
+ dma_addr_t dma_handle;
+ unsigned long attrs;
+};
+
+static void dmam_release(struct device *dev, void *res)
+{
+ struct dma_devres *this = res;
+
+ dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
+ this->attrs);
+}
+
+static int dmam_match(struct device *dev, void *res, void *match_data)
+{
+ struct dma_devres *this = res, *match = match_data;
+
+ if (this->vaddr == match->vaddr) {
+ WARN_ON(this->size != match->size ||
+ this->dma_handle != match->dma_handle);
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dmam_alloc_coherent - Managed dma_alloc_coherent()
+ * @dev: Device to allocate coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ *
+ * Managed dma_alloc_coherent(). Memory allocated using this function
+ * will be automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp)
+{
+ struct dma_devres *dr;
+ void *vaddr;
+
+ dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
+ if (!dr)
+ return NULL;
+
+ vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp);
+ if (!vaddr) {
+ devres_free(dr);
+ return NULL;
+ }
+
+ dr->vaddr = vaddr;
+ dr->dma_handle = *dma_handle;
+ dr->size = size;
+
+ devres_add(dev, dr);
+
+ return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_coherent);
+
+/**
+ * dmam_free_coherent - Managed dma_free_coherent()
+ * @dev: Device to free coherent memory for
+ * @size: Size of allocation
+ * @vaddr: Virtual address of the memory to free
+ * @dma_handle: DMA handle of the memory to free
+ *
+ * Managed dma_free_coherent().
+ */
+void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle)
+{
+ struct dma_devres match_data = { size, vaddr, dma_handle };
+
+ dma_free_coherent(dev, size, vaddr, dma_handle);
+ WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
+}
+EXPORT_SYMBOL(dmam_free_coherent);
+
+/**
+ * dmam_alloc_attrs - Managed dma_alloc_attrs()
+ * @dev: Device to allocate non_coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ * @attrs: Flags in the DMA_ATTR_* namespace.
+ *
+ * Managed dma_alloc_attrs(). Memory allocated using this function will be
+ * automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ struct dma_devres *dr;
+ void *vaddr;
+
+ dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
+ if (!dr)
+ return NULL;
+
+ vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
+ if (!vaddr) {
+ devres_free(dr);
+ return NULL;
+ }
+
+ dr->vaddr = vaddr;
+ dr->dma_handle = *dma_handle;
+ dr->size = size;
+ dr->attrs = attrs;
+
+ devres_add(dev, dr);
+
+ return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_attrs);
+
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+
+static void dmam_coherent_decl_release(struct device *dev, void *res)
+{
+ dma_release_declared_memory(dev);
+}
+
+/**
+ * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory()
+ * @dev: Device to declare coherent memory for
+ * @phys_addr: Physical address of coherent memory to be declared
+ * @device_addr: Device address of coherent memory to be declared
+ * @size: Size of coherent memory to be declared
+ * @flags: Flags
+ *
+ * Managed dma_declare_coherent_memory().
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void *res;
+ int rc;
+
+ res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL);
+ if (!res)
+ return -ENOMEM;
+
+ rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size,
+ flags);
+ if (!rc)
+ devres_add(dev, res);
+ else
+ devres_free(res);
+
+ return rc;
+}
+EXPORT_SYMBOL(dmam_declare_coherent_memory);
+
+/**
+ * dmam_release_declared_memory - Managed dma_release_declared_memory().
+ * @dev: Device to release declared coherent memory for
+ *
+ * Managed dmam_release_declared_memory().
+ */
+void dmam_release_declared_memory(struct device *dev)
+{
+ WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL));
+}
+EXPORT_SYMBOL(dmam_release_declared_memory);
+
+#endif
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ */
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size)
+{
+ struct page *page = virt_to_page(cpu_addr);
+ int ret;
+
+ ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+ if (unlikely(ret))
+ return ret;
+
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+ return 0;
+}
+EXPORT_SYMBOL(dma_common_get_sgtable);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+ int ret = -ENXIO;
+#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long off = vma->vm_pgoff;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (off < count && user_count <= (count - off))
+ ret = remap_pfn_range(vma, vma->vm_start,
+ page_to_pfn(virt_to_page(cpu_addr)) + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
+
+ return ret;
+}
+EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+static struct vm_struct *__dma_common_pages_remap(struct page **pages,
+ size_t size, unsigned long vm_flags, pgprot_t prot,
+ const void *caller)
+{
+ struct vm_struct *area;
+
+ area = get_vm_area_caller(size, vm_flags, caller);
+ if (!area)
+ return NULL;
+
+ if (map_vm_area(area, prot, pages)) {
+ vunmap(area->addr);
+ return NULL;
+ }
+
+ return area;
+}
+
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+ unsigned long vm_flags, pgprot_t prot,
+ const void *caller)
+{
+ struct vm_struct *area;
+
+ area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+ if (!area)
+ return NULL;
+
+ area->pages = pages;
+
+ return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+ unsigned long vm_flags,
+ pgprot_t prot, const void *caller)
+{
+ int i;
+ struct page **pages;
+ struct vm_struct *area;
+
+ pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+
+ for (i = 0; i < (size >> PAGE_SHIFT); i++)
+ pages[i] = nth_page(page, i);
+
+ area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+ kfree(pages);
+
+ if (!area)
+ return NULL;
+ return area->addr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (!area || (area->flags & vm_flags) != vm_flags) {
+ WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+ return;
+ }
+
+ unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
+ vunmap(cpu_addr);
+}
+#endif
+
+/*
+ * enables DMA API use for a device
+ */
+int dma_configure(struct device *dev)
+{
+ if (dev->bus->dma_configure)
+ return dev->bus->dma_configure(dev);
+ return 0;
+}
+
+void dma_deconfigure(struct device *dev)
+{
+ of_dma_deconfigure(dev);
+ acpi_dma_deconfigure(dev);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without providing cache
+ * coherence.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/scatterlist.h>
+
+static void dma_noncoherent_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t addr;
+
+ addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+ if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
+ size, dir);
+ return addr;
+}
+
+static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
+ if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
+ return nents;
+}
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+ arch_sync_dma_for_cpu_all(dev);
+}
+
+static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+ arch_sync_dma_for_cpu_all(dev);
+}
+
+static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+#endif
+
+const struct dma_map_ops dma_noncoherent_ops = {
+ .alloc = arch_dma_alloc,
+ .free = arch_dma_free,
+ .mmap = arch_dma_mmap,
+ .sync_single_for_device = dma_noncoherent_sync_single_for_device,
+ .sync_sg_for_device = dma_noncoherent_sync_sg_for_device,
+ .map_page = dma_noncoherent_map_page,
+ .map_sg = dma_noncoherent_map_sg,
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+ .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu,
+ .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu,
+ .unmap_page = dma_noncoherent_unmap_page,
+ .unmap_sg = dma_noncoherent_unmap_sg,
+#endif
+ .dma_supported = dma_direct_supported,
+ .mapping_error = dma_direct_mapping_error,
+ .cache_sync = arch_dma_cache_sync,
+};
+EXPORT_SYMBOL(dma_noncoherent_ops);
--- /dev/null
+/*
+ * Dynamic DMA mapping support.
+ *
+ * This implementation is a fallback for platforms that do not support
+ * I/O TLBs (aka DMA address translation hardware).
+ * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
+ * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
+ * Copyright (C) 2000, 2003 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API.
+ * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid
+ * unnecessary i-cache flushing.
+ * 04/07/.. ak Better overflow handling. Assorted fixes.
+ * 05/09/10 linville Add support for syncing ranges, support syncing for
+ * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 08/12/11 beckyb Add highmem support
+ */
+
+#include <linux/cache.h>
+#include <linux/dma-direct.h>
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/swiotlb.h>
+#include <linux/pfn.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/scatterlist.h>
+#include <linux/mem_encrypt.h>
+#include <linux/set_memory.h>
+
+#include <asm/io.h>
+#include <asm/dma.h>
+
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/iommu-helper.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/swiotlb.h>
+
+#define OFFSET(val,align) ((unsigned long) \
+ ( (val) & ( (align) - 1)))
+
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+
+/*
+ * Minimum IO TLB size to bother booting with. Systems with mainly
+ * 64bit capable cards will only lightly use the swiotlb. If we can't
+ * allocate a contiguous 1MB, we're probably in trouble anyway.
+ */
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+
+enum swiotlb_force swiotlb_force;
+
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+static phys_addr_t io_tlb_start, io_tlb_end;
+
+/*
+ * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
+ * io_tlb_end. This is command line adjustable via setup_io_tlb_npages.
+ */
+static unsigned long io_tlb_nslabs;
+
+/*
+ * When the IOMMU overflows we return a fallback buffer. This sets the size.
+ */
+static unsigned long io_tlb_overflow = 32*1024;
+
+static phys_addr_t io_tlb_overflow_buffer;
+
+/*
+ * This is a free list describing the number of free entries available from
+ * each index
+ */
+static unsigned int *io_tlb_list;
+static unsigned int io_tlb_index;
+
+/*
+ * Max segment that we can provide which (if pages are contingous) will
+ * not be bounced (unless SWIOTLB_FORCE is set).
+ */
+unsigned int max_segment;
+
+/*
+ * We need to save away the original address corresponding to a mapped entry
+ * for the sync operations.
+ */
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+static phys_addr_t *io_tlb_orig_addr;
+
+/*
+ * Protect the above data structures in the map and unmap calls
+ */
+static DEFINE_SPINLOCK(io_tlb_lock);
+
+static int late_alloc;
+
+static int __init
+setup_io_tlb_npages(char *str)
+{
+ if (isdigit(*str)) {
+ io_tlb_nslabs = simple_strtoul(str, &str, 0);
+ /* avoid tail segment of size < IO_TLB_SEGSIZE */
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+ if (*str == ',')
+ ++str;
+ if (!strcmp(str, "force")) {
+ swiotlb_force = SWIOTLB_FORCE;
+ } else if (!strcmp(str, "noforce")) {
+ swiotlb_force = SWIOTLB_NO_FORCE;
+ io_tlb_nslabs = 1;
+ }
+
+ return 0;
+}
+early_param("swiotlb", setup_io_tlb_npages);
+/* make io_tlb_overflow tunable too? */
+
+unsigned long swiotlb_nr_tbl(void)
+{
+ return io_tlb_nslabs;
+}
+EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
+
+unsigned int swiotlb_max_segment(void)
+{
+ return max_segment;
+}
+EXPORT_SYMBOL_GPL(swiotlb_max_segment);
+
+void swiotlb_set_max_segment(unsigned int val)
+{
+ if (swiotlb_force == SWIOTLB_FORCE)
+ max_segment = 1;
+ else
+ max_segment = rounddown(val, PAGE_SIZE);
+}
+
+/* default to 64MB */
+#define IO_TLB_DEFAULT_SIZE (64UL<<20)
+unsigned long swiotlb_size_or_default(void)
+{
+ unsigned long size;
+
+ size = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ return size ? size : (IO_TLB_DEFAULT_SIZE);
+}
+
+static bool no_iotlb_memory;
+
+void swiotlb_print_info(void)
+{
+ unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+ unsigned char *vstart, *vend;
+
+ if (no_iotlb_memory) {
+ pr_warn("software IO TLB: No low mem\n");
+ return;
+ }
+
+ vstart = phys_to_virt(io_tlb_start);
+ vend = phys_to_virt(io_tlb_end);
+
+ printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+ (unsigned long long)io_tlb_start,
+ (unsigned long long)io_tlb_end,
+ bytes >> 20, vstart, vend - 1);
+}
+
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations. This function allows the architecture to
+ * call SWIOTLB when the operations are possible. It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+ void *vaddr;
+ unsigned long bytes;
+
+ if (no_iotlb_memory || late_alloc)
+ return;
+
+ vaddr = phys_to_virt(io_tlb_start);
+ bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+ set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
+ memset(vaddr, 0, bytes);
+
+ vaddr = phys_to_virt(io_tlb_overflow_buffer);
+ bytes = PAGE_ALIGN(io_tlb_overflow);
+ set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
+ memset(vaddr, 0, bytes);
+}
+
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+{
+ void *v_overflow_buffer;
+ unsigned long i, bytes;
+
+ bytes = nslabs << IO_TLB_SHIFT;
+
+ io_tlb_nslabs = nslabs;
+ io_tlb_start = __pa(tlb);
+ io_tlb_end = io_tlb_start + bytes;
+
+ /*
+ * Get the overflow emergency buffer
+ */
+ v_overflow_buffer = memblock_virt_alloc_low_nopanic(
+ PAGE_ALIGN(io_tlb_overflow),
+ PAGE_SIZE);
+ if (!v_overflow_buffer)
+ return -ENOMEM;
+
+ io_tlb_overflow_buffer = __pa(v_overflow_buffer);
+
+ /*
+ * Allocate and initialize the free list array. This array is used
+ * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+ * between io_tlb_start and io_tlb_end.
+ */
+ io_tlb_list = memblock_virt_alloc(
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
+ PAGE_SIZE);
+ io_tlb_orig_addr = memblock_virt_alloc(
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
+ PAGE_SIZE);
+ for (i = 0; i < io_tlb_nslabs; i++) {
+ io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ io_tlb_index = 0;
+
+ if (verbose)
+ swiotlb_print_info();
+
+ swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+ return 0;
+}
+
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+void __init
+swiotlb_init(int verbose)
+{
+ size_t default_size = IO_TLB_DEFAULT_SIZE;
+ unsigned char *vstart;
+ unsigned long bytes;
+
+ if (!io_tlb_nslabs) {
+ io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ /* Get IO TLB memory from the low pages */
+ vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
+ if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
+ return;
+
+ if (io_tlb_start)
+ memblock_free_early(io_tlb_start,
+ PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ pr_warn("Cannot allocate SWIOTLB buffer");
+ no_iotlb_memory = true;
+}
+
+/*
+ * Systems with larger DMA zones (those that don't support ISA) can
+ * initialize the swiotlb later using the slab allocator if needed.
+ * This should be just like above, but with some error catching.
+ */
+int
+swiotlb_late_init_with_default_size(size_t default_size)
+{
+ unsigned long bytes, req_nslabs = io_tlb_nslabs;
+ unsigned char *vstart = NULL;
+ unsigned int order;
+ int rc = 0;
+
+ if (!io_tlb_nslabs) {
+ io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+
+ /*
+ * Get IO TLB memory from the low pages
+ */
+ order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
+ io_tlb_nslabs = SLABS_PER_PAGE << order;
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+ vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+ order);
+ if (vstart)
+ break;
+ order--;
+ }
+
+ if (!vstart) {
+ io_tlb_nslabs = req_nslabs;
+ return -ENOMEM;
+ }
+ if (order != get_order(bytes)) {
+ printk(KERN_WARNING "Warning: only able to allocate %ld MB "
+ "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+ io_tlb_nslabs = SLABS_PER_PAGE << order;
+ }
+ rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
+ if (rc)
+ free_pages((unsigned long)vstart, order);
+
+ return rc;
+}
+
+int
+swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
+{
+ unsigned long i, bytes;
+ unsigned char *v_overflow_buffer;
+
+ bytes = nslabs << IO_TLB_SHIFT;
+
+ io_tlb_nslabs = nslabs;
+ io_tlb_start = virt_to_phys(tlb);
+ io_tlb_end = io_tlb_start + bytes;
+
+ set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
+ memset(tlb, 0, bytes);
+
+ /*
+ * Get the overflow emergency buffer
+ */
+ v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
+ get_order(io_tlb_overflow));
+ if (!v_overflow_buffer)
+ goto cleanup2;
+
+ set_memory_decrypted((unsigned long)v_overflow_buffer,
+ io_tlb_overflow >> PAGE_SHIFT);
+ memset(v_overflow_buffer, 0, io_tlb_overflow);
+ io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
+
+ /*
+ * Allocate and initialize the free list array. This array is used
+ * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+ * between io_tlb_start and io_tlb_end.
+ */
+ io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs * sizeof(int)));
+ if (!io_tlb_list)
+ goto cleanup3;
+
+ io_tlb_orig_addr = (phys_addr_t *)
+ __get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs *
+ sizeof(phys_addr_t)));
+ if (!io_tlb_orig_addr)
+ goto cleanup4;
+
+ for (i = 0; i < io_tlb_nslabs; i++) {
+ io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ io_tlb_index = 0;
+
+ swiotlb_print_info();
+
+ late_alloc = 1;
+
+ swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+
+ return 0;
+
+cleanup4:
+ free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+ sizeof(int)));
+ io_tlb_list = NULL;
+cleanup3:
+ free_pages((unsigned long)v_overflow_buffer,
+ get_order(io_tlb_overflow));
+ io_tlb_overflow_buffer = 0;
+cleanup2:
+ io_tlb_end = 0;
+ io_tlb_start = 0;
+ io_tlb_nslabs = 0;
+ max_segment = 0;
+ return -ENOMEM;
+}
+
+void __init swiotlb_exit(void)
+{
+ if (!io_tlb_orig_addr)
+ return;
+
+ if (late_alloc) {
+ free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
+ get_order(io_tlb_overflow));
+ free_pages((unsigned long)io_tlb_orig_addr,
+ get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
+ free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+ sizeof(int)));
+ free_pages((unsigned long)phys_to_virt(io_tlb_start),
+ get_order(io_tlb_nslabs << IO_TLB_SHIFT));
+ } else {
+ memblock_free_late(io_tlb_overflow_buffer,
+ PAGE_ALIGN(io_tlb_overflow));
+ memblock_free_late(__pa(io_tlb_orig_addr),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
+ memblock_free_late(__pa(io_tlb_list),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
+ memblock_free_late(io_tlb_start,
+ PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ }
+ io_tlb_nslabs = 0;
+ max_segment = 0;
+}
+
+int is_swiotlb_buffer(phys_addr_t paddr)
+{
+ return paddr >= io_tlb_start && paddr < io_tlb_end;
+}
+
+/*
+ * Bounce: copy the swiotlb buffer back to the original dma location
+ */
+static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(orig_addr);
+ unsigned char *vaddr = phys_to_virt(tlb_addr);
+
+ if (PageHighMem(pfn_to_page(pfn))) {
+ /* The buffer does not have a mapping. Map it in and copy */
+ unsigned int offset = orig_addr & ~PAGE_MASK;
+ char *buffer;
+ unsigned int sz = 0;
+ unsigned long flags;
+
+ while (size) {
+ sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+ local_irq_save(flags);
+ buffer = kmap_atomic(pfn_to_page(pfn));
+ if (dir == DMA_TO_DEVICE)
+ memcpy(vaddr, buffer + offset, sz);
+ else
+ memcpy(buffer + offset, vaddr, sz);
+ kunmap_atomic(buffer);
+ local_irq_restore(flags);
+
+ size -= sz;
+ pfn++;
+ vaddr += sz;
+ offset = 0;
+ }
+ } else if (dir == DMA_TO_DEVICE) {
+ memcpy(vaddr, phys_to_virt(orig_addr), size);
+ } else {
+ memcpy(phys_to_virt(orig_addr), vaddr, size);
+ }
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
+ dma_addr_t tbl_dma_addr,
+ phys_addr_t orig_addr, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unsigned long flags;
+ phys_addr_t tlb_addr;
+ unsigned int nslots, stride, index, wrap;
+ int i;
+ unsigned long mask;
+ unsigned long offset_slots;
+ unsigned long max_slots;
+
+ if (no_iotlb_memory)
+ panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
+ if (mem_encrypt_active())
+ pr_warn_once("%s is active and system is using DMA bounce buffers\n",
+ sme_active() ? "SME" : "SEV");
+
+ mask = dma_get_seg_boundary(hwdev);
+
+ tbl_dma_addr &= mask;
+
+ offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+
+ /*
+ * Carefully handle integer overflow which can occur when mask == ~0UL.
+ */
+ max_slots = mask + 1
+ ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
+ : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+
+ /*
+ * For mappings greater than or equal to a page, we limit the stride
+ * (and hence alignment) to a page size.
+ */
+ nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ if (size >= PAGE_SIZE)
+ stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
+ else
+ stride = 1;
+
+ BUG_ON(!nslots);
+
+ /*
+ * Find suitable number of IO TLB entries size that will fit this
+ * request and allocate a buffer from that IO TLB pool.
+ */
+ spin_lock_irqsave(&io_tlb_lock, flags);
+ index = ALIGN(io_tlb_index, stride);
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ wrap = index;
+
+ do {
+ while (iommu_is_span_boundary(index, nslots, offset_slots,
+ max_slots)) {
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ if (index == wrap)
+ goto not_found;
+ }
+
+ /*
+ * If we find a slot that indicates we have 'nslots' number of
+ * contiguous buffers, we allocate the buffers from that slot
+ * and mark the entries as '0' indicating unavailable.
+ */
+ if (io_tlb_list[index] >= nslots) {
+ int count = 0;
+
+ for (i = index; i < (int) (index + nslots); i++)
+ io_tlb_list[i] = 0;
+ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+ tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
+
+ /*
+ * Update the indices to avoid searching in the next
+ * round.
+ */
+ io_tlb_index = ((index + nslots) < io_tlb_nslabs
+ ? (index + nslots) : 0);
+
+ goto found;
+ }
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ } while (index != wrap);
+
+not_found:
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
+ dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size);
+ return SWIOTLB_MAP_ERROR;
+found:
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+
+ /*
+ * Save away the mapping from the original address to the DMA address.
+ * This is needed when we sync the memory. Then we sync the buffer if
+ * needed.
+ */
+ for (i = 0; i < nslots; i++)
+ io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+
+ return tlb_addr;
+}
+
+/*
+ * Allocates bounce buffer and returns its physical address.
+ */
+static phys_addr_t
+map_single(struct device *hwdev, phys_addr_t phys, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ dma_addr_t start_dma_addr;
+
+ if (swiotlb_force == SWIOTLB_NO_FORCE) {
+ dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
+ &phys);
+ return SWIOTLB_MAP_ERROR;
+ }
+
+ start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
+ return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
+ dir, attrs);
+}
+
+/*
+ * tlb_addr is the physical address of the bounce buffer to unmap.
+ */
+void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unsigned long flags;
+ int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ phys_addr_t orig_addr = io_tlb_orig_addr[index];
+
+ /*
+ * First, sync the memory before unmapping the entry
+ */
+ if (orig_addr != INVALID_PHYS_ADDR &&
+ !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+ swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+
+ /*
+ * Return the buffer to the free list by setting the corresponding
+ * entries to indicate the number of contiguous entries available.
+ * While returning the entries to the free list, we merge the entries
+ * with slots below and above the pool being returned.
+ */
+ spin_lock_irqsave(&io_tlb_lock, flags);
+ {
+ count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
+ io_tlb_list[index + nslots] : 0);
+ /*
+ * Step 1: return the slots to the free list, merging the
+ * slots with superceeding slots
+ */
+ for (i = index + nslots - 1; i >= index; i--) {
+ io_tlb_list[i] = ++count;
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ /*
+ * Step 2: merge the returned slots with the preceding slots,
+ * if available (non zero)
+ */
+ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+ }
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+}
+
+void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ phys_addr_t orig_addr = io_tlb_orig_addr[index];
+
+ if (orig_addr == INVALID_PHYS_ADDR)
+ return;
+ orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
+
+ switch (target) {
+ case SYNC_FOR_CPU:
+ if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr,
+ size, DMA_FROM_DEVICE);
+ else
+ BUG_ON(dir != DMA_TO_DEVICE);
+ break;
+ case SYNC_FOR_DEVICE:
+ if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr,
+ size, DMA_TO_DEVICE);
+ else
+ BUG_ON(dir != DMA_FROM_DEVICE);
+ break;
+ default:
+ BUG();
+ }
+}
+
+static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
+ size_t size)
+{
+ u64 mask = DMA_BIT_MASK(32);
+
+ if (dev && dev->coherent_dma_mask)
+ mask = dev->coherent_dma_mask;
+ return addr + size - 1 <= mask;
+}
+
+static void *
+swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ unsigned long attrs)
+{
+ phys_addr_t phys_addr;
+
+ if (swiotlb_force == SWIOTLB_NO_FORCE)
+ goto out_warn;
+
+ phys_addr = swiotlb_tbl_map_single(dev,
+ __phys_to_dma(dev, io_tlb_start),
+ 0, size, DMA_FROM_DEVICE, attrs);
+ if (phys_addr == SWIOTLB_MAP_ERROR)
+ goto out_warn;
+
+ *dma_handle = __phys_to_dma(dev, phys_addr);
+ if (!dma_coherent_ok(dev, *dma_handle, size))
+ goto out_unmap;
+
+ memset(phys_to_virt(phys_addr), 0, size);
+ return phys_to_virt(phys_addr);
+
+out_unmap:
+ dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+ (unsigned long long)dev->coherent_dma_mask,
+ (unsigned long long)*dma_handle);
+
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in unmap_single.
+ * DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
+ swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+out_warn:
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+ dev_warn(dev,
+ "swiotlb: coherent allocation failed, size=%zu\n",
+ size);
+ dump_stack();
+ }
+ return NULL;
+}
+
+static bool swiotlb_free_buffer(struct device *dev, size_t size,
+ dma_addr_t dma_addr)
+{
+ phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
+
+ WARN_ON_ONCE(irqs_disabled());
+
+ if (!is_swiotlb_buffer(phys_addr))
+ return false;
+
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
+ * DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
+ swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ return true;
+}
+
+static void
+swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
+ int do_panic)
+{
+ if (swiotlb_force == SWIOTLB_NO_FORCE)
+ return;
+
+ /*
+ * Ran out of IOMMU space for this operation. This is very bad.
+ * Unfortunately the drivers cannot handle this operation properly.
+ * unless they check for dma_mapping_error (most don't)
+ * When the mapping is small enough return a static buffer to limit
+ * the damage, or panic when the transfer is too big.
+ */
+ dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
+ size);
+
+ if (size <= io_tlb_overflow || !do_panic)
+ return;
+
+ if (dir == DMA_BIDIRECTIONAL)
+ panic("DMA: Random memory could be DMA accessed\n");
+ if (dir == DMA_FROM_DEVICE)
+ panic("DMA: Random memory could be DMA written\n");
+ if (dir == DMA_TO_DEVICE)
+ panic("DMA: Random memory could be DMA read\n");
+}
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode. The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ phys_addr_t map, phys = page_to_phys(page) + offset;
+ dma_addr_t dev_addr = phys_to_dma(dev, phys);
+
+ BUG_ON(dir == DMA_NONE);
+ /*
+ * If the address happens to be in the device's DMA window,
+ * we can safely return the device addr and not worry about bounce
+ * buffering it.
+ */
+ if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
+ return dev_addr;
+
+ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+
+ /* Oh well, have to allocate and map a bounce buffer. */
+ map = map_single(dev, phys, size, dir, attrs);
+ if (map == SWIOTLB_MAP_ERROR) {
+ swiotlb_full(dev, size, dir, 1);
+ return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ }
+
+ dev_addr = __phys_to_dma(dev, map);
+
+ /* Ensure that the address returned is DMA'ble */
+ if (dma_capable(dev, dev_addr, size))
+ return dev_addr;
+
+ attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
+
+ return __phys_to_dma(dev, io_tlb_overflow_buffer);
+}
+
+/*
+ * Unmap a single streaming mode DMA translation. The dma_addr and size must
+ * match what was provided for in a previous swiotlb_map_page call. All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
+ BUG_ON(dir == DMA_NONE);
+
+ if (is_swiotlb_buffer(paddr)) {
+ swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ /*
+ * phys_to_virt doesn't work with hihgmem page but we could
+ * call dma_mark_clean() with hihgmem page here. However, we
+ * are fine since dma_mark_clean() is null on POWERPC. We can
+ * make dma_mark_clean() take a physical address if necessary.
+ */
+ dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unmap_single(hwdev, dev_addr, size, dir, attrs);
+}
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so. At the next point you give the dma
+ * address back to the card, you must first perform a
+ * swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
+ BUG_ON(dir == DMA_NONE);
+
+ if (is_swiotlb_buffer(paddr)) {
+ swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above swiotlb_map_page
+ * interface. Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ * DMA address/length pairs than there are SG table elements.
+ * (for example via virtual mapping capabilities)
+ * The routine returns the number of addr/length pairs actually
+ * used, at most nents.
+ *
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
+ * same here.
+ */
+int
+swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ BUG_ON(dir == DMA_NONE);
+
+ for_each_sg(sgl, sg, nelems, i) {
+ phys_addr_t paddr = sg_phys(sg);
+ dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
+
+ if (swiotlb_force == SWIOTLB_FORCE ||
+ !dma_capable(hwdev, dev_addr, sg->length)) {
+ phys_addr_t map = map_single(hwdev, sg_phys(sg),
+ sg->length, dir, attrs);
+ if (map == SWIOTLB_MAP_ERROR) {
+ /* Don't panic here, we expect map_sg users
+ to do proper error handling. */
+ swiotlb_full(hwdev, sg->length, dir, 0);
+ attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+ attrs);
+ sg_dma_len(sgl) = 0;
+ return 0;
+ }
+ sg->dma_address = __phys_to_dma(hwdev, map);
+ } else
+ sg->dma_address = dev_addr;
+ sg_dma_len(sg) = sg->length;
+ }
+ return nelems;
+}
+
+/*
+ * Unmap a set of streaming mode DMA translations. Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ BUG_ON(dir == DMA_NONE);
+
+ for_each_sg(sgl, sg, nelems, i)
+ unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+ attrs);
+}
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nelems, i)
+ swiotlb_sync_single(hwdev, sg->dma_address,
+ sg_dma_len(sg), dir, target);
+}
+
+void
+swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir)
+{
+ swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir)
+{
+ swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+
+int
+swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+ return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
+}
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly. For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+ return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+}
+
+void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ void *vaddr;
+
+ /* temporary workaround: */
+ if (gfp & __GFP_NOWARN)
+ attrs |= DMA_ATTR_NO_WARN;
+
+ /*
+ * Don't print a warning when the first allocation attempt fails.
+ * swiotlb_alloc_coherent() will print a warning when the DMA memory
+ * allocation ultimately failed.
+ */
+ gfp |= __GFP_NOWARN;
+
+ vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+ if (!vaddr)
+ vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
+ return vaddr;
+}
+
+void swiotlb_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr, unsigned long attrs)
+{
+ if (!swiotlb_free_buffer(dev, size, dma_addr))
+ dma_direct_free(dev, size, vaddr, dma_addr, attrs);
+}
+
+const struct dma_map_ops swiotlb_dma_ops = {
+ .mapping_error = swiotlb_dma_mapping_error,
+ .alloc = swiotlb_alloc,
+ .free = swiotlb_free,
+ .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
+ .sync_single_for_device = swiotlb_sync_single_for_device,
+ .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+ .sync_sg_for_device = swiotlb_sync_sg_for_device,
+ .map_sg = swiotlb_map_sg_attrs,
+ .unmap_sg = swiotlb_unmap_sg_attrs,
+ .map_page = swiotlb_map_page,
+ .unmap_page = swiotlb_unmap_page,
+ .dma_supported = dma_direct_supported,
+};
+EXPORT_SYMBOL(swiotlb_dma_ops);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMA operations that map to virtual addresses without flushing memory.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+static void *dma_virt_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp,
+ unsigned long attrs)
+{
+ void *ret;
+
+ ret = (void *)__get_free_pages(gfp, get_order(size));
+ if (ret)
+ *dma_handle = (uintptr_t)ret;
+ return ret;
+}
+
+static void dma_virt_free(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+ free_pages((unsigned long)cpu_addr, get_order(size));
+}
+
+static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ return (uintptr_t)(page_address(page) + offset);
+}
+
+static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ BUG_ON(!sg_page(sg));
+ sg_dma_address(sg) = (uintptr_t)sg_virt(sg);
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nents;
+}
+
+const struct dma_map_ops dma_virt_ops = {
+ .alloc = dma_virt_alloc,
+ .free = dma_virt_free,
+ .map_page = dma_virt_map_page,
+ .map_sg = dma_virt_map_sg,
+};
+EXPORT_SYMBOL(dma_virt_ops);
typeof(*event), group_node))
/*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
* Must be called with ctx->mutex and ctx->lock held.
*/
static void
}
/*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
* Must be called with ctx->mutex and ctx->lock held.
*/
static void
}
/*
- * Disable a event.
+ * Disable an event.
*
* If event->ctx is a cloned context, callers must make sure that
* every task struct that event->ctx->task could possibly point to
}
/*
- * Enable a event.
+ * Enable an event.
*
* If event->ctx is a cloned context, callers must make sure that
* every task struct that event->ctx->task could possibly point to
* events will refuse to restart because of rb::aux_mmap_count==0,
* see comments in perf_aux_output_begin().
*
- * Since this is happening on a event-local CPU, no trace is lost
+ * Since this is happening on an event-local CPU, no trace is lost
* while restarting.
*/
if (sd->restart)
int ret;
/*
- * Return end-of-file for a read on a event that is in
+ * Return end-of-file for a read on an event that is in
* error state (i.e. because it was pinned but it couldn't be
* scheduled on to the CPU at some point).
*/
}
EXPORT_SYMBOL_GPL(perf_event_update_userpage);
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
{
struct perf_event *event = vmf->vma->vm_file->private_data;
struct ring_buffer *rb;
- int ret = VM_FAULT_SIGBUS;
+ vm_fault_t ret = VM_FAULT_SIGBUS;
if (vmf->flags & FAULT_FLAG_MKWRITE) {
if (vmf->pgoff == 0)
static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs)
{
bool kernel = !event->attr.exclude_callchain_kernel;
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
- data->callchain = perf_callchain(event, regs);
+ if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ data->callchain = perf_callchain(event, regs);
+
size += data->callchain->nr;
header->size += size * sizeof(u64);
data->phys_addr = perf_virt_to_phys(data->addr);
}
-static void __always_inline
+static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs,
struct file *file, unsigned long offset,
unsigned long size)
{
+ /* d_inode(NULL) won't be equal to any mapped user-space file */
+ if (!filter->path.dentry)
+ return false;
+
if (d_inode(filter->path.dentry) != file_inode(file))
return false;
}
/*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
*/
static struct perf_event *
perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
/*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
*
* Returns:
* - valid pointer on success
mutex_unlock(&nr_bp_mutex);
}
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
int err;
__release_bp_slot(bp, old_type);
- err = __reserve_bp_slot(bp, bp->attr.bp_type);
+ err = __reserve_bp_slot(bp, new_type);
if (err) {
/*
* Reserve the old_type slot back in case
return err;
}
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
int ret;
mutex_lock(&nr_bp_mutex);
- ret = __modify_bp_slot(bp, old_type);
+ ret = __modify_bp_slot(bp, old_type, new_type);
mutex_unlock(&nr_bp_mutex);
return ret;
}
return 0;
}
-static int validate_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
{
- int ret;
+ int err;
- ret = arch_validate_hwbkpt_settings(bp);
- if (ret)
- return ret;
+ err = hw_breakpoint_arch_parse(bp, attr, hw);
+ if (err)
+ return err;
- if (arch_check_bp_in_kernelspace(bp)) {
- if (bp->attr.exclude_kernel)
+ if (arch_check_bp_in_kernelspace(hw)) {
+ if (attr->exclude_kernel)
return -EINVAL;
/*
* Don't let unprivileged users set a breakpoint in the trap
int register_perf_hw_breakpoint(struct perf_event *bp)
{
- int ret;
-
- ret = reserve_bp_slot(bp);
- if (ret)
- return ret;
+ struct arch_hw_breakpoint hw;
+ int err;
- ret = validate_hw_breakpoint(bp);
+ err = reserve_bp_slot(bp);
+ if (err)
+ return err;
- /* if arch_validate_hwbkpt_settings() fails then release bp slot */
- if (ret)
+ err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+ if (err) {
release_bp_slot(bp);
+ return err;
+ }
- return ret;
+ bp->hw.info = hw;
+
+ return 0;
}
/**
}
EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+ struct perf_event_attr *from)
+{
+ to->bp_addr = from->bp_addr;
+ to->bp_type = from->bp_type;
+ to->bp_len = from->bp_len;
+ to->disabled = from->disabled;
+}
+
int
modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
bool check)
{
- u64 old_addr = bp->attr.bp_addr;
- u64 old_len = bp->attr.bp_len;
- int old_type = bp->attr.bp_type;
- bool modify = attr->bp_type != old_type;
- int err = 0;
+ struct arch_hw_breakpoint hw;
+ int err;
- bp->attr.bp_addr = attr->bp_addr;
- bp->attr.bp_type = attr->bp_type;
- bp->attr.bp_len = attr->bp_len;
+ err = hw_breakpoint_parse(bp, attr, &hw);
+ if (err)
+ return err;
- if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
- return -EINVAL;
+ if (check) {
+ struct perf_event_attr old_attr;
- err = validate_hw_breakpoint(bp);
- if (!err && modify)
- err = modify_bp_slot(bp, old_type);
+ old_attr = bp->attr;
+ hw_breakpoint_copy_attr(&old_attr, attr);
+ if (memcmp(&old_attr, attr, sizeof(*attr)))
+ return -EINVAL;
+ }
- if (err) {
- bp->attr.bp_addr = old_addr;
- bp->attr.bp_type = old_type;
- bp->attr.bp_len = old_len;
- return err;
+ if (bp->attr.bp_type != attr->bp_type) {
+ err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+ if (err)
+ return err;
}
- bp->attr.disabled = attr->disabled;
+ hw_breakpoint_copy_attr(&bp->attr, attr);
+ bp->hw.info = hw;
+
return 0;
}
preempt_enable();
}
-static bool __always_inline
+static __always_inline bool
ring_buffer_has_space(unsigned long head, unsigned long tail,
unsigned long data_size, unsigned int size,
bool backward)
return CIRC_SPACE(tail, head, data_size) >= size;
}
-static int __always_inline
+static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
bool backward)
}
EXPORT_SYMBOL_GPL(perf_aux_output_begin);
-static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb)
{
if (rb->aux_overwrite)
return false;
EXPORT_SYMBOL_GPL(uprobe_register);
/*
- * uprobe_apply - unregister a already registered probe.
+ * uprobe_apply - unregister an already registered probe.
* @inode: the file in which the probe has to be removed.
* @offset: offset from the start of the file.
* @uc: consumer which wants to add more or remove some breakpoints
}
/*
- * uprobe_unregister - unregister a already registered probe.
+ * uprobe_unregister - unregister an already registered probe.
* @inode: the file in which the probe has to be removed.
* @offset: offset from the start of the file.
* @uc: identify which probe if multiple probes are colocated.
/*
* Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
*/
void uprobe_free_utask(struct task_struct *t)
{
if (should_fail(&fei_fault_attr, 1)) {
regs_set_return_value(regs, attr->retval);
override_function_with_return(regs);
- /* Kprobe specific fixup */
- reset_current_kprobe();
- preempt_enable_no_resched();
return 1;
}
struct kmem_cache *fs_cachep;
/* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+ if (vma)
+ vma_init(vma, mm);
+ return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+ struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+ if (new) {
+ *new = *orig;
+ INIT_LIST_HEAD(&new->anon_vma_chain);
+ }
+ return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
static void account_kernel_stack(struct task_struct *tsk, int account)
{
void *stack = task_stack_page(tsk);
continue;
}
charge = 0;
+ /*
+ * Don't duplicate many vmas if we've been oom-killed (for
+ * example)
+ */
+ if (fatal_signal_pending(current)) {
+ retval = -EINTR;
+ goto out;
+ }
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned long len = vma_pages(mpnt);
goto fail_nomem;
charge = len;
}
- tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
- *tmp = *mpnt;
- INIT_LIST_HEAD(&tmp->anon_vma_chain);
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
- kmem_cache_free(vm_area_cachep, tmp);
+ vm_area_free(tmp);
fail_nomem:
retval = -ENOMEM;
vm_unacct_memory(charge);
void __init proc_caches_init(void)
{
+ unsigned int mm_size;
+
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
sizeof(struct fs_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
+
/*
- * FIXME! The "sizeof(struct mm_struct)" currently includes the
- * whole struct cpumask for the OFFSTACK case. We could change
- * this to *only* allocate as much of it as required by the
- * maximum number of CPU's we can ever have. The cpumask_allocation
- * is at the end of the structure, exactly for that reason.
+ * The mm_cpumask is located at the end of mm_struct, and is
+ * dynamically sized based on the maximum CPU number this system
+ * can have, taking hotplug into account (nr_cpu_ids).
*/
+ mm_size = sizeof(struct mm_struct) + cpumask_size();
+
mm_cachep = kmem_cache_create_usercopy("mm_struct",
- sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
+ mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
offsetof(struct mm_struct, saved_auxv),
sizeof_field(struct mm_struct, saved_auxv),
endmenu
config GENERIC_IRQ_MULTI_HANDLER
- depends on !MULTI_IRQ_HANDLER
bool
help
Allow to specify the low level IRQ handler at run time.
BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE),
BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
+ BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
};
static void
* We free the descriptor, masks and stat fields via RCU. That
* allows demultiplex interrupts to do rcu based management of
* the child interrupts.
+ * This also allows us to use rcu in kstat_irqs_usr().
*/
call_rcu(&desc->rcu, delayed_free_desc);
}
* kstat_irqs_usr - Get the statistics for an interrupt
* @irq: The interrupt number
*
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
*/
unsigned int kstat_irqs_usr(unsigned int irq)
{
unsigned int sum;
- irq_lock_sparse();
+ rcu_read_lock();
sum = kstat_irqs(irq);
- irq_unlock_sparse();
+ rcu_read_unlock();
return sum;
}
static int irq_wait_for_interrupt(struct irqaction *action)
{
- set_current_state(TASK_INTERRUPTIBLE);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
+ if (kthread_should_stop()) {
+ /* may need to run one last time */
+ if (test_and_clear_bit(IRQTF_RUNTHREAD,
+ &action->thread_flags)) {
+ __set_current_state(TASK_RUNNING);
+ return 0;
+ }
+ __set_current_state(TASK_RUNNING);
+ return -1;
+ }
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
return 0;
}
schedule();
- set_current_state(TASK_INTERRUPTIBLE);
}
- __set_current_state(TASK_RUNNING);
- return -1;
}
/*
/*
* This is the regular exit path. __free_irq() is stopping the
* thread via kthread_stop() after calling
- * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
- * oneshot mask bit can be set. We cannot verify that as we
- * cannot touch the oneshot mask at this point anymore as
- * __setup_irq() might have given out currents thread_mask
- * again.
+ * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+ * oneshot mask bit can be set.
*/
task_work_cancel(current, irq_thread_dtor);
return 0;
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return 0;
+ /*
+ * No further action required for interrupts which are requested as
+ * threaded interrupts already
+ */
+ if (new->handler == irq_default_primary_handler)
+ return 0;
+
new->flags |= IRQF_ONESHOT;
/*
* thread handler. We force thread them as well by creating a
* secondary action.
*/
- if (new->handler != irq_default_primary_handler && new->thread_fn) {
+ if (new->handler && new->thread_fn) {
/* Allocate the secondary action */
new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!new->secondary)
/*
* Protects against a concurrent __free_irq() call which might wait
- * for synchronize_irq() to complete without holding the optional
- * chip bus lock and desc->lock.
+ * for synchronize_hardirq() to complete without holding the optional
+ * chip bus lock and desc->lock. Also protects against handing out
+ * a recycled oneshot thread_mask bit while it's still in use by
+ * its previous owner.
*/
mutex_lock(&desc->request_mutex);
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
- if (!desc)
- return NULL;
-
mutex_lock(&desc->request_mutex);
chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, flags);
/*
* Drop bus_lock here so the changes which were done in the chip
* callbacks above are synced out to the irq chips which hang
- * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+ * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
*
* Aside of that the bus_lock can also be taken from the threaded
* handler in irq_finalize_oneshot() which results in a deadlock
- * because synchronize_irq() would wait forever for the thread to
+ * because kthread_stop() would wait forever for the thread to
* complete, which is blocked on the bus lock.
*
* The still held desc->request_mutex() protects against a
unregister_handler_proc(irq, action);
/* Make sure it's not being used on another CPU: */
- synchronize_irq(irq);
+ synchronize_hardirq(irq);
#ifdef CONFIG_DEBUG_SHIRQ
/*
* is so by doing an extra call to the handler ....
*
* ( We do this after actually deregistering it, to make sure that a
- * 'real' IRQ doesn't run in * parallel with our fake. )
+ * 'real' IRQ doesn't run in parallel with our fake. )
*/
if (action->flags & IRQF_SHARED) {
local_irq_save(flags);
}
#endif
+ /*
+ * The action has already been removed above, but the thread writes
+ * its oneshot mask bit when it completes. Though request_mutex is
+ * held across this which prevents __setup_irq() from handing out
+ * the same bit to a newly requested action.
+ */
if (action->thread) {
kthread_stop(action->thread);
put_task_struct(action->thread);
seq_putc(p, '\n');
}
- irq_lock_sparse();
+ rcu_read_lock();
desc = irq_to_desc(i);
if (!desc)
goto outsparse;
- raw_spin_lock_irqsave(&desc->lock, flags);
- for_each_online_cpu(j)
- any_count |= kstat_irqs_cpu(i, j);
- action = desc->action;
- if ((!action || irq_desc_is_chained(desc)) && !any_count)
- goto out;
+ if (desc->kstat_irqs)
+ for_each_online_cpu(j)
+ any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+ if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+ goto outsparse;
seq_printf(p, "%*d: ", prec, i);
for_each_online_cpu(j)
- seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+ seq_printf(p, "%10u ", desc->kstat_irqs ?
+ *per_cpu_ptr(desc->kstat_irqs, j) : 0);
+ raw_spin_lock_irqsave(&desc->lock, flags);
if (desc->irq_data.chip) {
if (desc->irq_data.chip->irq_print_chip)
desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
if (desc->name)
seq_printf(p, "-%-8s", desc->name);
+ action = desc->action;
if (action) {
seq_printf(p, " %s", action->name);
while ((action = action->next) != NULL)
}
seq_putc(p, '\n');
-out:
raw_spin_unlock_irqrestore(&desc->lock, flags);
outsparse:
- irq_unlock_sparse();
+ rcu_read_unlock();
return 0;
}
#endif
static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
{
- enum kcov_mode mode;
+ unsigned int mode;
/*
* We are interested in code coverage as a function of a syscall inputs,
void kcov_task_init(struct task_struct *t)
{
- t->kcov_mode = KCOV_MODE_DISABLED;
+ WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
+ barrier();
t->kcov_size = 0;
t->kcov_area = NULL;
t->kcov = NULL;
return 0;
}
+/*
+ * Fault in a lazily-faulted vmalloc area before it can be used by
+ * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the
+ * vmalloc fault handling path is instrumented.
+ */
+static void kcov_fault_in_area(struct kcov *kcov)
+{
+ unsigned long stride = PAGE_SIZE / sizeof(unsigned long);
+ unsigned long *area = kcov->area;
+ unsigned long offset;
+
+ for (offset = 0; offset < kcov->size; offset += stride)
+ READ_ONCE(area[offset]);
+}
+
static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
unsigned long arg)
{
#endif
else
return -EINVAL;
+ kcov_fault_in_area(kcov);
/* Cache in task struct for performance. */
t->kcov_size = kcov->size;
t->kcov_area = kcov->area;
else
buf += mchunk;
mbytes -= mchunk;
+
+ cond_resched();
}
out:
return result;
else
buf += mchunk;
mbytes -= mchunk;
+
+ cond_resched();
}
out:
return result;
(kprobe_disabled(p) || kprobes_all_disarmed))
return;
- /* Both of break_handler and post_handler are not supported. */
- if (p->break_handler || p->post_handler)
+ /* kprobes with post_handler can not be optimized */
+ if (p->post_handler)
return;
op = container_of(p, struct optimized_kprobe, kp);
* there is still a relative jump) and disabled.
*/
op = container_of(ap, struct optimized_kprobe, kp);
- if (unlikely(list_empty(&op->list)))
- printk(KERN_WARNING "Warning: found a stray unused "
- "aggrprobe@%p\n", ap->addr);
+ WARN_ON_ONCE(list_empty(&op->list));
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again (remove from op->list) */
ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
(unsigned long)p->addr, 0, 0);
if (ret) {
- pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+ pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+ p->addr, ret);
return ret;
}
ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
(unsigned long)p->addr, 1, 0);
- WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+ WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+ p->addr, ret);
return ret;
}
#else /* !CONFIG_KPROBES_ON_FTRACE */
}
NOKPROBE_SYMBOL(aggr_fault_handler);
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct kprobe *cur = __this_cpu_read(kprobe_instance);
- int ret = 0;
-
- if (cur && cur->break_handler) {
- if (cur->break_handler(cur, regs))
- ret = 1;
- }
- reset_kprobe_instance();
- return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
/* Walks the list and increments nmissed count for multiprobe case */
void kprobes_inc_nmissed_count(struct kprobe *p)
{
}
NOKPROBE_SYMBOL(cleanup_rp_inst);
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
-*/
+/* Add the new probe to ap->list */
static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
- if (p->break_handler || p->post_handler)
+ if (p->post_handler)
unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */
- if (p->break_handler) {
- if (ap->break_handler)
- return -EEXIST;
- list_add_tail_rcu(&p->list, &ap->list);
- ap->break_handler = aggr_break_handler;
- } else
- list_add_rcu(&p->list, &ap->list);
+ list_add_rcu(&p->list, &ap->list);
if (p->post_handler && !ap->post_handler)
ap->post_handler = aggr_post_handler;
/* We don't care the kprobe which has gone. */
if (p->post_handler && !kprobe_gone(p))
ap->post_handler = aggr_post_handler;
- if (p->break_handler && !kprobe_gone(p))
- ap->break_handler = aggr_break_handler;
INIT_LIST_HEAD(&ap->list);
INIT_HLIST_NODE(&ap->hlist);
goto disarmed;
else {
/* If disabling probe has special handlers, update aggrprobe */
- if (p->break_handler && !kprobe_gone(p))
- ap->break_handler = NULL;
if (p->post_handler && !kprobe_gone(p)) {
list_for_each_entry_rcu(list_p, &ap->list, list) {
if ((list_p != p) && (list_p->post_handler))
return (unsigned long)entry;
}
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
- int ret = 0, i;
-
- if (num <= 0)
- return -EINVAL;
-
- for (i = 0; i < num; i++) {
- ret = register_jprobe(jps[i]);
-
- if (ret < 0) {
- if (i > 0)
- unregister_jprobes(jps, i);
- break;
- }
- }
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
- unsigned long addr, offset;
- struct kprobe *kp = &jp->kp;
-
- /*
- * Verify probepoint as well as the jprobe handler are
- * valid function entry points.
- */
- addr = arch_deref_entry_point(jp->entry);
-
- if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
- kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
- kp->pre_handler = setjmp_pre_handler;
- kp->break_handler = longjmp_break_handler;
- return register_kprobe(kp);
- }
-
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
- unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
- int i;
-
- if (num <= 0)
- return;
- mutex_lock(&kprobe_mutex);
- for (i = 0; i < num; i++)
- if (__unregister_kprobe_top(&jps[i]->kp) < 0)
- jps[i]->kp.addr = NULL;
- mutex_unlock(&kprobe_mutex);
-
- synchronize_sched();
- for (i = 0; i < num; i++) {
- if (jps[i]->kp.addr)
- __unregister_kprobe_bottom(&jps[i]->kp);
- }
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
#ifdef CONFIG_KRETPROBES
/*
* This kprobe pre_handler is registered with every kretprobe. When probe
rp->kp.pre_handler = pre_handler_kretprobe;
rp->kp.post_handler = NULL;
rp->kp.fault_handler = NULL;
- rp->kp.break_handler = NULL;
/* Pre-allocate memory for max kretprobe instances */
if (rp->maxactive <= 0) {
list_for_each_entry_rcu(kp, &p->list, list)
kp->flags |= KPROBE_FLAG_GONE;
p->post_handler = NULL;
- p->break_handler = NULL;
kill_optimized_kprobe(p);
}
/*
}
EXPORT_SYMBOL_GPL(enable_kprobe);
+/* Caller must NOT call this in usual path. This is only for critical case */
void dump_kprobe(struct kprobe *kp)
{
- printk(KERN_WARNING "Dumping kprobe:\n");
- printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
- kp->symbol_name, kp->addr, kp->offset);
+ pr_err("Dumping kprobe:\n");
+ pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+ kp->symbol_name, kp->offset, kp->addr);
}
NOKPROBE_SYMBOL(dump_kprobe);
entry = arch_deref_entry_point((void *)*iter);
if (!kernel_text_address(entry) ||
- !kallsyms_lookup_size_offset(entry, &size, &offset)) {
- pr_err("Failed to find blacklist at %p\n",
- (void *)entry);
+ !kallsyms_lookup_size_offset(entry, &size, &offset))
continue;
- }
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
if (!ent)
const char *sym, int offset, char *modname, struct kprobe *pp)
{
char *kprobe_type;
+ void *addr = p->addr;
if (p->pre_handler == pre_handler_kretprobe)
kprobe_type = "r";
- else if (p->pre_handler == setjmp_pre_handler)
- kprobe_type = "j";
else
kprobe_type = "k";
+ if (!kallsyms_show_value())
+ addr = NULL;
+
if (sym)
- seq_printf(pi, "%p %s %s+0x%x %s ",
- p->addr, kprobe_type, sym, offset,
+ seq_printf(pi, "%px %s %s+0x%x %s ",
+ addr, kprobe_type, sym, offset,
(modname ? modname : " "));
- else
- seq_printf(pi, "%p %s %p ",
- p->addr, kprobe_type, p->addr);
+ else /* try to use %pS */
+ seq_printf(pi, "%px %s %pS ",
+ addr, kprobe_type, p->addr);
if (!pp)
pp = p;
struct kprobe_blacklist_entry *ent =
list_entry(v, struct kprobe_blacklist_entry, list);
- seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
- (void *)ent->end_addr, (void *)ent->start_addr);
+ /*
+ * If /proc/kallsyms is not showing kernel address, we won't
+ * show them here either.
+ */
+ if (!kallsyms_show_value())
+ seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+ (void *)ent->start_addr);
+ else
+ seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+ (void *)ent->end_addr, (void *)ent->start_addr);
return 0;
}
if (!dir)
return -ENOMEM;
- file = debugfs_create_file("list", 0444, dir, NULL,
+ file = debugfs_create_file("list", 0400, dir, NULL,
&debugfs_kprobes_operations);
if (!file)
goto error;
if (!file)
goto error;
- file = debugfs_create_file("blacklist", 0444, dir, NULL,
+ file = debugfs_create_file("blacklist", 0400, dir, NULL,
&debugfs_kprobe_blacklist_ops);
if (!file)
goto error;
#endif /* CONFIG_DEBUG_FS */
module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
static void __kthread_parkme(struct kthread *self)
{
for (;;) {
- set_current_state(TASK_PARKED);
+ /*
+ * TASK_PARKED is a special state; we must serialize against
+ * possible pending wakeups to avoid store-store collisions on
+ * task->state.
+ *
+ * Such a collision might possibly result in the task state
+ * changin from TASK_PARKED and us failing the
+ * wait_task_inactive() in kthread_park().
+ */
+ set_special_state(TASK_PARKED);
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
+
+ complete(&self->parked);
schedule();
}
__set_current_state(TASK_RUNNING);
}
EXPORT_SYMBOL_GPL(kthread_parkme);
-void kthread_park_complete(struct task_struct *k)
-{
- complete_all(&to_kthread(k)->parked);
-}
-
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
- reinit_completion(&kthread->parked);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ /*
+ * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
+ */
wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
+ if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+ return -EBUSY;
+
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
+ /*
+ * Wait for __kthread_parkme() to complete(), this means we
+ * _will_ have TASK_PARKED and are about to call schedule().
+ */
wait_for_completion(&kthread->parked);
+ /*
+ * Now wait for that schedule() to complete and the task to
+ * get scheduled out.
+ */
+ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
}
return 0;
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
if (unlikely(!debug_locks))
return;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
for (i = 0; i < curr->lockdep_depth; i++) {
hlock = curr->held_locks + i;
print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
break;
}
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
* Davidlohr Bueso <dave@stgolabs.net>
* Based on kernel/rcu/torture.c.
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/kthread.h>
torture_param(int, stat_interval, 60,
"Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
"Enable verbose debugging printk()s");
static char *torture_type = "spin_lock";
rt_mutex_postunlock(&wake_q);
}
+static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+{
+ might_sleep();
+
+ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+ __rt_mutex_lock(lock, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+#endif
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
/**
* rt_mutex_lock - lock a rt_mutex
*
*/
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
- might_sleep();
-
- mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+ __rt_mutex_lock(lock, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
/**
* rt_mutex_lock_interruptible - lock a rt_mutex interruptible
might_sleep();
__down_read(sem);
+ rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_non_owner);
unsigned long pfn, pgoff, order;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
+ struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
+ align_end = align_start + align_size - 1;
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
mutex_lock(&pgmap_lock);
error = 0;
- align_end = align_start + align_size - 1;
foreach_order_pgoff(res, order, pgoff) {
error = __radix_tree_insert(&pgmap_radix,
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_enable;
/*
} else if (!count)
__put_page(page);
}
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
}
static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
-#ifndef CONFIG_MODULE_SIG_FORCE
module_param(sig_enforce, bool_enable_only, 0644);
-#endif /* !CONFIG_MODULE_SIG_FORCE */
/*
* Export sig_enforce kernel cmdline parameter to allow other subsystems rely
}
/* Not having a signature is only an error if we're strict. */
- if (err == -ENOKEY && !sig_enforce)
+ if (err == -ENOKEY && !is_module_sig_enforced())
err = 0;
return err;
* state - control system sleep states.
*
* show() returns available sleep state labels, which may be "mem", "standby",
- * "freeze" and "disk" (hibernation). See Documentation/power/states.txt for a
- * description of what they mean.
+ * "freeze" and "disk" (hibernation).
+ * See Documentation/admin-guide/pm/sleep-states.rst for a description of
+ * what they mean.
*
* store() accepts one of those strings, translates it into the proper
* enumerated value, and initiates a suspend transition.
/* Push all the CPUs into the idle loop. */
wake_up_all_idle_cpus();
/* Make the current CPU wait so it can enter the idle loop too. */
- swait_event(s2idle_wait_head,
+ swait_event_exclusive(s2idle_wait_head,
s2idle_state == S2IDLE_STATE_WAKE);
cpuidle_pause();
raw_spin_lock_irqsave(&s2idle_lock, flags);
if (s2idle_state > S2IDLE_STATE_NONE) {
s2idle_state = S2IDLE_STATE_WAKE;
- swake_up(&s2idle_wait_head);
+ swake_up_one(&s2idle_wait_head);
}
raw_spin_unlock_irqrestore(&s2idle_lock, flags);
}
WRITE_ONCE(*sp, rcu_seq_endval(sp));
}
-/* Take a snapshot of the update side's sequence number. */
+/*
+ * rcu_seq_snap - Take a snapshot of the update side's sequence number.
+ *
+ * This function returns the earliest value of the grace-period sequence number
+ * that will indicate that a full grace period has elapsed since the current
+ * time. Once the grace-period sequence number has reached this value, it will
+ * be safe to invoke all callbacks that have been registered prior to the
+ * current time. This value is the current grace-period number plus two to the
+ * power of the number of low-order bits reserved for state, then rounded up to
+ * the next value in which the state bits are all zero.
+ */
static inline unsigned long rcu_seq_snap(unsigned long *sp)
{
unsigned long s;
return READ_ONCE(*sp);
}
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not the
+ * corresponding update-side operation has started.
+ */
+static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
+{
+ return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
+}
+
/*
* Given a snapshot from rcu_seq_snap(), determine whether or not a
* full update-side operation has occurred.
return ULONG_CMP_GE(READ_ONCE(*sp), s);
}
+/*
+ * Has a grace period completed since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
+{
+ return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
+}
+
+/*
+ * Has a grace period started since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
+{
+ return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
+ new);
+}
+
+/*
+ * Roughly how many full grace periods have elapsed between the collection
+ * of the two specified grace periods?
+ */
+static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
+{
+ unsigned long rnd_diff;
+
+ if (old == new)
+ return 0;
+ /*
+ * Compute the number of grace periods (still shifted up), plus
+ * one if either of new and old is not an exact grace period.
+ */
+ rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
+ ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
+ ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
+ if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
+ return 1; /* Definitely no grace period has elapsed. */
+ return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
+}
+
/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
/* Is this rcu_node a leaf? */
#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
- unsigned long *gpnum, unsigned long *completed);
-void rcutorture_record_test_transition(void);
+ unsigned long *gp_seq);
void rcutorture_record_progress(unsigned long vernum);
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
unsigned long c);
#else
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
- int *flags,
- unsigned long *gpnum,
- unsigned long *completed)
+ int *flags, unsigned long *gp_seq)
{
*flags = 0;
- *gpnum = 0;
- *completed = 0;
+ *gp_seq = 0;
}
-static inline void rcutorture_record_test_transition(void) { }
static inline void rcutorture_record_progress(unsigned long vernum) { }
#ifdef CONFIG_RCU_TRACE
void do_trace_rcu_torture_read(const char *rcutorturename,
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum,
- unsigned long *completed)
+ unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *completed = sp->srcu_idx;
- *gpnum = *completed;
+ *gp_seq = sp->srcu_idx;
}
#elif defined(CONFIG_TREE_SRCU)
void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum, unsigned long *completed);
+ unsigned long *gp_seq);
#endif
#ifdef CONFIG_TINY_RCU
-static inline unsigned long rcu_batches_started(void) { return 0; }
-static inline unsigned long rcu_batches_started_bh(void) { return 0; }
-static inline unsigned long rcu_batches_started_sched(void) { return 0; }
-static inline unsigned long rcu_batches_completed(void) { return 0; }
-static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
-static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
static inline unsigned long
static inline void rcu_bh_force_quiescent_state(void) { }
static inline void rcu_sched_force_quiescent_state(void) { }
static inline void show_rcu_gp_kthreads(void) { }
+static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
#else /* #ifdef CONFIG_TINY_RCU */
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_get_gp_seq(void);
+unsigned long rcu_bh_get_gp_seq(void);
+unsigned long rcu_sched_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long rcu_exp_batches_completed_sched(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void show_rcu_gp_kthreads(void);
+int rcu_get_gp_kthreads_prio(void);
void rcu_force_quiescent_state(void);
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, !IS_ENABLED(MODULE),
"Shutdown at end of performance tests.");
-torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
static char *perf_type = "rcu";
void (*cleanup)(void);
int (*readlock)(void);
void (*readunlock)(int idx);
- unsigned long (*started)(void);
- unsigned long (*completed)(void);
+ unsigned long (*get_gp_seq)(void);
+ unsigned long (*gp_diff)(unsigned long new, unsigned long old);
unsigned long (*exp_completed)(void);
void (*async)(struct rcu_head *head, rcu_callback_t func);
void (*gp_barrier)(void);
.init = rcu_sync_perf_init,
.readlock = rcu_perf_read_lock,
.readunlock = rcu_perf_read_unlock,
- .started = rcu_batches_started,
- .completed = rcu_batches_completed,
+ .get_gp_seq = rcu_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed,
.async = call_rcu,
.gp_barrier = rcu_barrier,
.init = rcu_sync_perf_init,
.readlock = rcu_bh_perf_read_lock,
.readunlock = rcu_bh_perf_read_unlock,
- .started = rcu_batches_started_bh,
- .completed = rcu_batches_completed_bh,
+ .get_gp_seq = rcu_bh_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_bh,
.gp_barrier = rcu_barrier_bh,
.init = rcu_sync_perf_init,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
- .started = NULL,
- .completed = srcu_perf_completed,
+ .get_gp_seq = srcu_perf_completed,
+ .gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.cleanup = srcu_sync_perf_cleanup,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
- .started = NULL,
- .completed = srcu_perf_completed,
+ .get_gp_seq = srcu_perf_completed,
+ .gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.init = rcu_sync_perf_init,
.readlock = sched_perf_read_lock,
.readunlock = sched_perf_read_unlock,
- .started = rcu_batches_started_sched,
- .completed = rcu_batches_completed_sched,
+ .get_gp_seq = rcu_sched_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_sched,
.gp_barrier = rcu_barrier_sched,
.init = rcu_sync_perf_init,
.readlock = tasks_perf_read_lock,
.readunlock = tasks_perf_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
+ .gp_diff = rcu_seq_diff,
.async = call_rcu_tasks,
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
.name = "tasks"
};
-static bool __maybe_unused torturing_tasks(void)
+static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
{
- return cur_ops == &tasks_ops;
+ if (!cur_ops->gp_diff)
+ return new - old;
+ return cur_ops->gp_diff(new, old);
}
/*
b_rcu_perf_writer_started =
cur_ops->exp_completed() / 2;
} else {
- b_rcu_perf_writer_started =
- cur_ops->completed();
+ b_rcu_perf_writer_started = cur_ops->get_gp_seq();
}
}
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_finished =
- cur_ops->completed();
+ cur_ops->get_gp_seq();
}
if (shutdown) {
smp_mb(); /* Assign before wake. */
return 0;
}
-static inline void
+static void
rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
{
pr_alert("%s" PERF_FLAG
t_rcu_perf_writer_finished -
t_rcu_perf_writer_started,
ngps,
- b_rcu_perf_writer_finished -
- b_rcu_perf_writer_started);
+ rcuperf_seq_diff(b_rcu_perf_writer_finished,
+ b_rcu_perf_writer_started));
for (i = 0; i < nrealwriters; i++) {
if (!writer_durations)
break;
break;
}
if (i == ARRAY_SIZE(perf_ops)) {
- pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
- perf_type);
+ pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
pr_alert("rcu-perf types:");
for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
- pr_alert(" %s", perf_ops[i]->name);
- pr_alert("\n");
+ pr_cont(" %s", perf_ops[i]->name);
+ pr_cont("\n");
firsterr = -EINVAL;
goto unwind;
}
*
* See also: Documentation/RCU/torture.txt
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/torture.h>
#include <linux/vmalloc.h>
#include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
#include "rcu.h"
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
+/* Bits for ->extendables field, extendables param, and related definitions. */
+#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */
+#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */
+#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
+ RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */
+ /* Must be power of two minus one. */
+
torture_param(int, cbflood_inter_holdoff, HZ,
"Holdoff between floods (jiffies)");
torture_param(int, cbflood_intra_holdoff, 1,
torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
torture_param(int, cbflood_n_per_burst, 20000,
"# callbacks per burst in flood");
+torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
+ "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
torture_param(int, fqs_duration, 0,
"Duration of fqs bursts (us), 0 to disable");
torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
"Enable debug-object double call_rcu() testing");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0,
- "Time between CPU hotplugs (s), 0=disable");
+ "Time between CPU hotplugs (jiffies), 0=disable");
torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
"Interval between boost tests, seconds.");
torture_param(bool, test_no_idle_hz, true,
"Test support for tickless idle CPUs");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
"Enable verbose debugging printk()s");
static char *torture_type = "rcu";
static long n_rcu_torture_boost_rterror;
static long n_rcu_torture_boost_failure;
static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
+static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
-static long n_barrier_successes;
+static long n_barrier_successes; /* did rcu_barrier test succeed? */
static atomic_long_t n_cbfloods;
static struct list_head rcu_torture_removed;
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *rrsp);
void (*readunlock)(int idx);
- unsigned long (*started)(void);
- unsigned long (*completed)(void);
+ unsigned long (*get_gp_seq)(void);
+ unsigned long (*gp_diff)(unsigned long new, unsigned long old);
void (*deferred_free)(struct rcu_torture *p);
void (*sync)(void);
void (*exp_sync)(void);
void (*stats)(void);
int irq_capable;
int can_boost;
+ int extendables;
+ int ext_irq_conflict;
const char *name;
};
* force_quiescent_state. */
if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
- started = cur_ops->completed();
+ started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
mdelay(longdelay_ms);
- completed = cur_ops->completed();
+ completed = cur_ops->get_gp_seq();
do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
started, completed);
}
.readlock = rcu_torture_read_lock,
.read_delay = rcu_read_delay,
.readunlock = rcu_torture_read_unlock,
- .started = rcu_batches_started,
- .completed = rcu_batches_completed,
+ .get_gp_seq = rcu_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_torture_deferred_free,
.sync = synchronize_rcu,
.exp_sync = synchronize_rcu_expedited,
.readlock = rcu_bh_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = rcu_bh_torture_read_unlock,
- .started = rcu_batches_started_bh,
- .completed = rcu_batches_completed_bh,
+ .get_gp_seq = rcu_bh_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_bh_torture_deferred_free,
.sync = synchronize_rcu_bh,
.exp_sync = synchronize_rcu_bh_expedited,
.fqs = rcu_bh_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
+ .ext_irq_conflict = RCUTORTURE_RDR_RCU,
.name = "rcu_bh"
};
.readlock = rcu_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = rcu_torture_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
.deferred_free = rcu_busted_torture_deferred_free,
.sync = synchronize_rcu_busted,
.exp_sync = synchronize_rcu_busted,
.readlock = srcu_torture_read_lock,
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
- .started = NULL,
- .completed = srcu_torture_completed,
+ .get_gp_seq = srcu_torture_completed,
.deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
.exp_sync = srcu_torture_synchronize_expedited,
.readlock = srcu_torture_read_lock,
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
- .started = NULL,
- .completed = srcu_torture_completed,
+ .get_gp_seq = srcu_torture_completed,
.deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
.exp_sync = srcu_torture_synchronize_expedited,
.name = "srcud"
};
+/* As above, but broken due to inappropriate reader extension. */
+static struct rcu_torture_ops busted_srcud_ops = {
+ .ttype = SRCU_FLAVOR,
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = rcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .get_gp_seq = srcu_torture_completed,
+ .deferred_free = srcu_torture_deferred_free,
+ .sync = srcu_torture_synchronize,
+ .exp_sync = srcu_torture_synchronize_expedited,
+ .call = srcu_torture_call,
+ .cb_barrier = srcu_torture_barrier,
+ .stats = srcu_torture_stats,
+ .irq_capable = 1,
+ .extendables = RCUTORTURE_MAX_EXTEND,
+ .name = "busted_srcud"
+};
+
/*
* Definitions for sched torture testing.
*/
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .started = rcu_batches_started_sched,
- .completed = rcu_batches_completed_sched,
+ .get_gp_seq = rcu_sched_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
.deferred_free = rcu_sched_torture_deferred_free,
.sync = synchronize_sched,
.exp_sync = synchronize_sched_expedited,
.fqs = rcu_sched_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .extendables = RCUTORTURE_MAX_EXTEND,
.name = "sched"
};
.readlock = tasks_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = tasks_torture_read_unlock,
- .started = rcu_no_completed,
- .completed = rcu_no_completed,
+ .get_gp_seq = rcu_no_completed,
.deferred_free = rcu_tasks_torture_deferred_free,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
.name = "tasks"
};
+static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
+{
+ if (!cur_ops->gp_diff)
+ return new - old;
+ return cur_ops->gp_diff(new, old);
+}
+
static bool __maybe_unused torturing_tasks(void)
{
return cur_ops == &tasks_ops;
smp_store_release(&rbip->inflight, 0);
}
+static int old_rt_runtime = -1;
+
+static void rcu_torture_disable_rt_throttle(void)
+{
+ /*
+ * Disable RT throttling so that rcutorture's boost threads don't get
+ * throttled. Only possible if rcutorture is built-in otherwise the
+ * user should manually do this by setting the sched_rt_period_us and
+ * sched_rt_runtime sysctls.
+ */
+ if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1)
+ return;
+
+ old_rt_runtime = sysctl_sched_rt_runtime;
+ sysctl_sched_rt_runtime = -1;
+}
+
+static void rcu_torture_enable_rt_throttle(void)
+{
+ if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1)
+ return;
+
+ sysctl_sched_rt_runtime = old_rt_runtime;
+ old_rt_runtime = -1;
+}
+
+static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
+{
+ if (end - start > test_boost_duration * HZ - HZ / 2) {
+ VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+ n_rcu_torture_boost_failure++;
+
+ return true; /* failed */
+ }
+
+ return false; /* passed */
+}
+
static int rcu_torture_boost(void *arg)
{
unsigned long call_rcu_time;
init_rcu_head_on_stack(&rbi.rcu);
/* Each pass through the following loop does one boost-test cycle. */
do {
+ /* Track if the test failed already in this test interval? */
+ bool failed = false;
+
+ /* Increment n_rcu_torture_boosts once per boost-test */
+ while (!kthread_should_stop()) {
+ if (mutex_trylock(&boost_mutex)) {
+ n_rcu_torture_boosts++;
+ mutex_unlock(&boost_mutex);
+ break;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+ if (kthread_should_stop())
+ goto checkwait;
+
/* Wait for the next test interval. */
oldstarttime = boost_starttime;
while (ULONG_CMP_LT(jiffies, oldstarttime)) {
/* RCU core before ->inflight = 1. */
smp_store_release(&rbi.inflight, 1);
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
- if (jiffies - call_rcu_time >
- test_boost_duration * HZ - HZ / 2) {
- VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
- n_rcu_torture_boost_failure++;
- }
+ /* Check if the boost test failed */
+ failed = failed ||
+ rcu_torture_boost_failed(call_rcu_time,
+ jiffies);
call_rcu_time = jiffies;
}
stutter_wait("rcu_torture_boost");
goto checkwait;
}
+ /*
+ * If boost never happened, then inflight will always be 1, in
+ * this case the boost check would never happen in the above
+ * loop so do another one here.
+ */
+ if (!failed && smp_load_acquire(&rbi.inflight))
+ rcu_torture_boost_failed(call_rcu_time, jiffies);
+
/*
* Set the start time of the next test interval.
* Yes, this is vulnerable to long delays, but such
if (mutex_trylock(&boost_mutex)) {
boost_starttime = jiffies +
test_boost_interval * HZ;
- n_rcu_torture_boosts++;
mutex_unlock(&boost_mutex);
break;
}
break;
}
}
- rcutorture_record_progress(++rcu_torture_current_version);
+ rcu_torture_current_version++;
/* Cycle through nesting levels of rcu_expedite_gp() calls. */
if (can_expedite &&
!(torture_random(&rand) & 0xff & (!!expediting - 1))) {
}
/*
- * RCU torture reader from timer handler. Dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array. The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
+ * Do one extension of an RCU read-side critical section using the
+ * current reader state in readstate (set to zero for initial entry
+ * to extended critical section), set the new state as specified by
+ * newstate (set to zero for final exit from extended critical section),
+ * and random-number-generator state in trsp. If this is neither the
+ * beginning or end of the critical section and if there was actually a
+ * change, do a ->read_delay().
*/
-static void rcu_torture_timer(struct timer_list *unused)
+static void rcutorture_one_extend(int *readstate, int newstate,
+ struct torture_random_state *trsp)
+{
+ int idxnew = -1;
+ int idxold = *readstate;
+ int statesnew = ~*readstate & newstate;
+ int statesold = *readstate & ~newstate;
+
+ WARN_ON_ONCE(idxold < 0);
+ WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+
+ /* First, put new protection in place to avoid critical-section gap. */
+ if (statesnew & RCUTORTURE_RDR_BH)
+ local_bh_disable();
+ if (statesnew & RCUTORTURE_RDR_IRQ)
+ local_irq_disable();
+ if (statesnew & RCUTORTURE_RDR_PREEMPT)
+ preempt_disable();
+ if (statesnew & RCUTORTURE_RDR_RCU)
+ idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+
+ /* Next, remove old protection, irq first due to bh conflict. */
+ if (statesold & RCUTORTURE_RDR_IRQ)
+ local_irq_enable();
+ if (statesold & RCUTORTURE_RDR_BH)
+ local_bh_enable();
+ if (statesold & RCUTORTURE_RDR_PREEMPT)
+ preempt_enable();
+ if (statesold & RCUTORTURE_RDR_RCU)
+ cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+
+ /* Delay if neither beginning nor end and there was a change. */
+ if ((statesnew || statesold) && *readstate && newstate)
+ cur_ops->read_delay(trsp);
+
+ /* Update the reader state. */
+ if (idxnew == -1)
+ idxnew = idxold & ~RCUTORTURE_RDR_MASK;
+ WARN_ON_ONCE(idxnew < 0);
+ WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
+ *readstate = idxnew | newstate;
+ WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
+ WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+}
+
+/* Return the biggest extendables mask given current RCU and boot parameters. */
+static int rcutorture_extend_mask_max(void)
+{
+ int mask;
+
+ WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
+ mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
+ mask = mask | RCUTORTURE_RDR_RCU;
+ return mask;
+}
+
+/* Return a random protection state mask, but with at least one bit set. */
+static int
+rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
+{
+ int mask = rcutorture_extend_mask_max();
+ unsigned long randmask1 = torture_random(trsp) >> 8;
+ unsigned long randmask2 = randmask1 >> 1;
+
+ WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+ /* Half the time lots of bits, half the time only one bit. */
+ if (randmask1 & 0x1)
+ mask = mask & randmask2;
+ else
+ mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
+ if ((mask & RCUTORTURE_RDR_IRQ) &&
+ !(mask & RCUTORTURE_RDR_BH) &&
+ (oldmask & RCUTORTURE_RDR_BH))
+ mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+ if ((mask & RCUTORTURE_RDR_IRQ) &&
+ !(mask & cur_ops->ext_irq_conflict) &&
+ (oldmask & cur_ops->ext_irq_conflict))
+ mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
+ return mask ?: RCUTORTURE_RDR_RCU;
+}
+
+/*
+ * Do a randomly selected number of extensions of an existing RCU read-side
+ * critical section.
+ */
+static void rcutorture_loop_extend(int *readstate,
+ struct torture_random_state *trsp)
+{
+ int i;
+ int mask = rcutorture_extend_mask_max();
+
+ WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
+ if (!((mask - 1) & mask))
+ return; /* Current RCU flavor not extendable. */
+ i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
+ while (i--) {
+ mask = rcutorture_extend_mask(*readstate, trsp);
+ rcutorture_one_extend(readstate, mask, trsp);
+ }
+}
+
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read. Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp)
{
- int idx;
unsigned long started;
unsigned long completed;
- static DEFINE_TORTURE_RANDOM(rand);
- static DEFINE_SPINLOCK(rand_lock);
+ int newstate;
struct rcu_torture *p;
int pipe_count;
+ int readstate = 0;
unsigned long long ts;
- idx = cur_ops->readlock();
- if (cur_ops->started)
- started = cur_ops->started();
- else
- started = cur_ops->completed();
+ newstate = rcutorture_extend_mask(readstate, trsp);
+ rcutorture_one_extend(&readstate, newstate, trsp);
+ started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
srcu_read_lock_held(srcu_ctlp) ||
torturing_tasks());
if (p == NULL) {
- /* Leave because rcu_torture_writer is not yet underway */
- cur_ops->readunlock(idx);
- return;
+ /* Wait for rcu_torture_writer to get underway */
+ rcutorture_one_extend(&readstate, 0, trsp);
+ return false;
}
if (p->rtort_mbtest == 0)
atomic_inc(&n_rcu_torture_mberror);
- spin_lock(&rand_lock);
- cur_ops->read_delay(&rand);
- n_rcu_torture_timers++;
- spin_unlock(&rand_lock);
+ rcutorture_loop_extend(&readstate, trsp);
preempt_disable();
pipe_count = p->rtort_pipe_count;
if (pipe_count > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- completed = cur_ops->completed();
+ completed = cur_ops->get_gp_seq();
if (pipe_count > 1) {
- do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
- started, completed);
+ do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+ ts, started, completed);
rcu_ftrace_dump(DUMP_ALL);
}
__this_cpu_inc(rcu_torture_count[pipe_count]);
- completed = completed - started;
- if (cur_ops->started)
- completed++;
+ completed = rcutorture_seq_diff(completed, started);
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
__this_cpu_inc(rcu_torture_batch[completed]);
preempt_enable();
- cur_ops->readunlock(idx);
+ rcutorture_one_extend(&readstate, 0, trsp);
+ WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+ return true;
+}
+
+static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
+
+/*
+ * RCU torture reader from timer handler. Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array. The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(struct timer_list *unused)
+{
+ atomic_long_inc(&n_rcu_torture_timers);
+ (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand));
/* Test call_rcu() invocation from interrupt handler. */
if (cur_ops->call) {
static int
rcu_torture_reader(void *arg)
{
- unsigned long started;
- unsigned long completed;
- int idx;
DEFINE_TORTURE_RANDOM(rand);
- struct rcu_torture *p;
- int pipe_count;
struct timer_list t;
- unsigned long long ts;
VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
set_user_nice(current, MAX_NICE);
if (!timer_pending(&t))
mod_timer(&t, jiffies + 1);
}
- idx = cur_ops->readlock();
- if (cur_ops->started)
- started = cur_ops->started();
- else
- started = cur_ops->completed();
- ts = rcu_trace_clock_local();
- p = rcu_dereference_check(rcu_torture_current,
- rcu_read_lock_bh_held() ||
- rcu_read_lock_sched_held() ||
- srcu_read_lock_held(srcu_ctlp) ||
- torturing_tasks());
- if (p == NULL) {
- /* Wait for rcu_torture_writer to get underway */
- cur_ops->readunlock(idx);
+ if (!rcu_torture_one_read(&rand))
schedule_timeout_interruptible(HZ);
- continue;
- }
- if (p->rtort_mbtest == 0)
- atomic_inc(&n_rcu_torture_mberror);
- cur_ops->read_delay(&rand);
- preempt_disable();
- pipe_count = p->rtort_pipe_count;
- if (pipe_count > RCU_TORTURE_PIPE_LEN) {
- /* Should not happen, but... */
- pipe_count = RCU_TORTURE_PIPE_LEN;
- }
- completed = cur_ops->completed();
- if (pipe_count > 1) {
- do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
- ts, started, completed);
- rcu_ftrace_dump(DUMP_ALL);
- }
- __this_cpu_inc(rcu_torture_count[pipe_count]);
- completed = completed - started;
- if (cur_ops->started)
- completed++;
- if (completed > RCU_TORTURE_PIPE_LEN) {
- /* Should not happen, but... */
- completed = RCU_TORTURE_PIPE_LEN;
- }
- __this_cpu_inc(rcu_torture_batch[completed]);
- preempt_enable();
- cur_ops->readunlock(idx);
stutter_wait("rcu_torture_reader");
} while (!torture_must_stop());
if (irqreader && cur_ops->irq_capable) {
pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
- n_rcu_torture_timers);
+ atomic_long_read(&n_rcu_torture_timers));
torture_onoff_stats();
pr_cont("barrier: %ld/%ld:%ld ",
n_barrier_successes,
if (rtcv_snap == rcu_torture_current_version &&
rcu_torture_current != NULL) {
int __maybe_unused flags = 0;
- unsigned long __maybe_unused gpnum = 0;
- unsigned long __maybe_unused completed = 0;
+ unsigned long __maybe_unused gp_seq = 0;
rcutorture_get_gp_data(cur_ops->ttype,
- &flags, &gpnum, &completed);
+ &flags, &gp_seq);
srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
- &flags, &gpnum, &completed);
+ &flags, &gp_seq);
wtp = READ_ONCE(writer_task);
- pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
+ pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n",
rcu_torture_writer_state_getname(),
- rcu_torture_writer_state,
- gpnum, completed, flags,
+ rcu_torture_writer_state, gp_seq, flags,
wtp == NULL ? ~0UL : wtp->state,
wtp == NULL ? -1 : (int)task_cpu(wtp));
if (!splatted && wtp) {
return 0;
}
-static inline void
+static void
rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
{
pr_alert("%s" TORTURE_FLAG
mutex_lock(&boost_mutex);
t = boost_tasks[cpu];
boost_tasks[cpu] = NULL;
+ rcu_torture_enable_rt_throttle();
mutex_unlock(&boost_mutex);
/* This must be outside of the mutex, otherwise deadlock! */
/* Don't allow time recalculation while creating a new task. */
mutex_lock(&boost_mutex);
+ rcu_torture_disable_rt_throttle();
VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
cpu_to_node(cpu),
VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
}
if (!kthread_should_stop()) {
- stop_at = get_seconds() + stall_cpu;
+ stop_at = ktime_get_seconds() + stall_cpu;
/* RCU CPU stall is expected behavior in following code. */
rcu_read_lock();
if (stall_cpu_irqsoff)
preempt_disable();
pr_alert("rcu_torture_stall start on CPU %d.\n",
smp_processor_id());
- while (ULONG_CMP_LT(get_seconds(), stop_at))
+ while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
+ stop_at))
continue; /* Induce RCU CPU stall warning. */
if (stall_cpu_irqsoff)
local_irq_enable();
atomic_read(&barrier_cbs_invoked),
n_barrier_cbs);
WARN_ON_ONCE(1);
+ } else {
+ n_barrier_successes++;
}
- n_barrier_successes++;
schedule_timeout_interruptible(HZ / 10);
} while (!torture_must_stop());
torture_kthread_stopping("rcu_torture_barrier");
}
}
+static bool rcu_torture_can_boost(void)
+{
+ static int boost_warn_once;
+ int prio;
+
+ if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
+ return false;
+
+ prio = rcu_get_gp_kthreads_prio();
+ if (!prio)
+ return false;
+
+ if (prio < 2) {
+ if (boost_warn_once == 1)
+ return false;
+
+ pr_alert("%s: WARN: RCU kthread priority too low to test boosting. Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME);
+ boost_warn_once = 1;
+ return false;
+ }
+
+ return true;
+}
+
static enum cpuhp_state rcutor_hp;
static void
rcu_torture_cleanup(void)
{
int flags = 0;
- unsigned long gpnum = 0;
- unsigned long completed = 0;
+ unsigned long gp_seq = 0;
int i;
- rcutorture_record_test_transition();
if (torture_cleanup_begin()) {
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
fakewriter_tasks = NULL;
}
- rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
- srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
- &flags, &gpnum, &completed);
- pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n",
- cur_ops->name, gpnum, completed, flags);
+ rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+ pr_alert("%s: End-test grace-period state: g%lu f%#x\n",
+ cur_ops->name, gp_seq, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
for (i = 0; i < ncbflooders; i++)
torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
- if ((test_boost == 1 && cur_ops->can_boost) ||
- test_boost == 2)
+ if (rcu_torture_can_boost())
cpuhp_remove_state(rcutor_hp);
/*
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] = {
&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
- &sched_ops, &tasks_ops,
+ &busted_srcud_ops, &sched_ops, &tasks_ops,
};
if (!torture_init_begin(torture_type, verbose))
torture_type);
pr_alert("rcu-torture types:");
for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
- pr_alert(" %s", torture_ops[i]->name);
- pr_alert("\n");
+ pr_cont(" %s", torture_ops[i]->name);
+ pr_cont("\n");
firsterr = -EINVAL;
goto unwind;
}
test_boost_interval = 1;
if (test_boost_duration < 2)
test_boost_duration = 2;
- if ((test_boost == 1 && cur_ops->can_boost) ||
- test_boost == 2) {
+ if (rcu_torture_can_boost()) {
boost_starttime = jiffies + test_boost_interval * HZ;
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
if (firsterr)
goto unwind;
- firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+ firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
if (firsterr)
goto unwind;
firsterr = rcu_torture_stall_init();
goto unwind;
}
}
- rcutorture_record_test_transition();
torture_init_end();
return 0;
WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
if (!newval && READ_ONCE(sp->srcu_gp_waiting))
- swake_up(&sp->srcu_wq);
+ swake_up_one(&sp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
idx = sp->srcu_idx;
WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
- swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+ swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
/* Invoke the callbacks we removed above. */
*
*/
+#define pr_fmt(fmt) "rcu: " fmt
+
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
}
if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(sp))) {
- pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ pr_info("%s: Active srcu_struct %p state: %d\n",
+ __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
return; /* Caller forgot to stop doing call_srcu()? */
}
free_percpu(sp->sda);
* period s. Losers must either ensure that their desired grace-period
* number is recorded on at least their leaf srcu_node structure, or they
* must take steps to invoke their own callbacks.
+ *
+ * Note that this function also does the work of srcu_funnel_exp_start(),
+ * in some cases by directly invoking it.
*/
static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
unsigned long s, bool do_norm)
* more than one CPU, this means that when "func()" is invoked, each CPU
* is guaranteed to have executed a full memory barrier since the end of
* its last corresponding SRCU read-side critical section whose beginning
- * preceded the call to call_rcu(). It also means that each CPU executing
+ * preceded the call to call_srcu(). It also means that each CPU executing
* an SRCU read-side critical section that continues beyond the start of
- * "func()" must have executed a memory barrier after the call_rcu()
+ * "func()" must have executed a memory barrier after the call_srcu()
* but before the beginning of that SRCU read-side critical section.
* Note that these guarantees include CPUs that are offline, idle, or
* executing in user mode, as well as CPUs that are executing in the kernel.
*
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
* resulting SRCU callback function "func()", then both CPU A and CPU
* B are guaranteed to execute a full memory barrier during the time
- * interval between the call to call_rcu() and the invocation of "func()".
+ * interval between the call to call_srcu() and the invocation of "func()".
* This guarantee applies even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*
void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
- unsigned long *gpnum, unsigned long *completed)
+ unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *completed = rcu_seq_ctr(sp->srcu_gp_seq);
- *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+ *gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
unsigned long s0 = 0, s1 = 0;
idx = sp->srcu_idx & 0x1;
- pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+ pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
+ tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
- struct srcu_data *counts;
+ struct srcu_data *sdp;
- counts = per_cpu_ptr(sp->sda, cpu);
- u0 = counts->srcu_unlock_count[!idx];
- u1 = counts->srcu_unlock_count[idx];
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ u0 = sdp->srcu_unlock_count[!idx];
+ u1 = sdp->srcu_unlock_count[idx];
/*
* Make sure that a lock is always counted if the corresponding
*/
smp_rmb();
- l0 = counts->srcu_lock_count[!idx];
- l1 = counts->srcu_lock_count[idx];
+ l0 = sdp->srcu_lock_count[!idx];
+ l1 = sdp->srcu_lock_count[idx];
c0 = l0 - u0;
c1 = l1 - u1;
- pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+ pr_cont(" %d(%ld,%ld %1p)",
+ cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
s0 += c0;
s1 += c1;
}
{
if (user)
rcu_sched_qs();
- else if (!in_softirq())
+ if (user || !in_softirq())
rcu_bh_qs();
- if (user)
- rcu_note_voluntary_context_switch(current);
}
/*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
+
+#define pr_fmt(fmt) "rcu: " fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
.rda = &sname##_data, \
.call = cr, \
.gp_state = RCU_GP_IDLE, \
- .gpnum = 0UL - 300UL, \
- .completed = 0UL - 300UL, \
+ .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
.exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
.exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
+ .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
}
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
*/
static int rcu_scheduler_fully_active __read_mostly;
+static void
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
+/* Retreive RCU kthreads priority for rcutorture */
+int rcu_get_gp_kthreads_prio(void)
+{
+ return kthread_prio;
+}
+EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
+
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the delay, the more the grace periods between
*/
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
-/*
- * Track the rcutorture test sequence number and the update version
- * number within a given test. The rcutorture_testseq is incremented
- * on every rcutorture module load and unload, so has an odd value
- * when a test is running. The rcutorture_vernum is set to zero
- * when rcutorture starts and is incremented on each rcutorture update.
- * These variables enable correlating rcutorture output with the
- * RCU tracing information.
- */
-unsigned long rcutorture_testseq;
-unsigned long rcutorture_vernum;
-
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
- return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
+ return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
}
/*
if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
return;
trace_rcu_grace_period(TPS("rcu_sched"),
- __this_cpu_read(rcu_sched_data.gpnum),
+ __this_cpu_read(rcu_sched_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
trace_rcu_grace_period(TPS("rcu_bh"),
- __this_cpu_read(rcu_bh_data.gpnum),
+ __this_cpu_read(rcu_bh_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
}
return snap != rcu_dynticks_snap(rdtp);
}
-/*
- * Do a double-increment of the ->dynticks counter to emulate a
- * momentary idle-CPU quiescent state.
- */
-static void rcu_dynticks_momentary_idle(void)
-{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
- &rdtp->dynticks);
-
- /* It is illegal to call this from idle state. */
- WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
-}
-
/*
* Set the special (bottom) bit of the specified CPU so that it
* will take special action (such as flushing its TLB) on the
*
* We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts and must not be idle.
*/
static void rcu_momentary_dyntick_idle(void)
{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int special;
+
raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
- rcu_dynticks_momentary_idle();
+ special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ /* It is illegal to call this from idle state. */
+ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
}
/*
rcu_momentary_dyntick_idle();
this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
if (!preempt)
- rcu_note_voluntary_context_switch_lite(current);
+ rcu_tasks_qs(current);
out:
trace_rcu_utilization(TPS("End context switch"));
barrier(); /* Avoid RCU read-side critical sections leaking up. */
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
-module_param(jiffies_till_first_fqs, ulong, 0644);
-module_param(jiffies_till_next_fqs, ulong, 0644);
+static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+ ulong j;
+ int ret = kstrtoul(val, 0, &j);
+
+ if (!ret)
+ WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+ return ret;
+}
+
+static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+ ulong j;
+ int ret = kstrtoul(val, 0, &j);
+
+ if (!ret)
+ WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+ return ret;
+}
+
+static struct kernel_param_ops first_fqs_jiffies_ops = {
+ .set = param_set_first_fqs_jiffies,
+ .get = param_get_ulong,
+};
+
+static struct kernel_param_ops next_fqs_jiffies_ops = {
+ .set = param_set_next_fqs_jiffies,
+ .get = param_get_ulong,
+};
+
+module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
+module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
module_param(rcu_kick_kthreads, bool, 0644);
/*
static int rcu_pending(void);
/*
- * Return the number of RCU batches started thus far for debug & stats.
+ * Return the number of RCU GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started(void)
+unsigned long rcu_get_gp_seq(void)
{
- return rcu_state_p->gpnum;
+ return READ_ONCE(rcu_state_p->gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started);
+EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
/*
- * Return the number of RCU-sched batches started thus far for debug & stats.
+ * Return the number of RCU-sched GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started_sched(void)
+unsigned long rcu_sched_get_gp_seq(void)
{
- return rcu_sched_state.gpnum;
+ return READ_ONCE(rcu_sched_state.gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
/*
- * Return the number of RCU BH batches started thus far for debug & stats.
+ * Return the number of RCU-bh GPs completed thus far for debug & stats.
*/
-unsigned long rcu_batches_started_bh(void)
+unsigned long rcu_bh_get_gp_seq(void)
{
- return rcu_bh_state.gpnum;
+ return READ_ONCE(rcu_bh_state.gp_seq);
}
-EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
-
-/*
- * Return the number of RCU batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
- return rcu_state_p->completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU-sched batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_sched(void)
-{
- return rcu_sched_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
-/*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_bh(void)
-{
- return rcu_bh_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
/*
* Return the number of RCU expedited batches completed thus far for
*/
void show_rcu_gp_kthreads(void)
{
+ int cpu;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
pr_info("%s: wait state: %d ->state: %#lx\n",
rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
+ continue;
+ pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+ rnp->grplo, rnp->grphi, rnp->gp_seq,
+ rnp->gp_seq_needed);
+ if (!rcu_is_leaf_node(rnp))
+ continue;
+ for_each_leaf_node_possible_cpu(rnp, cpu) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ if (rdp->gpwrap ||
+ ULONG_CMP_GE(rsp->gp_seq,
+ rdp->gp_seq_needed))
+ continue;
+ pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+ cpu, rdp->gp_seq_needed);
+ }
+ }
/* sched_show_task(rsp->gp_kthread); */
}
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
-/*
- * Record the number of times rcutorture tests have been initiated and
- * terminated. This information allows the debugfs tracing stats to be
- * correlated to the rcutorture messages, even when the rcutorture module
- * is being repeatedly loaded and unloaded. In other words, we cannot
- * store this state in rcutorture itself.
- */
-void rcutorture_record_test_transition(void)
-{
- rcutorture_testseq++;
- rcutorture_vernum = 0;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
-
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
- unsigned long *gpnum, unsigned long *completed)
+ unsigned long *gp_seq)
{
struct rcu_state *rsp = NULL;
if (rsp == NULL)
return;
*flags = READ_ONCE(rsp->gp_flags);
- *gpnum = READ_ONCE(rsp->gpnum);
- *completed = READ_ONCE(rsp->completed);
+ *gp_seq = rcu_seq_current(&rsp->gp_seq);
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
-/*
- * Record the number of writer passes through the current rcutorture test.
- * This is also used to correlate debugfs tracing stats with the rcutorture
- * messages.
- */
-void rcutorture_record_progress(unsigned long vernum)
-{
- rcutorture_vernum++;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-
/*
* Return the root node of the specified rcu_state structure.
*/
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
- * Is the current CPU online? Disable preemption to avoid false positives
- * that could otherwise happen due to the current CPU number being sampled,
- * this task being preempted, its old CPU being taken offline, resuming
- * on some other CPU, then determining that its old CPU is now offline.
- * It is OK to use RCU on an offline processor during initial boot, hence
- * the check for rcu_scheduler_fully_active. Note also that it is OK
- * for a CPU coming online to use RCU for one jiffy prior to marking itself
- * online in the cpu_online_mask. Similarly, it is OK for a CPU going
- * offline to continue to use RCU for one jiffy after marking itself
- * offline in the cpu_online_mask. This leniency is necessary given the
- * non-atomic nature of the online and offline processing, for example,
- * the fact that a CPU enters the scheduler after completing the teardown
- * of the CPU.
+ * Is the current CPU online as far as RCU is concerned?
*
- * This is also why RCU internally marks CPUs online during in the
- * preparation phase and offline after the CPU has been taken down.
+ * Disable preemption to avoid false positives that could otherwise
+ * happen due to the current CPU number being sampled, this task being
+ * preempted, its old CPU being taken offline, resuming on some other CPU,
+ * then determining that its old CPU is now offline. Because there are
+ * multiple flavors of RCU, and because this function can be called in the
+ * midst of updating the flavors while a given CPU coming online or going
+ * offline, it is necessary to check all flavors. If any of the flavors
+ * believe that given CPU is online, it is considered to be online.
*
- * Disable checking if in an NMI handler because we cannot safely report
- * errors from NMI handlers anyway.
+ * Disable checking if in an NMI handler because we cannot safely
+ * report errors from NMI handlers anyway. In addition, it is OK to use
+ * RCU on an offline processor during initial boot, hence the check for
+ * rcu_scheduler_fully_active.
*/
bool rcu_lockdep_current_cpu_online(void)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
- bool ret;
+ struct rcu_state *rsp;
- if (in_nmi())
+ if (in_nmi() || !rcu_scheduler_fully_active)
return true;
preempt_disable();
- rdp = this_cpu_ptr(&rcu_sched_data);
- rnp = rdp->mynode;
- ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
- !rcu_scheduler_fully_active;
+ for_each_rcu_flavor(rsp) {
+ rdp = this_cpu_ptr(rsp->rda);
+ rnp = rdp->mynode;
+ if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
+ preempt_enable();
+ return true;
+ }
+ }
preempt_enable();
- return ret;
+ return false;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
/*
* We are reporting a quiescent state on behalf of some other CPU, so
* it is our responsibility to check for and handle potential overflow
- * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
* After all, the CPU might be in deep idle state, and thus executing no
* code whatsoever.
*/
static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rnp);
- if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+ if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
+ rnp->gp_seq))
WRITE_ONCE(rdp->gpwrap, true);
- if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
- rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+ if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
+ rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
}
/*
{
rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
return 1;
}
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp);
if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
- rdp->rcu_iw_gpnum = rnp->gpnum;
+ rdp->rcu_iw_gp_seq = rnp->gp_seq;
rdp->rcu_iw_pending = false;
}
raw_spin_unlock_rcu_node(rnp);
* of the current RCU grace period.
*/
if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rdp->dynticks_fqs++;
rcu_gpnum_ovf(rnp, rdp);
return 1;
ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
- READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+ rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
+ trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
rcu_gpnum_ovf(rnp, rdp);
return 1;
} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
smp_store_release(ruqp, true);
}
- /* Check for the CPU being offline. */
- if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
- rdp->offline_fqs++;
- rcu_gpnum_ovf(rnp, rdp);
- return 1;
+ /* If waiting too long on an offline CPU, complain. */
+ if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+ time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+ bool onl;
+ struct rcu_node *rnp1;
+
+ WARN_ON(1); /* Offline CPUs are supposed to report QS! */
+ pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+ __func__, rnp->grplo, rnp->grphi, rnp->level,
+ (long)rnp->gp_seq, (long)rnp->completedqs);
+ for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+ pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+ __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+ onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+ pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+ __func__, rdp->cpu, ".o"[onl],
+ (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+ (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+ return 1; /* Break things loose after complaining. */
}
/*
if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
resched_cpu(rdp->cpu);
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
- !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+ !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
rdp->rcu_iw_pending = true;
- rdp->rcu_iw_gpnum = rnp->gpnum;
+ rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
}
}
unsigned long j1;
rsp->gp_start = j;
- smp_wmb(); /* Record start time before stall time. */
j1 = rcu_jiffies_till_stall_check();
- WRITE_ONCE(rsp->jiffies_stall, j + j1);
+ /* Record ->gp_start before ->jiffies_stall. */
+ smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
rsp->jiffies_resched = j + j1 / 2;
rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
}
j = jiffies;
gpa = READ_ONCE(rsp->gp_activity);
if (j - gpa > 2 * HZ) {
- pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+ pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rsp->name, j - gpa,
- rsp->gpnum, rsp->completed,
+ (long)rcu_seq_current(&rsp->gp_seq),
rsp->gp_flags,
gp_state_getname(rsp->gp_state), rsp->gp_state,
rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
}
}
-static inline void panic_on_rcu_stall(void)
+static void panic_on_rcu_stall(void)
{
if (sysctl_panic_on_rcu_stall)
panic("RCU Stall\n");
}
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
{
int cpu;
- long delta;
unsigned long flags;
unsigned long gpa;
unsigned long j;
if (rcu_cpu_stall_suppress)
return;
- /* Only let one CPU complain about others per time interval. */
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- delta = jiffies - READ_ONCE(rsp->jiffies_stall);
- if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- WRITE_ONCE(rsp->jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
/*
* OK, time to rat on our buddy...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
- pr_err("INFO: %s detected stalls on CPUs/tasks:",
- rsp->name);
+ pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
print_cpu_stall_info_begin();
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
for_each_possible_cpu(cpu)
totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
cpu)->cblist);
- pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
+ pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
- (long)rsp->gpnum, (long)rsp->completed, totqlen);
+ (long)rcu_seq_current(&rsp->gp_seq), totqlen);
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
/* Complain about tasks blocking the grace period. */
rcu_print_detail_task_stall(rsp);
} else {
- if (READ_ONCE(rsp->gpnum) != gpnum ||
- READ_ONCE(rsp->completed) == gpnum) {
+ if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
sched_show_task(current);
}
}
+ /* Rewrite if needed in case of slow consoles. */
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
rcu_check_gp_kthread_starvation(rsp);
for_each_possible_cpu(cpu)
totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
cpu)->cblist);
- pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+ pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rsp->gp_start,
- (long)rsp->gpnum, (long)rsp->completed, totqlen);
+ (long)rcu_seq_current(&rsp->gp_seq), totqlen);
rcu_check_gp_kthread_starvation(rsp);
rcu_dump_cpu_stacks(rsp);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ /* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
WRITE_ONCE(rsp->jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
- unsigned long completed;
- unsigned long gpnum;
+ unsigned long gs1;
+ unsigned long gs2;
unsigned long gps;
unsigned long j;
+ unsigned long jn;
unsigned long js;
struct rcu_node *rnp;
/*
* Lots of memory barriers to reject false positives.
*
- * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
- * then rsp->gp_start, and finally rsp->completed. These values
- * are updated in the opposite order with memory barriers (or
- * equivalent) during grace-period initialization and cleanup.
- * Now, a false positive can occur if we get an new value of
- * rsp->gp_start and a old value of rsp->jiffies_stall. But given
- * the memory barriers, the only way that this can happen is if one
- * grace period ends and another starts between these two fetches.
- * Detect this by comparing rsp->completed with the previous fetch
- * from rsp->gpnum.
+ * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
+ * then rsp->gp_start, and finally another copy of rsp->gp_seq.
+ * These values are updated in the opposite order with memory
+ * barriers (or equivalent) during grace-period initialization
+ * and cleanup. Now, a false positive can occur if we get an new
+ * value of rsp->gp_start and a old value of rsp->jiffies_stall.
+ * But given the memory barriers, the only way that this can happen
+ * is if one grace period ends and another starts between these
+ * two fetches. This is detected by comparing the second fetch
+ * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
*
* Given this check, comparisons of jiffies, rsp->jiffies_stall,
* and rsp->gp_start suffice to forestall false positives.
*/
- gpnum = READ_ONCE(rsp->gpnum);
- smp_rmb(); /* Pick up ->gpnum first... */
+ gs1 = READ_ONCE(rsp->gp_seq);
+ smp_rmb(); /* Pick up ->gp_seq first... */
js = READ_ONCE(rsp->jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
gps = READ_ONCE(rsp->gp_start);
- smp_rmb(); /* ...and finally ->gp_start before ->completed. */
- completed = READ_ONCE(rsp->completed);
- if (ULONG_CMP_GE(completed, gpnum) ||
+ smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+ gs2 = READ_ONCE(rsp->gp_seq);
+ if (gs1 != gs2 ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
+ jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
if (rcu_gp_in_progress(rsp) &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+ (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+ cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
} else if (rcu_gp_in_progress(rsp) &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+ ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+ cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
/* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(rsp, gpnum);
+ print_other_cpu_stall(rsp, gs2);
}
}
WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
-/*
- * Determine the value that ->completed will have at the end of the
- * next subsequent grace period. This is used to tag callbacks so that
- * a CPU can invoke callbacks in a timely fashion even if that CPU has
- * been dyntick-idle for an extended period with callbacks under the
- * influence of RCU_FAST_NO_HZ.
- *
- * The caller must hold rnp->lock with interrupts disabled.
- */
-static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
- struct rcu_node *rnp)
-{
- raw_lockdep_assert_held_rcu_node(rnp);
-
- /*
- * If RCU is idle, we just wait for the next grace period.
- * But we can only be sure that RCU is idle if we are looking
- * at the root rcu_node structure -- otherwise, a new grace
- * period might have started, but just not yet gotten around
- * to initializing the current non-root rcu_node structure.
- */
- if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
- return rnp->completed + 1;
-
- /*
- * If the current rcu_node structure believes that RCU is
- * idle, and if the rcu_state structure does not yet reflect
- * the start of a new grace period, then the next grace period
- * will suffice. The memory barrier is needed to accurately
- * sample the rsp->gpnum, and pairs with the second lock
- * acquisition in rcu_gp_init(), which is augmented with
- * smp_mb__after_unlock_lock() for this purpose.
- */
- if (rnp->gpnum == rnp->completed) {
- smp_mb(); /* See above block comment. */
- if (READ_ONCE(rsp->gpnum) == rnp->completed)
- return rnp->completed + 1;
- }
-
- /*
- * Otherwise, wait for a possible partial grace period and
- * then the subsequent full grace period.
- */
- return rnp->completed + 2;
-}
-
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c, const char *s)
+ unsigned long gp_seq_req, const char *s)
{
- trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
- rnp->completed, c, rnp->level,
- rnp->grplo, rnp->grphi, s);
+ trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
+ rnp->level, rnp->grplo, rnp->grphi, s);
}
/*
+ * rcu_start_this_gp - Request the start of a particular grace period
+ * @rnp_start: The leaf node of the CPU from which to start.
+ * @rdp: The rcu_data corresponding to the CPU from which to start.
+ * @gp_seq_req: The gp_seq of the grace period to start.
+ *
* Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp[] field. Returns true if there
+ * rcu_node structure's ->gp_seq_needed field. Returns true if there
* is reason to awaken the grace-period kthread.
*
* The caller must hold the specified rcu_node structure's ->lock, which
* is why the caller is responsible for waking the grace-period kthread.
+ *
+ * Returns true if the GP thread needs to be awakened else false.
*/
-static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c)
+static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
+ unsigned long gp_seq_req)
{
bool ret = false;
struct rcu_state *rsp = rdp->rsp;
- struct rcu_node *rnp_root;
+ struct rcu_node *rnp;
/*
* Use funnel locking to either acquire the root rcu_node
* structure's lock or bail out if the need for this grace period
- * has already been recorded -- or has already started. If there
- * is already a grace period in progress in a non-leaf node, no
- * recording is needed because the end of the grace period will
- * scan the leaf rcu_node structures. Note that rnp->lock must
- * not be released.
+ * has already been recorded -- or if that grace period has in
+ * fact already started. If there is already a grace period in
+ * progress in a non-leaf node, no recording is needed because the
+ * end of the grace period will scan the leaf rcu_node structures.
+ * Note that rnp_start->lock must not be released.
*/
- raw_lockdep_assert_held_rcu_node(rnp);
- trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
- for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
- if (rnp_root != rnp)
- raw_spin_lock_rcu_node(rnp_root);
- WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
- need_future_gp_mask(), c));
- if (need_future_gp_element(rnp_root, c) ||
- ULONG_CMP_GE(rnp_root->gpnum, c) ||
- (rnp != rnp_root &&
- rnp_root->gpnum != rnp_root->completed)) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+ raw_lockdep_assert_held_rcu_node(rnp_start);
+ trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
+ for (rnp = rnp_start; 1; rnp = rnp->parent) {
+ if (rnp != rnp_start)
+ raw_spin_lock_rcu_node(rnp);
+ if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
+ rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
+ (rnp != rnp_start &&
+ rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+ TPS("Prestarted"));
goto unlock_out;
}
- need_future_gp_element(rnp_root, c) = true;
- if (rnp_root != rnp && rnp_root->parent != NULL)
- raw_spin_unlock_rcu_node(rnp_root);
- if (!rnp_root->parent)
+ rnp->gp_seq_needed = gp_seq_req;
+ if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+ /*
+ * We just marked the leaf or internal node, and a
+ * grace period is in progress, which means that
+ * rcu_gp_cleanup() will see the marking. Bail to
+ * reduce contention.
+ */
+ trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
+ TPS("Startedleaf"));
+ goto unlock_out;
+ }
+ if (rnp != rnp_start && rnp->parent != NULL)
+ raw_spin_unlock_rcu_node(rnp);
+ if (!rnp->parent)
break; /* At root, and perhaps also leaf. */
}
/* If GP already in progress, just leave, otherwise start one. */
- if (rnp_root->gpnum != rnp_root->completed) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
+ if (rcu_gp_in_progress(rsp)) {
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
goto unlock_out;
}
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+ rsp->gp_req_activity = jiffies;
if (!rsp->gp_kthread) {
- trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+ trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
- if (rnp != rnp_root)
- raw_spin_unlock_rcu_node(rnp_root);
+ /* Push furthest requested GP to leaf node and rcu_data structure. */
+ if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
+ rnp_start->gp_seq_needed = rnp->gp_seq_needed;
+ rdp->gp_seq_needed = rnp->gp_seq_needed;
+ }
+ if (rnp != rnp_start)
+ raw_spin_unlock_rcu_node(rnp);
return ret;
}
*/
static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
- unsigned long c = rnp->completed;
bool needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- need_future_gp_element(rnp, c) = false;
- needmore = need_any_future_gp(rnp);
- trace_rcu_this_gp(rnp, rdp, c,
+ needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
+ if (!needmore)
+ rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
+ trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
!READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
- swake_up(&rsp->gp_wq);
+ swake_up_one(&rsp->gp_wq);
}
/*
- * If there is room, assign a ->completed number to any callbacks on
- * this CPU that have not already been assigned. Also accelerate any
- * callbacks that were previously assigned a ->completed number that has
- * since proven to be too conservative, which can happen if callbacks get
- * assigned a ->completed number while RCU is idle, but with reference to
- * a non-root rcu_node structure. This function is idempotent, so it does
- * not hurt to call it repeatedly. Returns an flag saying that we should
- * awaken the RCU grace-period kthread.
+ * If there is room, assign a ->gp_seq number to any callbacks on this
+ * CPU that have not already been assigned. Also accelerate any callbacks
+ * that were previously assigned a ->gp_seq number that has since proven
+ * to be too conservative, which can happen if callbacks get assigned a
+ * ->gp_seq number while RCU is idle, but with reference to a non-root
+ * rcu_node structure. This function is idempotent, so it does not hurt
+ * to call it repeatedly. Returns an flag saying that we should awaken
+ * the RCU grace-period kthread.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- unsigned long c;
+ unsigned long gp_seq_req;
bool ret = false;
raw_lockdep_assert_held_rcu_node(rnp);
* accelerating callback invocation to an earlier grace-period
* number.
*/
- c = rcu_cbs_completed(rsp, rnp);
- if (rcu_segcblist_accelerate(&rdp->cblist, c))
- ret = rcu_start_this_gp(rnp, rdp, c);
+ gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+ if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
+ ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
else
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
return ret;
}
+/*
+ * Similar to rcu_accelerate_cbs(), but does not require that the leaf
+ * rcu_node structure's ->lock be held. It consults the cached value
+ * of ->gp_seq_needed in the rcu_data structure, and if that indicates
+ * that a new grace-period request be made, invokes rcu_accelerate_cbs()
+ * while holding the leaf rcu_node structure's ->lock.
+ */
+static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ unsigned long c;
+ bool needwake;
+
+ lockdep_assert_irqs_disabled();
+ c = rcu_seq_snap(&rsp->gp_seq);
+ if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ /* Old request still live, so mark recent callbacks. */
+ (void)rcu_segcblist_accelerate(&rdp->cblist, c);
+ return;
+ }
+ raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
+}
+
/*
* Move any callbacks whose grace period has completed to the
* RCU_DONE_TAIL sublist, then compact the remaining sublists and
- * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
* sublist. This function is idempotent, so it does not hurt to
* invoke it repeatedly. As long as it is not invoked -too- often...
* Returns true if the RCU grace-period kthread needs to be awakened.
return false;
/*
- * Find all callbacks whose ->completed numbers indicate that they
+ * Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
- rcu_segcblist_advance(&rdp->cblist, rnp->completed);
+ rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rsp, rnp, rdp);
raw_lockdep_assert_held_rcu_node(rnp);
- /* Handle the ends of any preceding grace periods first. */
- if (rdp->completed == rnp->completed &&
- !unlikely(READ_ONCE(rdp->gpwrap))) {
-
- /* No grace period end, so just accelerate recent callbacks. */
- ret = rcu_accelerate_cbs(rsp, rnp, rdp);
+ if (rdp->gp_seq == rnp->gp_seq)
+ return false; /* Nothing to do. */
+ /* Handle the ends of any preceding grace periods first. */
+ if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
+ unlikely(READ_ONCE(rdp->gpwrap))) {
+ ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
} else {
-
- /* Advance callbacks. */
- ret = rcu_advance_cbs(rsp, rnp, rdp);
-
- /* Remember that we saw this grace-period completion. */
- rdp->completed = rnp->completed;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
+ ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
}
- if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
+ /* Now handle the beginnings of any new-to-this-CPU grace periods. */
+ if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
+ unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
- rdp->gpnum = rnp->gpnum;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
+ trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
need_gp = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_gp;
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
rdp->core_needs_qs = need_gp;
zero_cpu_stall_ticks(rdp);
- WRITE_ONCE(rdp->gpwrap, false);
- rcu_gpnum_ovf(rnp, rdp);
}
+ rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
+ if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+ rdp->gp_seq_needed = rnp->gp_seq_needed;
+ WRITE_ONCE(rdp->gpwrap, false);
+ rcu_gpnum_ovf(rnp, rdp);
return ret;
}
local_irq_save(flags);
rnp = rdp->mynode;
- if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
- rdp->completed == READ_ONCE(rnp->completed) &&
+ if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
!unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
local_irq_restore(flags);
static void rcu_gp_slow(struct rcu_state *rsp, int delay)
{
if (delay > 0 &&
- !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+ !(rcu_seq_ctr(rsp->gp_seq) %
+ (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_uninterruptible(delay);
}
*/
static bool rcu_gp_init(struct rcu_state *rsp)
{
+ unsigned long flags;
unsigned long oldmask;
+ unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time(rsp);
- /* Record GP times before starting GP, hence smp_store_release(). */
- smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
- trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
+ /* Record GP times before starting GP, hence rcu_seq_start(). */
+ rcu_seq_start(&rsp->gp_seq);
+ trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
* for subsequent online CPUs, and that quiescent-state forcing
* will handle subsequent offline CPUs.
*/
+ rsp->gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rsp, rnp) {
- rcu_gp_slow(rsp, gp_preinit_delay);
+ spin_lock(&rsp->ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq_rcu_node(rnp);
+ spin_unlock(&rsp->ofl_lock);
continue;
}
/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
if (!oldmask != !rnp->qsmaskinit) {
- if (!oldmask) /* First online CPU for this rcu_node. */
- rcu_init_new_rnp(rnp);
- else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
- rnp->wait_blkd_tasks = true;
- else /* Last offline CPU and can propagate. */
+ if (!oldmask) { /* First online CPU for rcu_node. */
+ if (!rnp->wait_blkd_tasks) /* Ever offline? */
+ rcu_init_new_rnp(rnp);
+ } else if (rcu_preempt_has_tasks(rnp)) {
+ rnp->wait_blkd_tasks = true; /* blocked tasks */
+ } else { /* Last offline CPU and can propagate. */
rcu_cleanup_dead_rnp(rnp);
+ }
}
/*
* still offline, propagate up the rcu_node tree and
* clear ->wait_blkd_tasks. Otherwise, if one of this
* rcu_node structure's CPUs has since come back online,
- * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
- * checks for this, so just call it unconditionally).
+ * simply clear ->wait_blkd_tasks.
*/
if (rnp->wait_blkd_tasks &&
- (!rcu_preempt_has_tasks(rnp) ||
- rnp->qsmaskinit)) {
+ (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
rnp->wait_blkd_tasks = false;
- rcu_cleanup_dead_rnp(rnp);
+ if (!rnp->qsmaskinit)
+ rcu_cleanup_dead_rnp(rnp);
}
raw_spin_unlock_irq_rcu_node(rnp);
+ spin_unlock(&rsp->ofl_lock);
}
+ rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
/*
* Set the quiescent-state-needed bits in all the rcu_node
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
+ rsp->gp_state = RCU_GP_INIT;
rcu_for_each_node_breadth_first(rsp, rnp) {
rcu_gp_slow(rsp, gp_init_delay);
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_preempt_check_blocked_tasks(rnp);
+ rcu_preempt_check_blocked_tasks(rsp, rnp);
rnp->qsmask = rnp->qsmaskinit;
- WRITE_ONCE(rnp->gpnum, rsp->gpnum);
- if (WARN_ON_ONCE(rnp->completed != rsp->completed))
- WRITE_ONCE(rnp->completed, rsp->completed);
+ WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
- trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+ trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
- raw_spin_unlock_irq_rcu_node(rnp);
+ /* Quiescent states for tasks on any now-offline CPUs. */
+ mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+ rnp->rcu_gp_init_mask = mask;
+ if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ else
+ raw_spin_unlock_irq_rcu_node(rnp);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
}
}
/*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
* time.
*/
static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
{
unsigned long gp_duration;
bool needgp = false;
+ unsigned long new_gp_seq;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
struct swait_queue_head *sq;
raw_spin_unlock_irq_rcu_node(rnp);
/*
- * Propagate new ->completed value to rcu_node structures so
- * that other CPUs don't have to wait until the start of the next
- * grace period to process their callbacks. This also avoids
- * some nasty RCU grace-period initialization races by forcing
- * the end of the current grace period to be completely recorded in
- * all of the rcu_node structures before the beginning of the next
- * grace period is recorded in any of the rcu_node structures.
+ * Propagate new ->gp_seq value to rcu_node structures so that
+ * other CPUs don't have to wait until the start of the next grace
+ * period to process their callbacks. This also avoids some nasty
+ * RCU grace-period initialization races by forcing the end of
+ * the current grace period to be completely recorded in all of
+ * the rcu_node structures before the beginning of the next grace
+ * period is recorded in any of the rcu_node structures.
*/
+ new_gp_seq = rsp->gp_seq;
+ rcu_seq_end(&new_gp_seq);
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq_rcu_node(rnp);
- WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+ if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+ dump_blkd_tasks(rsp, rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
- WRITE_ONCE(rnp->completed, rsp->gpnum);
+ WRITE_ONCE(rnp->gp_seq, new_gp_seq);
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
- raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
+ raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
/* Declare grace period done. */
- WRITE_ONCE(rsp->completed, rsp->gpnum);
- trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
+ rcu_seq_end(&rsp->gp_seq);
+ trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
rsp->gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(rsp->rda);
- if (need_any_future_gp(rnp)) {
- trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+ if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
+ trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
TPS("CleanupMore"));
needgp = true;
}
/* Advance CBs to reduce false positives below. */
if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
+ rsp->gp_req_activity = jiffies;
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
TPS("newreq"));
+ } else {
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
}
- WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
raw_spin_unlock_irq_rcu_node(rnp);
}
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("reqwait"));
rsp->gp_state = RCU_GP_WAIT_GPS;
- swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+ swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
rsp->gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
first_gp_fqs = true;
j = jiffies_till_first_fqs;
- if (j > HZ) {
- j = HZ;
- jiffies_till_first_fqs = HZ;
- }
ret = 0;
for (;;) {
if (!ret) {
jiffies + 3 * j);
}
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
- ret = swait_event_idle_timeout(rsp->gp_wq,
+ ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
rcu_gp_fqs_check_wake(rsp, &gf), j);
rsp->gp_state = RCU_GP_DOING_FQS;
/* Locking provides needed memory barriers. */
if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqsstart"));
rcu_gp_fqs(rsp, first_gp_fqs);
first_gp_fqs = false;
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqsend"));
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = jiffies_till_next_fqs;
- if (j > HZ) {
- j = HZ;
- jiffies_till_next_fqs = HZ;
- } else if (j < 1) {
- j = 1;
- jiffies_till_next_fqs = 1;
- }
} else {
/* Deal with stray signal. */
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gp_seq),
TPS("fqswaitsig"));
ret = 1; /* Keep old FQS timing. */
j = jiffies;
* must be represented by the same rcu_node structure (which need not be a
* leaf rcu_node structure, though it often will be). The gps parameter
* is the grace-period snapshot, which means that the quiescent states
- * are valid only if rnp->gpnum is equal to gps. That structure's lock
+ * are valid only if rnp->gp_seq is equal to gps. That structure's lock
* must be held upon entry, and it is released before return.
+ *
+ * As a special case, if mask is zero, the bit-already-cleared check is
+ * disabled. This allows propagating quiescent state due to resumed tasks
+ * during grace-period initialization.
*/
static void
rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
/* Walk up the rcu_node hierarchy. */
for (;;) {
- if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
+ if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
/*
* Our bit has already been cleared, or the
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
rnp->qsmask &= ~mask;
- trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
+ trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
!!rnp->gp_tasks);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
+ rnp->completedqs = rnp->gp_seq;
mask = rnp->grpmask;
if (rnp->parent == NULL) {
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
-static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long flags)
+static void __maybe_unused
+rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
- if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
- rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+ if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
+ WARN_ON_ONCE(rsp != rcu_state_p) ||
+ WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
+ rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return; /* Still need more quiescent states! */
}
+ rnp->completedqs = rnp->gp_seq;
rnp_p = rnp->parent;
if (rnp_p == NULL) {
/*
return;
}
- /* Report up the rest of the hierarchy, tracking current ->gpnum. */
- gps = rnp->gpnum;
+ /* Report up the rest of the hierarchy, tracking current ->gp_seq. */
+ gps = rnp->gp_seq;
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
- rnp->completed == rnp->gpnum || rdp->gpwrap) {
+ if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
+ rdp->gpwrap) {
/*
* The grace period in which this quiescent state was
*/
needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
rcu_gp_kthread_wake(rsp);
*/
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
- RCU_TRACE(unsigned long mask;)
+ RCU_TRACE(bool blkd;)
RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
- RCU_TRACE(mask = rdp->grpmask;)
- trace_rcu_grace_period(rsp->name,
- rnp->gpnum + 1 - !!(rnp->qsmask & mask),
- TPS("cpuofl"));
+ RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
+ trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+ blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
}
/*
* This function therefore goes up the tree of rcu_node structures,
* clearing the corresponding bits in the ->qsmaskinit fields. Note that
* the leaf rcu_node structure's ->qsmaskinit field has already been
- * updated
+ * updated.
*
* This function does check that the specified rcu_node structure has
* all CPUs offline and no blocked tasks, so it is OK to invoke it
long mask;
struct rcu_node *rnp = rnp_leaf;
- raw_lockdep_assert_held_rcu_node(rnp);
+ raw_lockdep_assert_held_rcu_node(rnp_leaf);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
- rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+ WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
+ WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
return;
for (;;) {
mask = rnp->grpmask;
break;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
- rnp->qsmask &= ~mask;
+ /* Between grace periods, so better already be zero! */
+ WARN_ON_ONCE(rnp->qsmask);
if (rnp->qsmaskinit) {
raw_spin_unlock_rcu_node(rnp);
/* irqs remain disabled. */
rcu_sched_qs();
rcu_bh_qs();
+ rcu_note_voluntary_context_switch(current);
} else if (!in_softirq()) {
rcu_preempt_check_callbacks();
if (rcu_pending())
invoke_rcu_core();
- if (user)
- rcu_note_voluntary_context_switch(current);
+
trace_rcu_utilization(TPS("End scheduler-tick"));
}
/* rcu_initiate_boost() releases rnp->lock */
continue;
}
- if (rnp->parent &&
- (rnp->parent->qsmask & rnp->grpmask)) {
- /*
- * Race between grace-period
- * initialization and task exiting RCU
- * read-side critical section: Report.
- */
- rcu_report_unblock_qs_rnp(rsp, rnp, flags);
- /* rcu_report_unblock_qs_rnp() rlses ->lock */
- continue;
- }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ continue;
}
for_each_leaf_node_possible_cpu(rnp, cpu) {
unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
}
}
if (mask != 0) {
- /* Idle/offline CPUs, report (releases rnp->lock. */
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+ /* Idle/offline CPUs, report (releases rnp->lock). */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_gp_kthread_wake(rsp);
}
+/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void
+rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
+ unsigned long flags;
+ unsigned long j;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+ static atomic_t warned = ATOMIC_INIT(0);
+
+ if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+ return;
+ j = jiffies; /* Expensive access, and in common case don't get here. */
+ if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+ atomic_read(&warned))
+ return;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ j = jiffies;
+ if (rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+ atomic_read(&warned)) {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ /* Hold onto the leaf lock to make others see warned==1. */
+
+ if (rnp_root != rnp)
+ raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+ j = jiffies;
+ if (rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, rsp->gp_req_activity + gpssdelay) ||
+ time_before(j, rsp->gp_activity + gpssdelay) ||
+ atomic_xchg(&warned, 1)) {
+ raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
+ __func__, (long)READ_ONCE(rsp->gp_seq),
+ (long)READ_ONCE(rnp_root->gp_seq_needed),
+ j - rsp->gp_req_activity, j - rsp->gp_activity,
+ rsp->gp_flags, rsp->gp_state, rsp->name,
+ rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
+ WARN_ON(1);
+ if (rnp_root != rnp)
+ raw_spin_unlock_rcu_node(rnp_root);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
/*
* This does the RCU core processing work for the specified rcu_state
* and rcu_data structures. This may be called only from the CPU to
__rcu_process_callbacks(struct rcu_state *rsp)
{
unsigned long flags;
- bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
- struct rcu_node *rnp;
+ struct rcu_node *rnp = rdp->mynode;
WARN_ON_ONCE(!rdp->beenonline);
if (!rcu_gp_in_progress(rsp) &&
rcu_segcblist_is_enabled(&rdp->cblist)) {
local_irq_save(flags);
- if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
- local_irq_restore(flags);
- } else {
- rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
- }
+ if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+ rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
+ local_irq_restore(flags);
}
+ rcu_check_gp_start_stall(rsp, rnp, rdp);
+
/* If there are callbacks ready, invoke them. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_callbacks(rsp, rdp);
static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_head *head, unsigned long flags)
{
- bool needwake;
-
/*
* If called from an extended quiescent state, invoke the RCU
* core in order to force a re-evaluation of RCU's idleness.
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
- struct rcu_node *rnp = rdp->mynode;
-
- raw_spin_lock_rcu_node(rnp);
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
- raw_spin_unlock_rcu_node(rnp);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
} else {
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
* when there was in fact only one the whole time, as this just adds
* some overhead: RCU still operates correctly.
*/
-static inline int rcu_blocking_is_gp(void)
+static int rcu_blocking_is_gp(void)
{
int ret;
{
/*
* Any prior manipulation of RCU-protected data must happen
- * before the load from ->gpnum.
+ * before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
-
- /*
- * Make sure this load happens before the purportedly
- * time-consuming work between get_state_synchronize_rcu()
- * and cond_synchronize_rcu().
- */
- return smp_load_acquire(&rcu_state_p->gpnum);
+ return rcu_seq_snap(&rcu_state_p->gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
- unsigned long newstate;
-
- /*
- * Ensure that this load happens before any RCU-destructive
- * actions the caller might carry out after we return.
- */
- newstate = smp_load_acquire(&rcu_state_p->completed);
- if (ULONG_CMP_GE(oldstate, newstate))
+ if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
synchronize_rcu();
+ else
+ smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
{
/*
* Any prior manipulation of RCU-protected data must happen
- * before the load from ->gpnum.
+ * before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
-
- /*
- * Make sure this load happens before the purportedly
- * time-consuming work between get_state_synchronize_sched()
- * and cond_synchronize_sched().
- */
- return smp_load_acquire(&rcu_sched_state.gpnum);
+ return rcu_seq_snap(&rcu_sched_state.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
*/
void cond_synchronize_sched(unsigned long oldstate)
{
- unsigned long newstate;
-
- /*
- * Ensure that this load happens before any RCU-destructive
- * actions the caller might carry out after we return.
- */
- newstate = smp_load_acquire(&rcu_sched_state.completed);
- if (ULONG_CMP_GE(oldstate, newstate))
+ if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
synchronize_sched();
+ else
+ smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_sched);
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
- /* Has another RCU grace period completed? */
- if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
- return 1;
-
- /* Has a new RCU grace period started? */
- if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+ /* Have RCU grace period completed or started? */
+ if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
return 1;
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
-static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
{
long mask;
+ long oldmask;
struct rcu_node *rnp = rnp_leaf;
- raw_lockdep_assert_held_rcu_node(rnp);
+ raw_lockdep_assert_held_rcu_node(rnp_leaf);
+ WARN_ON_ONCE(rnp->wait_blkd_tasks);
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (rnp == NULL)
return;
raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
+ oldmask = rnp->qsmaskinit;
rnp->qsmaskinit |= mask;
raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
+ if (oldmask)
+ return;
}
}
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+ rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+ rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+ rdp->rcu_onl_gp_seq = rsp->gp_seq;
+ rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
/*
* Initialize a CPU's per-CPU RCU data. Note that only one online or
- * offline event can be happening at a given time. Note also that we
- * can accept some slop in the rsp->completed access due to the fact
- * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ * offline event can be happening at a given time. Note also that we can
+ * accept some slop in the rsp->gp_seq access due to the fact that this
+ * CPU cannot possibly have any RCU callbacks in flight yet.
*/
static void
rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
- rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
- rdp->completed = rnp->completed;
+ rdp->gp_seq = rnp->gp_seq;
+ rdp->gp_seq_needed = rnp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
- rdp->rcu_iw_gpnum = rnp->gpnum - 1;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+ rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+ trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
/* Allow lockless access for expedited grace periods. */
smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+ rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+ /* Report QS -after- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ } else {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
}
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function. We now remove it from the rcu_node tree's ->qsmaskinit
+ * function. We now remove it from the rcu_node tree's ->qsmaskinitnext
* bit masks.
*/
static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
+ spin_lock(&rsp->ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+ rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+ /* Report quiescent state -before- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ }
rnp->qsmaskinitnext &= ~mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ spin_unlock(&rsp->ofl_lock);
}
/*
struct task_struct *t;
/* Force priority into range. */
- if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
+ && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
+ kthread_prio = 2;
+ else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
kthread_prio = 1;
else if (kthread_prio < 0)
kthread_prio = 0;
else if (kthread_prio > 99)
kthread_prio = 99;
+
if (kthread_prio != kthread_prio_in)
pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
kthread_prio, kthread_prio_in);
raw_spin_lock_init(&rnp->fqslock);
lockdep_set_class_and_name(&rnp->fqslock,
&rcu_fqs_class[i], fqs[i]);
- rnp->gpnum = rsp->gpnum;
- rnp->completed = rsp->completed;
+ rnp->gp_seq = rsp->gp_seq;
+ rnp->gp_seq_needed = rsp->gp_seq;
+ rnp->completedqs = rsp->gp_seq;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
- pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
+ pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
rcu_fanout_leaf, nr_cpu_ids);
/*
raw_spinlock_t __private lock; /* Root rcu_node's lock protects */
/* some rcu_state fields as well as */
/* following. */
- unsigned long gpnum; /* Current grace period for this node. */
- /* This will either be equal to or one */
- /* behind the root rcu_node's gpnum. */
- unsigned long completed; /* Last GP completed for this node. */
- /* This will either be equal to or one */
- /* behind the root rcu_node's gpnum. */
+ unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
+ unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+ unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
+ unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask. */
/* Initialized from ->qsmaskinitnext at the */
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- u8 need_future_gp[4]; /* Counts of upcoming GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
bool exp_need_flush; /* Need to flush workitem? */
} ____cacheline_internodealigned_in_smp;
-/* Accessors for ->need_future_gp[] array. */
-#define need_future_gp_mask() \
- (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
-#define need_future_gp_element(rnp, c) \
- ((rnp)->need_future_gp[(c) & need_future_gp_mask()])
-#define need_any_future_gp(rnp) \
-({ \
- int __i; \
- bool __nonzero = false; \
- \
- for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \
- __nonzero = __nonzero || \
- READ_ONCE((rnp)->need_future_gp[__i]); \
- __nonzero; \
-})
-
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
- unsigned long completed; /* Track rsp->completed gp number */
- /* in order to detect GP end. */
- unsigned long gpnum; /* Highest gp number that this CPU */
- /* is aware of having started. */
+ unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
+ unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */
unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
/* for rcu_all_qs() invocations. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
- bool gpwrap; /* Possible gpnum/completed wrap. */
+ bool gpwrap; /* Possible ->gp_seq wrap. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
unsigned long ticks_this_gp; /* The number of scheduling-clock */
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
- unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long cond_resched_completed;
/* Grace period that needs help */
/* from cond_resched(). */
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- /* 7) RCU CPU stall data. */
+ /* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
bool rcu_iw_pending; /* Is ->rcu_iw pending? */
- unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */
+ unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */
+ unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */
+ short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */
+ unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */
+ short rcu_onl_gp_flags; /* ->gp_flags at last online. */
int cpu;
struct rcu_state *rsp;
u8 boost ____cacheline_internodealigned_in_smp;
/* Subject to priority boost. */
- unsigned long gpnum; /* Current gp number. */
- unsigned long completed; /* # of last completed gp. */
+ unsigned long gp_seq; /* Grace-period sequence #. */
struct task_struct *gp_kthread; /* Task for grace periods. */
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
/* but in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
+ unsigned long gp_req_activity; /* Time of last GP request */
+ /* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
struct list_head flavors; /* List of RCU flavors. */
+
+ spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+ /* Synchronize offline with */
+ /* GP pre-initialization. */
};
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */
#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */
#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */
-#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */
-#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */
-#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */
-#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */
+#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */
+#define RCU_GP_INIT 4 /* Grace-period initialization. */
+#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */
+#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */
#ifndef RCU_TREE_NONCORE
static const char * const gp_state_names[] = {
"RCU_GP_IDLE",
"RCU_GP_WAIT_GPS",
"RCU_GP_DONE_GPS",
+ "RCU_GP_ONOFF",
+ "RCU_GP_INIT",
"RCU_GP_WAIT_FQS",
"RCU_GP_DOING_FQS",
"RCU_GP_CLEANUP",
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp);
static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+ int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (wake) {
smp_mb(); /* EGP done before wake_up(). */
- swake_up(&rsp->expedited_wq);
+ swake_up_one(&rsp->expedited_wq);
}
break;
}
static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
smp_call_func_t func)
{
+ int cpu;
struct rcu_node *rnp;
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
rnp->rew.rew_func = func;
rnp->rew.rew_rsp = rsp;
if (!READ_ONCE(rcu_par_gp_wq) ||
- rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
- /* No workqueues yet. */
+ rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+ rcu_is_last_leaf_node(rsp, rnp)) {
+ /* No workqueues yet or last leaf, do direct call. */
sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
- queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+ preempt_disable();
+ cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+ /* If all offline, queue the work on an unbound CPU. */
+ if (unlikely(cpu > rnp->grphi))
+ cpu = WORK_CPU_UNBOUND;
+ queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+ preempt_enable();
rnp->exp_need_flush = true;
}
jiffies_start = jiffies;
for (;;) {
- ret = swait_event_timeout(
+ ret = swait_event_timeout_exclusive(
rsp->expedited_wq,
sync_rcu_preempt_exp_done_unlocked(rnp_root),
jiffies_stall);
pr_info("\tRCU event tracing is enabled.\n");
if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
(!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
- pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
- RCU_FANOUT);
+ pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n",
+ RCU_FANOUT);
if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
RCU_FANOUT_LEAF);
if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
- pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+ pr_info("\tBoot-time adjustment of leaf fanout to %d.\n",
+ rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_RCU_BOOST
- pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY);
+ pr_info("\tRCU priority boosting: priority %d delay %d ms.\n",
+ kthread_prio, CONFIG_RCU_BOOST_DELAY);
#endif
if (blimit != DEFAULT_RCU_BLIMIT)
pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit);
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake);
+static void rcu_read_unlock_special(struct task_struct *t);
/*
* Tell them what RCU they are running.
raw_lockdep_assert_held_rcu_node(rnp);
WARN_ON_ONCE(rdp->mynode != rnp);
WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
+ /* RCU better not be waiting on newly onlined CPUs! */
+ WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask &
+ rdp->grpmask);
/*
* Decide where to queue the newly blocked task. In theory,
* ->exp_tasks pointers, respectively, to reference the newly
* blocked tasks.
*/
- if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
rnp->gp_tasks = &t->rcu_node_entry;
+ WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
+ }
if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
rnp->exp_tasks = &t->rcu_node_entry;
WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
}
/*
- * Record a preemptible-RCU quiescent state for the specified CPU. Note
- * that this just means that the task currently running on the CPU is
- * not in a quiescent state. There might be any number of tasks blocked
- * while in an RCU read-side critical section.
+ * Record a preemptible-RCU quiescent state for the specified CPU.
+ * Note that this does not necessarily mean that the task currently running
+ * on the CPU is in a quiescent state: Instead, it means that the current
+ * grace period need not wait on any RCU read-side critical section that
+ * starts later on this CPU. It also means that if the current task is
+ * in an RCU read-side critical section, it has already added itself to
+ * some leaf rcu_node structure's ->blkd_tasks list. In addition to the
+ * current task, there might be any number of other tasks blocked while
+ * in an RCU read-side critical section.
*
- * As with the other rcu_*_qs() functions, callers to this function
- * must disable preemption.
+ * Callers to this function must disable preemption.
*/
static void rcu_preempt_qs(void)
{
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n");
if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
- __this_cpu_read(rcu_data_p->gpnum),
+ __this_cpu_read(rcu_data_p->gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
trace_rcu_preempt_task(rdp->rsp->name,
t->pid,
(rnp->qsmask & rdp->grpmask)
- ? rnp->gpnum
- : rnp->gpnum + 1);
+ ? rnp->gp_seq
+ : rcu_seq_snap(&rnp->gp_seq));
rcu_preempt_ctxt_queue(rnp, rdp);
} else if (t->rcu_read_lock_nesting < 0 &&
t->rcu_read_unlock_special.s) {
* notify RCU core processing or task having blocked during the RCU
* read-side critical section.
*/
-void rcu_read_unlock_special(struct task_struct *t)
+static void rcu_read_unlock_special(struct task_struct *t)
{
bool empty_exp;
bool empty_norm;
WARN_ON_ONCE(rnp != t->rcu_blocked_node);
WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+ WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
+ (!empty_norm || rnp->qsmask));
empty_exp = sync_rcu_preempt_exp_done(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
np = rcu_next_node_entry(t, rnp);
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
- rnp->gpnum, t->pid);
+ rnp->gp_seq, t->pid);
if (&t->rcu_node_entry == rnp->gp_tasks)
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
empty_exp_now = sync_rcu_preempt_exp_done(rnp);
if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
- rnp->gpnum,
+ rnp->gp_seq,
0, rnp->qsmask,
rnp->level,
rnp->grplo,
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
* period that still has RCU readers blocked! This function must be
- * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
* must be held by the caller.
*
* Also, if there are blocked tasks on the list, they automatically
* block the newly created grace period, so set up ->gp_tasks accordingly.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
struct task_struct *t;
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
- WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
- if (rcu_preempt_has_tasks(rnp)) {
+ if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+ dump_blkd_tasks(rsp, rnp, 10);
+ if (rcu_preempt_has_tasks(rnp) &&
+ (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
rnp->gp_tasks = rnp->blkd_tasks.next;
t = container_of(rnp->gp_tasks, struct task_struct,
rcu_node_entry);
trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
- rnp->gpnum, t->pid);
+ rnp->gp_seq, t->pid);
}
WARN_ON_ONCE(rnp->qsmask);
}
*/
static void rcu_preempt_check_callbacks(void)
{
+ struct rcu_state *rsp = &rcu_preempt_state;
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
}
if (t->rcu_read_lock_nesting > 0 &&
__this_cpu_read(rcu_data_p->core_needs_qs) &&
- __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
+ __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) &&
+ !t->rcu_read_unlock_special.b.need_qs &&
+ time_after(jiffies, rsp->gp_start + HZ))
t->rcu_read_unlock_special.b.need_qs = true;
}
__rcu_read_unlock();
}
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+ int cpu;
+ int i;
+ struct list_head *lhp;
+ bool onl;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp1;
+
+ raw_lockdep_assert_held_rcu_node(rnp);
+ pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+ __func__, rnp->grplo, rnp->grphi, rnp->level,
+ (long)rnp->gp_seq, (long)rnp->completedqs);
+ for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+ pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+ __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
+ pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
+ __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+ pr_info("%s: ->blkd_tasks", __func__);
+ i = 0;
+ list_for_each(lhp, &rnp->blkd_tasks) {
+ pr_cont(" %p", lhp);
+ if (++i >= 10)
+ break;
+ }
+ pr_cont("\n");
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+ pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+ cpu, ".o"[onl],
+ (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+ (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+ }
+}
+
#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *const rcu_state_p = &rcu_sched_state;
* so there is no need to check for blocked tasks. So check only for
* bogus qsmask values.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
WARN_ON_ONCE(rnp->qsmask);
}
{
}
+/*
+ * Dump the guaranteed-empty blocked-tasks state. Trust but verify.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+ WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
* completed since we last checked and there are
* callbacks not yet ready to invoke.
*/
- if ((rdp->completed != rnp->completed ||
+ if ((rcu_seq_completed_gp(rdp->gp_seq,
+ rcu_seq_current(&rnp->gp_seq)) ||
unlikely(READ_ONCE(rdp->gpwrap))) &&
rcu_segcblist_pend_cbs(&rdp->cblist))
note_gp_changes(rsp, rdp);
*/
touch_nmi_watchdog();
- if (rsp->gpnum == rdp->gpnum) {
+ ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq);
+ if (ticks_value) {
+ ticks_title = "GPs behind";
+ } else {
ticks_title = "ticks this GP";
ticks_value = rdp->ticks_this_gp;
- } else {
- ticks_title = "GPs behind";
- ticks_value = rsp->gpnum - rdp->gpnum;
}
print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
- delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
- pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
+ delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+ pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
- return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+ return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1];
}
static void rcu_init_one_nocb(struct rcu_node *rnp)
WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
del_timer(&rdp->nocb_timer);
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
- smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
- swake_up(&rdp_leader->nocb_wq);
+ smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+ swake_up_one(&rdp_leader->nocb_wq);
} else {
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
}
bool needwake;
struct rcu_node *rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- c = rcu_cbs_completed(rdp->rsp, rnp);
- needwake = rcu_start_this_gp(rnp, rdp, c);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (needwake)
- rcu_gp_kthread_wake(rdp->rsp);
+ local_irq_save(flags);
+ c = rcu_seq_snap(&rdp->rsp->gp_seq);
+ if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ local_irq_restore(flags);
+ } else {
+ raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+ needwake = rcu_start_this_gp(rnp, rdp, c);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rdp->rsp);
+ }
/*
* Wait for the grace period. Do so interruptibly to avoid messing
*/
trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
for (;;) {
- swait_event_interruptible(
- rnp->nocb_gp_wq[c & 0x1],
- (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
+ swait_event_interruptible_exclusive(
+ rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
+ (d = rcu_seq_done(&rnp->gp_seq, c)));
if (likely(d))
break;
WARN_ON(signal_pending(current));
/* Wait for callbacks to appear. */
if (!rcu_nocb_poll) {
trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
- swait_event_interruptible(my_rdp->nocb_wq,
+ swait_event_interruptible_exclusive(my_rdp->nocb_wq,
!READ_ONCE(my_rdp->nocb_leader_sleep));
raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
my_rdp->nocb_leader_sleep = true;
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
/* List was empty, so wake up the follower. */
- swake_up(&rdp->nocb_wq);
+ swake_up_one(&rdp->nocb_wq);
}
}
{
for (;;) {
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
- swait_event_interruptible(rdp->nocb_wq,
+ swait_event_interruptible_exclusive(rdp->nocb_wq,
READ_ONCE(rdp->nocb_follower_head));
if (smp_load_acquire(&rdp->nocb_follower_head)) {
/* ^^^ Ensure CB invocation follows _head test. */
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
-/*
- * An adaptive-ticks CPU can potentially execute in kernel mode for an
- * arbitrarily long period of time with the scheduling-clock tick turned
- * off. RCU will be paying attention to this CPU because it is in the
- * kernel, but the CPU cannot be guaranteed to be executing the RCU state
- * machine because the scheduling-clock tick has been disabled. Therefore,
- * if an adaptive-ticks CPU is failing to respond to the current grace
- * period and has not be idle from an RCU perspective, kick it.
- */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
- if (tick_nohz_full_cpu(cpu))
- smp_send_reschedule(cpu);
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
-}
-
/*
* Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
* grace-period kthread will do force_quiescent_state() processing?
*/
static void rcu_bind_gp_kthread(void)
{
- int __maybe_unused cpu;
-
if (!tick_nohz_full_enabled())
return;
housekeeping_affine(current, HK_FLAG_RCU);
#ifdef CONFIG_TASKS_RCU
/*
- * Simple variant of RCU whose quiescent states are voluntary context switch,
- * user-space execution, and idle. As such, grace periods can take one good
- * long time. There are no read-side primitives similar to rcu_read_lock()
- * and rcu_read_unlock() because this implementation is intended to get
- * the system into a safe state for some of the manipulations involved in
- * tracing and the like. Finally, this implementation does not support
- * high call_rcu_tasks() rates from multiple CPUs. If this is required,
- * per-CPU callback lists will be needed.
+ * Simple variant of RCU whose quiescent states are voluntary context
+ * switch, cond_resched_rcu_qs(), user-space execution, and idle.
+ * As such, grace periods can take one good long time. There are no
+ * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+ * because this implementation is intended to get the system into a safe
+ * state for some of the manipulations involved in tracing and the like.
+ * Finally, this implementation does not support high call_rcu_tasks()
+ * rates from multiple CPUs. If this is required, per-CPU callback lists
+ * will be needed.
*/
/* Global list of callbacks and associated lock. */
* period elapses, in other words after all currently executing RCU
* read-side critical sections have completed. call_rcu_tasks() assumes
* that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), entry into idle, or transition to usermode
- * execution. As such, there are no read-side primitives analogous to
- * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
- * to determine that all tasks have passed through a safe state, not so
- * much for data-strcuture synchronization.
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution. As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
*
* See the description of call_rcu() for more detailed information on
* memory ordering guarantees.
struct rcu_head *list;
struct rcu_head *next;
LIST_HEAD(rcu_tasks_holdouts);
+ int fract;
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_FLAG_RCU);
* holdouts. When the list is empty, we are done.
*/
lastreport = jiffies;
- while (!list_empty(&rcu_tasks_holdouts)) {
+
+ /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
+ fract = 10;
+
+ for (;;) {
bool firstreport;
bool needreport;
int rtst;
struct task_struct *t1;
- schedule_timeout_interruptible(HZ);
+ if (list_empty(&rcu_tasks_holdouts))
+ break;
+
+ /* Slowly back off waiting for holdouts */
+ schedule_timeout_interruptible(HZ/fract);
+
+ if (fract > 1)
+ fract--;
+
rtst = READ_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 &&
time_after(jiffies, lastreport + rtst);
list = next;
cond_resched();
}
+ /* Paranoid sleep to keep this from entering a tight loop */
schedule_timeout_uninterruptible(HZ/10);
}
}
/*
* fault() vm_op implementation for relay file mapping.
*/
-static int relay_buf_fault(struct vm_fault *vmf)
+static vm_fault_t relay_buf_fault(struct vm_fault *vmf)
{
struct page *page;
struct rchan_buf *buf = vmf->vma->vm_private_data;
{
u32 cpu_id = raw_smp_processor_id();
- if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id, &t->rseq->cpu_id_start))
return -EFAULT;
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
trace_rseq_update(t);
return 0;
/*
* Reset cpu_id_start to its initial state (0).
*/
- if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
return -EFAULT;
/*
* Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
* in after unregistration can figure out that rseq needs to be
* registered again.
*/
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
return 0;
}
static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
{
struct rseq_cs __user *urseq_cs;
- unsigned long ptr;
+ u64 ptr;
u32 __user *usig;
u32 sig;
int ret;
- ret = __get_user(ptr, &t->rseq->rseq_cs);
- if (ret)
- return ret;
+ if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+ return -EFAULT;
if (!ptr) {
memset(rseq_cs, 0, sizeof(*rseq_cs));
return 0;
}
- urseq_cs = (struct rseq_cs __user *)ptr;
+ if (ptr >= TASK_SIZE)
+ return -EINVAL;
+ urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
return -EFAULT;
- if (rseq_cs->version > 0)
- return -EINVAL;
+ if (rseq_cs->start_ip >= TASK_SIZE ||
+ rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+ rseq_cs->abort_ip >= TASK_SIZE ||
+ rseq_cs->version > 0)
+ return -EINVAL;
+ /* Check for overflow. */
+ if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+ return -EINVAL;
/* Ensure that abort_ip is not in the critical section. */
if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
return -EINVAL;
- usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+ usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
ret = get_user(sig, usig);
if (ret)
return ret;
printk_ratelimited(KERN_WARNING
"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
sig, current->rseq_sig, current->pid, usig);
- return -EPERM;
+ return -EINVAL;
}
return 0;
}
int ret;
/* Get thread flags. */
- ret = __get_user(flags, &t->rseq->flags);
+ ret = get_user(flags, &t->rseq->flags);
if (ret)
return ret;
* of code outside of the rseq assembly block. This performs
* a lazy clear of the rseq_cs field.
*
- * Set rseq_cs to NULL with single-copy atomicity.
+ * Set rseq_cs to NULL.
*/
- return __put_user(0UL, &t->rseq->rseq_cs);
+ if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+ return -EFAULT;
+ return 0;
}
/*
* respect to other threads scheduled on the same CPU, and with respect
* to signal handlers.
*/
-void __rseq_handle_notify_resume(struct pt_regs *regs)
+void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
{
struct task_struct *t = current;
- int ret;
+ int ret, sig;
if (unlikely(t->flags & PF_EXITING))
return;
return;
error:
- force_sig(SIGSEGV, t);
+ sig = ksig ? ksig->sig : 0;
+ force_sigsegv(sig, t);
}
#ifdef CONFIG_DEBUG_RSEQ
obj-y += idle.o fair.o rt.o deadline.o
obj-y += wait.o wait_bit.o swait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
*
*/
#include "sched.h"
+#include <linux/sched_clock.h>
/*
* Scheduler clock - returns current time in nanosec units.
}
EXPORT_SYMBOL_GPL(sched_clock);
-__read_mostly int sched_clock_running;
-
-void sched_clock_init(void)
-{
- sched_clock_running = 1;
-}
+static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
/*
smp_mb(); /* matches sched_clock_init_late() */
- if (sched_clock_running == 2)
+ if (static_key_count(&sched_clock_running.key) == 2)
__clear_sched_clock_stable();
}
+static void __sched_clock_gtod_offset(void)
+{
+ struct sched_clock_data *scd = this_scd();
+
+ __scd_stamp(scd);
+ __gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
+}
+
+void __init sched_clock_init(void)
+{
+ /*
+ * Set __gtod_offset such that once we mark sched_clock_running,
+ * sched_clock_tick() continues where sched_clock() left off.
+ *
+ * Even if TSC is buggered, we're still UP at this point so it
+ * can't really be out of sync.
+ */
+ local_irq_disable();
+ __sched_clock_gtod_offset();
+ local_irq_enable();
+
+ static_branch_inc(&sched_clock_running);
+}
/*
* We run this as late_initcall() such that it runs after all built-in drivers,
* notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
*/
static int __init sched_clock_init_late(void)
{
- sched_clock_running = 2;
+ static_branch_inc(&sched_clock_running);
/*
* Ensure that it is impossible to not do a static_key update.
*
if (sched_clock_stable())
return sched_clock() + __sched_clock_offset;
- if (unlikely(!sched_clock_running))
- return 0ull;
+ if (!static_branch_unlikely(&sched_clock_running))
+ return sched_clock();
preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (sched_clock_stable())
return;
- if (unlikely(!sched_clock_running))
+ if (!static_branch_unlikely(&sched_clock_running))
return;
lockdep_assert_irqs_disabled();
void sched_clock_tick_stable(void)
{
- u64 gtod, clock;
-
if (!sched_clock_stable())
return;
* TSC to be unstable, any computation will be computing crap.
*/
local_irq_disable();
- gtod = ktime_get_ns();
- clock = sched_clock();
- __gtod_offset = (clock + __sched_clock_offset) - gtod;
+ __sched_clock_gtod_offset();
local_irq_enable();
}
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+void __init sched_clock_init(void)
+{
+ static_branch_inc(&sched_clock_running);
+ local_irq_disable();
+ generic_sched_clock_init();
+ local_irq_enable();
+}
+
u64 sched_clock_cpu(int cpu)
{
- if (unlikely(!sched_clock_running))
+ if (!static_branch_unlikely(&sched_clock_running))
return 0;
return sched_clock();
*
* See also complete_all(), wait_for_completion() and related routines.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void complete(struct completion *x)
{
*
* This will wake up all threads waiting on this particular completion event.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*
* Since complete_all() sets the completion of @x permanently to done
* to allow multiple waiters to finish, a call to reinit_completion()
*/
#include "sched.h"
-#include <linux/kthread.h>
#include <linux/nospec.h>
+#include <linux/kcov.h>
+
#include <asm/switch_to.h>
#include <asm/tlb.h>
#include "../workqueue_internal.h"
#include "../smpboot.h"
+#include "pelt.h"
+
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
*/
const_debug unsigned int sysctl_sched_nr_migrate = 32;
-/*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
/*
* period over which we measure -rt task CPU usage in us.
* default: 1s
rq->clock_task += delta;
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
- sched_rt_avg_update(rq, irq_delta + steal);
+ update_irq_load_avg(rq, irq_delta + steal);
#endif
}
* its already queued (either by us or someone else) and will get the
* wakeup due to that.
*
- * This cmpxchg() implies a full barrier, which pairs with the write
- * barrier implied by the wakeup in wake_up_q().
+ * This cmpxchg() executes a full barrier, which pairs with the full
+ * barrier executed by the wakeup in wake_up_q().
*/
if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
return;
task->wake_q.next = NULL;
/*
- * wake_up_process() implies a wmb() to pair with the queueing
- * in wake_q_add() so as not to miss wakeups.
+ * wake_up_process() executes a full barrier, which pairs with
+ * the queueing in wake_q_add() so as not to miss wakeups.
*/
wake_up_process(task);
put_task_struct(task);
return true;
}
#endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
- s64 period = sched_avg_period();
-
- while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
- /*
- * Inline assembly required to prevent the compiler
- * optimising this loop into a divmod call.
- * See __iter_div_u64_rem() for another example of this.
- */
- asm("" : "+rm" (rq->age_stamp));
- rq->age_stamp += period;
- rq->rt_avg /= 2;
- }
-}
-
#endif /* CONFIG_SMP */
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
__set_task_cpu(p, new_cpu);
}
+#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
if (task_on_rq_queued(p)) {
/*
* Cross migrate two tasks
*/
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+ int target_cpu, int curr_cpu)
{
struct migration_swap_arg arg;
int ret = -EINVAL;
arg = (struct migration_swap_arg){
.src_task = cur,
- .src_cpu = task_cpu(cur),
+ .src_cpu = curr_cpu,
.dst_task = p,
- .dst_cpu = task_cpu(p),
+ .dst_cpu = target_cpu,
};
if (arg.src_cpu == arg.dst_cpu)
out:
return ret;
}
+#endif /* CONFIG_NUMA_BALANCING */
/*
* wait_task_inactive - wait for a thread to unschedule.
* rq(c1)->lock (if not at the same time, then in that order).
* C) LOCK of the rq(c1)->lock scheduling in task
*
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
* Note: the CPU doing B need not be c0 or c1
*
* Example:
* UNLOCK rq(0)->lock
*
*
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
*/
/**
* Atomic against schedule() which would dequeue a task, also see
* set_current_state().
*
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
* be possible to, falsely, observe p->on_rq == 0 and get stuck
* in smp_cond_load_acquire() below.
*
- * sched_ttwu_pending() try_to_wake_up()
- * [S] p->on_rq = 1; [L] P->state
- * UNLOCK rq->lock -----.
- * \
- * +--- RMB
- * schedule() /
- * LOCK rq->lock -----'
- * UNLOCK rq->lock
+ * sched_ttwu_pending() try_to_wake_up()
+ * STORE p->on_rq = 1 LOAD p->state
+ * UNLOCK rq->lock
+ *
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * UNLOCK rq->lock
*
* [task p]
- * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
*
- * Pairs with the UNLOCK+LOCK on rq->lock from the
- * last wakeup of our task and the schedule that got our task
- * current.
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
* One must be running (->on_cpu == 1) in order to remove oneself
* from the runqueue.
*
- * [S] ->on_cpu = 1; [L] ->on_rq
- * UNLOCK rq->lock
- * RMB
- * LOCK rq->lock
- * [S] ->on_rq = 0; [L] ->on_cpu
+ * __schedule() (switch to task 'p') try_to_wake_up()
+ * STORE p->on_cpu = 1 LOAD p->on_rq
+ * UNLOCK rq->lock
+ *
+ * __schedule() (put 'p' to sleep)
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * STORE p->on_rq = 0 LOAD p->on_cpu
*
- * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
- * from the consecutive calls to schedule(); the first switching to our
- * task, the second putting it to sleep.
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
*
* Return: 1 if the process was woken up, 0 if it was already running.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
*/
int wake_up_process(struct task_struct *p)
{
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
- int cpu = get_cpu();
__sched_fork(clone_flags, p);
/*
p->sched_reset_on_fork = 0;
}
- if (dl_prio(p->prio)) {
- put_cpu();
+ if (dl_prio(p->prio))
return -EAGAIN;
- } else if (rt_prio(p->prio)) {
+ else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
- } else {
+ else
p->sched_class = &fair_sched_class;
- }
init_entity_runnable_average(&p->se);
* We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
- __set_task_cpu(p, cpu);
+ __set_task_cpu(p, smp_processor_id());
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
-
- put_cpu();
return 0;
}
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
+ kcov_prepare_switch(prev);
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
rseq_preempt(prev);
finish_task(prev);
finish_lock_switch(rq);
finish_arch_post_lock_switch();
+ kcov_finish_switch(current);
fire_sched_in_preempt_notifiers(current);
/*
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
- if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
- switch (prev_state) {
- case TASK_DEAD:
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
-
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
+ if (unlikely(prev_state == TASK_DEAD)) {
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
- /* Task is done with its stack. */
- put_task_stack(prev);
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
- put_task_struct(prev);
- break;
+ /* Task is done with its stack. */
+ put_task_stack(prev);
- case TASK_PARKED:
- kthread_park_complete(prev);
- break;
- }
+ put_task_struct(prev);
}
tick_nohz_task_switch();
struct tick_work *twork = container_of(dwork, struct tick_work, work);
int cpu = twork->cpu;
struct rq *rq = cpu_rq(cpu);
+ struct task_struct *curr;
struct rq_flags rf;
+ u64 delta;
/*
* Handle the tick only if it appears the remote CPU is running in full
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
- if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
- struct task_struct *curr;
- u64 delta;
+ if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+ goto out_requeue;
- rq_lock_irq(rq, &rf);
- update_rq_clock(rq);
- curr = rq->curr;
- delta = rq_clock_task(rq) - curr->se.exec_start;
+ rq_lock_irq(rq, &rf);
+ curr = rq->curr;
+ if (is_idle_task(curr))
+ goto out_unlock;
- /*
- * Make sure the next tick runs within a reasonable
- * amount of time.
- */
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
- curr->sched_class->task_tick(rq, curr, 0);
- rq_unlock_irq(rq, &rf);
- }
+ update_rq_clock(rq);
+ delta = rq_clock_task(rq) - curr->se.exec_start;
+ /*
+ * Make sure the next tick runs within a reasonable
+ * amount of time.
+ */
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ curr->sched_class->task_tick(rq, curr, 0);
+
+out_unlock:
+ rq_unlock_irq(rq, &rf);
+
+out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
}
}
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
- struct rq *rq = cpu_rq(cpu);
-
- rq->age_stamp = sched_clock_cpu(cpu);
-}
-
/*
* used to mark begin/end of suspend/resume:
*/
int sched_cpu_starting(unsigned int cpu)
{
- set_cpu_rq_start_time(cpu);
sched_rq_cpu_starting(cpu);
sched_tick_start(cpu);
return 0;
int i, j;
unsigned long alloc_size = 0, ptr;
- sched_clock_init();
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
idle_thread_set_boot_cpu();
- set_cpu_rq_start_time(smp_processor_id());
#endif
init_sched_fair_class();
seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
+ if (schedstat_enabled() && tg != &root_task_group) {
+ u64 ws = 0;
+ int i;
+
+ for_each_possible_cpu(i)
+ ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+ seq_printf(sf, "wait_sum %llu\n", ws);
+ }
+
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
unsigned int iowait_boost_max;
u64 last_update;
- /* The fields below are only needed when sharing a policy: */
- unsigned long util_cfs;
- unsigned long util_dl;
+ unsigned long bw_dl;
unsigned long max;
/* The field below is for single-CPU policies only: */
return cpufreq_driver_resolve_freq(policy, freq);
}
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ * cpu_util_{cfs,rt,dl,irq}()
+ * cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long util, irq, max;
- sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
- sg_cpu->util_cfs = cpu_util_cfs(rq);
- sg_cpu->util_dl = cpu_util_dl(rq);
-}
+ sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+ sg_cpu->bw_dl = cpu_bw_dl(rq);
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
- struct rq *rq = cpu_rq(sg_cpu->cpu);
+ if (rt_rq_is_runnable(&rq->rt))
+ return max;
- if (rq->rt.rt_nr_running)
- return sg_cpu->max;
+ /*
+ * Early check to see if IRQ/steal time saturates the CPU, can be
+ * because of inaccuracies in how we track these -- see
+ * update_irq_load_avg().
+ */
+ irq = cpu_util_irq(rq);
+ if (unlikely(irq >= max))
+ return max;
+
+ /*
+ * Because the time spend on RT/DL tasks is visible as 'lost' time to
+ * CFS tasks and we use the same metric to track the effective
+ * utilization (PELT windows are synchronized) we can directly add them
+ * to obtain the CPU's actual utilization.
+ */
+ util = cpu_util_cfs(rq);
+ util += cpu_util_rt(rq);
+
+ /*
+ * We do not make cpu_util_dl() a permanent part of this sum because we
+ * want to use cpu_bw_dl() later on, but we need to check if the
+ * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+ * f_max when there is no idle time.
+ *
+ * NOTE: numerical errors or stop class might cause us to not quite hit
+ * saturation when we should -- something for later.
+ */
+ if ((util + cpu_util_dl(rq)) >= max)
+ return max;
+
+ /*
+ * There is still idle time; further improve the number by using the
+ * irq metric. Because IRQ/steal time is hidden from the task clock we
+ * need to scale the task numbers:
+ *
+ * 1 - irq
+ * U' = irq + ------- * U
+ * max
+ */
+ util = scale_irq_capacity(util, irq, max);
+ util += irq;
/*
- * Utilization required by DEADLINE must always be granted while, for
- * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
- * gracefully reduce the frequency when no tasks show up for longer
+ * Bandwidth required by DEADLINE must always be granted while, for
+ * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+ * to gracefully reduce the frequency when no tasks show up for longer
* periods of time.
*
- * Ideally we would like to set util_dl as min/guaranteed freq and
- * util_cfs + util_dl as requested freq. However, cpufreq is not yet
- * ready for such an interface. So, we only do the latter for now.
+ * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+ * bw_dl as requested freq. However, cpufreq is not yet ready for such
+ * an interface. So, we only do the latter for now.
*/
- return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+ return min(max, util + sg_cpu->bw_dl);
}
/**
*/
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
- if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
sg_policy->need_freq_update = true;
}
busy = sugov_cpu_is_busy(sg_cpu);
- sugov_get_util(sg_cpu);
+ util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
- util = sugov_aggregate_util(sg_cpu);
sugov_iowait_apply(sg_cpu, time, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
/*
struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
- sugov_get_util(j_sg_cpu);
+ j_util = sugov_get_util(j_sg_cpu);
j_max = j_sg_cpu->max;
- j_util = sugov_aggregate_util(j_sg_cpu);
sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
if (j_util * max > j_max * util) {
* Fabio Checconi <fchecconi@gmail.com>
*/
#include "sched.h"
+#include "pelt.h"
struct dl_bandwidth def_dl_bandwidth;
curr->se.exec_start = now;
cgroup_account_cputime(curr, delta_exec);
- sched_rt_avg_update(rq, delta_exec);
-
if (dl_entity_is_special(dl_se))
return;
deadline_queue_push_tasks(rq);
+ if (rq->curr->sched_class != &dl_sched_class)
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
return p;
}
{
update_curr_dl(rq);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
}
{
update_curr_dl(rq);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
/*
* Even when we have runtime, update_curr_dl() might have resulted in us
* not being the leftmost task anymore. In that case NEED_RESCHED will
sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
add_rq_bw(&next_task->dl, &later_rq->dl);
+
+ /*
+ * Update the later_rq clock here, because the clock is used
+ * by the cpufreq_update_util() inside __add_running_bw().
+ */
+ update_rq_clock(later_rq);
add_running_bw(&next_task->dl, &later_rq->dl);
- activate_task(later_rq, next_task, 0);
+ activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
resched_curr(later_rq);
if (task_on_rq_queued(p) && p->dl.dl_runtime)
task_non_contending(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ /*
+ * Inactive timer is armed. However, p is leaving DEADLINE and
+ * might migrate away from this rq while continuing to run on
+ * some other class. We need to remove its contribution from
+ * this rq running_bw now, or sub_rq_bw (below) will complain.
+ */
+ if (p->dl.dl_non_contending)
+ sub_running_bw(&p->dl, &rq->dl);
sub_rq_bw(&p->dl, &rq->dl);
+ }
/*
* We cannot use inactive_task_timer() to invoke sub_running_bw()
cmp += 3;
}
- for (i = 0; i < __SCHED_FEAT_NR; i++) {
- if (strcmp(cmp, sched_feat_names[i]) == 0) {
- if (neg) {
- sysctl_sched_features &= ~(1UL << i);
- sched_feat_disable(i);
- } else {
- sysctl_sched_features |= (1UL << i);
- sched_feat_enable(i);
- }
- break;
- }
+ i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+ if (i < 0)
+ return i;
+
+ if (neg) {
+ sysctl_sched_features &= ~(1UL << i);
+ sched_feat_disable(i);
+ } else {
+ sysctl_sched_features |= (1UL << i);
+ sched_feat_enable(i);
}
- return i;
+ return 0;
}
static ssize_t
{
char buf[64];
char *cmp;
- int i;
+ int ret;
struct inode *inode;
if (cnt > 63)
/* Ensure the static_key remains in a consistent state */
inode = file_inode(filp);
inode_lock(inode);
- i = sched_feat_set(cmp);
+ ret = sched_feat_set(cmp);
inode_unlock(inode);
- if (i == __SCHED_FEAT_NR)
- return -EINVAL;
+ if (ret < 0)
+ return ret;
*ppos += cnt;
#undef PU
}
-extern __read_mostly int sched_clock_running;
-
static void print_cpu(struct seq_file *m, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long tpf, unsigned long gsf, unsigned long gpf)
{
SEQ_printf(m, "numa_faults node=%d ", node);
- SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
- SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+ SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+ SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
}
#endif
return cfs_rq->rq;
}
-/* An entity is a task if it doesn't "own" a runqueue */
-#define entity_is_task(se) (!se->my_q)
-
static inline struct task_struct *task_of(struct sched_entity *se)
{
SCHED_WARN_ON(!entity_is_task(se));
return container_of(cfs_rq, struct rq, cfs);
}
-#define entity_is_task(se) 1
#define for_each_sched_entity(se) \
for (; se; se = NULL)
}
#ifdef CONFIG_SMP
-
+#include "pelt.h"
#include "sched-pelt.h"
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
* To solve this problem, we also cap the util_avg of successive tasks to
* only 1/2 of the left utilization budget:
*
- * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
*
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
*
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
*
* task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
* cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
- long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+ long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+ long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
if (cap > 0) {
if (cfs_rq->avg.util_avg != 0) {
* of each group. Skip other nodes.
*/
if (sched_numa_topology_type == NUMA_BACKPLANE &&
- dist > maxdist)
+ dist >= maxdist)
continue;
/* Add up the faults from nearby nodes. */
/* Cached statistics for all CPUs within a node */
struct numa_stats {
- unsigned long nr_running;
unsigned long load;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
- /* Approximate capacity in terms of runnable tasks on a node */
- unsigned long task_capacity;
- int has_free_capacity;
+ unsigned int nr_running;
};
/*
* the @ns structure is NULL'ed and task_numa_compare() will
* not find this node attractive.
*
- * We'll either bail at !has_free_capacity, or we'll detect a huge
- * imbalance and bail there.
+ * We'll detect a huge imbalance and bail there.
*/
if (!cpus)
return;
smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
capacity = cpus / smt; /* cores */
- ns->task_capacity = min_t(unsigned, capacity,
+ capacity = min_t(unsigned, capacity,
DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
- ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
}
struct task_numa_env {
src_capacity = env->src_stats.compute_capacity;
dst_capacity = env->dst_stats.compute_capacity;
- /* We care about the slope of the imbalance, not the direction. */
- if (dst_load < src_load)
- swap(dst_load, src_load);
+ imb = abs(dst_load * src_capacity - src_load * dst_capacity);
- /* Is the difference below the threshold? */
- imb = dst_load * src_capacity * 100 -
- src_load * dst_capacity * env->imbalance_pct;
- if (imb <= 0)
- return false;
-
- /*
- * The imbalance is above the allowed threshold.
- * Compare it with the old imbalance.
- */
orig_src_load = env->src_stats.load;
orig_dst_load = env->dst_stats.load;
- if (orig_dst_load < orig_src_load)
- swap(orig_dst_load, orig_src_load);
-
- old_imb = orig_dst_load * src_capacity * 100 -
- orig_src_load * dst_capacity * env->imbalance_pct;
+ old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
/* Would this change make things worse? */
return (imb > old_imb);
* be exchanged with the source task
*/
static void task_numa_compare(struct task_numa_env *env,
- long taskimp, long groupimp)
+ long taskimp, long groupimp, bool maymove)
{
- struct rq *src_rq = cpu_rq(env->src_cpu);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
struct task_struct *cur;
long src_load, dst_load;
if (cur == env->p)
goto unlock;
+ if (!cur) {
+ if (maymove || imp > env->best_imp)
+ goto assign;
+ else
+ goto unlock;
+ }
+
/*
* "imp" is the fault differential for the source task between the
* source and destination node. Calculate the total differential for
* the source task and potential destination task. The more negative
- * the value is, the more rmeote accesses that would be expected to
+ * the value is, the more remote accesses that would be expected to
* be incurred if the tasks were swapped.
*/
- if (cur) {
- /* Skip this swap candidate if cannot move to the source CPU: */
- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
- goto unlock;
+ /* Skip this swap candidate if cannot move to the source cpu */
+ if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+ goto unlock;
+ /*
+ * If dst and source tasks are in the same NUMA group, or not
+ * in any group then look only at task weights.
+ */
+ if (cur->numa_group == env->p->numa_group) {
+ imp = taskimp + task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
/*
- * If dst and source tasks are in the same NUMA group, or not
- * in any group then look only at task weights.
+ * Add some hysteresis to prevent swapping the
+ * tasks within a group over tiny differences.
*/
- if (cur->numa_group == env->p->numa_group) {
- imp = taskimp + task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- /*
- * Add some hysteresis to prevent swapping the
- * tasks within a group over tiny differences.
- */
- if (cur->numa_group)
- imp -= imp/16;
- } else {
- /*
- * Compare the group weights. If a task is all by
- * itself (not part of a group), use the task weight
- * instead.
- */
- if (cur->numa_group)
- imp += group_weight(cur, env->src_nid, dist) -
- group_weight(cur, env->dst_nid, dist);
- else
- imp += task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- }
+ if (cur->numa_group)
+ imp -= imp / 16;
+ } else {
+ /*
+ * Compare the group weights. If a task is all by itself
+ * (not part of a group), use the task weight instead.
+ */
+ if (cur->numa_group && env->p->numa_group)
+ imp += group_weight(cur, env->src_nid, dist) -
+ group_weight(cur, env->dst_nid, dist);
+ else
+ imp += task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
}
- if (imp <= env->best_imp && moveimp <= env->best_imp)
+ if (imp <= env->best_imp)
goto unlock;
- if (!cur) {
- /* Is there capacity at our destination? */
- if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
- !env->dst_stats.has_free_capacity)
- goto unlock;
-
- goto balance;
- }
-
- /* Balance doesn't matter much if we're running a task per CPU: */
- if (imp > env->best_imp && src_rq->nr_running == 1 &&
- dst_rq->nr_running == 1)
+ if (maymove && moveimp > imp && moveimp > env->best_imp) {
+ imp = moveimp - 1;
+ cur = NULL;
goto assign;
+ }
/*
* In the overloaded case, try and keep the load balanced.
*/
-balance:
- load = task_h_load(env->p);
+ load = task_h_load(env->p) - task_h_load(cur);
+ if (!load)
+ goto assign;
+
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
- if (moveimp > imp && moveimp > env->best_imp) {
- /*
- * If the improvement from just moving env->p direction is
- * better than swapping tasks around, check if a move is
- * possible. Store a slightly smaller score than moveimp,
- * so an actually idle CPU will win.
- */
- if (!load_too_imbalanced(src_load, dst_load, env)) {
- imp = moveimp - 1;
- cur = NULL;
- goto assign;
- }
- }
-
- if (imp <= env->best_imp)
- goto unlock;
-
- if (cur) {
- load = task_h_load(cur);
- dst_load -= load;
- src_load += load;
- }
-
if (load_too_imbalanced(src_load, dst_load, env))
goto unlock;
+assign:
/*
* One idle CPU per node is evaluated for a task numa move.
* Call select_idle_sibling to maybe find a better one.
local_irq_enable();
}
-assign:
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
static void task_numa_find_cpu(struct task_numa_env *env,
long taskimp, long groupimp)
{
+ long src_load, dst_load, load;
+ bool maymove = false;
int cpu;
+ load = task_h_load(env->p);
+ dst_load = env->dst_stats.load + load;
+ src_load = env->src_stats.load - load;
+
+ /*
+ * If the improvement from just moving env->p direction is better
+ * than swapping tasks around, check if a move is possible.
+ */
+ maymove = !load_too_imbalanced(src_load, dst_load, env);
+
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
continue;
env->dst_cpu = cpu;
- task_numa_compare(env, taskimp, groupimp);
+ task_numa_compare(env, taskimp, groupimp, maymove);
}
}
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
- struct numa_stats *src = &env->src_stats;
- struct numa_stats *dst = &env->dst_stats;
-
- if (src->has_free_capacity && !dst->has_free_capacity)
- return false;
-
- /*
- * Only consider a task move if the source has a higher load
- * than the destination, corrected for CPU capacity on each node.
- *
- * src->load dst->load
- * --------------------- vs ---------------------
- * src->compute_capacity dst->compute_capacity
- */
- if (src->load * dst->compute_capacity * env->imbalance_pct >
-
- dst->load * src->compute_capacity * 100)
- return true;
-
- return false;
-}
-
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
- p->numa_preferred_nid = task_node(p);
+ sched_setnuma(p, task_node(p));
return -EINVAL;
}
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
- if (numa_has_capacity(&env))
- task_numa_find_cpu(&env, taskimp, groupimp);
+ task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
- if (numa_has_capacity(&env))
- task_numa_find_cpu(&env, taskimp, groupimp);
+ task_numa_find_cpu(&env, taskimp, groupimp);
}
}
* trying for a better one later. Do not set the preferred node here.
*/
if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
-
if (env.best_cpu == -1)
nid = env.src_nid;
else
- nid = env.dst_nid;
+ nid = cpu_to_node(env.best_cpu);
- if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
- sched_setnuma(p, env.dst_nid);
+ if (nid != p->numa_preferred_nid)
+ sched_setnuma(p, nid);
}
/* No better CPU than the current one was found. */
return ret;
}
- ret = migrate_swap(p, env.best_task);
+ ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
put_task_struct(env.best_task);
static void task_numa_placement(struct task_struct *p)
{
- int seq, nid, max_nid = -1, max_group_nid = -1;
- unsigned long max_faults = 0, max_group_faults = 0;
+ int seq, nid, max_nid = -1;
+ unsigned long max_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
unsigned long total_faults;
u64 runtime, period;
}
}
- if (faults > max_faults) {
- max_faults = faults;
+ if (!p->numa_group) {
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+ } else if (group_faults > max_faults) {
+ max_faults = group_faults;
max_nid = nid;
}
-
- if (group_faults > max_group_faults) {
- max_group_faults = group_faults;
- max_group_nid = nid;
- }
}
- update_task_scan_period(p, fault_types[0], fault_types[1]);
-
if (p->numa_group) {
numa_group_count_active_nodes(p->numa_group);
spin_unlock_irq(group_lock);
- max_nid = preferred_group_nid(p, max_group_nid);
+ max_nid = preferred_group_nid(p, max_nid);
}
if (max_faults) {
/* Set the new preferred node */
if (max_nid != p->numa_preferred_nid)
sched_setnuma(p, max_nid);
-
- if (task_node(p) != p->numa_preferred_nid)
- numa_migrate_preferred(p);
}
+
+ update_task_scan_period(p, fault_types[0], fault_types[1]);
}
static inline int get_numa_group(struct numa_group *grp)
numa_is_active_node(mem_node, ng))
local = 1;
- task_numa_placement(p);
-
/*
* Retry task to preferred node migration periodically, in case it
* case it previously failed, or the scheduler moved us.
*/
- if (time_after(jiffies, p->numa_migrate_retry))
+ if (time_after(jiffies, p->numa_migrate_retry)) {
+ task_numa_placement(p);
numa_migrate_preferred(p);
+ }
if (migrated)
p->numa_pages_migrated += pages;
} while (0)
#ifdef CONFIG_SMP
-/*
- * XXX we want to get rid of these helpers and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
- return scale_load_down(se->load.weight);
-}
-
-static inline long se_runnable(struct sched_entity *se)
-{
- return scale_load_down(se->runnable_weight);
-}
-
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
}
#ifdef CONFIG_SMP
-/*
- * Approximate:
- * val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
- */
-static u64 decay_load(u64 val, u64 n)
-{
- unsigned int local_n;
-
- if (unlikely(n > LOAD_AVG_PERIOD * 63))
- return 0;
-
- /* after bounds checking we can collapse to 32-bit */
- local_n = n;
-
- /*
- * As y^PERIOD = 1/2, we can combine
- * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
- * With a look-up table which covers y^n (n<PERIOD)
- *
- * To achieve constant time decay_load.
- */
- if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
- val >>= local_n / LOAD_AVG_PERIOD;
- local_n %= LOAD_AVG_PERIOD;
- }
-
- val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
- return val;
-}
-
-static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
-{
- u32 c1, c2, c3 = d3; /* y^0 == 1 */
-
- /*
- * c1 = d1 y^p
- */
- c1 = decay_load((u64)d1, periods);
-
- /*
- * p-1
- * c2 = 1024 \Sum y^n
- * n=1
- *
- * inf inf
- * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
- * n=0 n=p
- */
- c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
-
- return c1 + c2 + c3;
-}
-
-/*
- * Accumulate the three separate parts of the sum; d1 the remainder
- * of the last (incomplete) period, d2 the span of full periods and d3
- * the remainder of the (incomplete) current period.
- *
- * d1 d2 d3
- * ^ ^ ^
- * | | |
- * |<->|<----------------->|<--->|
- * ... |---x---|------| ... |------|-----x (now)
- *
- * p-1
- * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
- * n=1
- *
- * = u y^p + (Step 1)
- *
- * p-1
- * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
- * n=1
- */
-static __always_inline u32
-accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
- unsigned long load, unsigned long runnable, int running)
-{
- unsigned long scale_freq, scale_cpu;
- u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
- u64 periods;
-
- scale_freq = arch_scale_freq_capacity(cpu);
- scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
- delta += sa->period_contrib;
- periods = delta / 1024; /* A period is 1024us (~1ms) */
-
- /*
- * Step 1: decay old *_sum if we crossed period boundaries.
- */
- if (periods) {
- sa->load_sum = decay_load(sa->load_sum, periods);
- sa->runnable_load_sum =
- decay_load(sa->runnable_load_sum, periods);
- sa->util_sum = decay_load((u64)(sa->util_sum), periods);
-
- /*
- * Step 2
- */
- delta %= 1024;
- contrib = __accumulate_pelt_segments(periods,
- 1024 - sa->period_contrib, delta);
- }
- sa->period_contrib = delta;
-
- contrib = cap_scale(contrib, scale_freq);
- if (load)
- sa->load_sum += load * contrib;
- if (runnable)
- sa->runnable_load_sum += runnable * contrib;
- if (running)
- sa->util_sum += contrib * scale_cpu;
-
- return periods;
-}
-
-/*
- * We can represent the historical contribution to runnable average as the
- * coefficients of a geometric series. To do this we sub-divide our runnable
- * history into segments of approximately 1ms (1024us); label the segment that
- * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
- *
- * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
- * p0 p1 p2
- * (now) (~1ms ago) (~2ms ago)
- *
- * Let u_i denote the fraction of p_i that the entity was runnable.
- *
- * We then designate the fractions u_i as our co-efficients, yielding the
- * following representation of historical load:
- * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
- *
- * We choose y based on the with of a reasonably scheduling period, fixing:
- * y^32 = 0.5
- *
- * This means that the contribution to load ~32ms ago (u_32) will be weighted
- * approximately half as much as the contribution to load within the last ms
- * (u_0).
- *
- * When a period "rolls over" and we have new u_0`, multiplying the previous
- * sum again by y is sufficient to update:
- * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
- * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
- */
-static __always_inline int
-___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
- unsigned long load, unsigned long runnable, int running)
-{
- u64 delta;
-
- delta = now - sa->last_update_time;
- /*
- * This should only happen when time goes backwards, which it
- * unfortunately does during sched clock init when we swap over to TSC.
- */
- if ((s64)delta < 0) {
- sa->last_update_time = now;
- return 0;
- }
-
- /*
- * Use 1024ns as the unit of measurement since it's a reasonable
- * approximation of 1us and fast to compute.
- */
- delta >>= 10;
- if (!delta)
- return 0;
-
- sa->last_update_time += delta << 10;
-
- /*
- * running is a subset of runnable (weight) so running can't be set if
- * runnable is clear. But there are some corner cases where the current
- * se has been already dequeued but cfs_rq->curr still points to it.
- * This means that weight will be 0 but not running for a sched_entity
- * but also for a cfs_rq if the latter becomes idle. As an example,
- * this happens during idle_balance() which calls
- * update_blocked_averages()
- */
- if (!load)
- runnable = running = 0;
-
- /*
- * Now we know we crossed measurement unit boundaries. The *_avg
- * accrues by two steps:
- *
- * Step 1: accumulate *_sum since last_update_time. If we haven't
- * crossed period boundaries, finish.
- */
- if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
- return 0;
-
- return 1;
-}
-
-static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
-{
- u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
-
- /*
- * Step 2: update *_avg.
- */
- sa->load_avg = div_u64(load * sa->load_sum, divider);
- sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider);
- sa->util_avg = sa->util_sum / divider;
-}
-
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
-static inline void cfs_se_util_change(struct sched_avg *avg)
-{
- unsigned int enqueued;
-
- if (!sched_feat(UTIL_EST))
- return;
-
- /* Avoid store if the flag has been already set */
- enqueued = avg->util_est.enqueued;
- if (!(enqueued & UTIL_AVG_UNCHANGED))
- return;
-
- /* Reset flag to report util_avg has been updated */
- enqueued &= ~UTIL_AVG_UNCHANGED;
- WRITE_ONCE(avg->util_est.enqueued, enqueued);
-}
-
-/*
- * sched_entity:
- *
- * task:
- * se_runnable() == se_weight()
- *
- * group: [ see update_cfs_group() ]
- * se_weight() = tg->weight * grq->load_avg / tg->load_avg
- * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
- *
- * load_sum := runnable_sum
- * load_avg = se_weight(se) * runnable_avg
- *
- * runnable_load_sum := runnable_sum
- * runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
- *
- * cfq_rs:
- *
- * load_sum = \Sum se_weight(se) * se->avg.load_sum
- * load_avg = \Sum se->avg.load_avg
- *
- * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- * runnable_load_avg = \Sum se->avg.runable_load_avg
- */
-
-static int
-__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
-{
- if (entity_is_task(se))
- se->runnable_weight = se->load.weight;
-
- if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
- return 1;
- }
-
- return 0;
-}
-
-static int
-__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- if (entity_is_task(se))
- se->runnable_weight = se->load.weight;
-
- if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
- cfs_rq->curr == se)) {
-
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
- cfs_se_util_change(&se->avg);
- return 1;
- }
-
- return 0;
-}
-
-static int
-__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
-{
- if (___update_load_sum(now, cpu, &cfs_rq->avg,
- scale_load_down(cfs_rq->load.weight),
- scale_load_down(cfs_rq->runnable_weight),
- cfs_rq->curr != NULL)) {
-
- ___update_load_avg(&cfs_rq->avg, 1, 1);
- return 1;
- }
-
- return 0;
-}
-
#ifdef CONFIG_FAIR_GROUP_SCHED
/**
* update_tg_load_avg - update the tg's load avg
if (!sched_feat(UTIL_EST))
return;
- /*
- * Update root cfs_rq's estimated utilization
- *
- * If *p is the last task then the root cfs_rq's estimated utilization
- * of a CPU is 0 by definition.
- */
- ue.enqueued = 0;
- if (cfs_rq->nr_running) {
- ue.enqueued = cfs_rq->avg.util_est.enqueued;
- ue.enqueued -= min_t(unsigned int, ue.enqueued,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
- }
+ /* Update root cfs_rq's estimated utilization */
+ ue.enqueued = cfs_rq->avg.util_est.enqueued;
+ ue.enqueued -= min_t(unsigned int, ue.enqueued,
+ (_task_util_est(p) | UTIL_AVG_UNCHANGED));
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
/*
#else /* CONFIG_SMP */
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
- return 0;
-}
-
#define UPDATE_TG 0x0
#define SKIP_AGE_LOAD 0x0
#define DO_ATTACH 0x0
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
u64 amount = 0, min_amount, expires;
+ int expires_seq;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
cfs_b->idle = 0;
}
}
+ expires_seq = cfs_b->expires_seq;
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
* spread between our sched_clock and the one on which runtime was
* issued.
*/
- if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+ if (cfs_rq->expires_seq != expires_seq) {
+ cfs_rq->expires_seq = expires_seq;
cfs_rq->runtime_expires = expires;
+ }
return cfs_rq->runtime_remaining > 0;
}
* has not truly expired.
*
* Fortunately we can check determine whether this the case by checking
- * whether the global deadline has advanced. It is valid to compare
- * cfs_b->runtime_expires without any locks since we only care about
- * exact equality, so a partial write will still work.
+ * whether the global deadline(cfs_b->expires_seq) has advanced.
*/
-
- if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+ if (cfs_rq->expires_seq == cfs_b->expires_seq) {
/* extend local deadline, drift is bounded above by 2 ticks */
cfs_rq->runtime_expires += TICK_NSEC;
} else {
throttled_hierarchy(dest_cfs_rq);
}
-/* updated child weight may affect parent so we have to do this bottom up */
static int tg_unthrottle_up(struct task_group *tg, void *data)
{
struct rq *rq = data;
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ u64 overrun;
+
lockdep_assert_held(&cfs_b->lock);
- if (!cfs_b->period_active) {
- cfs_b->period_active = 1;
- hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
- }
+ if (cfs_b->period_active)
+ return;
+
+ cfs_b->period_active = 1;
+ overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
}
-
- sched_avg_update(this_rq);
}
/* Used instead of source_load when we know the type == 0 */
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
- unsigned long src_faults, dst_faults;
- int src_nid, dst_nid;
+ unsigned long src_weight, dst_weight;
+ int src_nid, dst_nid, dist;
if (!static_branch_likely(&sched_numa_balancing))
return -1;
return 0;
/* Leaving a core idle is often worse than degrading locality. */
- if (env->idle != CPU_NOT_IDLE)
+ if (env->idle == CPU_IDLE)
return -1;
+ dist = node_distance(src_nid, dst_nid);
if (numa_group) {
- src_faults = group_faults(p, src_nid);
- dst_faults = group_faults(p, dst_nid);
+ src_weight = group_weight(p, src_nid, dist);
+ dst_weight = group_weight(p, dst_nid, dist);
} else {
- src_faults = task_faults(p, src_nid);
- dst_faults = task_faults(p, dst_nid);
+ src_weight = task_weight(p, src_nid, dist);
+ dst_weight = task_weight(p, dst_nid, dist);
}
- return dst_faults < src_faults;
+ return dst_weight < src_weight;
}
#else
return false;
}
+static inline bool others_have_blocked(struct rq *rq)
+{
+ if (READ_ONCE(rq->avg_rt.util_avg))
+ return true;
+
+ if (READ_ONCE(rq->avg_dl.util_avg))
+ return true;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+ if (READ_ONCE(rq->avg_irq.util_avg))
+ return true;
+#endif
+
+ return false;
+}
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
if (cfs_rq_has_blocked(cfs_rq))
done = false;
}
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_irq_load_avg(rq, 0);
+ /* Don't need periodic decay once load/util_avg are null */
+ if (others_have_blocked(rq))
+ done = false;
#ifdef CONFIG_NO_HZ_COMMON
rq->last_blocked_load_update_tick = jiffies;
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+ update_irq_load_avg(rq, 0);
#ifdef CONFIG_NO_HZ_COMMON
rq->last_blocked_load_update_tick = jiffies;
- if (!cfs_rq_has_blocked(cfs_rq))
+ if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
rq->has_blocked_load = 0;
#endif
rq_unlock_irqrestore(rq, &rf);
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, used, age_stamp, avg;
- s64 delta;
+ unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+ unsigned long used, free;
+ unsigned long irq;
- /*
- * Since we're reading these variables without serialization make sure
- * we read them once before doing sanity checks on them.
- */
- age_stamp = READ_ONCE(rq->age_stamp);
- avg = READ_ONCE(rq->rt_avg);
- delta = __rq_clock_broken(rq) - age_stamp;
+ irq = cpu_util_irq(rq);
- if (unlikely(delta < 0))
- delta = 0;
+ if (unlikely(irq >= max))
+ return 1;
- total = sched_avg_period() + delta;
+ used = READ_ONCE(rq->avg_rt.util_avg);
+ used += READ_ONCE(rq->avg_dl.util_avg);
- used = div_u64(avg, total);
+ if (unlikely(used >= max))
+ return 1;
- if (likely(used < SCHED_CAPACITY_SCALE))
- return SCHED_CAPACITY_SCALE - used;
+ free = max - used;
- return 1;
+ return scale_irq_capacity(free, irq, max);
}
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
- unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+ unsigned long capacity = scale_rt_capacity(cpu);
struct sched_group *sdg = sd->groups;
- cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
- capacity *= scale_rt_capacity(cpu);
- capacity >>= SCHED_CAPACITY_SHIFT;
+ cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
if (!capacity)
capacity = 1;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Per Entity Load Tracking
+ *
+ * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Interactivity improvements by Mike Galbraith
+ * (C) 2007 Mike Galbraith <efault@gmx.de>
+ *
+ * Various enhancements by Dmitry Adamushko.
+ * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
+ *
+ * Group scheduling enhancements by Srivatsa Vaddagiri
+ * Copyright IBM Corporation, 2007
+ * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
+ *
+ * Scaled math optimizations by Thomas Gleixner
+ * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ * Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ * Move PELT related code from fair.c into this pelt.c file
+ * Author: Vincent Guittot <vincent.guittot@linaro.org>
+ */
+
+#include <linux/sched.h>
+#include "sched.h"
+#include "sched-pelt.h"
+#include "pelt.h"
+
+/*
+ * Approximate:
+ * val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static u64 decay_load(u64 val, u64 n)
+{
+ unsigned int local_n;
+
+ if (unlikely(n > LOAD_AVG_PERIOD * 63))
+ return 0;
+
+ /* after bounds checking we can collapse to 32-bit */
+ local_n = n;
+
+ /*
+ * As y^PERIOD = 1/2, we can combine
+ * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+ * With a look-up table which covers y^n (n<PERIOD)
+ *
+ * To achieve constant time decay_load.
+ */
+ if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+ val >>= local_n / LOAD_AVG_PERIOD;
+ local_n %= LOAD_AVG_PERIOD;
+ }
+
+ val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+ return val;
+}
+
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+ u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+ /*
+ * c1 = d1 y^p
+ */
+ c1 = decay_load((u64)d1, periods);
+
+ /*
+ * p-1
+ * c2 = 1024 \Sum y^n
+ * n=1
+ *
+ * inf inf
+ * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+ * n=0 n=p
+ */
+ c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+ return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ * d1 d2 d3
+ * ^ ^ ^
+ * | | |
+ * |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ * p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ * n=1
+ *
+ * = u y^p + (Step 1)
+ *
+ * p-1
+ * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
+ * n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+ unsigned long load, unsigned long runnable, int running)
+{
+ unsigned long scale_freq, scale_cpu;
+ u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+ u64 periods;
+
+ scale_freq = arch_scale_freq_capacity(cpu);
+ scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+ delta += sa->period_contrib;
+ periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+ /*
+ * Step 1: decay old *_sum if we crossed period boundaries.
+ */
+ if (periods) {
+ sa->load_sum = decay_load(sa->load_sum, periods);
+ sa->runnable_load_sum =
+ decay_load(sa->runnable_load_sum, periods);
+ sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+ /*
+ * Step 2
+ */
+ delta %= 1024;
+ contrib = __accumulate_pelt_segments(periods,
+ 1024 - sa->period_contrib, delta);
+ }
+ sa->period_contrib = delta;
+
+ contrib = cap_scale(contrib, scale_freq);
+ if (load)
+ sa->load_sum += load * contrib;
+ if (runnable)
+ sa->runnable_load_sum += runnable * contrib;
+ if (running)
+ sa->util_sum += contrib * scale_cpu;
+
+ return periods;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series. To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ * p0 p1 p2
+ * (now) (~1ms ago) (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ * y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+ unsigned long load, unsigned long runnable, int running)
+{
+ u64 delta;
+
+ delta = now - sa->last_update_time;
+ /*
+ * This should only happen when time goes backwards, which it
+ * unfortunately does during sched clock init when we swap over to TSC.
+ */
+ if ((s64)delta < 0) {
+ sa->last_update_time = now;
+ return 0;
+ }
+
+ /*
+ * Use 1024ns as the unit of measurement since it's a reasonable
+ * approximation of 1us and fast to compute.
+ */
+ delta >>= 10;
+ if (!delta)
+ return 0;
+
+ sa->last_update_time += delta << 10;
+
+ /*
+ * running is a subset of runnable (weight) so running can't be set if
+ * runnable is clear. But there are some corner cases where the current
+ * se has been already dequeued but cfs_rq->curr still points to it.
+ * This means that weight will be 0 but not running for a sched_entity
+ * but also for a cfs_rq if the latter becomes idle. As an example,
+ * this happens during idle_balance() which calls
+ * update_blocked_averages()
+ */
+ if (!load)
+ runnable = running = 0;
+
+ /*
+ * Now we know we crossed measurement unit boundaries. The *_avg
+ * accrues by two steps:
+ *
+ * Step 1: accumulate *_sum since last_update_time. If we haven't
+ * crossed period boundaries, finish.
+ */
+ if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
+ return 0;
+
+ return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+ u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+ /*
+ * Step 2: update *_avg.
+ */
+ sa->load_avg = div_u64(load * sa->load_sum, divider);
+ sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider);
+ WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+}
+
+/*
+ * sched_entity:
+ *
+ * task:
+ * se_runnable() == se_weight()
+ *
+ * group: [ see update_cfs_group() ]
+ * se_weight() = tg->weight * grq->load_avg / tg->load_avg
+ * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ * load_sum := runnable_sum
+ * load_avg = se_weight(se) * runnable_avg
+ *
+ * runnable_load_sum := runnable_sum
+ * runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rq:
+ *
+ * load_sum = \Sum se_weight(se) * se->avg.load_sum
+ * load_avg = \Sum se->avg.load_avg
+ *
+ * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ * runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ se->runnable_weight = se->load.weight;
+
+ if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+ ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ return 1;
+ }
+
+ return 0;
+}
+
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ se->runnable_weight = se->load.weight;
+
+ if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+ cfs_rq->curr == se)) {
+
+ ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ cfs_se_util_change(&se->avg);
+ return 1;
+ }
+
+ return 0;
+}
+
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+ if (___update_load_sum(now, cpu, &cfs_rq->avg,
+ scale_load_down(cfs_rq->load.weight),
+ scale_load_down(cfs_rq->runnable_weight),
+ cfs_rq->curr != NULL)) {
+
+ ___update_load_avg(&cfs_rq->avg, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * rt_rq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ * load_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ if (___update_load_sum(now, rq->cpu, &rq->avg_rt,
+ running,
+ running,
+ running)) {
+
+ ___update_load_avg(&rq->avg_rt, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * dl_rq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ */
+
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ if (___update_load_sum(now, rq->cpu, &rq->avg_dl,
+ running,
+ running,
+ running)) {
+
+ ___update_load_avg(&rq->avg_dl, 1, 1);
+ return 1;
+ }
+
+ return 0;
+}
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+/*
+ * irq:
+ *
+ * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ * util_sum = cpu_scale * load_sum
+ * runnable_load_sum = load_sum
+ *
+ */
+
+int update_irq_load_avg(struct rq *rq, u64 running)
+{
+ int ret = 0;
+ /*
+ * We know the time that has been used by interrupt since last update
+ * but we don't when. Let be pessimistic and assume that interrupt has
+ * happened just before the update. This is not so far from reality
+ * because interrupt will most probably wake up task and trig an update
+ * of rq clock during which the metric si updated.
+ * We start to decay with normal context time and then we add the
+ * interrupt context time.
+ * We can safely remove running from rq->clock because
+ * rq->clock += delta with delta >= running
+ */
+ ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq,
+ 0,
+ 0,
+ 0);
+ ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq,
+ 1,
+ 1,
+ 1);
+
+ if (ret)
+ ___update_load_avg(&rq->avg_irq, 1, 1);
+
+ return ret;
+}
+#endif
--- /dev/null
+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+ return 0;
+}
+#endif
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+ unsigned int enqueued;
+
+ if (!sched_feat(UTIL_EST))
+ return;
+
+ /* Avoid store if the flag has been already set */
+ enqueued = avg->util_est.enqueued;
+ if (!(enqueued & UTIL_AVG_UNCHANGED))
+ return;
+
+ /* Reset flag to report util_avg has been updated */
+ enqueued &= ~UTIL_AVG_UNCHANGED;
+ WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+ return 0;
+}
+
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ return 0;
+}
+
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+ return 0;
+}
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+ return 0;
+}
+#endif
+
+
*/
#include "sched.h"
+#include "pelt.h"
+
int sched_rr_timeslice = RR_TIMESLICE;
int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
rt_se = rt_rq->tg->rt_se[cpu];
- if (!rt_se)
+ if (!rt_se) {
dequeue_top_rt_rq(rt_rq);
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
+ }
else if (on_rt_rq(rt_se))
dequeue_rt_entity(rt_se, 0);
}
* can be time-consuming. Try to avoid it when possible.
*/
raw_spin_lock(&rt_rq->rt_runtime_lock);
+ if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
+ rt_rq->rt_runtime = rt_b->rt_runtime;
skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
if (skip)
curr->se.exec_start = now;
cgroup_account_cputime(curr, delta_exec);
- sched_rt_avg_update(rq, delta_exec);
-
if (!rt_bandwidth_enabled())
return;
sub_nr_running(rq, rt_rq->rt_nr_running);
rt_rq->rt_queued = 0;
- /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_util(rq, 0);
}
static void
if (rt_rq->rt_queued)
return;
- if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+
+ if (rt_rq_throttled(rt_rq))
return;
- add_nr_running(rq, rt_rq->rt_nr_running);
- rt_rq->rt_queued = 1;
+ if (rt_rq->rt_nr_running) {
+ add_nr_running(rq, rt_rq->rt_nr_running);
+ rt_rq->rt_queued = 1;
+ }
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
cpufreq_update_util(rq, 0);
rt_queue_push_tasks(rq);
+ /*
+ * If prev task was rt, put_prev_task() has already updated the
+ * utilization. We only care of the case where we start to schedule a
+ * rt task
+ */
+ if (rq->curr->sched_class != &rt_sched_class)
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
return p;
}
{
update_curr_rt(rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
/*
* The previous task needs to be made eligible for pushing
* if it is still active
struct sched_rt_entity *rt_se = &p->rt;
update_curr_rt(rq);
+ update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
watchdog(rq, p);
u64 runtime;
s64 hierarchical_quota;
u64 runtime_expires;
+ int expires_seq;
- int idle;
- int period_active;
+ short idle;
+ short period_active;
struct hrtimer period_timer;
struct hrtimer slack_timer;
struct list_head throttled_cfs_rq;
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
+ int expires_seq;
u64 runtime_expires;
s64 runtime_remaining;
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
+
#endif /* CONFIG_SMP */
int rt_queued;
#endif
};
+static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_queued && rt_rq->rt_nr_running;
+}
+
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
u64 bw_ratio;
};
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se) (!se->my_q)
+#else
+#define entity_is_task(se) 1
+#endif
+
#ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+ return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ return scale_load_down(se->runnable_weight);
+}
static inline bool sched_asym_prefer(int a, int b)
{
struct list_head cfs_tasks;
- u64 rt_avg;
- u64 age_stamp;
+ struct sched_avg avg_rt;
+ struct sched_avg avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
+ struct sched_avg avg_irq;
+#endif
u64 idle_stamp;
u64 avg_idle;
};
extern void sched_setnuma(struct task_struct *p, int node);
extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+ int cpu, int scpu);
extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
#else
static inline void
extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
-extern const_debug unsigned int sysctl_sched_time_avg;
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;
-static inline u64 sched_avg_period(void)
-{
- return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
#ifdef CONFIG_SCHED_HRTICK
/*
#endif
#ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
return SCHED_CAPACITY_SCALE;
}
#endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
- rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
- sched_avg_update(rq);
-}
#else
#ifndef arch_scale_cpu_capacity
static __always_inline
return SCHED_CAPACITY_SCALE;
}
#endif
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
-static inline void sched_avg_update(struct rq *rq) { }
#endif
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
#endif
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
}
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+ return READ_ONCE(rq->avg_dl.util_avg);
+}
+
static inline unsigned long cpu_util_cfs(struct rq *rq)
{
unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
return util;
}
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+ return READ_ONCE(rq->avg_rt.util_avg);
+}
+#endif
+
+#ifdef HAVE_SCHED_AVG_IRQ
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+ return rq->avg_irq.util_avg;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+ util *= (max - irq);
+ util /= max;
+
+ return util;
+
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+ return 0;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+ return util;
+}
#endif
}
EXPORT_SYMBOL(swake_up_locked);
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
{
unsigned long flags;
swake_up_locked(q);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
/*
* Does not allow usage from IRQ disabled, since we must be able to
}
EXPORT_SYMBOL(swake_up_all);
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
wait->task = current;
if (list_empty(&wait->task_list))
- list_add(&wait->task_list, &q->task_list);
+ list_add_tail(&wait->task_list, &q->task_list);
}
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
unsigned long flags;
set_current_state(state);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
- if (signal_pending_state(state, current))
- return -ERESTARTSYS;
+ unsigned long flags;
+ long ret = 0;
- prepare_to_swait(q, wait, state);
+ raw_spin_lock_irqsave(&q->lock, flags);
+ if (unlikely(signal_pending_state(state, current))) {
+ /*
+ * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
+ * must not see us.
+ */
+ list_del_init(&wait->task_list);
+ ret = -ERESTARTSYS;
+ } else {
+ __prepare_to_swait(q, wait);
+ set_current_state(state);
+ }
+ raw_spin_unlock_irqrestore(&q->lock, flags);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(prepare_to_swait_event);
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
}
- if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
+ if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
}
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
*
* On UP it can prevent extra preemption.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
* if (condition)
* break;
*
- * p->state = mode; condition = true;
- * smp_mb(); // A smp_wmb(); // C
- * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN;
- * schedule() try_to_wake_up();
- * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~
- * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true;
- * smp_mb() // B smp_wmb(); // C
- * wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ * // in wait_woken() // in woken_wake_function()
*
+ * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN;
+ * smp_mb(); // A try_to_wake_up():
+ * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier>
+ * schedule() if (p->state & mode)
+ * p->state = TASK_RUNNING; p->state = TASK_RUNNING;
+ * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~
+ * smp_mb(); // B condition = true;
+ * } smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN;
*/
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
{
- set_current_state(mode); /* A */
/*
- * The above implies an smp_mb(), which matches with the smp_wmb() from
- * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
- * also observe all state before the wakeup.
+ * The below executes an smp_mb(), which matches with the full barrier
+ * executed by the try_to_wake_up() in woken_wake_function() such that
+ * either we see the store to wq_entry->flags in woken_wake_function()
+ * or woken_wake_function() sees our store to current->state.
*/
+ set_current_state(mode); /* A */
if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
timeout = schedule_timeout(timeout);
__set_current_state(TASK_RUNNING);
/*
- * The below implies an smp_mb(), it too pairs with the smp_wmb() from
- * woken_wake_function() such that we must either observe the wait
- * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
- * an event.
+ * The below executes an smp_mb(), which matches with the smp_mb() (C)
+ * in woken_wake_function() such that either we see the wait condition
+ * being true or the store to wq_entry->flags in woken_wake_function()
+ * follows ours in the coherence order.
*/
smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
{
- /*
- * Although this function is called under waitqueue lock, LOCK
- * doesn't imply write barrier and the users expects write
- * barrier semantics on wakeup functions. The following
- * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with smp_store_mb() in wait_woken().
- */
- smp_wmb(); /* C */
+ /* Pairs with the smp_store_mb() in wait_woken(). */
+ smp_mb(); /* C */
wq_entry->flags |= WQ_FLAG_WOKEN;
return default_wake_function(wq_entry, mode, sync, key);
mutex_lock(&smpboot_threads_lock);
list_for_each_entry(cur, &hotplug_threads, list)
- if (cpumask_test_cpu(cpu, cur->cpumask))
- smpboot_unpark_thread(cur, cpu);
+ smpboot_unpark_thread(cur, cpu);
mutex_unlock(&smpboot_threads_lock);
return 0;
}
}
/**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
* to hotplug
* @plug_thread: Hotplug thread descriptor
- * @cpumask: The cpumask where threads run
*
* Creates and starts the threads on all online cpus.
*/
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
{
unsigned int cpu;
int ret = 0;
- if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
- return -ENOMEM;
- cpumask_copy(plug_thread->cpumask, cpumask);
-
get_online_cpus();
mutex_lock(&smpboot_threads_lock);
for_each_online_cpu(cpu) {
ret = __smpboot_create_thread(plug_thread, cpu);
if (ret) {
smpboot_destroy_threads(plug_thread);
- free_cpumask_var(plug_thread->cpumask);
goto out;
}
- if (cpumask_test_cpu(cpu, cpumask))
- smpboot_unpark_thread(plug_thread, cpu);
+ smpboot_unpark_thread(plug_thread, cpu);
}
list_add(&plug_thread->list, &hotplug_threads);
out:
put_online_cpus();
return ret;
}
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
/**
* smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
smpboot_destroy_threads(plug_thread);
mutex_unlock(&smpboot_threads_lock);
put_online_cpus();
- free_cpumask_var(plug_thread->cpumask);
}
EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread: Hotplug thread descriptor
- * @new: Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
- const struct cpumask *new)
-{
- struct cpumask *old = plug_thread->cpumask;
- static struct cpumask tmp;
- unsigned int cpu;
-
- lockdep_assert_cpus_held();
- mutex_lock(&smpboot_threads_lock);
-
- /* Park threads that were exclusively enabled on the old mask. */
- cpumask_andnot(&tmp, old, new);
- for_each_cpu_and(cpu, &tmp, cpu_online_mask)
- smpboot_park_thread(plug_thread, cpu);
-
- /* Unpark threads that are exclusively enabled on the new mask. */
- cpumask_andnot(&tmp, new, old);
- for_each_cpu_and(cpu, &tmp, cpu_online_mask)
- smpboot_unpark_thread(plug_thread, cpu);
-
- cpumask_copy(old, new);
-
- mutex_unlock(&smpboot_threads_lock);
-}
-
static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
/*
/*
* If ksoftirqd is scheduled, we do not want to process pending softirqs
- * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness,
+ * unless we're doing some of the synchronous softirqs.
*/
-static bool ksoftirqd_running(void)
+#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
+static bool ksoftirqd_running(unsigned long pending)
{
struct task_struct *tsk = __this_cpu_read(ksoftirqd);
+ if (pending & SOFTIRQ_NOW_MASK)
+ return false;
return tsk && (tsk->state == TASK_RUNNING);
}
{
lockdep_assert_irqs_disabled();
+ if (preempt_count() == cnt)
+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
- preempt_count_sub(cnt);
+
+ __preempt_count_sub(cnt);
}
/*
pending = local_softirq_pending();
- if (pending && !ksoftirqd_running())
+ if (pending && !ksoftirqd_running(pending))
do_softirq_own_stack();
local_irq_restore(flags);
static inline void invoke_softirq(void)
{
- if (ksoftirqd_running())
+ if (ksoftirqd_running(local_softirq_pending()))
return;
if (!force_irqthreads) {
/* Make sure that timer wheel updates are propagated */
if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
- if (!in_interrupt())
+ if (!in_irq())
tick_nohz_irq_exit();
}
#endif
unsigned long flags;
bool enabled;
+ preempt_disable();
raw_spin_lock_irqsave(&stopper->lock, flags);
enabled = stopper->enabled;
if (enabled)
raw_spin_unlock_irqrestore(&stopper->lock, flags);
wake_up_q(&wakeq);
+ preempt_enable();
return enabled;
}
struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
DEFINE_WAKE_Q(wakeq);
int err;
+
retry:
+ /*
+ * The waking up of stopper threads has to happen in the same
+ * scheduling context as the queueing. Otherwise, there is a
+ * possibility of one of the above stoppers being woken up by another
+ * CPU, and preempting us. This will cause us to not wake up the other
+ * stopper forever.
+ */
+ preempt_disable();
raw_spin_lock_irq(&stopper1->lock);
raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
- err = -ENOENT;
- if (!stopper1->enabled || !stopper2->enabled)
+ if (!stopper1->enabled || !stopper2->enabled) {
+ err = -ENOENT;
goto unlock;
+ }
+
/*
* Ensure that if we race with __stop_cpus() the stoppers won't get
* queued up in reverse order leading to system deadlock.
* It can be falsely true but it is safe to spin until it is cleared,
* queue_stop_cpus_work() does everything under preempt_disable().
*/
- err = -EDEADLK;
- if (unlikely(stop_cpus_in_progress))
- goto unlock;
+ if (unlikely(stop_cpus_in_progress)) {
+ err = -EDEADLK;
+ goto unlock;
+ }
err = 0;
__cpu_stop_queue_work(stopper1, work1, &wakeq);
__cpu_stop_queue_work(stopper2, work2, &wakeq);
+
unlock:
raw_spin_unlock(&stopper2->lock);
raw_spin_unlock_irq(&stopper1->lock);
if (unlikely(err == -EDEADLK)) {
+ preempt_enable();
+
while (stop_cpus_in_progress)
cpu_relax();
+
goto retry;
}
wake_up_q(&wakeq);
+ preempt_enable();
return err;
}
{
unsigned long mem_total, sav_total;
unsigned int mem_unit, bitcount;
- struct timespec tp;
+ struct timespec64 tp;
memset(info, 0, sizeof(struct sysinfo));
- get_monotonic_boottime(&tp);
+ ktime_get_boottime_ts64(&tp);
info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "sched_time_avg_ms",
- .data = &sysctl_sched_time_avg,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- },
#ifdef CONFIG_SCHEDSTATS
{
.procname = "sched_schedstats",
}
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
- if (preemptible()) {
- handler_errors++;
- pr_err("jprobe-handler is preemptible\n");
- }
- if (value != rand1) {
- handler_errors++;
- pr_err("incorrect value in jprobe handler\n");
- }
-
- jph_val = rand1;
- jprobe_return();
- return 0;
-}
-
-static struct jprobe jp = {
- .entry = j_kprobe_target,
- .kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
- int ret;
-
- ret = register_jprobe(&jp);
- if (ret < 0) {
- pr_err("register_jprobe returned %d\n", ret);
- return ret;
- }
-
- ret = target(rand1);
- unregister_jprobe(&jp);
- if (jph_val == 0) {
- pr_err("jprobe handler not called\n");
- handler_errors++;
- }
-
- return 0;
-}
-
-static struct jprobe jp2 = {
- .entry = j_kprobe_target,
- .kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
- int ret;
- struct jprobe *jps[2] = {&jp, &jp2};
-
- /* addr and flags should be cleard for reusing kprobe. */
- jp.kp.addr = NULL;
- jp.kp.flags = 0;
- ret = register_jprobes(jps, 2);
- if (ret < 0) {
- pr_err("register_jprobes returned %d\n", ret);
- return ret;
- }
-
- jph_val = 0;
- ret = target(rand1);
- if (jph_val == 0) {
- pr_err("jprobe handler not called\n");
- handler_errors++;
- }
-
- jph_val = 0;
- ret = target2(rand1);
- if (jph_val == 0) {
- pr_err("jprobe handler2 not called\n");
- handler_errors++;
- }
- unregister_jprobes(jps, 2);
-
- return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
#ifdef CONFIG_KRETPROBES
static u32 krph_val;
if (ret < 0)
errors++;
- num_tests++;
- ret = test_jprobe();
- if (ret < 0)
- errors++;
-
- num_tests++;
- ret = test_jprobes();
- if (ret < 0)
- errors++;
-
#ifdef CONFIG_KRETPROBES
num_tests++;
ret = test_kretprobe();
* @timr: Pointer to the posixtimer data struct
* @now: Current time to forward the timer against
*/
-static int alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
{
struct alarm *alarm = &timr->it.alarm.alarmtimer;
- return (int) alarm_forward(alarm, timr->it_interval, now);
+ return alarm_forward(alarm, timr->it_interval, now);
}
/**
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now = alarm_bases[type].gettime();
- exp = ktime_add(now, exp);
+
+ exp = ktime_add_safe(now, exp);
}
ret = alarmtimer_do_nsleep(&alarm, exp, type);
dev->cpumask = cpumask_of(smp_processor_id());
}
+ if (dev->cpumask == cpu_all_mask) {
+ WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+ dev->name);
+ dev->cpumask = cpu_possible_mask;
+ }
+
raw_spin_lock_irqsave(&clockevents_lock, flags);
list_add(&dev->list, &clockevent_devices);
/*[Clocksource internal variables]---------
* curr_clocksource:
* currently selected clocksource.
+ * suspend_clocksource:
+ * used to calculate the suspend time.
* clocksource_list:
* linked list with the registered clocksources
* clocksource_mutex:
* Name of the user-specified clocksource.
*/
static struct clocksource *curr_clocksource;
+static struct clocksource *suspend_clocksource;
static LIST_HEAD(clocksource_list);
static DEFINE_MUTEX(clocksource_mutex);
static char override_name[CS_NAME_LEN];
static int finished_booting;
+static u64 suspend_start;
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
static void clocksource_watchdog_work(struct work_struct *work);
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
+static bool clocksource_is_suspend(struct clocksource *cs)
+{
+ return cs == suspend_clocksource;
+}
+
+static void __clocksource_suspend_select(struct clocksource *cs)
+{
+ /*
+ * Skip the clocksource which will be stopped in suspend state.
+ */
+ if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
+ return;
+
+ /*
+ * The nonstop clocksource can be selected as the suspend clocksource to
+ * calculate the suspend time, so it should not supply suspend/resume
+ * interfaces to suspend the nonstop clocksource when system suspends.
+ */
+ if (cs->suspend || cs->resume) {
+ pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
+ cs->name);
+ }
+
+ /* Pick the best rating. */
+ if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
+ suspend_clocksource = cs;
+}
+
+/**
+ * clocksource_suspend_select - Select the best clocksource for suspend timing
+ * @fallback: if select a fallback clocksource
+ */
+static void clocksource_suspend_select(bool fallback)
+{
+ struct clocksource *cs, *old_suspend;
+
+ old_suspend = suspend_clocksource;
+ if (fallback)
+ suspend_clocksource = NULL;
+
+ list_for_each_entry(cs, &clocksource_list, list) {
+ /* Skip current if we were requested for a fallback. */
+ if (fallback && cs == old_suspend)
+ continue;
+
+ __clocksource_suspend_select(cs);
+ }
+}
+
+/**
+ * clocksource_start_suspend_timing - Start measuring the suspend timing
+ * @cs: current clocksource from timekeeping
+ * @start_cycles: current cycles from timekeeping
+ *
+ * This function will save the start cycle values of suspend timer to calculate
+ * the suspend time when resuming system.
+ *
+ * This function is called late in the suspend process from timekeeping_suspend(),
+ * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * now. It is therefore possible to start the suspend timer without taking the
+ * clocksource mutex.
+ */
+void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
+{
+ if (!suspend_clocksource)
+ return;
+
+ /*
+ * If current clocksource is the suspend timer, we should use the
+ * tkr_mono.cycle_last value as suspend_start to avoid same reading
+ * from suspend timer.
+ */
+ if (clocksource_is_suspend(cs)) {
+ suspend_start = start_cycles;
+ return;
+ }
+
+ if (suspend_clocksource->enable &&
+ suspend_clocksource->enable(suspend_clocksource)) {
+ pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
+ return;
+ }
+
+ suspend_start = suspend_clocksource->read(suspend_clocksource);
+}
+
+/**
+ * clocksource_stop_suspend_timing - Stop measuring the suspend timing
+ * @cs: current clocksource from timekeeping
+ * @cycle_now: current cycles from timekeeping
+ *
+ * This function will calculate the suspend time from suspend timer.
+ *
+ * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
+ *
+ * This function is called early in the resume process from timekeeping_resume(),
+ * that means there is only one cpu, no processes are running and the interrupts
+ * are disabled. It is therefore possible to stop the suspend timer without
+ * taking the clocksource mutex.
+ */
+u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
+{
+ u64 now, delta, nsec = 0;
+
+ if (!suspend_clocksource)
+ return 0;
+
+ /*
+ * If current clocksource is the suspend timer, we should use the
+ * tkr_mono.cycle_last value from timekeeping as current cycle to
+ * avoid same reading from suspend timer.
+ */
+ if (clocksource_is_suspend(cs))
+ now = cycle_now;
+ else
+ now = suspend_clocksource->read(suspend_clocksource);
+
+ if (now > suspend_start) {
+ delta = clocksource_delta(now, suspend_start,
+ suspend_clocksource->mask);
+ nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
+ suspend_clocksource->shift);
+ }
+
+ /*
+ * Disable the suspend timer to save power if current clocksource is
+ * not the suspend timer.
+ */
+ if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
+ suspend_clocksource->disable(suspend_clocksource);
+
+ return nsec;
+}
+
/**
* clocksource_suspend - suspend the clocksource(s)
*/
clocksource_select();
clocksource_select_watchdog(false);
+ __clocksource_suspend_select(cs);
mutex_unlock(&clocksource_mutex);
return 0;
}
clocksource_select();
clocksource_select_watchdog(false);
+ clocksource_suspend_select(false);
mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);
return -EBUSY;
}
+ if (clocksource_is_suspend(cs)) {
+ /*
+ * Select and try to install a replacement suspend clocksource.
+ * If no replacement suspend clocksource, we will just let the
+ * clocksource go and have no suspend clocksource.
+ */
+ clocksource_suspend_select(true);
+ }
+
clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
if (tick_init_highres()) {
- printk(KERN_WARNING "Could not switch to high resolution "
- "mode on CPU %d\n", base->cpu);
+ pr_warn("Could not switch to high resolution mode on CPU %u\n",
+ base->cpu);
return;
}
base->hres_active = 1;
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
- printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
- ktime_to_ns(delta));
+ pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
}
/* called with interrupts disabled */
int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
{
switch(restart->nanosleep.type) {
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
case TT_COMPAT:
if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp))
return -EFAULT;
{
struct timespec64 next;
- getnstimeofday64(&next);
+ ktime_get_real_ts64(&next);
if (!fail)
next.tv_sec = 659;
else {
if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
return;
- getnstimeofday64(&now);
+ ktime_get_real_ts64(&now);
adjust = now;
if (persistent_clock_is_local)
* Architectures are strongly encouraged to use rtclib and not
* implement this legacy API.
*/
- getnstimeofday64(&now);
+ ktime_get_real_ts64(&now);
if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
if (persistent_clock_is_local)
adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
/*
* Propagate a new txc->status value into the NTP state:
*/
-static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
+static inline void process_adj_status(const struct timex *txc)
{
if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
time_state = TIME_OK;
}
-static inline void process_adjtimex_modes(struct timex *txc,
- struct timespec64 *ts,
- s32 *time_tai)
+static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
{
if (txc->modes & ADJ_STATUS)
- process_adj_status(txc, ts);
+ process_adj_status(txc);
if (txc->modes & ADJ_NANO)
time_status |= STA_NANO;
* adjtimex mainly allows reading (and writing, if superuser) of
* kernel time-keeping variables. used by xntpd.
*/
-int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
{
int result;
/* If there are input parameters, then process them: */
if (txc->modes)
- process_adjtimex_modes(txc, ts, time_tai);
+ process_adjtimex_modes(txc, time_tai);
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
static int __init ntp_tick_adj_setup(char *str)
{
- int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
-
+ int rc = kstrtos64(str, 0, &ntp_tick_adj);
if (rc)
return rc;
- ntp_tick_adj <<= NTP_SCALE_SHIFT;
+ ntp_tick_adj <<= NTP_SCALE_SHIFT;
return 1;
}
extern u64 ntp_tick_length(void);
extern ktime_t ntp_get_next_leap(void);
extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
+extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
#endif /* _LINUX_NTP_INTERNAL_H */
continue;
timer->it.cpu.expires += incr;
- timer->it_overrun += 1 << i;
+ timer->it_overrun += 1LL << i;
delta -= incr;
}
}
/*
* Disarm any old timer after extracting its expiry time.
*/
- lockdep_assert_irqs_disabled();
ret = 0;
old_incr = timer->it.cpu.incr;
/*
* Now re-arm for the new expiry time.
*/
- lockdep_assert_irqs_disabled();
arm_timer(timer);
unlock:
unlock_task_sighand(p, &flags);
ktime_get_ts64(tp);
break;
case CLOCK_BOOTTIME:
- get_monotonic_boottime64(tp);
+ ktime_get_boottime_ts64(tp);
break;
default:
return -EINVAL;
#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
#endif
-/*
- * parisc wants ENOTSUP instead of EOPNOTSUPP
- */
-#ifndef ENOTSUP
-# define ENANOSLEEP_NOTSUP EOPNOTSUPP
-#else
-# define ENANOSLEEP_NOTSUP ENOTSUP
-#endif
-
/*
* The timer ID is turned into a timer address by idr_find().
* Verifying a valid ID consists of:
*/
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
{
- getrawmonotonic64(tp);
+ ktime_get_raw_ts64(tp);
return 0;
}
static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
{
- *tp = current_kernel_time64();
+ ktime_get_coarse_real_ts64(tp);
return 0;
}
static int posix_get_monotonic_coarse(clockid_t which_clock,
struct timespec64 *tp)
{
- *tp = get_monotonic_coarse64();
+ ktime_get_coarse_ts64(tp);
return 0;
}
static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
- get_monotonic_boottime64(tp);
+ ktime_get_boottime_ts64(tp);
return 0;
}
static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
- timekeeping_clocktai64(tp);
+ ktime_get_clocktai_ts64(tp);
return 0;
}
}
__initcall(init_posix_timers);
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+ s64 sum = timr->it_overrun_last + (s64)baseval;
+
+ return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
static void common_hrtimer_rearm(struct k_itimer *timr)
{
struct hrtimer *timer = &timr->it.real.timer;
if (!timr->it_interval)
return;
- timr->it_overrun += (unsigned int) hrtimer_forward(timer,
- timer->base->get_time(),
- timr->it_interval);
+ timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+ timr->it_interval);
hrtimer_restart(timer);
}
timr->it_active = 1;
timr->it_overrun_last = timr->it_overrun;
- timr->it_overrun = -1;
+ timr->it_overrun = -1LL;
++timr->it_requeue_pending;
- info->si_overrun += timr->it_overrun_last;
+ info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
}
unlock_timer(timr, flags);
now = ktime_add(now, kj);
}
#endif
- timr->it_overrun += (unsigned int)
- hrtimer_forward(timer, now,
- timr->it_interval);
+ timr->it_overrun += hrtimer_forward(timer, now,
+ timr->it_interval);
ret = HRTIMER_RESTART;
++timr->it_requeue_pending;
timr->it_active = 1;
new_timer->it_id = (timer_t) new_timer_id;
new_timer->it_clock = which_clock;
new_timer->kclock = kc;
- new_timer->it_overrun = -1;
+ new_timer->it_overrun = -1LL;
if (event) {
rcu_read_lock();
return __hrtimer_expires_remaining_adjusted(timer, now);
}
-static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
+static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
{
struct hrtimer *timer = &timr->it.real.timer;
- return (int)hrtimer_forward(timer, now, timr->it_interval);
+ return hrtimer_forward(timer, now, timr->it_interval);
}
/*
/* Get the time remaining on a POSIX.1b interval timer. */
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
- struct itimerspec __user *, setting)
+ struct __kernel_itimerspec __user *, setting)
{
struct itimerspec64 cur_setting;
return ret;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
struct compat_itimerspec __user *, setting)
{
}
return ret;
}
+
#endif
/*
if (!timr)
return -EINVAL;
- overrun = timr->it_overrun_last;
+ overrun = timer_overrun_to_int(timr, 0);
unlock_timer(timr, flags);
return overrun;
/* Set a POSIX.1b interval timer */
SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
- const struct itimerspec __user *, new_setting,
- struct itimerspec __user *, old_setting)
+ const struct __kernel_itimerspec __user *, new_setting,
+ struct __kernel_itimerspec __user *, old_setting)
{
struct itimerspec64 new_spec, old_spec;
struct itimerspec64 *rtn = old_setting ? &old_spec : NULL;
return error;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
struct compat_itimerspec __user *, new,
struct compat_itimerspec __user *, old)
if (!kc)
return -EINVAL;
if (!kc->nsleep)
- return -ENANOSLEEP_NOTSUP;
+ return -EOPNOTSUPP;
if (get_timespec64(&t, rqtp))
return -EFAULT;
if (!kc)
return -EINVAL;
if (!kc->nsleep)
- return -ENANOSLEEP_NOTSUP;
+ return -EOPNOTSUPP;
if (compat_get_timespec64(&t, rqtp))
return -EFAULT;
void (*timer_get)(struct k_itimer *timr,
struct itimerspec64 *cur_setting);
void (*timer_rearm)(struct k_itimer *timr);
- int (*timer_forward)(struct k_itimer *timr, ktime_t now);
+ s64 (*timer_forward)(struct k_itimer *timr, ktime_t now);
ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now);
int (*timer_try_to_cancel)(struct k_itimer *timr);
void (*timer_arm)(struct k_itimer *timr, ktime_t expires,
pr_debug("Registered %pF as sched_clock source\n", read);
}
-void __init sched_clock_postinit(void)
+void __init generic_sched_clock_init(void)
{
/*
* If no sched_clock() function has been provided at that point,
.max_delta_ticks = ULONG_MAX,
.mult = 1,
.shift = 0,
- .cpumask = cpu_all_mask,
+ .cpumask = cpu_possible_mask,
};
static enum hrtimer_restart bc_handler(struct hrtimer *t)
*/
return !curdev ||
newdev->rating > curdev->rating ||
- (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
- !tick_check_percpu(curdev, newdev, smp_processor_id()));
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
}
/*
static inline bool local_timer_softirq_pending(void)
{
- return local_softirq_pending() & TIMER_SOFTIRQ;
+ return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
}
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
*/
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
*/
SYSCALL_DEFINE1(time, time_t __user *, tloc)
{
- time_t i = get_seconds();
+ time_t i = (time_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
/* compat_time_t is a 32 bit "long" and needs to get converted. */
COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
{
- struct timeval tv;
compat_time_t i;
- do_gettimeofday(&tv);
- i = tv.tv_sec;
+ i = (compat_time_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
- return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+ return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
+ HZ_TO_MSEC_SHR32;
# else
- return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+ return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
EXPORT_SYMBOL_GPL(compat_put_timespec64);
int get_itimerspec64(struct itimerspec64 *it,
- const struct itimerspec __user *uit)
+ const struct __kernel_itimerspec __user *uit)
{
int ret;
EXPORT_SYMBOL_GPL(get_itimerspec64);
int put_itimerspec64(const struct itimerspec64 *it,
- struct itimerspec __user *uit)
+ struct __kernel_itimerspec __user *uit)
{
int ret;
return ret;
}
EXPORT_SYMBOL_GPL(put_itimerspec64);
+
+int get_compat_itimerspec64(struct itimerspec64 *its,
+ const struct compat_itimerspec __user *uits)
+{
+
+ if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
+ __compat_get_timespec64(&its->it_value, &uits->it_value))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
+
+int put_compat_itimerspec64(const struct itimerspec64 *its,
+ struct compat_itimerspec __user *uits)
+{
+ if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
+ __compat_put_timespec64(&its->it_value, &uits->it_value))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#define TK_MIRROR (1 << 1)
#define TK_CLOCK_WAS_SET (1 << 2)
+enum timekeeping_adv_mode {
+ /* Update timekeeper when a tick has passed */
+ TK_ADV_TICK,
+
+ /* Update timekeeper on a direct frequency change */
+ TK_ADV_FREQ
+};
+
/*
* The most important data for readout fits into a single 64 byte
* cache line.
}
}
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
{
struct timespec64 ts;
* a read of the fast-timekeeper tkrs (which is protected by its own locking
* and update logic).
*/
-static inline u64 tk_clock_read(struct tk_read_base *tkr)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
{
struct clocksource *clock = READ_ONCE(tkr->clock);
}
}
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
{
struct timekeeper *tk = &tk_core.timekeeper;
u64 now, last, mask, max, delta;
static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
{
}
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
{
u64 cycle_now, delta;
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
{
u64 nsec;
return nsec + arch_gettimeoffset();
}
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
{
u64 delta;
return timekeeping_delta_to_ns(tkr, delta);
}
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
{
u64 delta;
* slightly wrong timestamp (a few nanoseconds). See
* @ktime_get_mono_fast_ns.
*/
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+ struct tk_fast *tkf)
{
struct tk_read_base *base = tkf->base;
* number of cycles every time until timekeeping is resumed at which time the
* proper readout base for the fast timekeeper will be restored automatically.
*/
-static void halt_fast_timekeeper(struct timekeeper *tk)
+static void halt_fast_timekeeper(const struct timekeeper *tk)
{
static struct tk_read_base tkr_dummy;
- struct tk_read_base *tkr = &tk->tkr_mono;
+ const struct tk_read_base *tkr = &tk->tkr_mono;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
cycles_at_suspend = tk_clock_read(tkr);
*
* Adds or subtracts an offset value from the current time.
*/
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long flags;
}
/**
- * read_boot_clock64 - Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ * from the boot.
*
* Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- * XXX - Do be sure to remove it once all arches implement it.
+ * wall_time - current time as returned by persistent clock
+ * boot_offset - offset that is defined as wall_time - boot_time
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
*/
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+ struct timespec64 *boot_offset)
{
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
+ read_persistent_clock64(wall_time);
+ *boot_offset = ns_to_timespec64(local_clock());
}
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
/* Flag for if there is a persistent clock on this platform */
static bool persistent_clock_exists;
*/
void __init timekeeping_init(void)
{
+ struct timespec64 wall_time, boot_offset, wall_to_mono;
struct timekeeper *tk = &tk_core.timekeeper;
struct clocksource *clock;
unsigned long flags;
- struct timespec64 now, boot, tmp;
-
- read_persistent_clock64(&now);
- if (!timespec64_valid_strict(&now)) {
- pr_warn("WARNING: Persistent clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- now.tv_sec = 0;
- now.tv_nsec = 0;
- } else if (now.tv_sec || now.tv_nsec)
- persistent_clock_exists = true;
- read_boot_clock64(&boot);
- if (!timespec64_valid_strict(&boot)) {
- pr_warn("WARNING: Boot clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- boot.tv_sec = 0;
- boot.tv_nsec = 0;
+ read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+ if (timespec64_valid_strict(&wall_time) &&
+ timespec64_to_ns(&wall_time) > 0) {
+ persistent_clock_exists = true;
+ } else if (timespec64_to_ns(&wall_time) != 0) {
+ pr_warn("Persistent clock returned invalid value");
+ wall_time = (struct timespec64){0};
}
+ if (timespec64_compare(&wall_time, &boot_offset) < 0)
+ boot_offset = (struct timespec64){0};
+
+ /*
+ * We want set wall_to_mono, so the following is true:
+ * wall time + wall_to_mono = boot time
+ */
+ wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
ntp_init();
clock->enable(clock);
tk_setup_internals(tk, clock);
- tk_set_xtime(tk, &now);
+ tk_set_xtime(tk, &wall_time);
tk->raw_sec = 0;
- if (boot.tv_sec == 0 && boot.tv_nsec == 0)
- boot = tk_xtime(tk);
- set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
- tk_set_wall_to_mono(tk, tmp);
+ tk_set_wall_to_mono(tk, wall_to_mono);
timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
* adds the sleep offset to the timekeeping variables.
*/
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
- struct timespec64 *delta)
+ const struct timespec64 *delta)
{
if (!timespec64_valid_strict(delta)) {
printk_deferred(KERN_WARNING
*/
bool timekeeping_rtc_skipresume(void)
{
- return sleeptime_injected;
+ return !suspend_timing_needed;
}
/**
* This function should only be called by rtc_resume(), and allows
* a suspend offset to be injected into the timekeeping values.
*/
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
+ suspend_timing_needed = false;
+
timekeeping_forward_now(tk);
__timekeeping_inject_sleeptime(tk, delta);
struct clocksource *clock = tk->tkr_mono.clock;
unsigned long flags;
struct timespec64 ts_new, ts_delta;
- u64 cycle_now;
+ u64 cycle_now, nsec;
+ bool inject_sleeptime = false;
- sleeptime_injected = false;
read_persistent_clock64(&ts_new);
clockevents_resume();
* usable source. The rtc part is handled separately in rtc core code.
*/
cycle_now = tk_clock_read(&tk->tkr_mono);
- if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
- cycle_now > tk->tkr_mono.cycle_last) {
- u64 nsec, cyc_delta;
-
- cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
- tk->tkr_mono.mask);
- nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+ nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+ if (nsec > 0) {
ts_delta = ns_to_timespec64(nsec);
- sleeptime_injected = true;
+ inject_sleeptime = true;
} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
- sleeptime_injected = true;
+ inject_sleeptime = true;
}
- if (sleeptime_injected)
+ if (inject_sleeptime) {
+ suspend_timing_needed = false;
__timekeeping_inject_sleeptime(tk, &ts_delta);
+ }
/* Re-base the last cycle value */
tk->tkr_mono.cycle_last = cycle_now;
unsigned long flags;
struct timespec64 delta, delta_delta;
static struct timespec64 old_delta;
+ struct clocksource *curr_clock;
+ u64 cycle_now;
read_persistent_clock64(&timekeeping_suspend_time);
if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
persistent_clock_exists = true;
+ suspend_timing_needed = true;
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
timekeeping_forward_now(tk);
timekeeping_suspended = 1;
+ /*
+ * Since we've called forward_now, cycle_last stores the value
+ * just read from the current clocksource. Save this to potentially
+ * use in suspend timing.
+ */
+ curr_clock = tk->tkr_mono.clock;
+ cycle_now = tk->tkr_mono.cycle_last;
+ clocksource_start_suspend_timing(curr_clock, cycle_now);
+
if (persistent_clock_exists) {
/*
* To avoid drift caused by repeated suspend/resumes,
return offset;
}
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
*/
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
{
struct timekeeper *real_tk = &tk_core.timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
offset = real_tk->cycle_interval;
+
+ if (mode != TK_ADV_TICK)
+ goto out;
#else
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
/* Check if there's really nothing to do */
- if (offset < real_tk->cycle_interval)
+ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
goto out;
+#endif
/* Do some additional sanity checking */
timekeeping_check_update(tk, offset);
clock_was_set_delayed();
}
+/**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+ timekeeping_advance(TK_ADV_TICK);
+}
+
/**
* getboottime64 - Return the real time of system boot.
* @ts: pointer to the timespec64 to be set
/**
* timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
{
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
return ret;
}
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ /* Update the multiplier immediately if frequency was set directly */
+ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+ timekeeping_advance(TK_ADV_FREQ);
+
if (tai != orig_tai)
clock_was_set();
}
late_initcall(tk_debug_sleep_time_init);
-void tk_debug_account_sleep_time(struct timespec64 *t)
+void tk_debug_account_sleep_time(const struct timespec64 *t)
{
/* Cap bin index so we don't overflow the array */
int bin = min(fls(t->tv_sec), NUM_BINS-1);
#include <linux/time.h>
#ifdef CONFIG_DEBUG_FS
-extern void tk_debug_account_sleep_time(struct timespec64 *t);
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
#else
#define tk_debug_account_sleep_time(x)
#endif
* wheel:
*/
base->next_expiry = timer->expires;
- wake_up_nohz_cpu(base->cpu);
+ wake_up_nohz_cpu(base->cpu);
}
static void
raw_spin_lock_irq(&base->lock);
+ /*
+ * timer_base::must_forward_clk must be cleared before running
+ * timers so that any timer functions that call mod_timer() will
+ * not try to forward the base. Idle tracking / clock forwarding
+ * logic is only used with BASE_STD timers.
+ *
+ * The must_forward_clk flag is cleared unconditionally also for
+ * the deferrable base. The deferrable base is not affected by idle
+ * tracking and never forwarded, so clearing the flag is a NOOP.
+ *
+ * The fact that the deferrable base is never forwarded can cause
+ * large variations in granularity for deferrable timers, but they
+ * can be deferred for long periods due to idle anyway.
+ */
+ base->must_forward_clk = false;
+
while (time_after_eq(jiffies, base->clk)) {
levels = collect_expired_timers(base, heads);
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
- /*
- * must_forward_clk must be cleared before running timers so that any
- * timer functions that call mod_timer will not try to forward the
- * base. idle trcking / clock forwarding logic is only used with
- * BASE_STD timers.
- *
- * The deferrable base does not do idle tracking at all, so we do
- * not forward it. This can result in very large variations in
- * granularity for deferrable timers, but they can be deferred for
- * long periods due to idle.
- */
- base->must_forward_clk = false;
-
__run_timers(base);
if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
* Author: Paul E. McKenney <paulmck@us.ibm.com>
* Based on kernel/rcu/torture.c.
*/
+
+#define pr_fmt(fmt) fmt
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
static char *torture_type;
-static bool verbose;
+static int verbose;
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlining %d\n",
torture_type, cpu);
"torture_onoff task: offline %d failed: errno %d\n",
torture_type, cpu, ret);
} else {
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlined %d\n",
torture_type, cpu);
if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: onlining %d\n",
torture_type, cpu);
"torture_onoff task: online %d failed: errno %d\n",
torture_type, cpu, ret);
} else {
- if (verbose)
+ if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: onlined %d\n",
torture_type, cpu);
* The runnable parameter points to a flag that controls whether or not
* the test is currently runnable. If there is no such flag, pass in NULL.
*/
-bool torture_init_begin(char *ttype, bool v)
+bool torture_init_begin(char *ttype, int v)
{
mutex_lock(&fullstop_mutex);
if (torture_type != NULL) {
config HAVE_FTRACE_NMI_ENTER
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_FUNCTION_TRACER
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_FUNCTION_GRAPH_TRACER
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_DYNAMIC_FTRACE
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_DYNAMIC_FTRACE_WITH_REGS
bool
config HAVE_FTRACE_MCOUNT_RECORD
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_SYSCALL_TRACEPOINTS
bool
help
- See Documentation/trace/ftrace-design.txt
+ See Documentation/trace/ftrace-design.rst
config HAVE_FENTRY
bool
help
This allows the user to add tracing events (similar to tracepoints)
on the fly via the ftrace interface. See
- Documentation/trace/kprobetrace.txt for more details.
+ Documentation/trace/kprobetrace.rst for more details.
Those events can be inserted wherever kprobes can probe, and record
various register and memory values.
implementation and works via page faults. Tracing is disabled by
default and can be enabled at run-time.
- See Documentation/trace/mmiotrace.txt.
+ See Documentation/trace/mmiotrace.rst.
If you are not helping to develop drivers, say N.
config TRACING_MAP
op->saved_func(ip, parent_ip, op, regs);
}
-/**
- * clear_ftrace_function - reset the ftrace function
- *
- * This NULLs the ftrace function and in essence stops
- * tracing. There may be lag
- */
-void clear_ftrace_function(void)
-{
- ftrace_trace_function = ftrace_stub;
-}
-
static void ftrace_sync(struct work_struct *work)
{
/*
{
ftrace_disabled = 1;
ftrace_enabled = 0;
- clear_ftrace_function();
+ ftrace_trace_function = ftrace_stub;
}
/**
return !atomic_read(&buffer->record_disabled);
}
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf;
-
if (tr->stop_count)
return;
arch_spin_lock(&tr->max_lock);
- buf = tr->trace_buffer.buffer;
- tr->trace_buffer.buffer = tr->max_buffer.buffer;
- tr->max_buffer.buffer = buf;
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
+ swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
+__printf(3, 0)
static int
__trace_array_vprintk(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, va_list args)
return len;
}
+__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}
+__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
return ret;
}
+__printf(3, 4)
int trace_array_printk_buf(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
return ret;
}
+__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
print_event_info(buf, m);
- seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
- seq_printf(m, "# | | | %s | |\n", tgid ? " | " : "");
+ seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
+ seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
}
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
tgid ? tgid_space : space);
seq_printf(m, "# %s||| / delay\n",
tgid ? tgid_space : space);
- seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n",
+ seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n",
tgid ? " TGID " : space);
- seq_printf(m, "# | | | %s|||| | |\n",
+ seq_printf(m, "# | | %s | |||| | |\n",
tgid ? " | " : space);
}
static inline struct ring_buffer_iter *
trace_buffer_iter(struct trace_iterator *iter, int cpu)
{
- if (iter->buffer_iter && iter->buffer_iter[cpu])
- return iter->buffer_iter[cpu];
- return NULL;
+ return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
}
int tracer_init(struct tracer *t, struct trace_array *tr);
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
- C(INVALID_VALUE, "Invalid value (did you forget quotes)?"),
+ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
+ C(NO_FILTER, "No filter found"),
#undef C
#define C(a, b) FILT_ERR_##a
goto out_free;
}
+ if (!N) {
+ /* No program? */
+ ret = -EINVAL;
+ parse_error(pe, FILT_ERR_NO_FILTER, ptr - str);
+ goto out_free;
+ }
+
prog[N].pred = NULL; /* #13 */
prog[N].target = 1; /* TRUE */
prog[N+1].pred = NULL;
* @filter_str: filter string
* @set_str: remember @filter_str and enable detailed error in filter
* @filterp: out param for created filter (always updated on return)
+ * Must be a pointer that references a NULL pointer.
*
* Creates a filter for @call with @filter_str. If @set_str is %true,
* @filter_str is copied and recorded in the new filter.
struct filter_parse_error *pe = NULL;
int err;
+ /* filterp must point to NULL */
+ if (WARN_ON(*filterp))
+ *filterp = NULL;
+
err = create_filter_start(filter_string, set_str, &pe, filterp);
if (err)
return err;
else if (system)
snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
else
- strncpy(err, var, MAX_FILTER_STR_VAL);
+ strscpy(err, var, MAX_FILTER_STR_VAL);
hist_err(str, err);
}
goto out_free;
out_reg:
+ /* Up the trigger_data count to make sure reg doesn't free it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
/*
* The above returns on success the # of functions enabled,
* Consider no functions a failure too.
*/
if (!ret) {
+ cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
ret = -ENOENT;
- goto out_free;
- } else if (ret < 0)
- goto out_free;
- ret = 0;
+ } else if (ret > 0)
+ ret = 0;
+
+ /* Down the counter of trigger_data or free it if not used anymore */
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
goto out;
}
+ /* Up the trigger_data count to make sure nothing frees it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
+
if (trigger) {
number = strsep(&trigger, ":");
goto out_disable;
/* Just return zero, not the number of enabled functions */
ret = 0;
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
- kfree(trigger_data);
+ event_trigger_free(trigger_ops, trigger_data);
kfree(enable_data);
goto out;
}
struct ftrace_graph_ret *graph_ret;
struct ftrace_graph_ent *call;
unsigned long long duration;
+ int cpu = iter->cpu;
int i;
graph_ret = &ret_entry->ret;
if (data) {
struct fgraph_cpu_data *cpu_data;
- int cpu = iter->cpu;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+ cpu, iter->ent->pid, flags);
+
return trace_handle_return(s);
}
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
+ struct event_file_link *link = NULL;
int ret = 0;
if (file) {
- struct event_file_link *link;
-
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
ret = -ENOMEM;
else
ret = enable_kprobe(&tk->rp.kp);
}
+
+ if (ret) {
+ if (file) {
+ /* Notice the if is true on not WARN() */
+ if (!WARN_ON_ONCE(!link))
+ list_del_rcu(&link->list);
+ kfree(link);
+ tk->tp.flags &= ~TP_FLAG_TRACE;
+ } else {
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
+ }
+ }
out:
return ret;
}
/*
* We need to check and see if we modified the pc of the
- * pt_regs, and if so clear the kprobe and return 1 so that we
- * don't do the single stepping.
- * The ftrace kprobe handler leaves it up to us to re-enable
- * preemption here before returning if we've modified the ip.
+ * pt_regs, and if so return 1 so that we don't do the
+ * single stepping.
*/
- if (orig_ip != instruction_pointer(regs)) {
- reset_current_kprobe();
- preempt_enable_no_resched();
+ if (orig_ip != instruction_pointer(regs))
return 1;
- }
if (!ret)
return 0;
}
}
ret = __register_trace_kprobe(tk);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(tk->tp.call.print_fmt);
goto error;
+ }
return &tk->tp.call;
error:
}
__unregister_trace_kprobe(tk);
+
+ kfree(tk->tp.call.print_fmt);
free_trace_kprobe(tk);
}
#endif /* CONFIG_PERF_EVENTS */
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
trace_seq_printf(s, "(%5d) ", tgid);
}
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
+
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
#include <linux/tick.h>
-#include <linux/workqueue.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
#include <asm/irq_regs.h>
#include <linux/kvm_para.h>
-#include <linux/kthread.h>
static DEFINE_MUTEX(watchdog_mutex);
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
static u64 __read_mostly sample_period;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
__this_cpu_inc(hrtimer_interrupts);
}
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+ __this_cpu_write(soft_lockup_hrtimer_cnt,
+ __this_cpu_read(hrtimer_interrupts));
+ __touch_watchdog();
+ complete(this_cpu_ptr(&softlockup_completion));
+
+ return 0;
+}
+
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
watchdog_interrupt_count();
/* kick the softlockup detector */
- wake_up_process(__this_cpu_read(softlockup_watchdog));
+ if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+ reinit_completion(this_cpu_ptr(&softlockup_completion));
+ stop_one_cpu_nowait(smp_processor_id(),
+ softlockup_fn, NULL,
+ this_cpu_ptr(&softlockup_stop_work));
+ }
/* .. and repeat */
hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
return HRTIMER_RESTART;
}
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
- struct sched_param param = { .sched_priority = prio };
-
- sched_setscheduler(current, policy, ¶m);
-}
-
static void watchdog_enable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+ struct completion *done = this_cpu_ptr(&softlockup_completion);
+
+ WARN_ON_ONCE(cpu != smp_processor_id());
+
+ init_completion(done);
+ complete(done);
/*
* Start the timer first to prevent the NMI watchdog triggering
/* Enable the perf event */
if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
watchdog_nmi_enable(cpu);
-
- watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
}
static void watchdog_disable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
- watchdog_set_prio(SCHED_NORMAL, 0);
+ WARN_ON_ONCE(cpu != smp_processor_id());
+
/*
* Disable the perf event first. That prevents that a large delay
* between disabling the timer and disabling the perf event causes
*/
watchdog_nmi_disable(cpu);
hrtimer_cancel(hrtimer);
+ wait_for_completion(this_cpu_ptr(&softlockup_completion));
}
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
{
- watchdog_disable(cpu);
+ watchdog_disable(smp_processor_id());
+ return 0;
}
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
{
- return __this_cpu_read(hrtimer_interrupts) !=
- __this_cpu_read(soft_lockup_hrtimer_cnt);
+ int cpu;
+
+ if (!softlockup_initialized)
+ return;
+
+ for_each_cpu(cpu, &watchdog_allowed_mask)
+ smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+ cpumask_clear(&watchdog_allowed_mask);
}
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
{
- __this_cpu_write(soft_lockup_hrtimer_cnt,
- __this_cpu_read(hrtimer_interrupts));
- __touch_watchdog();
+ watchdog_enable(smp_processor_id());
+ return 0;
}
-static struct smp_hotplug_thread watchdog_threads = {
- .store = &softlockup_watchdog,
- .thread_should_run = watchdog_should_run,
- .thread_fn = watchdog,
- .thread_comm = "watchdog/%u",
- .setup = watchdog_enable,
- .cleanup = watchdog_cleanup,
- .park = watchdog_disable,
- .unpark = watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
{
- lockdep_assert_held(&watchdog_mutex);
-
- if (!softlockup_threads_initialized)
- return;
+ int cpu;
- smpboot_update_cpumask_percpu_thread(&watchdog_threads,
- &watchdog_allowed_mask);
+ cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+ for_each_cpu(cpu, &watchdog_allowed_mask)
+ smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
}
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
{
- cpumask_clear(&watchdog_allowed_mask);
- softlockup_update_smpboot_threads();
+ watchdog_enable(cpu);
+ return 0;
}
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
{
- cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
- softlockup_update_smpboot_threads();
+ watchdog_disable(cpu);
+ return 0;
}
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
- softlockup_park_all_threads();
+
+ softlockup_stop_all();
set_sample_period();
lockup_detector_update_enable();
if (watchdog_enabled && watchdog_thresh)
- softlockup_unpark_threads();
+ softlockup_start_all();
+
watchdog_nmi_start();
cpus_read_unlock();
/*
*/
static __init void lockup_detector_setup(void)
{
- int ret;
-
/*
* If sysctl is off and watchdog got disabled on the command line,
* nothing to do here.
!(watchdog_enabled && watchdog_thresh))
return;
- ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
- &watchdog_allowed_mask);
- if (ret) {
- pr_err("Failed to initialize soft lockup detector threads\n");
- return;
- }
-
mutex_lock(&watchdog_mutex);
- softlockup_threads_initialized = true;
lockup_detector_reconfigure();
+ softlockup_initialized = true;
mutex_unlock(&watchdog_mutex);
}
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
watchdog_overflow_callback, NULL);
if (IS_ERR(evt)) {
- pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
- PTR_ERR(evt));
+ pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+ PTR_ERR(evt));
return PTR_ERR(evt);
}
this_cpu_write(watchdog_ev, evt);
See:
- Documentation/assoc_array.txt
+ Documentation/core-api/assoc_array.rst
for more information.
depends on HAS_IOMEM && !NO_IOPORT_MAP
default y
-config HAS_DMA
- bool
- depends on !NO_DMA
- default y
+source "kernel/dma/Kconfig"
config SGL_ALLOC
bool
default n
-config NEED_SG_DMA_LENGTH
- bool
-
-config NEED_DMA_MAP_STATE
- bool
-
-config ARCH_DMA_ADDR_T_64BIT
- def_bool 64BIT || PHYS_ADDR_T_64BIT
-
config IOMMU_HELPER
bool
-config ARCH_HAS_SYNC_DMA_FOR_DEVICE
- bool
-
-config ARCH_HAS_SYNC_DMA_FOR_CPU
- bool
- select NEED_DMA_MAP_STATE
-
-config DMA_DIRECT_OPS
- bool
- depends on HAS_DMA
-
-config DMA_NONCOHERENT_OPS
- bool
- depends on HAS_DMA
- select DMA_DIRECT_OPS
-
-config DMA_NONCOHERENT_MMAP
- bool
- depends on DMA_NONCOHERENT_OPS
-
-config DMA_NONCOHERENT_CACHE_SYNC
- bool
- depends on DMA_NONCOHERENT_OPS
-
-config DMA_VIRT_OPS
- bool
- depends on HAS_DMA
-
-config SWIOTLB
- bool
- select DMA_DIRECT_OPS
- select NEED_DMA_MAP_STATE
-
config CHECK_SIGNATURE
bool
If unsure, say N.
+config FUNCTION_ERROR_INJECTION
+ def_bool y
+ depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES
+
config FAULT_INJECTION
bool "Fault-injection framework"
depends on DEBUG_KERNEL
Provide fault-injection framework.
For more details, see Documentation/fault-injection/.
-config FUNCTION_ERROR_INJECTION
- def_bool y
- depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES
-
config FAILSLAB
bool "Fault-injection capability for kmalloc"
depends on FAULT_INJECTION
Only works with drivers that use the generic timeout handling,
for others it wont do anything.
-config FAIL_MMC_REQUEST
- bool "Fault-injection capability for MMC IO"
- depends on FAULT_INJECTION_DEBUG_FS && MMC
- help
- Provide fault-injection capability for MMC IO.
- This will make the mmc core return data errors. This is
- useful to test the error handling in the mmc block device
- and to test how the mmc host driver handles retries from
- the block device.
-
config FAIL_FUTEX
bool "Fault-injection capability for futexes"
select DEBUG_FS
help
Provide fault-injection capability for futexes.
+config FAULT_INJECTION_DEBUG_FS
+ bool "Debugfs entries for fault-injection capabilities"
+ depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+ help
+ Enable configuration of fault-injection capabilities via debugfs.
+
config FAIL_FUNCTION
bool "Fault-injection capability for functions"
depends on FAULT_INJECTION_DEBUG_FS && FUNCTION_ERROR_INJECTION
an error value and have to handle it. This is useful to test the
error handling in various subsystems.
-config FAULT_INJECTION_DEBUG_FS
- bool "Debugfs entries for fault-injection capabilities"
- depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+config FAIL_MMC_REQUEST
+ bool "Fault-injection capability for MMC IO"
+ depends on FAULT_INJECTION_DEBUG_FS && MMC
help
- Enable configuration of fault-injection capabilities via debugfs.
+ Provide fault-injection capability for MMC IO.
+ This will make the mmc core return data errors. This is
+ useful to test the error handling in the mmc block device
+ and to test how the mmc host driver handles retries from
+ the block device.
config FAULT_INJECTION_STACKTRACE_FILTER
bool "stacktrace filter for fault-injection capabilities"
default n
help
This option provides for testing basic kprobes functionality on
- boot. A sample kprobe, jprobe and kretprobe are inserted and
+ boot. Samples of kprobe and kretprobe are inserted and
verified for functionality.
Say N if you are unsure.
config KASAN
bool "KASan: runtime memory debugger"
- depends on SLUB || (SLAB && !DEBUG_SLAB)
+ depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+ select SLUB_DEBUG if SLUB
select CONSTRUCTORS
select STACKDEPOT
help
config ARCH_HAS_UBSAN_SANITIZE_ALL
bool
-config ARCH_WANTS_UBSAN_NO_NULL
- def_bool n
-
config UBSAN
bool "Undefined behaviour sanity checker"
help
Enabling this option on architectures that support unaligned
accesses may produce a lot of false positives.
-config UBSAN_NULL
- bool "Enable checking of null pointers"
- depends on UBSAN
- default y if !ARCH_WANTS_UBSAN_NO_NULL
- help
- This option enables detection of memory accesses via a
- null pointer.
-
config TEST_UBSAN
tristate "Module for testing for undefined behavior detection"
depends on m && UBSAN
sha1.o chacha20.o irq_regs.o argv_split.o \
flex_proportions.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o seq_buf.o siphash.o \
+ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
nmi_backtrace.o nodemask.o win_minmax.o
lib-$(CONFIG_PRINTK) += dump_stack.o
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
-lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
-lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
-lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
lib-y += kobject.o klist.o
obj-y += lockref.o
obj-$(CONFIG_DEBUG_LIST) += list_debug.o
obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
-ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
- lib-y += dec_and_lock.o
-endif
-
obj-$(CONFIG_BITREVERSE) += bitrev.o
obj-$(CONFIG_RATIONAL) += rational.o
obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
obj-$(CONFIG_AUDIT_GENERIC) += audit.o
obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
-obj-$(CONFIG_SWIOTLB) += swiotlb.o
obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
obj-$(CONFIG_LRU_CACHE) += lru_cache.o
-obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
-
obj-$(CONFIG_GENERIC_CSUM) += checksum.o
obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
}
EXPORT_SYMBOL(atomic64_xchg);
-int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
{
unsigned long flags;
raw_spinlock_t *lock = lock_addr(v);
- int ret = 0;
+ long long val;
raw_spin_lock_irqsave(lock, flags);
- if (v->counter != u) {
+ val = v->counter;
+ if (val != u)
v->counter += a;
- ret = 1;
- }
raw_spin_unlock_irqrestore(lock, flags);
- return ret;
+
+ return val;
}
-EXPORT_SYMBOL(atomic64_add_unless);
+EXPORT_SYMBOL(atomic64_fetch_add_unless);
limit++;
if (is_on_stack)
- pr_warn("object is on stack, but not annotated\n");
+ pr_warn("object %p is on stack %p, but NOT annotated.\n", addr,
+ task_stack_page(current));
else
- pr_warn("object is not on stack, but annotated\n");
+ pr_warn("object %p is NOT on stack %p, but annotated.\n", addr,
+ task_stack_page(current));
+
WARN_ON(1);
}
if (!obj_cache || debug_objects_replace_static_objects()) {
debug_objects_enabled = 0;
- if (obj_cache)
- kmem_cache_destroy(obj_cache);
+ kmem_cache_destroy(obj_cache);
pr_warn("out of memory.\n");
} else
debug_objects_selftest();
}
EXPORT_SYMBOL(_atomic_dec_and_lock);
+
+int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags)
+{
+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+ if (atomic_add_unless(atomic, -1, 1))
+ return 0;
+
+ /* Otherwise do it the slow way */
+ spin_lock_irqsave(lock, *flags);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ spin_unlock_irqrestore(lock, *flags);
+ return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
+++ /dev/null
-/*
- * Copyright (C) 2008 Advanced Micro Devices, Inc.
- *
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#include <linux/sched/task_stack.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
-#include <linux/sched/task.h>
-#include <linux/stacktrace.h>
-#include <linux/dma-debug.h>
-#include <linux/spinlock.h>
-#include <linux/vmalloc.h>
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
-#include <linux/export.h>
-#include <linux/device.h>
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/ctype.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-
-#include <asm/sections.h>
-
-#define HASH_SIZE 1024ULL
-#define HASH_FN_SHIFT 13
-#define HASH_FN_MASK (HASH_SIZE - 1)
-
-/* allow architectures to override this if absolutely required */
-#ifndef PREALLOC_DMA_DEBUG_ENTRIES
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-#endif
-
-enum {
- dma_debug_single,
- dma_debug_page,
- dma_debug_sg,
- dma_debug_coherent,
- dma_debug_resource,
-};
-
-enum map_err_types {
- MAP_ERR_CHECK_NOT_APPLICABLE,
- MAP_ERR_NOT_CHECKED,
- MAP_ERR_CHECKED,
-};
-
-#define DMA_DEBUG_STACKTRACE_ENTRIES 5
-
-/**
- * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
- * @list: node on pre-allocated free_entries list
- * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
- * @type: single, page, sg, coherent
- * @pfn: page frame of the start address
- * @offset: offset of mapping relative to pfn
- * @size: length of the mapping
- * @direction: enum dma_data_direction
- * @sg_call_ents: 'nents' from dma_map_sg
- * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
- * @map_err_type: track whether dma_mapping_error() was checked
- * @stacktrace: support backtraces when a violation is detected
- */
-struct dma_debug_entry {
- struct list_head list;
- struct device *dev;
- int type;
- unsigned long pfn;
- size_t offset;
- u64 dev_addr;
- u64 size;
- int direction;
- int sg_call_ents;
- int sg_mapped_ents;
- enum map_err_types map_err_type;
-#ifdef CONFIG_STACKTRACE
- struct stack_trace stacktrace;
- unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
-#endif
-};
-
-typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
-
-struct hash_bucket {
- struct list_head list;
- spinlock_t lock;
-} ____cacheline_aligned_in_smp;
-
-/* Hash list to save the allocated dma addresses */
-static struct hash_bucket dma_entry_hash[HASH_SIZE];
-/* List of pre-allocated dma_debug_entry's */
-static LIST_HEAD(free_entries);
-/* Lock for the list above */
-static DEFINE_SPINLOCK(free_entries_lock);
-
-/* Global disable flag - will be set in case of an error */
-static bool global_disable __read_mostly;
-
-/* Early initialization disable flag, set at the end of dma_debug_init */
-static bool dma_debug_initialized __read_mostly;
-
-static inline bool dma_debug_disabled(void)
-{
- return global_disable || !dma_debug_initialized;
-}
-
-/* Global error count */
-static u32 error_count;
-
-/* Global error show enable*/
-static u32 show_all_errors __read_mostly;
-/* Number of errors to show */
-static u32 show_num_errors = 1;
-
-static u32 num_free_entries;
-static u32 min_free_entries;
-static u32 nr_total_entries;
-
-/* number of preallocated entries requested by kernel cmdline */
-static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
-
-/* debugfs dentry's for the stuff above */
-static struct dentry *dma_debug_dent __read_mostly;
-static struct dentry *global_disable_dent __read_mostly;
-static struct dentry *error_count_dent __read_mostly;
-static struct dentry *show_all_errors_dent __read_mostly;
-static struct dentry *show_num_errors_dent __read_mostly;
-static struct dentry *num_free_entries_dent __read_mostly;
-static struct dentry *min_free_entries_dent __read_mostly;
-static struct dentry *filter_dent __read_mostly;
-
-/* per-driver filter related state */
-
-#define NAME_MAX_LEN 64
-
-static char current_driver_name[NAME_MAX_LEN] __read_mostly;
-static struct device_driver *current_driver __read_mostly;
-
-static DEFINE_RWLOCK(driver_name_lock);
-
-static const char *const maperr2str[] = {
- [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
- [MAP_ERR_NOT_CHECKED] = "dma map error not checked",
- [MAP_ERR_CHECKED] = "dma map error checked",
-};
-
-static const char *type2name[5] = { "single", "page",
- "scather-gather", "coherent",
- "resource" };
-
-static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
- "DMA_FROM_DEVICE", "DMA_NONE" };
-
-/*
- * The access to some variables in this macro is racy. We can't use atomic_t
- * here because all these variables are exported to debugfs. Some of them even
- * writeable. This is also the reason why a lock won't help much. But anyway,
- * the races are no big deal. Here is why:
- *
- * error_count: the addition is racy, but the worst thing that can happen is
- * that we don't count some errors
- * show_num_errors: the subtraction is racy. Also no big deal because in
- * worst case this will result in one warning more in the
- * system log than the user configured. This variable is
- * writeable via debugfs.
- */
-static inline void dump_entry_trace(struct dma_debug_entry *entry)
-{
-#ifdef CONFIG_STACKTRACE
- if (entry) {
- pr_warning("Mapped at:\n");
- print_stack_trace(&entry->stacktrace, 0);
- }
-#endif
-}
-
-static bool driver_filter(struct device *dev)
-{
- struct device_driver *drv;
- unsigned long flags;
- bool ret;
-
- /* driver filter off */
- if (likely(!current_driver_name[0]))
- return true;
-
- /* driver filter on and initialized */
- if (current_driver && dev && dev->driver == current_driver)
- return true;
-
- /* driver filter on, but we can't filter on a NULL device... */
- if (!dev)
- return false;
-
- if (current_driver || !current_driver_name[0])
- return false;
-
- /* driver filter on but not yet initialized */
- drv = dev->driver;
- if (!drv)
- return false;
-
- /* lock to protect against change of current_driver_name */
- read_lock_irqsave(&driver_name_lock, flags);
-
- ret = false;
- if (drv->name &&
- strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
- current_driver = drv;
- ret = true;
- }
-
- read_unlock_irqrestore(&driver_name_lock, flags);
-
- return ret;
-}
-
-#define err_printk(dev, entry, format, arg...) do { \
- error_count += 1; \
- if (driver_filter(dev) && \
- (show_all_errors || show_num_errors > 0)) { \
- WARN(1, "%s %s: " format, \
- dev ? dev_driver_string(dev) : "NULL", \
- dev ? dev_name(dev) : "NULL", ## arg); \
- dump_entry_trace(entry); \
- } \
- if (!show_all_errors && show_num_errors > 0) \
- show_num_errors -= 1; \
- } while (0);
-
-/*
- * Hash related functions
- *
- * Every DMA-API request is saved into a struct dma_debug_entry. To
- * have quick access to these structs they are stored into a hash.
- */
-static int hash_fn(struct dma_debug_entry *entry)
-{
- /*
- * Hash function is based on the dma address.
- * We use bits 20-27 here as the index into the hash
- */
- return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK;
-}
-
-/*
- * Request exclusive access to a hash bucket for a given dma_debug_entry.
- */
-static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
- unsigned long *flags)
- __acquires(&dma_entry_hash[idx].lock)
-{
- int idx = hash_fn(entry);
- unsigned long __flags;
-
- spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags);
- *flags = __flags;
- return &dma_entry_hash[idx];
-}
-
-/*
- * Give up exclusive access to the hash bucket
- */
-static void put_hash_bucket(struct hash_bucket *bucket,
- unsigned long *flags)
- __releases(&bucket->lock)
-{
- unsigned long __flags = *flags;
-
- spin_unlock_irqrestore(&bucket->lock, __flags);
-}
-
-static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
-{
- return ((a->dev_addr == b->dev_addr) &&
- (a->dev == b->dev)) ? true : false;
-}
-
-static bool containing_match(struct dma_debug_entry *a,
- struct dma_debug_entry *b)
-{
- if (a->dev != b->dev)
- return false;
-
- if ((b->dev_addr <= a->dev_addr) &&
- ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
- return true;
-
- return false;
-}
-
-/*
- * Search a given entry in the hash bucket list
- */
-static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
- struct dma_debug_entry *ref,
- match_fn match)
-{
- struct dma_debug_entry *entry, *ret = NULL;
- int matches = 0, match_lvl, last_lvl = -1;
-
- list_for_each_entry(entry, &bucket->list, list) {
- if (!match(ref, entry))
- continue;
-
- /*
- * Some drivers map the same physical address multiple
- * times. Without a hardware IOMMU this results in the
- * same device addresses being put into the dma-debug
- * hash multiple times too. This can result in false
- * positives being reported. Therefore we implement a
- * best-fit algorithm here which returns the entry from
- * the hash which fits best to the reference value
- * instead of the first-fit.
- */
- matches += 1;
- match_lvl = 0;
- entry->size == ref->size ? ++match_lvl : 0;
- entry->type == ref->type ? ++match_lvl : 0;
- entry->direction == ref->direction ? ++match_lvl : 0;
- entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
-
- if (match_lvl == 4) {
- /* perfect-fit - return the result */
- return entry;
- } else if (match_lvl > last_lvl) {
- /*
- * We found an entry that fits better then the
- * previous one or it is the 1st match.
- */
- last_lvl = match_lvl;
- ret = entry;
- }
- }
-
- /*
- * If we have multiple matches but no perfect-fit, just return
- * NULL.
- */
- ret = (matches == 1) ? ret : NULL;
-
- return ret;
-}
-
-static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
- struct dma_debug_entry *ref)
-{
- return __hash_bucket_find(bucket, ref, exact_match);
-}
-
-static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
- struct dma_debug_entry *ref,
- unsigned long *flags)
-{
-
- unsigned int max_range = dma_get_max_seg_size(ref->dev);
- struct dma_debug_entry *entry, index = *ref;
- unsigned int range = 0;
-
- while (range <= max_range) {
- entry = __hash_bucket_find(*bucket, ref, containing_match);
-
- if (entry)
- return entry;
-
- /*
- * Nothing found, go back a hash bucket
- */
- put_hash_bucket(*bucket, flags);
- range += (1 << HASH_FN_SHIFT);
- index.dev_addr -= (1 << HASH_FN_SHIFT);
- *bucket = get_hash_bucket(&index, flags);
- }
-
- return NULL;
-}
-
-/*
- * Add an entry to a hash bucket
- */
-static void hash_bucket_add(struct hash_bucket *bucket,
- struct dma_debug_entry *entry)
-{
- list_add_tail(&entry->list, &bucket->list);
-}
-
-/*
- * Remove entry from a hash bucket list
- */
-static void hash_bucket_del(struct dma_debug_entry *entry)
-{
- list_del(&entry->list);
-}
-
-static unsigned long long phys_addr(struct dma_debug_entry *entry)
-{
- if (entry->type == dma_debug_resource)
- return __pfn_to_phys(entry->pfn) + entry->offset;
-
- return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
-}
-
-/*
- * Dump mapping entries for debugging purposes
- */
-void debug_dma_dump_mappings(struct device *dev)
-{
- int idx;
-
- for (idx = 0; idx < HASH_SIZE; idx++) {
- struct hash_bucket *bucket = &dma_entry_hash[idx];
- struct dma_debug_entry *entry;
- unsigned long flags;
-
- spin_lock_irqsave(&bucket->lock, flags);
-
- list_for_each_entry(entry, &bucket->list, list) {
- if (!dev || dev == entry->dev) {
- dev_info(entry->dev,
- "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n",
- type2name[entry->type], idx,
- phys_addr(entry), entry->pfn,
- entry->dev_addr, entry->size,
- dir2name[entry->direction],
- maperr2str[entry->map_err_type]);
- }
- }
-
- spin_unlock_irqrestore(&bucket->lock, flags);
- }
-}
-
-/*
- * For each mapping (initial cacheline in the case of
- * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
- * scatterlist, or the cacheline specified in dma_map_single) insert
- * into this tree using the cacheline as the key. At
- * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If
- * the entry already exists at insertion time add a tag as a reference
- * count for the overlapping mappings. For now, the overlap tracking
- * just ensures that 'unmaps' balance 'maps' before marking the
- * cacheline idle, but we should also be flagging overlaps as an API
- * violation.
- *
- * Memory usage is mostly constrained by the maximum number of available
- * dma-debug entries in that we need a free dma_debug_entry before
- * inserting into the tree. In the case of dma_map_page and
- * dma_alloc_coherent there is only one dma_debug_entry and one
- * dma_active_cacheline entry to track per event. dma_map_sg(), on the
- * other hand, consumes a single dma_debug_entry, but inserts 'nents'
- * entries into the tree.
- *
- * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if any cachelines in the given page are in the active set.
- */
-static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
-static DEFINE_SPINLOCK(radix_lock);
-#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
-#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
-#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
-
-static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
-{
- return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
- (entry->offset >> L1_CACHE_SHIFT);
-}
-
-static int active_cacheline_read_overlap(phys_addr_t cln)
-{
- int overlap = 0, i;
-
- for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
- if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
- overlap |= 1 << i;
- return overlap;
-}
-
-static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
-{
- int i;
-
- if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
- return overlap;
-
- for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
- if (overlap & 1 << i)
- radix_tree_tag_set(&dma_active_cacheline, cln, i);
- else
- radix_tree_tag_clear(&dma_active_cacheline, cln, i);
-
- return overlap;
-}
-
-static void active_cacheline_inc_overlap(phys_addr_t cln)
-{
- int overlap = active_cacheline_read_overlap(cln);
-
- overlap = active_cacheline_set_overlap(cln, ++overlap);
-
- /* If we overflowed the overlap counter then we're potentially
- * leaking dma-mappings. Otherwise, if maps and unmaps are
- * balanced then this overflow may cause false negatives in
- * debug_dma_assert_idle() as the cacheline may be marked idle
- * prematurely.
- */
- WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
- "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
- ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
-}
-
-static int active_cacheline_dec_overlap(phys_addr_t cln)
-{
- int overlap = active_cacheline_read_overlap(cln);
-
- return active_cacheline_set_overlap(cln, --overlap);
-}
-
-static int active_cacheline_insert(struct dma_debug_entry *entry)
-{
- phys_addr_t cln = to_cacheline_number(entry);
- unsigned long flags;
- int rc;
-
- /* If the device is not writing memory then we don't have any
- * concerns about the cpu consuming stale data. This mitigates
- * legitimate usages of overlapping mappings.
- */
- if (entry->direction == DMA_TO_DEVICE)
- return 0;
-
- spin_lock_irqsave(&radix_lock, flags);
- rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
- if (rc == -EEXIST)
- active_cacheline_inc_overlap(cln);
- spin_unlock_irqrestore(&radix_lock, flags);
-
- return rc;
-}
-
-static void active_cacheline_remove(struct dma_debug_entry *entry)
-{
- phys_addr_t cln = to_cacheline_number(entry);
- unsigned long flags;
-
- /* ...mirror the insert case */
- if (entry->direction == DMA_TO_DEVICE)
- return;
-
- spin_lock_irqsave(&radix_lock, flags);
- /* since we are counting overlaps the final put of the
- * cacheline will occur when the overlap count is 0.
- * active_cacheline_dec_overlap() returns -1 in that case
- */
- if (active_cacheline_dec_overlap(cln) < 0)
- radix_tree_delete(&dma_active_cacheline, cln);
- spin_unlock_irqrestore(&radix_lock, flags);
-}
-
-/**
- * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_cacheline tree
- *
- * Place a call to this routine in cases where the cpu touching the page
- * before the dma completes (page is dma_unmapped) will lead to data
- * corruption.
- */
-void debug_dma_assert_idle(struct page *page)
-{
- static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
- struct dma_debug_entry *entry = NULL;
- void **results = (void **) &ents;
- unsigned int nents, i;
- unsigned long flags;
- phys_addr_t cln;
-
- if (dma_debug_disabled())
- return;
-
- if (!page)
- return;
-
- cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
- spin_lock_irqsave(&radix_lock, flags);
- nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
- CACHELINES_PER_PAGE);
- for (i = 0; i < nents; i++) {
- phys_addr_t ent_cln = to_cacheline_number(ents[i]);
-
- if (ent_cln == cln) {
- entry = ents[i];
- break;
- } else if (ent_cln >= cln + CACHELINES_PER_PAGE)
- break;
- }
- spin_unlock_irqrestore(&radix_lock, flags);
-
- if (!entry)
- return;
-
- cln = to_cacheline_number(entry);
- err_printk(entry->dev, entry,
- "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
- &cln);
-}
-
-/*
- * Wrapper function for adding an entry to the hash.
- * This function takes care of locking itself.
- */
-static void add_dma_entry(struct dma_debug_entry *entry)
-{
- struct hash_bucket *bucket;
- unsigned long flags;
- int rc;
-
- bucket = get_hash_bucket(entry, &flags);
- hash_bucket_add(bucket, entry);
- put_hash_bucket(bucket, &flags);
-
- rc = active_cacheline_insert(entry);
- if (rc == -ENOMEM) {
- pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
- global_disable = true;
- }
-
- /* TODO: report -EEXIST errors here as overlapping mappings are
- * not supported by the DMA API
- */
-}
-
-static struct dma_debug_entry *__dma_entry_alloc(void)
-{
- struct dma_debug_entry *entry;
-
- entry = list_entry(free_entries.next, struct dma_debug_entry, list);
- list_del(&entry->list);
- memset(entry, 0, sizeof(*entry));
-
- num_free_entries -= 1;
- if (num_free_entries < min_free_entries)
- min_free_entries = num_free_entries;
-
- return entry;
-}
-
-/* struct dma_entry allocator
- *
- * The next two functions implement the allocator for
- * struct dma_debug_entries.
- */
-static struct dma_debug_entry *dma_entry_alloc(void)
-{
- struct dma_debug_entry *entry;
- unsigned long flags;
-
- spin_lock_irqsave(&free_entries_lock, flags);
-
- if (list_empty(&free_entries)) {
- global_disable = true;
- spin_unlock_irqrestore(&free_entries_lock, flags);
- pr_err("DMA-API: debugging out of memory - disabling\n");
- return NULL;
- }
-
- entry = __dma_entry_alloc();
-
- spin_unlock_irqrestore(&free_entries_lock, flags);
-
-#ifdef CONFIG_STACKTRACE
- entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
- entry->stacktrace.entries = entry->st_entries;
- entry->stacktrace.skip = 2;
- save_stack_trace(&entry->stacktrace);
-#endif
-
- return entry;
-}
-
-static void dma_entry_free(struct dma_debug_entry *entry)
-{
- unsigned long flags;
-
- active_cacheline_remove(entry);
-
- /*
- * add to beginning of the list - this way the entries are
- * more likely cache hot when they are reallocated.
- */
- spin_lock_irqsave(&free_entries_lock, flags);
- list_add(&entry->list, &free_entries);
- num_free_entries += 1;
- spin_unlock_irqrestore(&free_entries_lock, flags);
-}
-
-int dma_debug_resize_entries(u32 num_entries)
-{
- int i, delta, ret = 0;
- unsigned long flags;
- struct dma_debug_entry *entry;
- LIST_HEAD(tmp);
-
- spin_lock_irqsave(&free_entries_lock, flags);
-
- if (nr_total_entries < num_entries) {
- delta = num_entries - nr_total_entries;
-
- spin_unlock_irqrestore(&free_entries_lock, flags);
-
- for (i = 0; i < delta; i++) {
- entry = kzalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- break;
-
- list_add_tail(&entry->list, &tmp);
- }
-
- spin_lock_irqsave(&free_entries_lock, flags);
-
- list_splice(&tmp, &free_entries);
- nr_total_entries += i;
- num_free_entries += i;
- } else {
- delta = nr_total_entries - num_entries;
-
- for (i = 0; i < delta && !list_empty(&free_entries); i++) {
- entry = __dma_entry_alloc();
- kfree(entry);
- }
-
- nr_total_entries -= i;
- }
-
- if (nr_total_entries != num_entries)
- ret = 1;
-
- spin_unlock_irqrestore(&free_entries_lock, flags);
-
- return ret;
-}
-
-/*
- * DMA-API debugging init code
- *
- * The init code does two things:
- * 1. Initialize core data structures
- * 2. Preallocate a given number of dma_debug_entry structs
- */
-
-static int prealloc_memory(u32 num_entries)
-{
- struct dma_debug_entry *entry, *next_entry;
- int i;
-
- for (i = 0; i < num_entries; ++i) {
- entry = kzalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- goto out_err;
-
- list_add_tail(&entry->list, &free_entries);
- }
-
- num_free_entries = num_entries;
- min_free_entries = num_entries;
-
- pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
-
- return 0;
-
-out_err:
-
- list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
- list_del(&entry->list);
- kfree(entry);
- }
-
- return -ENOMEM;
-}
-
-static ssize_t filter_read(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- char buf[NAME_MAX_LEN + 1];
- unsigned long flags;
- int len;
-
- if (!current_driver_name[0])
- return 0;
-
- /*
- * We can't copy to userspace directly because current_driver_name can
- * only be read under the driver_name_lock with irqs disabled. So
- * create a temporary copy first.
- */
- read_lock_irqsave(&driver_name_lock, flags);
- len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
- read_unlock_irqrestore(&driver_name_lock, flags);
-
- return simple_read_from_buffer(user_buf, count, ppos, buf, len);
-}
-
-static ssize_t filter_write(struct file *file, const char __user *userbuf,
- size_t count, loff_t *ppos)
-{
- char buf[NAME_MAX_LEN];
- unsigned long flags;
- size_t len;
- int i;
-
- /*
- * We can't copy from userspace directly. Access to
- * current_driver_name is protected with a write_lock with irqs
- * disabled. Since copy_from_user can fault and may sleep we
- * need to copy to temporary buffer first
- */
- len = min(count, (size_t)(NAME_MAX_LEN - 1));
- if (copy_from_user(buf, userbuf, len))
- return -EFAULT;
-
- buf[len] = 0;
-
- write_lock_irqsave(&driver_name_lock, flags);
-
- /*
- * Now handle the string we got from userspace very carefully.
- * The rules are:
- * - only use the first token we got
- * - token delimiter is everything looking like a space
- * character (' ', '\n', '\t' ...)
- *
- */
- if (!isalnum(buf[0])) {
- /*
- * If the first character userspace gave us is not
- * alphanumerical then assume the filter should be
- * switched off.
- */
- if (current_driver_name[0])
- pr_info("DMA-API: switching off dma-debug driver filter\n");
- current_driver_name[0] = 0;
- current_driver = NULL;
- goto out_unlock;
- }
-
- /*
- * Now parse out the first token and use it as the name for the
- * driver to filter for.
- */
- for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
- current_driver_name[i] = buf[i];
- if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
- break;
- }
- current_driver_name[i] = 0;
- current_driver = NULL;
-
- pr_info("DMA-API: enable driver filter for driver [%s]\n",
- current_driver_name);
-
-out_unlock:
- write_unlock_irqrestore(&driver_name_lock, flags);
-
- return count;
-}
-
-static const struct file_operations filter_fops = {
- .read = filter_read,
- .write = filter_write,
- .llseek = default_llseek,
-};
-
-static int dma_debug_fs_init(void)
-{
- dma_debug_dent = debugfs_create_dir("dma-api", NULL);
- if (!dma_debug_dent) {
- pr_err("DMA-API: can not create debugfs directory\n");
- return -ENOMEM;
- }
-
- global_disable_dent = debugfs_create_bool("disabled", 0444,
- dma_debug_dent,
- &global_disable);
- if (!global_disable_dent)
- goto out_err;
-
- error_count_dent = debugfs_create_u32("error_count", 0444,
- dma_debug_dent, &error_count);
- if (!error_count_dent)
- goto out_err;
-
- show_all_errors_dent = debugfs_create_u32("all_errors", 0644,
- dma_debug_dent,
- &show_all_errors);
- if (!show_all_errors_dent)
- goto out_err;
-
- show_num_errors_dent = debugfs_create_u32("num_errors", 0644,
- dma_debug_dent,
- &show_num_errors);
- if (!show_num_errors_dent)
- goto out_err;
-
- num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444,
- dma_debug_dent,
- &num_free_entries);
- if (!num_free_entries_dent)
- goto out_err;
-
- min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444,
- dma_debug_dent,
- &min_free_entries);
- if (!min_free_entries_dent)
- goto out_err;
-
- filter_dent = debugfs_create_file("driver_filter", 0644,
- dma_debug_dent, NULL, &filter_fops);
- if (!filter_dent)
- goto out_err;
-
- return 0;
-
-out_err:
- debugfs_remove_recursive(dma_debug_dent);
-
- return -ENOMEM;
-}
-
-static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
-{
- struct dma_debug_entry *entry;
- unsigned long flags;
- int count = 0, i;
-
- for (i = 0; i < HASH_SIZE; ++i) {
- spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
- list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
- if (entry->dev == dev) {
- count += 1;
- *out_entry = entry;
- }
- }
- spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
- }
-
- return count;
-}
-
-static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
-{
- struct device *dev = data;
- struct dma_debug_entry *uninitialized_var(entry);
- int count;
-
- if (dma_debug_disabled())
- return 0;
-
- switch (action) {
- case BUS_NOTIFY_UNBOUND_DRIVER:
- count = device_dma_allocations(dev, &entry);
- if (count == 0)
- break;
- err_printk(dev, entry, "DMA-API: device driver has pending "
- "DMA allocations while released from device "
- "[count=%d]\n"
- "One of leaked entries details: "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped with %s] [mapped as %s]\n",
- count, entry->dev_addr, entry->size,
- dir2name[entry->direction], type2name[entry->type]);
- break;
- default:
- break;
- }
-
- return 0;
-}
-
-void dma_debug_add_bus(struct bus_type *bus)
-{
- struct notifier_block *nb;
-
- if (dma_debug_disabled())
- return;
-
- nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
- if (nb == NULL) {
- pr_err("dma_debug_add_bus: out of memory\n");
- return;
- }
-
- nb->notifier_call = dma_debug_device_change;
-
- bus_register_notifier(bus, nb);
-}
-
-static int dma_debug_init(void)
-{
- int i;
-
- /* Do not use dma_debug_initialized here, since we really want to be
- * called to set dma_debug_initialized
- */
- if (global_disable)
- return 0;
-
- for (i = 0; i < HASH_SIZE; ++i) {
- INIT_LIST_HEAD(&dma_entry_hash[i].list);
- spin_lock_init(&dma_entry_hash[i].lock);
- }
-
- if (dma_debug_fs_init() != 0) {
- pr_err("DMA-API: error creating debugfs entries - disabling\n");
- global_disable = true;
-
- return 0;
- }
-
- if (prealloc_memory(nr_prealloc_entries) != 0) {
- pr_err("DMA-API: debugging out of memory error - disabled\n");
- global_disable = true;
-
- return 0;
- }
-
- nr_total_entries = num_free_entries;
-
- dma_debug_initialized = true;
-
- pr_info("DMA-API: debugging enabled by kernel config\n");
- return 0;
-}
-core_initcall(dma_debug_init);
-
-static __init int dma_debug_cmdline(char *str)
-{
- if (!str)
- return -EINVAL;
-
- if (strncmp(str, "off", 3) == 0) {
- pr_info("DMA-API: debugging disabled on kernel command line\n");
- global_disable = true;
- }
-
- return 0;
-}
-
-static __init int dma_debug_entries_cmdline(char *str)
-{
- if (!str)
- return -EINVAL;
- if (!get_option(&str, &nr_prealloc_entries))
- nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
- return 0;
-}
-
-__setup("dma_debug=", dma_debug_cmdline);
-__setup("dma_debug_entries=", dma_debug_entries_cmdline);
-
-static void check_unmap(struct dma_debug_entry *ref)
-{
- struct dma_debug_entry *entry;
- struct hash_bucket *bucket;
- unsigned long flags;
-
- bucket = get_hash_bucket(ref, &flags);
- entry = bucket_find_exact(bucket, ref);
-
- if (!entry) {
- /* must drop lock before calling dma_mapping_error */
- put_hash_bucket(bucket, &flags);
-
- if (dma_mapping_error(ref->dev, ref->dev_addr)) {
- err_printk(ref->dev, NULL,
- "DMA-API: device driver tries to free an "
- "invalid DMA memory address\n");
- } else {
- err_printk(ref->dev, NULL,
- "DMA-API: device driver tries to free DMA "
- "memory it has not allocated [device "
- "address=0x%016llx] [size=%llu bytes]\n",
- ref->dev_addr, ref->size);
- }
- return;
- }
-
- if (ref->size != entry->size) {
- err_printk(ref->dev, entry, "DMA-API: device driver frees "
- "DMA memory with different size "
- "[device address=0x%016llx] [map size=%llu bytes] "
- "[unmap size=%llu bytes]\n",
- ref->dev_addr, entry->size, ref->size);
- }
-
- if (ref->type != entry->type) {
- err_printk(ref->dev, entry, "DMA-API: device driver frees "
- "DMA memory with wrong function "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped as %s] [unmapped as %s]\n",
- ref->dev_addr, ref->size,
- type2name[entry->type], type2name[ref->type]);
- } else if ((entry->type == dma_debug_coherent) &&
- (phys_addr(ref) != phys_addr(entry))) {
- err_printk(ref->dev, entry, "DMA-API: device driver frees "
- "DMA memory with different CPU address "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[cpu alloc address=0x%016llx] "
- "[cpu free address=0x%016llx]",
- ref->dev_addr, ref->size,
- phys_addr(entry),
- phys_addr(ref));
- }
-
- if (ref->sg_call_ents && ref->type == dma_debug_sg &&
- ref->sg_call_ents != entry->sg_call_ents) {
- err_printk(ref->dev, entry, "DMA-API: device driver frees "
- "DMA sg list with different entry count "
- "[map count=%d] [unmap count=%d]\n",
- entry->sg_call_ents, ref->sg_call_ents);
- }
-
- /*
- * This may be no bug in reality - but most implementations of the
- * DMA API don't handle this properly, so check for it here
- */
- if (ref->direction != entry->direction) {
- err_printk(ref->dev, entry, "DMA-API: device driver frees "
- "DMA memory with different direction "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped with %s] [unmapped with %s]\n",
- ref->dev_addr, ref->size,
- dir2name[entry->direction],
- dir2name[ref->direction]);
- }
-
- /*
- * Drivers should use dma_mapping_error() to check the returned
- * addresses of dma_map_single() and dma_map_page().
- * If not, print this warning message. See Documentation/DMA-API.txt.
- */
- if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
- err_printk(ref->dev, entry,
- "DMA-API: device driver failed to check map error"
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped as %s]",
- ref->dev_addr, ref->size,
- type2name[entry->type]);
- }
-
- hash_bucket_del(entry);
- dma_entry_free(entry);
-
- put_hash_bucket(bucket, &flags);
-}
-
-static void check_for_stack(struct device *dev,
- struct page *page, size_t offset)
-{
- void *addr;
- struct vm_struct *stack_vm_area = task_stack_vm_area(current);
-
- if (!stack_vm_area) {
- /* Stack is direct-mapped. */
- if (PageHighMem(page))
- return;
- addr = page_address(page) + offset;
- if (object_is_on_stack(addr))
- err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
- } else {
- /* Stack is vmalloced. */
- int i;
-
- for (i = 0; i < stack_vm_area->nr_pages; i++) {
- if (page != stack_vm_area->pages[i])
- continue;
-
- addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
- err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
- break;
- }
- }
-}
-
-static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
-{
- unsigned long a1 = (unsigned long)addr;
- unsigned long b1 = a1 + len;
- unsigned long a2 = (unsigned long)start;
- unsigned long b2 = (unsigned long)end;
-
- return !(b1 <= a2 || a1 >= b2);
-}
-
-static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
-{
- if (overlap(addr, len, _stext, _etext) ||
- overlap(addr, len, __start_rodata, __end_rodata))
- err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
-}
-
-static void check_sync(struct device *dev,
- struct dma_debug_entry *ref,
- bool to_cpu)
-{
- struct dma_debug_entry *entry;
- struct hash_bucket *bucket;
- unsigned long flags;
-
- bucket = get_hash_bucket(ref, &flags);
-
- entry = bucket_find_contain(&bucket, ref, &flags);
-
- if (!entry) {
- err_printk(dev, NULL, "DMA-API: device driver tries "
- "to sync DMA memory it has not allocated "
- "[device address=0x%016llx] [size=%llu bytes]\n",
- (unsigned long long)ref->dev_addr, ref->size);
- goto out;
- }
-
- if (ref->size > entry->size) {
- err_printk(dev, entry, "DMA-API: device driver syncs"
- " DMA memory outside allocated range "
- "[device address=0x%016llx] "
- "[allocation size=%llu bytes] "
- "[sync offset+size=%llu]\n",
- entry->dev_addr, entry->size,
- ref->size);
- }
-
- if (entry->direction == DMA_BIDIRECTIONAL)
- goto out;
-
- if (ref->direction != entry->direction) {
- err_printk(dev, entry, "DMA-API: device driver syncs "
- "DMA memory with different direction "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped with %s] [synced with %s]\n",
- (unsigned long long)ref->dev_addr, entry->size,
- dir2name[entry->direction],
- dir2name[ref->direction]);
- }
-
- if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
- !(ref->direction == DMA_TO_DEVICE))
- err_printk(dev, entry, "DMA-API: device driver syncs "
- "device read-only DMA memory for cpu "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped with %s] [synced with %s]\n",
- (unsigned long long)ref->dev_addr, entry->size,
- dir2name[entry->direction],
- dir2name[ref->direction]);
-
- if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
- !(ref->direction == DMA_FROM_DEVICE))
- err_printk(dev, entry, "DMA-API: device driver syncs "
- "device write-only DMA memory to device "
- "[device address=0x%016llx] [size=%llu bytes] "
- "[mapped with %s] [synced with %s]\n",
- (unsigned long long)ref->dev_addr, entry->size,
- dir2name[entry->direction],
- dir2name[ref->direction]);
-
- if (ref->sg_call_ents && ref->type == dma_debug_sg &&
- ref->sg_call_ents != entry->sg_call_ents) {
- err_printk(ref->dev, entry, "DMA-API: device driver syncs "
- "DMA sg list with different entry count "
- "[map count=%d] [sync count=%d]\n",
- entry->sg_call_ents, ref->sg_call_ents);
- }
-
-out:
- put_hash_bucket(bucket, &flags);
-}
-
-static void check_sg_segment(struct device *dev, struct scatterlist *sg)
-{
-#ifdef CONFIG_DMA_API_DEBUG_SG
- unsigned int max_seg = dma_get_max_seg_size(dev);
- u64 start, end, boundary = dma_get_seg_boundary(dev);
-
- /*
- * Either the driver forgot to set dma_parms appropriately, or
- * whoever generated the list forgot to check them.
- */
- if (sg->length > max_seg)
- err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
- sg->length, max_seg);
- /*
- * In some cases this could potentially be the DMA API
- * implementation's fault, but it would usually imply that
- * the scatterlist was built inappropriately to begin with.
- */
- start = sg_dma_address(sg);
- end = start + sg_dma_len(sg) - 1;
- if ((start ^ end) & ~boundary)
- err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
- start, end, boundary);
-#endif
-}
-
-void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
- size_t size, int direction, dma_addr_t dma_addr,
- bool map_single)
-{
- struct dma_debug_entry *entry;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- if (dma_mapping_error(dev, dma_addr))
- return;
-
- entry = dma_entry_alloc();
- if (!entry)
- return;
-
- entry->dev = dev;
- entry->type = dma_debug_page;
- entry->pfn = page_to_pfn(page);
- entry->offset = offset,
- entry->dev_addr = dma_addr;
- entry->size = size;
- entry->direction = direction;
- entry->map_err_type = MAP_ERR_NOT_CHECKED;
-
- if (map_single)
- entry->type = dma_debug_single;
-
- check_for_stack(dev, page, offset);
-
- if (!PageHighMem(page)) {
- void *addr = page_address(page) + offset;
-
- check_for_illegal_area(dev, addr, size);
- }
-
- add_dma_entry(entry);
-}
-EXPORT_SYMBOL(debug_dma_map_page);
-
-void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
- struct dma_debug_entry ref;
- struct dma_debug_entry *entry;
- struct hash_bucket *bucket;
- unsigned long flags;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- ref.dev = dev;
- ref.dev_addr = dma_addr;
- bucket = get_hash_bucket(&ref, &flags);
-
- list_for_each_entry(entry, &bucket->list, list) {
- if (!exact_match(&ref, entry))
- continue;
-
- /*
- * The same physical address can be mapped multiple
- * times. Without a hardware IOMMU this results in the
- * same device addresses being put into the dma-debug
- * hash multiple times too. This can result in false
- * positives being reported. Therefore we implement a
- * best-fit algorithm here which updates the first entry
- * from the hash which fits the reference value and is
- * not currently listed as being checked.
- */
- if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
- entry->map_err_type = MAP_ERR_CHECKED;
- break;
- }
- }
-
- put_hash_bucket(bucket, &flags);
-}
-EXPORT_SYMBOL(debug_dma_mapping_error);
-
-void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
- size_t size, int direction, bool map_single)
-{
- struct dma_debug_entry ref = {
- .type = dma_debug_page,
- .dev = dev,
- .dev_addr = addr,
- .size = size,
- .direction = direction,
- };
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- if (map_single)
- ref.type = dma_debug_single;
-
- check_unmap(&ref);
-}
-EXPORT_SYMBOL(debug_dma_unmap_page);
-
-void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction)
-{
- struct dma_debug_entry *entry;
- struct scatterlist *s;
- int i;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- for_each_sg(sg, s, mapped_ents, i) {
- entry = dma_entry_alloc();
- if (!entry)
- return;
-
- entry->type = dma_debug_sg;
- entry->dev = dev;
- entry->pfn = page_to_pfn(sg_page(s));
- entry->offset = s->offset,
- entry->size = sg_dma_len(s);
- entry->dev_addr = sg_dma_address(s);
- entry->direction = direction;
- entry->sg_call_ents = nents;
- entry->sg_mapped_ents = mapped_ents;
-
- check_for_stack(dev, sg_page(s), s->offset);
-
- if (!PageHighMem(sg_page(s))) {
- check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
- }
-
- check_sg_segment(dev, s);
-
- add_dma_entry(entry);
- }
-}
-EXPORT_SYMBOL(debug_dma_map_sg);
-
-static int get_nr_mapped_entries(struct device *dev,
- struct dma_debug_entry *ref)
-{
- struct dma_debug_entry *entry;
- struct hash_bucket *bucket;
- unsigned long flags;
- int mapped_ents;
-
- bucket = get_hash_bucket(ref, &flags);
- entry = bucket_find_exact(bucket, ref);
- mapped_ents = 0;
-
- if (entry)
- mapped_ents = entry->sg_mapped_ents;
- put_hash_bucket(bucket, &flags);
-
- return mapped_ents;
-}
-
-void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, int dir)
-{
- struct scatterlist *s;
- int mapped_ents = 0, i;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- for_each_sg(sglist, s, nelems, i) {
-
- struct dma_debug_entry ref = {
- .type = dma_debug_sg,
- .dev = dev,
- .pfn = page_to_pfn(sg_page(s)),
- .offset = s->offset,
- .dev_addr = sg_dma_address(s),
- .size = sg_dma_len(s),
- .direction = dir,
- .sg_call_ents = nelems,
- };
-
- if (mapped_ents && i >= mapped_ents)
- break;
-
- if (!i)
- mapped_ents = get_nr_mapped_entries(dev, &ref);
-
- check_unmap(&ref);
- }
-}
-EXPORT_SYMBOL(debug_dma_unmap_sg);
-
-void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt)
-{
- struct dma_debug_entry *entry;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- if (unlikely(virt == NULL))
- return;
-
- /* handle vmalloc and linear addresses */
- if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
- return;
-
- entry = dma_entry_alloc();
- if (!entry)
- return;
-
- entry->type = dma_debug_coherent;
- entry->dev = dev;
- entry->offset = offset_in_page(virt);
- entry->size = size;
- entry->dev_addr = dma_addr;
- entry->direction = DMA_BIDIRECTIONAL;
-
- if (is_vmalloc_addr(virt))
- entry->pfn = vmalloc_to_pfn(virt);
- else
- entry->pfn = page_to_pfn(virt_to_page(virt));
-
- add_dma_entry(entry);
-}
-EXPORT_SYMBOL(debug_dma_alloc_coherent);
-
-void debug_dma_free_coherent(struct device *dev, size_t size,
- void *virt, dma_addr_t addr)
-{
- struct dma_debug_entry ref = {
- .type = dma_debug_coherent,
- .dev = dev,
- .offset = offset_in_page(virt),
- .dev_addr = addr,
- .size = size,
- .direction = DMA_BIDIRECTIONAL,
- };
-
- /* handle vmalloc and linear addresses */
- if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
- return;
-
- if (is_vmalloc_addr(virt))
- ref.pfn = vmalloc_to_pfn(virt);
- else
- ref.pfn = page_to_pfn(virt_to_page(virt));
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- check_unmap(&ref);
-}
-EXPORT_SYMBOL(debug_dma_free_coherent);
-
-void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
- int direction, dma_addr_t dma_addr)
-{
- struct dma_debug_entry *entry;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- entry = dma_entry_alloc();
- if (!entry)
- return;
-
- entry->type = dma_debug_resource;
- entry->dev = dev;
- entry->pfn = PHYS_PFN(addr);
- entry->offset = offset_in_page(addr);
- entry->size = size;
- entry->dev_addr = dma_addr;
- entry->direction = direction;
- entry->map_err_type = MAP_ERR_NOT_CHECKED;
-
- add_dma_entry(entry);
-}
-EXPORT_SYMBOL(debug_dma_map_resource);
-
-void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
- size_t size, int direction)
-{
- struct dma_debug_entry ref = {
- .type = dma_debug_resource,
- .dev = dev,
- .dev_addr = dma_addr,
- .size = size,
- .direction = direction,
- };
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- check_unmap(&ref);
-}
-EXPORT_SYMBOL(debug_dma_unmap_resource);
-
-void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
- size_t size, int direction)
-{
- struct dma_debug_entry ref;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- ref.type = dma_debug_single;
- ref.dev = dev;
- ref.dev_addr = dma_handle;
- ref.size = size;
- ref.direction = direction;
- ref.sg_call_ents = 0;
-
- check_sync(dev, &ref, true);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
-
-void debug_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- int direction)
-{
- struct dma_debug_entry ref;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- ref.type = dma_debug_single;
- ref.dev = dev;
- ref.dev_addr = dma_handle;
- ref.size = size;
- ref.direction = direction;
- ref.sg_call_ents = 0;
-
- check_sync(dev, &ref, false);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_for_device);
-
-void debug_dma_sync_single_range_for_cpu(struct device *dev,
- dma_addr_t dma_handle,
- unsigned long offset, size_t size,
- int direction)
-{
- struct dma_debug_entry ref;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- ref.type = dma_debug_single;
- ref.dev = dev;
- ref.dev_addr = dma_handle;
- ref.size = offset + size;
- ref.direction = direction;
- ref.sg_call_ents = 0;
-
- check_sync(dev, &ref, true);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
-
-void debug_dma_sync_single_range_for_device(struct device *dev,
- dma_addr_t dma_handle,
- unsigned long offset,
- size_t size, int direction)
-{
- struct dma_debug_entry ref;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- ref.type = dma_debug_single;
- ref.dev = dev;
- ref.dev_addr = dma_handle;
- ref.size = offset + size;
- ref.direction = direction;
- ref.sg_call_ents = 0;
-
- check_sync(dev, &ref, false);
-}
-EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
-
-void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nelems, int direction)
-{
- struct scatterlist *s;
- int mapped_ents = 0, i;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- for_each_sg(sg, s, nelems, i) {
-
- struct dma_debug_entry ref = {
- .type = dma_debug_sg,
- .dev = dev,
- .pfn = page_to_pfn(sg_page(s)),
- .offset = s->offset,
- .dev_addr = sg_dma_address(s),
- .size = sg_dma_len(s),
- .direction = direction,
- .sg_call_ents = nelems,
- };
-
- if (!i)
- mapped_ents = get_nr_mapped_entries(dev, &ref);
-
- if (i >= mapped_ents)
- break;
-
- check_sync(dev, &ref, true);
- }
-}
-EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
-
-void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
- int nelems, int direction)
-{
- struct scatterlist *s;
- int mapped_ents = 0, i;
-
- if (unlikely(dma_debug_disabled()))
- return;
-
- for_each_sg(sg, s, nelems, i) {
-
- struct dma_debug_entry ref = {
- .type = dma_debug_sg,
- .dev = dev,
- .pfn = page_to_pfn(sg_page(s)),
- .offset = s->offset,
- .dev_addr = sg_dma_address(s),
- .size = sg_dma_len(s),
- .direction = direction,
- .sg_call_ents = nelems,
- };
- if (!i)
- mapped_ents = get_nr_mapped_entries(dev, &ref);
-
- if (i >= mapped_ents)
- break;
-
- check_sync(dev, &ref, false);
- }
-}
-EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
-
-static int __init dma_debug_driver_setup(char *str)
-{
- int i;
-
- for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
- current_driver_name[i] = *str;
- if (*str == 0)
- break;
- }
-
- if (current_driver_name[0])
- pr_info("DMA-API: enable driver filter for driver [%s]\n",
- current_driver_name);
-
-
- return 1;
-}
-__setup("dma_debug_driver=", dma_debug_driver_setup);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DMA operations that map physical memory directly without using an IOMMU or
- * flushing caches.
- */
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-contiguous.h>
-#include <linux/pfn.h>
-#include <linux/set_memory.h>
-
-#define DIRECT_MAPPING_ERROR 0
-
-/*
- * Most architectures use ZONE_DMA for the first 16 Megabytes, but
- * some use it for entirely different regions:
- */
-#ifndef ARCH_ZONE_DMA_BITS
-#define ARCH_ZONE_DMA_BITS 24
-#endif
-
-/*
- * For AMD SEV all DMA must be to unencrypted addresses.
- */
-static inline bool force_dma_unencrypted(void)
-{
- return sev_active();
-}
-
-static bool
-check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
- const char *caller)
-{
- if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
- if (!dev->dma_mask) {
- dev_err(dev,
- "%s: call on device without dma_mask\n",
- caller);
- return false;
- }
-
- if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
- dev_err(dev,
- "%s: overflow %pad+%zu of device mask %llx\n",
- caller, &dma_addr, size, *dev->dma_mask);
- }
- return false;
- }
- return true;
-}
-
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
-{
- dma_addr_t addr = force_dma_unencrypted() ?
- __phys_to_dma(dev, phys) : phys_to_dma(dev, phys);
- return addr + size - 1 <= dev->coherent_dma_mask;
-}
-
-void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- int page_order = get_order(size);
- struct page *page = NULL;
- void *ret;
-
- /* we always manually zero the memory once we are done: */
- gfp &= ~__GFP_ZERO;
-
- /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
- if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
- gfp |= GFP_DMA;
- if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
- gfp |= GFP_DMA32;
-
-again:
- /* CMA can be used only in the context which permits sleeping */
- if (gfpflags_allow_blocking(gfp)) {
- page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
- if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
- dma_release_from_contiguous(dev, page, count);
- page = NULL;
- }
- }
- if (!page)
- page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
-
- if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
- __free_pages(page, page_order);
- page = NULL;
-
- if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
- dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
- !(gfp & (GFP_DMA32 | GFP_DMA))) {
- gfp |= GFP_DMA32;
- goto again;
- }
-
- if (IS_ENABLED(CONFIG_ZONE_DMA) &&
- dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
- !(gfp & GFP_DMA)) {
- gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
- goto again;
- }
- }
-
- if (!page)
- return NULL;
- ret = page_address(page);
- if (force_dma_unencrypted()) {
- set_memory_decrypted((unsigned long)ret, 1 << page_order);
- *dma_handle = __phys_to_dma(dev, page_to_phys(page));
- } else {
- *dma_handle = phys_to_dma(dev, page_to_phys(page));
- }
- memset(ret, 0, size);
- return ret;
-}
-
-/*
- * NOTE: this function must never look at the dma_addr argument, because we want
- * to be able to use it as a helper for iommu implementations as well.
- */
-void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t dma_addr, unsigned long attrs)
-{
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned int page_order = get_order(size);
-
- if (force_dma_unencrypted())
- set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
- if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
- free_pages((unsigned long)cpu_addr, page_order);
-}
-
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset;
-
- if (!check_addr(dev, dma_addr, size, __func__))
- return DIRECT_MAPPING_ERROR;
- return dma_addr;
-}
-
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
- enum dma_data_direction dir, unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sgl, sg, nents, i) {
- BUG_ON(!sg_page(sg));
-
- sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
- if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
- return 0;
- sg_dma_len(sg) = sg->length;
- }
-
- return nents;
-}
-
-int dma_direct_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_ZONE_DMA
- if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
- return 0;
-#else
- /*
- * Because 32-bit DMA masks are so common we expect every architecture
- * to be able to satisfy them - either by not supporting more physical
- * memory, or by providing a ZONE_DMA32. If neither is the case, the
- * architecture needs to use an IOMMU instead of the direct mapping.
- */
- if (mask < DMA_BIT_MASK(32))
- return 0;
-#endif
- /*
- * Various PCI/PCIe bridges have broken support for > 32bit DMA even
- * if the device itself might support it.
- */
- if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
- return 0;
- return 1;
-}
-
-int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
- return dma_addr == DIRECT_MAPPING_ERROR;
-}
-
-const struct dma_map_ops dma_direct_ops = {
- .alloc = dma_direct_alloc,
- .free = dma_direct_free,
- .map_page = dma_direct_map_page,
- .map_sg = dma_direct_map_sg,
- .dma_supported = dma_direct_supported,
- .mapping_error = dma_direct_mapping_error,
-};
-EXPORT_SYMBOL(dma_direct_ops);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2018 Christoph Hellwig.
- *
- * DMA operations that map physical memory directly without providing cache
- * coherence.
- */
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/scatterlist.h>
-
-static void dma_noncoherent_sync_single_for_device(struct device *dev,
- dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
- arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
-}
-
-static void dma_noncoherent_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sgl, sg, nents, i)
- arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
-}
-
-static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t addr;
-
- addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
- if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
- size, dir);
- return addr;
-}
-
-static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
- if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
- return nents;
-}
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
- dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
- arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
-}
-
-static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sgl, sg, nents, i)
- arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
-}
-
-static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
-}
-#endif
-
-const struct dma_map_ops dma_noncoherent_ops = {
- .alloc = arch_dma_alloc,
- .free = arch_dma_free,
- .mmap = arch_dma_mmap,
- .sync_single_for_device = dma_noncoherent_sync_single_for_device,
- .sync_sg_for_device = dma_noncoherent_sync_sg_for_device,
- .map_page = dma_noncoherent_map_page,
- .map_sg = dma_noncoherent_map_sg,
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
- .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu,
- .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu,
- .unmap_page = dma_noncoherent_unmap_page,
- .unmap_sg = dma_noncoherent_unmap_sg,
-#endif
- .dma_supported = dma_direct_supported,
- .mapping_error = dma_direct_mapping_error,
- .cache_sync = arch_dma_cache_sync,
-};
-EXPORT_SYMBOL(dma_noncoherent_ops);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * lib/dma-virt.c
- *
- * DMA operations that map to virtual addresses without flushing memory.
- */
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-
-static void *dma_virt_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
-{
- void *ret;
-
- ret = (void *)__get_free_pages(gfp, get_order(size));
- if (ret)
- *dma_handle = (uintptr_t)ret;
- return ret;
-}
-
-static void dma_virt_free(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_addr,
- unsigned long attrs)
-{
- free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- return (uintptr_t)(page_address(page) + offset);
-}
-
-static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sgl, sg, nents, i) {
- BUG_ON(!sg_page(sg));
- sg_dma_address(sg) = (uintptr_t)sg_virt(sg);
- sg_dma_len(sg) = sg->length;
- }
-
- return nents;
-}
-
-const struct dma_map_ops dma_virt_ops = {
- .alloc = dma_virt_alloc,
- .free = dma_virt_free,
- .map_page = dma_virt_map_page,
- .map_sg = dma_virt_map_sg,
-};
-EXPORT_SYMBOL(dma_virt_ops);
if (ioremap_pmd_enabled() &&
((next - addr) == PMD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
- pmd_free_pte_page(pmd)) {
+ pmd_free_pte_page(pmd, addr)) {
if (pmd_set_huge(pmd, phys_addr + addr, prot))
continue;
}
if (ioremap_pud_enabled() &&
((next - addr) == PUD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
- pud_free_pmd_page(pud)) {
+ pud_free_pmd_page(pud, addr)) {
if (pud_set_huge(pud, phys_addr + addr, prot))
continue;
}
return ret;
}
+static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+ struct iov_iter *i)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t n, off, xfer = 0;
+ int idx;
+
+ if (!sanity(i))
+ return 0;
+
+ bytes = n = push_pipe(i, bytes, &idx, &off);
+ if (unlikely(!n))
+ return 0;
+ for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+ size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+ unsigned long rem;
+
+ rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
+ chunk);
+ i->idx = idx;
+ i->iov_offset = off + chunk - rem;
+ xfer += chunk - rem;
+ if (rem)
+ break;
+ n -= chunk;
+ addr += chunk;
+ }
+ i->count -= xfer;
+ return xfer;
+}
+
+/**
+ * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * @addr: source kernel address
+ * @bytes: total transfer length
+ * @iter: destination iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_to_iter() for protecting read/write to persistent memory.
+ * Unless / until an architecture can guarantee identical performance
+ * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
+ * performance regression to switch more users to the mcsafe version.
+ *
+ * Otherwise, the main differences between this and typical _copy_to_iter().
+ *
+ * * Typical tail/residue handling after a fault retries the copy
+ * byte-by-byte until the fault happens again. Re-triggering machine
+ * checks is potentially fatal so the implementation uses source
+ * alignment and poison alignment assumptions to avoid re-triggering
+ * hardware exceptions.
+ *
+ * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
+ * Compare to copy_to_iter() where only ITER_IOVEC attempts might return
+ * a short copy.
+ *
+ * See MCSAFE_TEST for self-test.
+ */
size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
{
const char *from = addr;
unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
- if (unlikely(i->type & ITER_PIPE)) {
- WARN_ON(1);
- return 0;
- }
+ if (unlikely(i->type & ITER_PIPE))
+ return copy_pipe_to_iter_mcsafe(addr, bytes, i);
if (iter_is_iovec(i))
might_fault();
iterate_and_advance(i, bytes, v,
EXPORT_SYMBOL(_copy_from_iter_nocache);
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * _copy_from_iter_flushcache - write destination through cpu cache
+ * @addr: destination kernel address
+ * @bytes: total transfer length
+ * @iter: source iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_from_iter() for ensuring that writes to persistent memory
+ * are flushed through the CPU cache. It is differentiated from
+ * _copy_from_iter_nocache() in that guarantees all data is flushed for
+ * all iterator types. The _copy_from_iter_nocache() only attempts to
+ * bypass the cache for the ITER_IOVEC case, and on some archs may use
+ * instructions that strand dirty-data in the cache.
+ */
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
spin_lock_irqsave(&tags->lock, flags);
/* Fastpath */
- if (likely(tags->nr_free >= 0)) {
+ if (likely(tags->nr_free)) {
tag = tags->freelist[--tags->nr_free];
spin_unlock_irqrestore(&tags->lock, flags);
return tag;
asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
}
-static inline void LOAD_DATA(int x, int n, u8 *ptr)
+static inline void LOAD_DATA(int x, u8 *ptr)
{
- typedef struct { u8 _[16*n]; } addrtype;
+ typedef struct { u8 _[16 * $#]; } addrtype;
register addrtype *__ptr asm("1") = (addrtype *) ptr;
asm volatile ("VLM %2,%3,0,%r1"
- : : "m" (*__ptr), "a" (__ptr), "i" (x), "i" (x + n - 1));
+ : : "m" (*__ptr), "a" (__ptr), "i" (x),
+ "i" (x + $# - 1));
}
-static inline void STORE_DATA(int x, int n, u8 *ptr)
+static inline void STORE_DATA(int x, u8 *ptr)
{
- typedef struct { u8 _[16*n]; } addrtype;
+ typedef struct { u8 _[16 * $#]; } addrtype;
register addrtype *__ptr asm("1") = (addrtype *) ptr;
asm volatile ("VSTM %2,%3,0,1"
- : "=m" (*__ptr) : "a" (__ptr), "i" (x), "i" (x + n - 1));
+ : "=m" (*__ptr) : "a" (__ptr), "i" (x),
+ "i" (x + $# - 1));
}
static inline void COPY_VEC(int x, int y)
q = dptr[z0 + 2]; /* RS syndrome */
for (d = 0; d < bytes; d += $#*NSIZE) {
- LOAD_DATA(0,$#,&dptr[z0][d]);
+ LOAD_DATA(0,&dptr[z0][d]);
COPY_VEC(8+$$,0+$$);
for (z = z0 - 1; z >= 0; z--) {
MASK(16+$$,8+$$);
AND(16+$$,16+$$,25);
SHLBYTE(8+$$,8+$$);
XOR(8+$$,8+$$,16+$$);
- LOAD_DATA(16,$#,&dptr[z][d]);
+ LOAD_DATA(16,&dptr[z][d]);
XOR(0+$$,0+$$,16+$$);
XOR(8+$$,8+$$,16+$$);
}
- STORE_DATA(0,$#,&p[d]);
- STORE_DATA(8,$#,&q[d]);
+ STORE_DATA(0,&p[d]);
+ STORE_DATA(8,&q[d]);
}
kernel_fpu_end(&vxstate, KERNEL_VXR);
}
for (d = 0; d < bytes; d += $#*NSIZE) {
/* P/Q data pages */
- LOAD_DATA(0,$#,&dptr[z0][d]);
+ LOAD_DATA(0,&dptr[z0][d]);
COPY_VEC(8+$$,0+$$);
for (z = z0 - 1; z >= start; z--) {
MASK(16+$$,8+$$);
AND(16+$$,16+$$,25);
SHLBYTE(8+$$,8+$$);
XOR(8+$$,8+$$,16+$$);
- LOAD_DATA(16,$#,&dptr[z][d]);
+ LOAD_DATA(16,&dptr[z][d]);
XOR(0+$$,0+$$,16+$$);
XOR(8+$$,8+$$,16+$$);
}
SHLBYTE(8+$$,8+$$);
XOR(8+$$,8+$$,16+$$);
}
- LOAD_DATA(16,$#,&p[d]);
+ LOAD_DATA(16,&p[d]);
XOR(16+$$,16+$$,0+$$);
- STORE_DATA(16,$#,&p[d]);
- LOAD_DATA(16,$#,&q[d]);
+ STORE_DATA(16,&p[d]);
+ LOAD_DATA(16,&q[d]);
XOR(16+$$,16+$$,8+$$);
- STORE_DATA(16,$#,&q[d]);
+ STORE_DATA(16,&q[d]);
}
kernel_fpu_end(&vxstate, KERNEL_VXR);
}
*
*/
+#include <linux/mutex.h>
#include <linux/refcount.h>
+#include <linux/spinlock.h>
#include <linux/bug.h>
-#ifdef CONFIG_REFCOUNT_FULL
-
/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
* @i: the value to add to the refcount
* @r: the refcount
*
*
* Return: false if the passed refcount is 0, true otherwise
*/
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
{
unsigned int new, val = atomic_read(&r->refs);
return true;
}
-EXPORT_SYMBOL(refcount_add_not_zero);
+EXPORT_SYMBOL(refcount_add_not_zero_checked);
/**
- * refcount_add - add a value to a refcount
+ * refcount_add_checked - add a value to a refcount
* @i: the value to add to the refcount
* @r: the refcount
*
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
*/
-void refcount_add(unsigned int i, refcount_t *r)
+void refcount_add_checked(unsigned int i, refcount_t *r)
{
- WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+ WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
}
-EXPORT_SYMBOL(refcount_add);
+EXPORT_SYMBOL(refcount_add_checked);
/**
- * refcount_inc_not_zero - increment a refcount unless it is 0
+ * refcount_inc_not_zero_checked - increment a refcount unless it is 0
* @r: the refcount to increment
*
* Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
*
* Return: true if the increment was successful, false otherwise
*/
-bool refcount_inc_not_zero(refcount_t *r)
+bool refcount_inc_not_zero_checked(refcount_t *r)
{
unsigned int new, val = atomic_read(&r->refs);
return true;
}
-EXPORT_SYMBOL(refcount_inc_not_zero);
+EXPORT_SYMBOL(refcount_inc_not_zero_checked);
/**
- * refcount_inc - increment a refcount
+ * refcount_inc_checked - increment a refcount
* @r: the refcount to increment
*
* Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
* Will WARN if the refcount is 0, as this represents a possible use-after-free
* condition.
*/
-void refcount_inc(refcount_t *r)
+void refcount_inc_checked(refcount_t *r)
{
- WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+ WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
}
-EXPORT_SYMBOL(refcount_inc);
+EXPORT_SYMBOL(refcount_inc_checked);
/**
- * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
* @i: amount to subtract from the refcount
* @r: the refcount
*
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
{
unsigned int new, val = atomic_read(&r->refs);
return !new;
}
-EXPORT_SYMBOL(refcount_sub_and_test);
+EXPORT_SYMBOL(refcount_sub_and_test_checked);
/**
- * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
* @r: the refcount
*
* Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-bool refcount_dec_and_test(refcount_t *r)
+bool refcount_dec_and_test_checked(refcount_t *r)
{
- return refcount_sub_and_test(1, r);
+ return refcount_sub_and_test_checked(1, r);
}
-EXPORT_SYMBOL(refcount_dec_and_test);
+EXPORT_SYMBOL(refcount_dec_and_test_checked);
/**
- * refcount_dec - decrement a refcount
+ * refcount_dec_checked - decrement a refcount
* @r: the refcount
*
* Similar to atomic_dec(), it will WARN on underflow and fail to decrement
* Provides release memory ordering, such that prior loads and stores are done
* before.
*/
-void refcount_dec(refcount_t *r)
+void refcount_dec_checked(refcount_t *r)
{
- WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+ WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
}
-EXPORT_SYMBOL(refcount_dec);
-#endif /* CONFIG_REFCOUNT_FULL */
+EXPORT_SYMBOL(refcount_dec_checked);
/**
* refcount_dec_if_one - decrement a refcount if it is 1
}
EXPORT_SYMBOL(refcount_dec_and_lock);
+/**
+ * refcount_dec_and_lock_irqsave - return holding spinlock with disabled
+ * interrupts if able to decrement refcount to 0
+ * @r: the refcount
+ * @lock: the spinlock to be locked
+ * @flags: saved IRQ-flags if the is acquired
+ *
+ * Same as refcount_dec_and_lock() above except that the spinlock is acquired
+ * with disabled interupts.
+ *
+ * Return: true and hold spinlock if able to decrement refcount to 0, false
+ * otherwise
+ */
+bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock,
+ unsigned long *flags)
+{
+ if (refcount_dec_not_one(r))
+ return false;
+
+ spin_lock_irqsave(lock, *flags);
+ if (!refcount_dec_and_test(r)) {
+ spin_unlock_irqrestore(lock, *flags);
+ return false;
+ }
+
+ return true;
+}
+EXPORT_SYMBOL(refcount_dec_and_lock_irqsave);
skip++;
if (list == iter->list) {
iter->p = p;
- skip = skip;
+ iter->skip = skip;
goto found;
}
}
static size_t rounded_hashtable_size(const struct rhashtable_params *params)
{
- return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
- (unsigned long)params->min_size);
+ size_t retsize;
+
+ if (params->nelem_hint)
+ retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+ (unsigned long)params->min_size);
+ else
+ retsize = max(HASH_DEFAULT_SIZE,
+ (unsigned long)params->min_size);
+
+ return retsize;
}
static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
struct bucket_table *tbl;
size_t size;
- size = HASH_DEFAULT_SIZE;
-
if ((!params->key_len && !params->obj_hashfn) ||
(params->obj_hashfn && !params->obj_cmpfn))
return -EINVAL;
ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
- if (params->nelem_hint)
- size = rounded_hashtable_size(&ht->p);
+ size = rounded_hashtable_size(&ht->p);
if (params->locks_mul)
ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
void (*free_fn)(void *ptr, void *arg),
void *arg)
{
- struct bucket_table *tbl;
+ struct bucket_table *tbl, *next_tbl;
unsigned int i;
cancel_work_sync(&ht->run_work);
mutex_lock(&ht->mutex);
tbl = rht_dereference(ht->tbl, ht);
+restart:
if (free_fn) {
for (i = 0; i < tbl->size; i++) {
struct rhash_head *pos, *next;
}
}
+ next_tbl = rht_dereference(tbl->future_tbl, ht);
bucket_table_free(tbl);
+ if (next_tbl) {
+ tbl = next_tbl;
+ goto restart;
+ }
mutex_unlock(&ht->mutex);
}
EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
**/
struct scatterlist *sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
if (sg_is_last(sg))
return NULL;
for_each_sg(sgl, sg, nents, i)
ret = sg;
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sgl[0].sg_magic != SG_MAGIC);
BUG_ON(!sg_is_last(ret));
-#endif
return ret;
}
EXPORT_SYMBOL(sg_last);
+++ /dev/null
-/*
- * Dynamic DMA mapping support.
- *
- * This implementation is a fallback for platforms that do not support
- * I/O TLBs (aka DMA address translation hardware).
- * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
- * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
- * Copyright (C) 2000, 2003 Hewlett-Packard Co
- * David Mosberger-Tang <davidm@hpl.hp.com>
- *
- * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API.
- * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid
- * unnecessary i-cache flushing.
- * 04/07/.. ak Better overflow handling. Assorted fixes.
- * 05/09/10 linville Add support for syncing ranges, support syncing for
- * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
- * 08/12/11 beckyb Add highmem support
- */
-
-#include <linux/cache.h>
-#include <linux/dma-direct.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/swiotlb.h>
-#include <linux/pfn.h>
-#include <linux/types.h>
-#include <linux/ctype.h>
-#include <linux/highmem.h>
-#include <linux/gfp.h>
-#include <linux/scatterlist.h>
-#include <linux/mem_encrypt.h>
-#include <linux/set_memory.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/iommu-helper.h>
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/swiotlb.h>
-
-#define OFFSET(val,align) ((unsigned long) \
- ( (val) & ( (align) - 1)))
-
-#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
-
-/*
- * Minimum IO TLB size to bother booting with. Systems with mainly
- * 64bit capable cards will only lightly use the swiotlb. If we can't
- * allocate a contiguous 1MB, we're probably in trouble anyway.
- */
-#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
-
-enum swiotlb_force swiotlb_force;
-
-/*
- * Used to do a quick range check in swiotlb_tbl_unmap_single and
- * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
- * API.
- */
-static phys_addr_t io_tlb_start, io_tlb_end;
-
-/*
- * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
- * io_tlb_end. This is command line adjustable via setup_io_tlb_npages.
- */
-static unsigned long io_tlb_nslabs;
-
-/*
- * When the IOMMU overflows we return a fallback buffer. This sets the size.
- */
-static unsigned long io_tlb_overflow = 32*1024;
-
-static phys_addr_t io_tlb_overflow_buffer;
-
-/*
- * This is a free list describing the number of free entries available from
- * each index
- */
-static unsigned int *io_tlb_list;
-static unsigned int io_tlb_index;
-
-/*
- * Max segment that we can provide which (if pages are contingous) will
- * not be bounced (unless SWIOTLB_FORCE is set).
- */
-unsigned int max_segment;
-
-/*
- * We need to save away the original address corresponding to a mapped entry
- * for the sync operations.
- */
-#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
-static phys_addr_t *io_tlb_orig_addr;
-
-/*
- * Protect the above data structures in the map and unmap calls
- */
-static DEFINE_SPINLOCK(io_tlb_lock);
-
-static int late_alloc;
-
-static int __init
-setup_io_tlb_npages(char *str)
-{
- if (isdigit(*str)) {
- io_tlb_nslabs = simple_strtoul(str, &str, 0);
- /* avoid tail segment of size < IO_TLB_SEGSIZE */
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
- if (*str == ',')
- ++str;
- if (!strcmp(str, "force")) {
- swiotlb_force = SWIOTLB_FORCE;
- } else if (!strcmp(str, "noforce")) {
- swiotlb_force = SWIOTLB_NO_FORCE;
- io_tlb_nslabs = 1;
- }
-
- return 0;
-}
-early_param("swiotlb", setup_io_tlb_npages);
-/* make io_tlb_overflow tunable too? */
-
-unsigned long swiotlb_nr_tbl(void)
-{
- return io_tlb_nslabs;
-}
-EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
-
-unsigned int swiotlb_max_segment(void)
-{
- return max_segment;
-}
-EXPORT_SYMBOL_GPL(swiotlb_max_segment);
-
-void swiotlb_set_max_segment(unsigned int val)
-{
- if (swiotlb_force == SWIOTLB_FORCE)
- max_segment = 1;
- else
- max_segment = rounddown(val, PAGE_SIZE);
-}
-
-/* default to 64MB */
-#define IO_TLB_DEFAULT_SIZE (64UL<<20)
-unsigned long swiotlb_size_or_default(void)
-{
- unsigned long size;
-
- size = io_tlb_nslabs << IO_TLB_SHIFT;
-
- return size ? size : (IO_TLB_DEFAULT_SIZE);
-}
-
-static bool no_iotlb_memory;
-
-void swiotlb_print_info(void)
-{
- unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
- unsigned char *vstart, *vend;
-
- if (no_iotlb_memory) {
- pr_warn("software IO TLB: No low mem\n");
- return;
- }
-
- vstart = phys_to_virt(io_tlb_start);
- vend = phys_to_virt(io_tlb_end);
-
- printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
- (unsigned long long)io_tlb_start,
- (unsigned long long)io_tlb_end,
- bytes >> 20, vstart, vend - 1);
-}
-
-/*
- * Early SWIOTLB allocation may be too early to allow an architecture to
- * perform the desired operations. This function allows the architecture to
- * call SWIOTLB when the operations are possible. It needs to be called
- * before the SWIOTLB memory is used.
- */
-void __init swiotlb_update_mem_attributes(void)
-{
- void *vaddr;
- unsigned long bytes;
-
- if (no_iotlb_memory || late_alloc)
- return;
-
- vaddr = phys_to_virt(io_tlb_start);
- bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
- set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
- memset(vaddr, 0, bytes);
-
- vaddr = phys_to_virt(io_tlb_overflow_buffer);
- bytes = PAGE_ALIGN(io_tlb_overflow);
- set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
- memset(vaddr, 0, bytes);
-}
-
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
-{
- void *v_overflow_buffer;
- unsigned long i, bytes;
-
- bytes = nslabs << IO_TLB_SHIFT;
-
- io_tlb_nslabs = nslabs;
- io_tlb_start = __pa(tlb);
- io_tlb_end = io_tlb_start + bytes;
-
- /*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = memblock_virt_alloc_low_nopanic(
- PAGE_ALIGN(io_tlb_overflow),
- PAGE_SIZE);
- if (!v_overflow_buffer)
- return -ENOMEM;
-
- io_tlb_overflow_buffer = __pa(v_overflow_buffer);
-
- /*
- * Allocate and initialize the free list array. This array is used
- * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
- * between io_tlb_start and io_tlb_end.
- */
- io_tlb_list = memblock_virt_alloc(
- PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
- PAGE_SIZE);
- io_tlb_orig_addr = memblock_virt_alloc(
- PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
- PAGE_SIZE);
- for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
- io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
- }
- io_tlb_index = 0;
-
- if (verbose)
- swiotlb_print_info();
-
- swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
- return 0;
-}
-
-/*
- * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the DMA API.
- */
-void __init
-swiotlb_init(int verbose)
-{
- size_t default_size = IO_TLB_DEFAULT_SIZE;
- unsigned char *vstart;
- unsigned long bytes;
-
- if (!io_tlb_nslabs) {
- io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
-
- bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
- /* Get IO TLB memory from the low pages */
- vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
- if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
- return;
-
- if (io_tlb_start)
- memblock_free_early(io_tlb_start,
- PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
- pr_warn("Cannot allocate SWIOTLB buffer");
- no_iotlb_memory = true;
-}
-
-/*
- * Systems with larger DMA zones (those that don't support ISA) can
- * initialize the swiotlb later using the slab allocator if needed.
- * This should be just like above, but with some error catching.
- */
-int
-swiotlb_late_init_with_default_size(size_t default_size)
-{
- unsigned long bytes, req_nslabs = io_tlb_nslabs;
- unsigned char *vstart = NULL;
- unsigned int order;
- int rc = 0;
-
- if (!io_tlb_nslabs) {
- io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
-
- /*
- * Get IO TLB memory from the low pages
- */
- order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
- io_tlb_nslabs = SLABS_PER_PAGE << order;
- bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
- while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
- vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
- order);
- if (vstart)
- break;
- order--;
- }
-
- if (!vstart) {
- io_tlb_nslabs = req_nslabs;
- return -ENOMEM;
- }
- if (order != get_order(bytes)) {
- printk(KERN_WARNING "Warning: only able to allocate %ld MB "
- "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
- io_tlb_nslabs = SLABS_PER_PAGE << order;
- }
- rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
- if (rc)
- free_pages((unsigned long)vstart, order);
-
- return rc;
-}
-
-int
-swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
-{
- unsigned long i, bytes;
- unsigned char *v_overflow_buffer;
-
- bytes = nslabs << IO_TLB_SHIFT;
-
- io_tlb_nslabs = nslabs;
- io_tlb_start = virt_to_phys(tlb);
- io_tlb_end = io_tlb_start + bytes;
-
- set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
- memset(tlb, 0, bytes);
-
- /*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
- get_order(io_tlb_overflow));
- if (!v_overflow_buffer)
- goto cleanup2;
-
- set_memory_decrypted((unsigned long)v_overflow_buffer,
- io_tlb_overflow >> PAGE_SHIFT);
- memset(v_overflow_buffer, 0, io_tlb_overflow);
- io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
-
- /*
- * Allocate and initialize the free list array. This array is used
- * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
- * between io_tlb_start and io_tlb_end.
- */
- io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs * sizeof(int)));
- if (!io_tlb_list)
- goto cleanup3;
-
- io_tlb_orig_addr = (phys_addr_t *)
- __get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs *
- sizeof(phys_addr_t)));
- if (!io_tlb_orig_addr)
- goto cleanup4;
-
- for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
- io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
- }
- io_tlb_index = 0;
-
- swiotlb_print_info();
-
- late_alloc = 1;
-
- swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
-
- return 0;
-
-cleanup4:
- free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
- sizeof(int)));
- io_tlb_list = NULL;
-cleanup3:
- free_pages((unsigned long)v_overflow_buffer,
- get_order(io_tlb_overflow));
- io_tlb_overflow_buffer = 0;
-cleanup2:
- io_tlb_end = 0;
- io_tlb_start = 0;
- io_tlb_nslabs = 0;
- max_segment = 0;
- return -ENOMEM;
-}
-
-void __init swiotlb_exit(void)
-{
- if (!io_tlb_orig_addr)
- return;
-
- if (late_alloc) {
- free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
- get_order(io_tlb_overflow));
- free_pages((unsigned long)io_tlb_orig_addr,
- get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
- free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
- sizeof(int)));
- free_pages((unsigned long)phys_to_virt(io_tlb_start),
- get_order(io_tlb_nslabs << IO_TLB_SHIFT));
- } else {
- memblock_free_late(io_tlb_overflow_buffer,
- PAGE_ALIGN(io_tlb_overflow));
- memblock_free_late(__pa(io_tlb_orig_addr),
- PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
- memblock_free_late(__pa(io_tlb_list),
- PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
- memblock_free_late(io_tlb_start,
- PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
- }
- io_tlb_nslabs = 0;
- max_segment = 0;
-}
-
-int is_swiotlb_buffer(phys_addr_t paddr)
-{
- return paddr >= io_tlb_start && paddr < io_tlb_end;
-}
-
-/*
- * Bounce: copy the swiotlb buffer back to the original dma location
- */
-static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir)
-{
- unsigned long pfn = PFN_DOWN(orig_addr);
- unsigned char *vaddr = phys_to_virt(tlb_addr);
-
- if (PageHighMem(pfn_to_page(pfn))) {
- /* The buffer does not have a mapping. Map it in and copy */
- unsigned int offset = orig_addr & ~PAGE_MASK;
- char *buffer;
- unsigned int sz = 0;
- unsigned long flags;
-
- while (size) {
- sz = min_t(size_t, PAGE_SIZE - offset, size);
-
- local_irq_save(flags);
- buffer = kmap_atomic(pfn_to_page(pfn));
- if (dir == DMA_TO_DEVICE)
- memcpy(vaddr, buffer + offset, sz);
- else
- memcpy(buffer + offset, vaddr, sz);
- kunmap_atomic(buffer);
- local_irq_restore(flags);
-
- size -= sz;
- pfn++;
- vaddr += sz;
- offset = 0;
- }
- } else if (dir == DMA_TO_DEVICE) {
- memcpy(vaddr, phys_to_virt(orig_addr), size);
- } else {
- memcpy(phys_to_virt(orig_addr), vaddr, size);
- }
-}
-
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t orig_addr, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- unsigned long flags;
- phys_addr_t tlb_addr;
- unsigned int nslots, stride, index, wrap;
- int i;
- unsigned long mask;
- unsigned long offset_slots;
- unsigned long max_slots;
-
- if (no_iotlb_memory)
- panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
-
- if (mem_encrypt_active())
- pr_warn_once("%s is active and system is using DMA bounce buffers\n",
- sme_active() ? "SME" : "SEV");
-
- mask = dma_get_seg_boundary(hwdev);
-
- tbl_dma_addr &= mask;
-
- offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-
- /*
- * Carefully handle integer overflow which can occur when mask == ~0UL.
- */
- max_slots = mask + 1
- ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
- : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
-
- /*
- * For mappings greater than or equal to a page, we limit the stride
- * (and hence alignment) to a page size.
- */
- nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- if (size >= PAGE_SIZE)
- stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
- else
- stride = 1;
-
- BUG_ON(!nslots);
-
- /*
- * Find suitable number of IO TLB entries size that will fit this
- * request and allocate a buffer from that IO TLB pool.
- */
- spin_lock_irqsave(&io_tlb_lock, flags);
- index = ALIGN(io_tlb_index, stride);
- if (index >= io_tlb_nslabs)
- index = 0;
- wrap = index;
-
- do {
- while (iommu_is_span_boundary(index, nslots, offset_slots,
- max_slots)) {
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- if (index == wrap)
- goto not_found;
- }
-
- /*
- * If we find a slot that indicates we have 'nslots' number of
- * contiguous buffers, we allocate the buffers from that slot
- * and mark the entries as '0' indicating unavailable.
- */
- if (io_tlb_list[index] >= nslots) {
- int count = 0;
-
- for (i = index; i < (int) (index + nslots); i++)
- io_tlb_list[i] = 0;
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
- /*
- * Update the indices to avoid searching in the next
- * round.
- */
- io_tlb_index = ((index + nslots) < io_tlb_nslabs
- ? (index + nslots) : 0);
-
- goto found;
- }
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- } while (index != wrap);
-
-not_found:
- spin_unlock_irqrestore(&io_tlb_lock, flags);
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
- dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size);
- return SWIOTLB_MAP_ERROR;
-found:
- spin_unlock_irqrestore(&io_tlb_lock, flags);
-
- /*
- * Save away the mapping from the original address to the DMA address.
- * This is needed when we sync the memory. Then we sync the buffer if
- * needed.
- */
- for (i = 0; i < nslots; i++)
- io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
- (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
-
- return tlb_addr;
-}
-
-/*
- * Allocates bounce buffer and returns its physical address.
- */
-static phys_addr_t
-map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t start_dma_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE) {
- dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
- &phys);
- return SWIOTLB_MAP_ERROR;
- }
-
- start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
- return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
- dir, attrs);
-}
-
-/*
- * tlb_addr is the physical address of the bounce buffer to unmap.
- */
-void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- unsigned long flags;
- int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
- phys_addr_t orig_addr = io_tlb_orig_addr[index];
-
- /*
- * First, sync the memory before unmapping the entry
- */
- if (orig_addr != INVALID_PHYS_ADDR &&
- !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
- ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
-
- /*
- * Return the buffer to the free list by setting the corresponding
- * entries to indicate the number of contiguous entries available.
- * While returning the entries to the free list, we merge the entries
- * with slots below and above the pool being returned.
- */
- spin_lock_irqsave(&io_tlb_lock, flags);
- {
- count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
- io_tlb_list[index + nslots] : 0);
- /*
- * Step 1: return the slots to the free list, merging the
- * slots with superceeding slots
- */
- for (i = index + nslots - 1; i >= index; i--) {
- io_tlb_list[i] = ++count;
- io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
- }
- /*
- * Step 2: merge the returned slots with the preceding slots,
- * if available (non zero)
- */
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- }
- spin_unlock_irqrestore(&io_tlb_lock, flags);
-}
-
-void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir,
- enum dma_sync_target target)
-{
- int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
- phys_addr_t orig_addr = io_tlb_orig_addr[index];
-
- if (orig_addr == INVALID_PHYS_ADDR)
- return;
- orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
-
- switch (target) {
- case SYNC_FOR_CPU:
- if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
- swiotlb_bounce(orig_addr, tlb_addr,
- size, DMA_FROM_DEVICE);
- else
- BUG_ON(dir != DMA_TO_DEVICE);
- break;
- case SYNC_FOR_DEVICE:
- if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
- swiotlb_bounce(orig_addr, tlb_addr,
- size, DMA_TO_DEVICE);
- else
- BUG_ON(dir != DMA_FROM_DEVICE);
- break;
- default:
- BUG();
- }
-}
-
-static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
- size_t size)
-{
- u64 mask = DMA_BIT_MASK(32);
-
- if (dev && dev->coherent_dma_mask)
- mask = dev->coherent_dma_mask;
- return addr + size - 1 <= mask;
-}
-
-static void *
-swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
- unsigned long attrs)
-{
- phys_addr_t phys_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- goto out_warn;
-
- phys_addr = swiotlb_tbl_map_single(dev,
- __phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, attrs);
- if (phys_addr == SWIOTLB_MAP_ERROR)
- goto out_warn;
-
- *dma_handle = __phys_to_dma(dev, phys_addr);
- if (!dma_coherent_ok(dev, *dma_handle, size))
- goto out_unmap;
-
- memset(phys_to_virt(phys_addr), 0, size);
- return phys_to_virt(phys_addr);
-
-out_unmap:
- dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
- (unsigned long long)dev->coherent_dma_mask,
- (unsigned long long)*dma_handle);
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
-out_warn:
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
- dev_warn(dev,
- "swiotlb: coherent allocation failed, size=%zu\n",
- size);
- dump_stack();
- }
- return NULL;
-}
-
-static bool swiotlb_free_buffer(struct device *dev, size_t size,
- dma_addr_t dma_addr)
-{
- phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
-
- WARN_ON_ONCE(irqs_disabled());
-
- if (!is_swiotlb_buffer(phys_addr))
- return false;
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
- return true;
-}
-
-static void
-swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
- int do_panic)
-{
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- return;
-
- /*
- * Ran out of IOMMU space for this operation. This is very bad.
- * Unfortunately the drivers cannot handle this operation properly.
- * unless they check for dma_mapping_error (most don't)
- * When the mapping is small enough return a static buffer to limit
- * the damage, or panic when the transfer is too big.
- */
- dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
- size);
-
- if (size <= io_tlb_overflow || !do_panic)
- return;
-
- if (dir == DMA_BIDIRECTIONAL)
- panic("DMA: Random memory could be DMA accessed\n");
- if (dir == DMA_FROM_DEVICE)
- panic("DMA: Random memory could be DMA written\n");
- if (dir == DMA_TO_DEVICE)
- panic("DMA: Random memory could be DMA read\n");
-}
-
-/*
- * Map a single buffer of the indicated size for DMA in streaming mode. The
- * physical address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
- */
-dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- phys_addr_t map, phys = page_to_phys(page) + offset;
- dma_addr_t dev_addr = phys_to_dma(dev, phys);
-
- BUG_ON(dir == DMA_NONE);
- /*
- * If the address happens to be in the device's DMA window,
- * we can safely return the device addr and not worry about bounce
- * buffering it.
- */
- if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
- return dev_addr;
-
- trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-
- /* Oh well, have to allocate and map a bounce buffer. */
- map = map_single(dev, phys, size, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- swiotlb_full(dev, size, dir, 1);
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
- }
-
- dev_addr = __phys_to_dma(dev, map);
-
- /* Ensure that the address returned is DMA'ble */
- if (dma_capable(dev, dev_addr, size))
- return dev_addr;
-
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
-
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
-}
-
-/*
- * Unmap a single streaming mode DMA translation. The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_page call. All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
- BUG_ON(dir == DMA_NONE);
-
- if (is_swiotlb_buffer(paddr)) {
- swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
- return;
- }
-
- if (dir != DMA_FROM_DEVICE)
- return;
-
- /*
- * phys_to_virt doesn't work with hihgmem page but we could
- * call dma_mark_clean() with hihgmem page here. However, we
- * are fine since dma_mark_clean() is null on POWERPC. We can
- * make dma_mark_clean() take a physical address if necessary.
- */
- dma_mark_clean(phys_to_virt(paddr), size);
-}
-
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- unmap_single(hwdev, dev_addr, size, dir, attrs);
-}
-
-/*
- * Make physical memory consistent for a single streaming mode DMA translation
- * after a transfer.
- *
- * If you perform a swiotlb_map_page() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the dma mapping, you must
- * call this function before doing so. At the next point you give the dma
- * address back to the card, you must first perform a
- * swiotlb_dma_sync_for_device, and then the device again owns the buffer
- */
-static void
-swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- enum dma_sync_target target)
-{
- phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
-
- BUG_ON(dir == DMA_NONE);
-
- if (is_swiotlb_buffer(paddr)) {
- swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
- return;
- }
-
- if (dir != DMA_FROM_DEVICE)
- return;
-
- dma_mark_clean(phys_to_virt(paddr), size);
-}
-
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir)
-{
- swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir)
-{
- swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
-}
-
-/*
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_page
- * interface. Here the scatter gather list elements are each tagged with the
- * appropriate dma address and length. They are obtained via
- * sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
- * Device ownership issues as mentioned above for swiotlb_map_page are the
- * same here.
- */
-int
-swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir, unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- BUG_ON(dir == DMA_NONE);
-
- for_each_sg(sgl, sg, nelems, i) {
- phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
-
- if (swiotlb_force == SWIOTLB_FORCE ||
- !dma_capable(hwdev, dev_addr, sg->length)) {
- phys_addr_t map = map_single(hwdev, sg_phys(sg),
- sg->length, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- /* Don't panic here, we expect map_sg users
- to do proper error handling. */
- swiotlb_full(hwdev, sg->length, dir, 0);
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
- attrs);
- sg_dma_len(sgl) = 0;
- return 0;
- }
- sg->dma_address = __phys_to_dma(hwdev, map);
- } else
- sg->dma_address = dev_addr;
- sg_dma_len(sg) = sg->length;
- }
- return nelems;
-}
-
-/*
- * Unmap a set of streaming mode DMA translations. Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
- */
-void
-swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- BUG_ON(dir == DMA_NONE);
-
- for_each_sg(sgl, sg, nelems, i)
- unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
- attrs);
-}
-
-/*
- * Make physical memory consistent for a set of streaming mode DMA translations
- * after a transfer.
- *
- * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
- * and usage.
- */
-static void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- enum dma_sync_target target)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sgl, sg, nelems, i)
- swiotlb_sync_single(hwdev, sg->dma_address,
- sg_dma_len(sg), dir, target);
-}
-
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir)
-{
- swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir)
-{
- swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
-}
-
-int
-swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
- return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
-}
-
-/*
- * Return whether the given device DMA address mask can be supported
- * properly. For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask to
- * this function.
- */
-int
-swiotlb_dma_supported(struct device *hwdev, u64 mask)
-{
- return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
-}
-
-void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- void *vaddr;
-
- /* temporary workaround: */
- if (gfp & __GFP_NOWARN)
- attrs |= DMA_ATTR_NO_WARN;
-
- /*
- * Don't print a warning when the first allocation attempt fails.
- * swiotlb_alloc_coherent() will print a warning when the DMA memory
- * allocation ultimately failed.
- */
- gfp |= __GFP_NOWARN;
-
- vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
- if (!vaddr)
- vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
- return vaddr;
-}
-
-void swiotlb_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, unsigned long attrs)
-{
- if (!swiotlb_free_buffer(dev, size, dma_addr))
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
-}
-
-const struct dma_map_ops swiotlb_dma_ops = {
- .mapping_error = swiotlb_dma_mapping_error,
- .alloc = swiotlb_alloc,
- .free = swiotlb_free,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = swiotlb_sync_sg_for_device,
- .map_sg = swiotlb_map_sg_attrs,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .map_page = swiotlb_map_page,
- .unmap_page = swiotlb_unmap_page,
- .dma_supported = dma_direct_supported,
-};
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Ctx heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{
{ 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
},
.fill_helper = bpf_fill_maxinsns6,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Call heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
CLASSIC | FLAG_NO_DATA,
+#endif
{ },
{ { 1, 0 }, { 10, 0 } },
.fill_helper = bpf_fill_maxinsns7,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Jump heavy test",
{
"BPF_MAXINSNS: exec all MSH",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ 0xfa, 0xfb, 0xfc, 0xfd, },
{ { 4, 0xababab83 } },
.fill_helper = bpf_fill_maxinsns13,
+ .expected_errcode = -ENOTSUPP,
},
{
"BPF_MAXINSNS: ld_abs+get_processor_id",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{ { 1, 0xbee } },
.fill_helper = bpf_fill_ld_abs_get_processor_id,
+ .expected_errcode = -ENOTSUPP,
},
/*
* LD_IND / LD_ABS on fragmented SKBs
spin_lock_bh(&wb->work_lock);
if (!test_and_clear_bit(WB_registered, &wb->state)) {
spin_unlock_bh(&wb->work_lock);
- /*
- * Wait for wb shutdown to finish if someone else is just
- * running wb_shutdown(). Otherwise we could proceed to wb /
- * bdi destruction before wb_shutdown() is finished.
- */
- wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
return;
}
- set_bit(WB_shutting_down, &wb->state);
spin_unlock_bh(&wb->work_lock);
cgwb_remove_from_bdi_list(wb);
mod_delayed_work(bdi_wq, &wb->dwork, 0);
flush_delayed_work(&wb->dwork);
WARN_ON(!list_empty(&wb->work_list));
- /*
- * Make sure bit gets cleared after shutdown is finished. Matches with
- * the barrier provided by test_and_clear_bit() above.
- */
- smp_wmb();
- clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
release_work);
+ mutex_lock(&wb->bdi->cgwb_release_mutex);
wb_shutdown(wb);
css_put(wb->memcg_css);
css_put(wb->blkcg_css);
+ mutex_unlock(&wb->bdi->cgwb_release_mutex);
fprop_local_destroy_percpu(&wb->memcg_completions);
percpu_ref_exit(&wb->refcnt);
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
bdi->cgwb_congested_tree = RB_ROOT;
+ mutex_init(&bdi->cgwb_release_mutex);
ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
if (!ret) {
spin_lock_irq(&cgwb_lock);
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
+ spin_unlock_irq(&cgwb_lock);
+ mutex_lock(&bdi->cgwb_release_mutex);
+ spin_lock_irq(&cgwb_lock);
while (!list_empty(&bdi->wb_list)) {
wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
bdi_node);
spin_lock_irq(&cgwb_lock);
}
spin_unlock_irq(&cgwb_lock);
+ mutex_unlock(&bdi->cgwb_release_mutex);
}
/**
struct dentry *root = debugfs_create_dir("cleancache", NULL);
if (root == NULL)
return -ENXIO;
- debugfs_create_u64("succ_gets", S_IRUGO, root, &cleancache_succ_gets);
- debugfs_create_u64("failed_gets", S_IRUGO,
- root, &cleancache_failed_gets);
- debugfs_create_u64("puts", S_IRUGO, root, &cleancache_puts);
- debugfs_create_u64("invalidates", S_IRUGO,
- root, &cleancache_invalidates);
+ debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets);
+ debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets);
+ debugfs_create_u64("puts", 0444, root, &cleancache_puts);
+ debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates);
#endif
return 0;
}
tmp = debugfs_create_dir(name, cma_debugfs_root);
- debugfs_create_file("alloc", S_IWUSR, tmp, cma,
- &cma_alloc_fops);
-
- debugfs_create_file("free", S_IWUSR, tmp, cma,
- &cma_free_fops);
-
- debugfs_create_file("base_pfn", S_IRUGO, tmp,
- &cma->base_pfn, &cma_debugfs_fops);
- debugfs_create_file("count", S_IRUGO, tmp,
- &cma->count, &cma_debugfs_fops);
- debugfs_create_file("order_per_bit", S_IRUGO, tmp,
- &cma->order_per_bit, &cma_debugfs_fops);
- debugfs_create_file("used", S_IRUGO, tmp, cma, &cma_used_fops);
- debugfs_create_file("maxchunk", S_IRUGO, tmp, cma, &cma_maxchunk_fops);
+ debugfs_create_file("alloc", 0200, tmp, cma, &cma_alloc_fops);
+ debugfs_create_file("free", 0200, tmp, cma, &cma_free_fops);
+ debugfs_create_file("base_pfn", 0444, tmp,
+ &cma->base_pfn, &cma_debugfs_fops);
+ debugfs_create_file("count", 0444, tmp, &cma->count, &cma_debugfs_fops);
+ debugfs_create_file("order_per_bit", 0444, tmp,
+ &cma->order_per_bit, &cma_debugfs_fops);
+ debugfs_create_file("used", 0444, tmp, cma, &cma_used_fops);
+ debugfs_create_file("maxchunk", 0444, tmp, cma, &cma_maxchunk_fops);
u32s = DIV_ROUND_UP(cma_bitmap_maxno(cma), BITS_PER_BYTE * sizeof(u32));
- debugfs_create_u32_array("bitmap", S_IRUGO, tmp, (u32*)cma->bitmap, u32s);
+ debugfs_create_u32_array("bitmap", 0444, tmp, (u32 *)cma->bitmap, u32s);
}
static int __init cma_debugfs_init(void)
return count;
}
-static DEVICE_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);
+static DEVICE_ATTR(compact, 0200, NULL, sysfs_compact_node);
int compaction_register_node(struct node *node)
{
void __dump_page(struct page *page, const char *reason)
{
+ bool page_poisoned = PagePoisoned(page);
+ int mapcount;
+
+ /*
+ * If struct page is poisoned don't access Page*() functions as that
+ * leads to recursive loop. Page*() check for poisoned pages, and calls
+ * dump_page() when detected.
+ */
+ if (page_poisoned) {
+ pr_emerg("page:%px is uninitialized and poisoned", page);
+ goto hex_only;
+ }
+
/*
* Avoid VM_BUG_ON() in page_mapcount().
* page->_mapcount space in struct page is used by sl[aou]b pages to
* encode own info.
*/
- int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+ mapcount = PageSlab(page) ? 0 : page_mapcount(page);
pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
+hex_only:
print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
sizeof(unsigned long), page,
sizeof(struct page), false);
pr_alert("page dumped because: %s\n", reason);
#ifdef CONFIG_MEMCG
- if (page->mem_cgroup)
+ if (!page_poisoned && page->mem_cgroup)
pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
return PAGE_SIZE - size;
}
-static DEVICE_ATTR(pools, S_IRUGO, show_pools, NULL);
+static DEVICE_ATTR(pools, 0444, show_pools, NULL);
/**
* dma_pool_create - Creates a pool of consistent memory blocks, for dma.
static int __init failslab_debugfs_init(void)
{
struct dentry *dir;
- umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ umode_t mode = S_IFREG | 0600;
dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
if (IS_ERR(dir))
struct dentry *root = debugfs_create_dir("frontswap", NULL);
if (root == NULL)
return -ENXIO;
- debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads);
- debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores);
- debugfs_create_u64("failed_stores", S_IRUGO, root,
- &frontswap_failed_stores);
- debugfs_create_u64("invalidates", S_IRUGO,
- root, &frontswap_invalidates);
+ debugfs_create_u64("loads", 0444, root, &frontswap_loads);
+ debugfs_create_u64("succ_stores", 0444, root, &frontswap_succ_stores);
+ debugfs_create_u64("failed_stores", 0444, root,
+ &frontswap_failed_stores);
+ debugfs_create_u64("invalidates", 0444, root, &frontswap_invalidates);
#endif
return 0;
}
int locked = 0;
long ret = 0;
- VM_BUG_ON(start & ~PAGE_MASK);
- VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
for (nstart = start; nstart < end; nstart = nend) {
if (vma_is_dax(vma))
return;
page = pmd_page(_pmd);
+ if (!PageDirty(page) && pmd_dirty(_pmd))
+ set_page_dirty(page);
if (!PageReferenced(page) && pmd_young(_pmd))
SetPageReferenced(page);
page_remove_rmap(page, true);
*/
if (hstate_is_gigantic(h))
adjust_managed_page_count(page, 1 << h->order);
+ cond_resched();
}
}
return 0;
}
+/*
+ * When a new function is introduced to vm_operations_struct and added
+ * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
+ * This is because under System V memory model, mappings created via
+ * shmget/shmat with "huge page" specified are backed by hugetlbfs files,
+ * their original vm_ops are overwritten with shm_vm_ops.
+ */
const struct vm_operations_struct hugetlb_vm_ops = {
.fault = hugetlb_vm_op_fault,
.open = hugetlb_vm_op_open,
#define INIT_MM_CONTEXT(name)
#endif
+/*
+ * For dynamically allocated mm_structs, there is a dynamically sized cpumask
+ * at the end of the structure, the size of which depends on the maximum CPU
+ * number the system can see. That way we allocate only as much memory for
+ * mm_cpumask() as needed for the hundreds, or thousands of processes that
+ * a system typically runs.
+ *
+ * Since there is only one init_mm in the entire system, keep it simple
+ * and size this cpu_bitmask to NR_CPUS.
+ */
struct mm_struct init_mm = {
.mm_rb = RB_ROOT,
.pgd = swapper_pg_dir,
.arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
.user_ns = &init_user_ns,
+ .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0},
INIT_MM_CONTEXT(init_mm)
};
int kasan_module_alloc(void *addr, size_t size)
{
void *ret;
+ size_t scaled_size;
size_t shadow_size;
unsigned long shadow_start;
shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
- shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT,
- PAGE_SIZE);
+ scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+ shadow_size = round_up(scaled_size, PAGE_SIZE);
if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
return -EINVAL;
#define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */
#define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */
#define STABLE_FLAG 0x200 /* is listed from the stable tree */
+#define KSM_FLAG_MASK (SEQNR_MASK|UNSTABLE_FLAG|STABLE_FLAG)
+ /* to mask all the flags */
/* The stable and unstable tree heads */
static struct rb_root one_stable_tree[1] = { RB_ROOT };
anon_vma_lock_read(anon_vma);
anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
0, ULONG_MAX) {
+ unsigned long addr;
+
cond_resched();
vma = vmac->vma;
- if (rmap_item->address < vma->vm_start ||
- rmap_item->address >= vma->vm_end)
+
+ /* Ignore the stable/unstable/sqnr flags */
+ addr = rmap_item->address & ~KSM_FLAG_MASK;
+
+ if (addr < vma->vm_start || addr >= vma->vm_end)
continue;
/*
* Initially we examine only the vma which covers this
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
continue;
- if (!rwc->rmap_one(page, vma,
- rmap_item->address, rwc->arg)) {
+ if (!rwc->rmap_one(page, vma, addr, rwc->arg)) {
anon_vma_unlock_read(anon_vma);
return;
}
#include <linux/kmemleak.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
+#include <linux/bootmem.h>
#include <asm/sections.h>
#include <linux/io.h>
* so we use WARN_ONCE() here to see the stack trace if
* fail happens.
*/
- WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n");
+ WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
+ "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
}
return __memblock_find_range_top_down(start, end, size, align, nid,
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
+#if defined(CONFIG_NO_BOOTMEM)
/**
* memblock_virt_alloc_internal - allocate boot memory block
* @size: size of memory block to be allocated in bytes
(u64)max_addr);
return NULL;
}
+#endif
/**
* __memblock_free_early - free boot memory block
struct dentry *root = debugfs_create_dir("memblock", NULL);
if (!root)
return -ENXIO;
- debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
- debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+ debugfs_create_file("memory", 0444, root,
+ &memblock.memory, &memblock_debug_fops);
+ debugfs_create_file("reserved", 0444, root,
+ &memblock.reserved, &memblock_debug_fops);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
- debugfs_create_file("physmem", S_IRUGO, root, &memblock.physmem, &memblock_debug_fops);
+ debugfs_create_file("physmem", 0444, root,
+ &memblock.physmem, &memblock_debug_fops);
#endif
return 0;
int nid;
int i;
- while ((memcg = parent_mem_cgroup(memcg))) {
+ for (; memcg; memcg = parent_mem_cgroup(memcg)) {
for_each_node(nid) {
mz = mem_cgroup_nodeinfo(memcg, nid);
for (i = 0; i <= DEF_PRIORITY; i++) {
seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
- seq_printf(sf, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL));
+ seq_printf(sf, "oom_kill %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
return 0;
}
static DEFINE_IDR(mem_cgroup_idr);
+static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
+{
+ if (memcg->id.id > 0) {
+ idr_remove(&mem_cgroup_idr, memcg->id.id);
+ memcg->id.id = 0;
+ }
+}
+
static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
{
VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0);
{
VM_BUG_ON(atomic_read(&memcg->id.ref) < n);
if (atomic_sub_and_test(n, &memcg->id.ref)) {
- idr_remove(&mem_cgroup_idr, memcg->id.id);
- memcg->id.id = 0;
+ mem_cgroup_id_remove(memcg);
/* Memcg ID pins CSS */
css_put(&memcg->css);
idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
return memcg;
fail:
- if (memcg->id.id > 0)
- idr_remove(&mem_cgroup_idr, memcg->id.id);
+ mem_cgroup_id_remove(memcg);
__mem_cgroup_free(memcg);
return NULL;
}
return &memcg->css;
fail:
+ mem_cgroup_id_remove(memcg);
mem_cgroup_free(memcg);
return ERR_PTR(-ENOMEM);
}
atomic_long_read(&memcg->memory_events[MEMCG_MAX]));
seq_printf(m, "oom %lu\n",
atomic_long_read(&memcg->memory_events[MEMCG_OOM]));
- seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL));
+ seq_printf(m, "oom_kill %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
return 0;
}
elow = memcg->memory.low;
parent = parent_mem_cgroup(memcg);
+ /* No parent means a non-hierarchical mode on v1 memcg */
+ if (!parent)
+ return MEMCG_PROT_NONE;
+
if (parent == root)
goto exit;
goto err_fd;
}
file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
- file->f_flags |= O_RDWR | O_LARGEFILE;
+ file->f_flags |= O_LARGEFILE;
if (flags & MFD_ALLOW_SEALING) {
file_seals = memfd_file_seals_ptr(file);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-/*
- * See the comment near struct mmu_table_batch.
- */
-
static void tlb_remove_table_smp_sync(void *arg)
{
- /* Simply deliver the interrupt */
+ struct mm_struct __maybe_unused *mm = arg;
+ /*
+ * On most architectures this does nothing. Simply delivering the
+ * interrupt is enough to prevent races with software page table
+ * walking like that done in get_user_pages_fast.
+ *
+ * See the comment near struct mmu_table_batch.
+ */
+ tlb_flush_remove_tables_local(mm);
}
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
{
/*
* This isn't an RCU grace period and hence the page-tables cannot be
* It is however sufficient for software page-table walkers that rely on
* IRQ disabling. See the comment near struct mmu_table_batch.
*/
- smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+ smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1);
__tlb_remove_table(table);
}
{
struct mmu_table_batch **batch = &tlb->batch;
+ tlb_flush_remove_tables(tlb->mm);
+
if (*batch) {
call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
*batch = NULL;
if (*batch == NULL) {
*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
if (*batch == NULL) {
- tlb_remove_table_one(table);
+ tlb_remove_table_one(table, tlb);
return;
}
(*batch)->nr = 0;
do {
next = pmd_addr_end(addr, end);
if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
- if (next - addr != HPAGE_PMD_SIZE) {
- VM_BUG_ON_VMA(vma_is_anonymous(vma) &&
- !rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+ if (next - addr != HPAGE_PMD_SIZE)
__split_huge_pmd(vma, pmd, addr, false, NULL);
- } else if (zap_huge_pmd(tlb, vma, pmd, addr))
+ else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/* fall through */
}
return -EINVAL;
maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
+ if (!maddr)
+ return -ENOMEM;
+
if (write)
memcpy_toio(maddr + offset, buf, len);
else
/* Create pseudo-vma that contains just the policy */
memset(&pvma, 0, sizeof(struct vm_area_struct));
+ vma_init(&pvma, NULL);
pvma.vm_end = TASK_SIZE; /* policy covers entire file */
mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
if (vma->vm_file)
fput(vma->vm_file);
mpol_put(vma_policy(vma));
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return next;
}
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
-
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
+ struct list_head *uf);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
unsigned long retval;
goto out;
/* Ok, looks good - let it rip. */
- if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
+ if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
goto out;
set_brk:
anon_vma_merge(vma, next);
mm->map_count--;
mpol_put(vma_policy(next));
- kmem_cache_free(vm_area_cachep, next);
+ vm_area_free(next);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we must remove another next too. It would clutter
* specific mapper. the address has already been validated, but
* not unmapped, but the maps are removed from the list.
*/
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(mm);
if (!vma) {
error = -ENOMEM;
goto unacct_error;
}
- vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
vma->vm_flags = vm_flags;
vma->vm_page_prot = vm_get_page_prot(vm_flags);
vma->vm_pgoff = pgoff;
- INIT_LIST_HEAD(&vma->anon_vma_chain);
if (file) {
if (vm_flags & VM_DENYWRITE) {
error = shmem_zero_setup(vma);
if (error)
goto free_vma;
+ } else {
+ vma_set_anonymous(vma);
}
vma_link(mm, vma, prev, rb_link, rb_parent);
if (vm_flags & VM_DENYWRITE)
allow_write_access(file);
free_vma:
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
unacct_error:
if (charged)
vm_unacct_memory(charged);
return err;
}
- new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ new = vm_area_dup(vma);
if (!new)
return -ENOMEM;
- /* most fields are the same, copy all, and then fixup */
- *new = *vma;
-
- INIT_LIST_HEAD(&new->anon_vma_chain);
-
if (new_below)
new->vm_end = addr;
else {
out_free_mpol:
mpol_put(vma_policy(new));
out_free_vma:
- kmem_cache_free(vm_area_cachep, new);
+ vm_area_free(new);
return err;
}
* anonymous maps. eventually we may be able to do some
* brk-specific accounting here.
*/
-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
+static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
- unsigned long len;
struct rb_node **rb_link, *rb_parent;
pgoff_t pgoff = addr >> PAGE_SHIFT;
int error;
- len = PAGE_ALIGN(request);
- if (len < request)
- return -ENOMEM;
- if (!len)
- return 0;
-
/* Until we need other flags, refuse anything except VM_EXEC. */
if ((flags & (~VM_EXEC)) != 0)
return -EINVAL;
/*
* create a vma struct for an anonymous mapping
*/
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(mm);
if (!vma) {
vm_unacct_memory(len >> PAGE_SHIFT);
return -ENOMEM;
}
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma->vm_mm = mm;
+ vma_set_anonymous(vma);
vma->vm_start = addr;
vma->vm_end = addr + len;
vma->vm_pgoff = pgoff;
return 0;
}
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
-{
- return do_brk_flags(addr, len, 0, uf);
-}
-
-int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
+int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
{
struct mm_struct *mm = current->mm;
+ unsigned long len;
int ret;
bool populate;
LIST_HEAD(uf);
+ len = PAGE_ALIGN(request);
+ if (len < request)
+ return -ENOMEM;
+ if (!len)
+ return 0;
+
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
}
*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
} else {
- new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ new_vma = vm_area_dup(vma);
if (!new_vma)
goto out;
- *new_vma = *vma;
new_vma->vm_start = addr;
new_vma->vm_end = addr + len;
new_vma->vm_pgoff = pgoff;
if (vma_dup_policy(vma, new_vma))
goto out_free_vma;
- INIT_LIST_HEAD(&new_vma->anon_vma_chain);
if (anon_vma_clone(new_vma, vma))
goto out_free_mempol;
if (new_vma->vm_file)
out_free_mempol:
mpol_put(vma_policy(new_vma));
out_free_vma:
- kmem_cache_free(vm_area_cachep, new_vma);
+ vm_area_free(new_vma);
out:
return NULL;
}
int ret;
struct vm_area_struct *vma;
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(mm);
if (unlikely(vma == NULL))
return ERR_PTR(-ENOMEM);
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
return vma;
out:
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return ERR_PTR(ret);
}
drop_rmap_locks(vma);
}
-#define LATENCY_LIMIT (64 * PAGE_SIZE)
-
unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len,
next = (new_addr + PMD_SIZE) & PMD_MASK;
if (extent > next - new_addr)
extent = next - new_addr;
- if (extent > LATENCY_LIMIT)
- extent = LATENCY_LIMIT;
move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
new_pmd, new_addr, need_rmap_locks, &need_flush);
}
if (vma->vm_file)
fput(vma->vm_file);
put_nommu_region(vma->vm_region);
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
}
/*
if (ret < len)
memset(base + ret, 0, len - ret);
+ } else {
+ vma_set_anonymous(vma);
}
return 0;
if (!region)
goto error_getting_region;
- vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ vma = vm_area_alloc(current->mm);
if (!vma)
goto error_getting_vma;
region->vm_flags = vm_flags;
region->vm_pgoff = pgoff;
- INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_flags = vm_flags;
vma->vm_pgoff = pgoff;
kmem_cache_free(vm_region_jar, region);
if (vma->vm_file)
fput(vma->vm_file);
- kmem_cache_free(vm_area_cachep, vma);
+ vm_area_free(vma);
return ret;
sharing_violation:
if (!region)
return -ENOMEM;
- new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ new = vm_area_dup(vma);
if (!new) {
kmem_cache_free(vm_region_jar, region);
return -ENOMEM;
}
/* most fields are the same, copy all, and then fixup */
- *new = *vma;
*region = *vma->vm_region;
new->vm_region = region;
/* Raise event before sending signal: task reaper must see this */
count_vm_event(OOM_KILL);
- count_memcg_event_mm(mm, OOM_KILL);
+ memcg_memory_event_mm(mm, MEMCG_OOM_KILL);
/*
* We should send SIGKILL before granting access to memory reserves
static int __init fail_page_alloc_debugfs(void)
{
- umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ umode_t mode = S_IFREG | 0600;
struct dentry *dir;
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
free_area_init_core(pgdat);
}
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
/*
* Only struct pages that are backed by physical memory are zeroed and
* initialized by going through __init_single_page(). But, there are some
if (pgcnt)
pr_info("Reserved but unavailable: %lld pages", pgcnt);
}
-#endif /* CONFIG_HAVE_MEMBLOCK */
+#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
+ zero_resv_unavail();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
free_area_init_node(nid, NULL,
node_set_state(nid, N_MEMORY);
check_for_memory(pgdat, nid);
}
- zero_resv_unavail();
}
static int __init cmdline_parse_core(char *p, unsigned long *core,
start = (void *)PAGE_ALIGN((unsigned long)start);
end = (void *)((unsigned long)end & PAGE_MASK);
for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+ struct page *page = virt_to_page(pos);
+ void *direct_map_addr;
+
+ /*
+ * 'direct_map_addr' might be different from 'pos'
+ * because some architectures' virt_to_page()
+ * work with aliases. Getting the direct map
+ * address ensures that we get a _writeable_
+ * alias for the memset().
+ */
+ direct_map_addr = page_address(page);
if ((unsigned int)poison <= 0xFF)
- memset(pos, poison, PAGE_SIZE);
- free_reserved_page(virt_to_page(pos));
+ memset(direct_map_addr, poison, PAGE_SIZE);
+
+ free_reserved_page(page);
}
if (pages && s)
void __init free_area_init(unsigned long *zones_size)
{
+ zero_resv_unavail();
free_area_init_node(0, zones_size,
__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
- zero_resv_unavail();
}
static int page_alloc_cpu_dead(unsigned int cpu)
}
static struct bin_attribute page_idle_bitmap_attr =
- __BIN_ATTR(bitmap, S_IRUSR | S_IWUSR,
+ __BIN_ATTR(bitmap, 0600,
page_idle_bitmap_read, page_idle_bitmap_write, 0);
static struct bin_attribute *page_idle_bin_attrs[] = {
return 0;
}
- dentry = debugfs_create_file("page_owner", S_IRUSR, NULL,
- NULL, &proc_page_owner_operations);
+ dentry = debugfs_create_file("page_owner", 0400, NULL,
+ NULL, &proc_page_owner_operations);
return PTR_ERR_OR_ZERO(dentry);
}
#include <linux/backing-dev.h>
#include <linux/page_idle.h>
#include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
#include <asm/tlbflush.h>
set_pte_at(mm, address, pvmw.pte, pteval);
}
- } else if (pte_unused(pteval)) {
+ } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
/*
* The guest indicated that the page content is of no
* interest anymore. Simply discard the pte, vmscan
* will take care of the rest.
+ * A future reference will then fault in a new zero
+ * page. When userfaultfd is active, we must not drop
+ * this page though, as its main user (postcopy
+ * migration) will not expect userfaults on already
+ * copied pages.
*/
dec_mm_counter(mm, mm_counter(page));
/* We have to invalidate as we cleared the pte */
{
/* Create a pseudo vma that just contains the policy */
memset(vma, 0, sizeof(*vma));
+ vma_init(vma, NULL);
/* Bias interleave by inode number to distribute better across nodes */
vma->vm_pgoff = index + info->vfs_inode.i_ino;
vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
if (len > PAGE_SIZE)
return -ENAMETOOLONG;
- inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
+ inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0,
+ VM_NORESERVE);
if (!inode)
return -ENOSPC;
sbinfo->max_blocks << (PAGE_SHIFT - 10));
if (sbinfo->max_inodes != shmem_default_max_inodes())
seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes);
- if (sbinfo->mode != (S_IRWXUGO | S_ISVTX))
+ if (sbinfo->mode != (0777 | S_ISVTX))
seq_printf(seq, ",mode=%03ho", sbinfo->mode);
if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
seq_printf(seq, ",uid=%u",
if (!sbinfo)
return -ENOMEM;
- sbinfo->mode = S_IRWXUGO | S_ISVTX;
+ sbinfo->mode = 0777 | S_ISVTX;
sbinfo->uid = current_fsuid();
sbinfo->gid = current_fsgid();
sb->s_fs_info = sbinfo;
/* common code */
-static const struct dentry_operations anon_ops = {
- .d_dname = simple_dname
-};
-
static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size,
unsigned long flags, unsigned int i_flags)
{
- struct file *res;
struct inode *inode;
- struct path path;
- struct super_block *sb;
- struct qstr this;
+ struct file *res;
if (IS_ERR(mnt))
return ERR_CAST(mnt);
if (shmem_acct_size(flags, size))
return ERR_PTR(-ENOMEM);
- res = ERR_PTR(-ENOMEM);
- this.name = name;
- this.len = strlen(name);
- this.hash = 0; /* will go */
- sb = mnt->mnt_sb;
- path.mnt = mntget(mnt);
- path.dentry = d_alloc_pseudo(sb, &this);
- if (!path.dentry)
- goto put_memory;
- d_set_d_op(path.dentry, &anon_ops);
-
- res = ERR_PTR(-ENOSPC);
- inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
- if (!inode)
- goto put_memory;
-
+ inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0,
+ flags);
+ if (unlikely(!inode)) {
+ shmem_unacct_size(flags, size);
+ return ERR_PTR(-ENOSPC);
+ }
inode->i_flags |= i_flags;
- d_instantiate(path.dentry, inode);
inode->i_size = size;
clear_nlink(inode); /* It is unlinked */
res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
+ if (!IS_ERR(res))
+ res = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+ &shmem_file_operations);
if (IS_ERR(res))
- goto put_path;
-
- res = alloc_file(&path, FMODE_WRITE | FMODE_READ,
- &shmem_file_operations);
- if (IS_ERR(res))
- goto put_path;
-
- return res;
-
-put_memory:
- shmem_unacct_size(flags, size);
-put_path:
- path_put(&path);
+ iput(inode);
return res;
}
s->memcg_params.root_cache = NULL;
RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
INIT_LIST_HEAD(&s->memcg_params.children);
+ s->memcg_params.dying = false;
}
static int init_memcg_params(struct kmem_cache *s,
list_del(&s->list);
if (s->flags & SLAB_TYPESAFE_BY_RCU) {
+#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_unlink(s);
+#endif
list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
schedule_work(&slab_caches_to_rcu_destroy_work);
} else {
#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_unlink(s);
sysfs_slab_release(s);
#else
slab_kmem_cache_release(s);
* The memory cgroup could have been offlined while the cache
* creation work was pending.
*/
- if (memcg->kmem_state != KMEM_ONLINE)
+ if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
goto out_unlock;
idx = memcg_cache_id(memcg);
WARN_ON_ONCE(s->memcg_params.deact_fn))
return;
+ if (s->memcg_params.root_cache->memcg_params.dying)
+ return;
+
/* pin memcg so that @s doesn't get destroyed in the middle */
css_get(&s->memcg_params.memcg->css);
return -EBUSY;
return 0;
}
+
+static void flush_memcg_workqueue(struct kmem_cache *s)
+{
+ mutex_lock(&slab_mutex);
+ s->memcg_params.dying = true;
+ mutex_unlock(&slab_mutex);
+
+ /*
+ * SLUB deactivates the kmem_caches through call_rcu_sched. Make
+ * sure all registered rcu callbacks have been invoked.
+ */
+ if (IS_ENABLED(CONFIG_SLUB))
+ rcu_barrier_sched();
+
+ /*
+ * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
+ * deactivates the memcg kmem_caches through workqueue. Make sure all
+ * previous workitems on workqueue are processed.
+ */
+ flush_workqueue(memcg_kmem_cache_wq);
+}
#else
static inline int shutdown_memcg_caches(struct kmem_cache *s)
{
return 0;
}
+
+static inline void flush_memcg_workqueue(struct kmem_cache *s)
+{
+}
#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
void slab_kmem_cache_release(struct kmem_cache *s)
if (unlikely(!s))
return;
+ flush_memcg_workqueue(s);
+
get_online_cpus();
get_online_mems();
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
#ifdef CONFIG_SLAB
-#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
+#define SLABINFO_RIGHTS (0600)
#else
-#define SLABINFO_RIGHTS S_IRUSR
+#define SLABINFO_RIGHTS (0400)
#endif
static void print_slabinfo_header(struct seq_file *m)
kset_unregister(s->memcg_kset);
#endif
kobject_uevent(&s->kobj, KOBJ_REMOVE);
- kobject_del(&s->kobj);
out:
kobject_put(&s->kobj);
}
schedule_work(&s->kobj_remove_work);
}
+void sysfs_slab_unlink(struct kmem_cache *s)
+{
+ if (slab_state >= FULL)
+ kobject_del(&s->kobj);
+}
+
void sysfs_slab_release(struct kmem_cache *s)
{
if (slab_state >= FULL)
static inline unsigned char swap_count(unsigned char ent)
{
- return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */
+ return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */
}
/* returns 1 if swap entry is freed */
static int __init proc_vmalloc_init(void)
{
if (IS_ENABLED(CONFIG_NUMA))
- proc_create_seq_private("vmallocinfo", S_IRUSR, NULL,
+ proc_create_seq_private("vmallocinfo", 0400, NULL,
&vmalloc_op,
nr_node_ids * sizeof(unsigned int), NULL);
else
- proc_create_seq("vmallocinfo", S_IRUSR, NULL, &vmalloc_op);
+ proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op);
return 0;
}
module_init(proc_vmalloc_init);
* to occur in the future. Keep on running the
* update worker thread.
*/
- preempt_disable();
queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
- preempt_enable();
}
}
}
pool->stat_dentry = entry;
- entry = debugfs_create_file("classes", S_IFREG | S_IRUGO,
- pool->stat_dentry, pool, &zs_stats_size_fops);
+ entry = debugfs_create_file("classes", S_IFREG | 0444,
+ pool->stat_dentry, pool,
+ &zs_stats_size_fops);
if (!entry) {
pr_warn("%s: debugfs file entry <%s> creation failed\n",
name, "classes");
ret = -ENOMEM;
goto reject;
}
+
+ /* A second zswap_is_full() check after
+ * zswap_shrink() to make sure it's now
+ * under the max_pool_percent
+ */
+ if (zswap_is_full()) {
+ ret = -ENOMEM;
+ goto reject;
+ }
}
/* allocate entry */
if (!zswap_debugfs_root)
return -ENOMEM;
- debugfs_create_u64("pool_limit_hit", S_IRUGO,
- zswap_debugfs_root, &zswap_pool_limit_hit);
- debugfs_create_u64("reject_reclaim_fail", S_IRUGO,
- zswap_debugfs_root, &zswap_reject_reclaim_fail);
- debugfs_create_u64("reject_alloc_fail", S_IRUGO,
- zswap_debugfs_root, &zswap_reject_alloc_fail);
- debugfs_create_u64("reject_kmemcache_fail", S_IRUGO,
- zswap_debugfs_root, &zswap_reject_kmemcache_fail);
- debugfs_create_u64("reject_compress_poor", S_IRUGO,
- zswap_debugfs_root, &zswap_reject_compress_poor);
- debugfs_create_u64("written_back_pages", S_IRUGO,
- zswap_debugfs_root, &zswap_written_back_pages);
- debugfs_create_u64("duplicate_entry", S_IRUGO,
- zswap_debugfs_root, &zswap_duplicate_entry);
- debugfs_create_u64("pool_total_size", S_IRUGO,
- zswap_debugfs_root, &zswap_pool_total_size);
- debugfs_create_atomic_t("stored_pages", S_IRUGO,
- zswap_debugfs_root, &zswap_stored_pages);
+ debugfs_create_u64("pool_limit_hit", 0444,
+ zswap_debugfs_root, &zswap_pool_limit_hit);
+ debugfs_create_u64("reject_reclaim_fail", 0444,
+ zswap_debugfs_root, &zswap_reject_reclaim_fail);
+ debugfs_create_u64("reject_alloc_fail", 0444,
+ zswap_debugfs_root, &zswap_reject_alloc_fail);
+ debugfs_create_u64("reject_kmemcache_fail", 0444,
+ zswap_debugfs_root, &zswap_reject_kmemcache_fail);
+ debugfs_create_u64("reject_compress_poor", 0444,
+ zswap_debugfs_root, &zswap_reject_compress_poor);
+ debugfs_create_u64("written_back_pages", 0444,
+ zswap_debugfs_root, &zswap_written_back_pages);
+ debugfs_create_u64("duplicate_entry", 0444,
+ zswap_debugfs_root, &zswap_duplicate_entry);
+ debugfs_create_u64("pool_total_size", 0444,
+ zswap_debugfs_root, &zswap_pool_total_size);
+ debugfs_create_atomic_t("stored_pages", 0444,
+ zswap_debugfs_root, &zswap_stored_pages);
debugfs_create_atomic_t("same_filled_pages", 0444,
- zswap_debugfs_root, &zswap_same_filled_pages);
+ zswap_debugfs_root, &zswap_same_filled_pages);
return 0;
}
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
}
free_and_return:
- v9fs_put_trans(clnt->trans_mod);
+ if (ret)
+ v9fs_put_trans(clnt->trans_mod);
kfree(tmp_options);
return ret;
}
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_NET) += ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
obj-$(CONFIG_BPFILTER) += bpfilter/
-endif
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = atalk_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = atalk_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = atalk_compat_ioctl,
ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
- refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = atmvcc->atm_options;
+ atm_account_tx(atmvcc, skb);
dev->stats.tx_packets++;
dev->stats.tx_bytes += skb->len;
memcpy(here, llc_oui, sizeof(llc_oui));
((__be16 *) here)[3] = skb->protocol;
}
- refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = vcc->atm_options;
+ atm_account_tx(vcc, skb);
entry->vccs->last_use = jiffies;
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev);
old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */
goto out;
}
pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
- refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+ atm_account_tx(vcc, skb);
skb->dev = NULL; /* for paths shared with net_device interfaces */
- ATM_SKB(skb)->atm_options = vcc->atm_options;
if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
kfree_skb(skb);
error = -EFAULT;
return error;
}
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
- struct atm_vcc *vcc = ATM_SD(sock);
- __poll_t mask = 0;
+ struct atm_vcc *vcc;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
+
+ vcc = ATM_SD(sock);
/* exceptional events */
if (sk->sk_err)
int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_setsockopt(struct socket *sock, int level, int optname,
struct net_device *dev = skb->dev;
ATM_SKB(skb)->vcc = vcc;
- ATM_SKB(skb)->atm_options = vcc->atm_options;
+ atm_account_tx(vcc, skb);
- refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
if (vcc->send(vcc, skb) < 0) {
dev->stats.tx_dropped++;
return;
sizeof(struct llc_snap_hdr));
}
- refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = entry->shortcut->atm_options;
+ atm_account_tx(entry->shortcut, skb);
entry->shortcut->send(entry->shortcut, skb);
entry->packets_fwded++;
mpc->in_ops->put(entry);
* the packet count limit, so...
*/
if (atm_may_send(pvcc->atmvcc, size) &&
- atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT))
+ atomic_inc_not_zero(&pvcc->inflight))
return 1;
/*
return 1;
}
- refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
+ atm_account_tx(vcc, skb);
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pvc_getname,
- .poll_mask = vcc_poll_mask,
+ .poll = vcc_poll,
.ioctl = vcc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vcc_compat_ioctl,
struct sock *sk = sk_atm(vcc);
pr_debug("(%d) %d -= %d\n",
- vcc->vci, sk_wmem_alloc_get(sk), skb->truesize);
- WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
+ vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
+ WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
dev_kfree_skb_any(skb);
sk->sk_write_space(sk);
}
.socketpair = sock_no_socketpair,
.accept = svc_accept,
.getname = svc_getname,
- .poll_mask = vcc_poll_mask,
+ .poll = vcc_poll,
.ioctl = svc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = svc_compat_ioctl,
.socketpair = sock_no_socketpair,
.accept = ax25_accept,
.getname = ax25_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ax25_ioctl,
.listen = ax25_listen,
.shutdown = ax25_shutdown,
{
struct batadv_neigh_ifinfo *router_ifinfo = NULL;
struct batadv_neigh_node *router;
- struct batadv_gw_node *curr_gw;
+ struct batadv_gw_node *curr_gw = NULL;
int ret = 0;
void *hdr;
ret = 0;
out:
+ if (curr_gw)
+ batadv_gw_node_put(curr_gw);
if (router_ifinfo)
batadv_neigh_ifinfo_put(router_ifinfo);
if (router)
{
struct batadv_neigh_ifinfo *router_ifinfo = NULL;
struct batadv_neigh_node *router;
- struct batadv_gw_node *curr_gw;
+ struct batadv_gw_node *curr_gw = NULL;
int ret = 0;
void *hdr;
ret = 0;
out:
+ if (curr_gw)
+ batadv_gw_node_put(curr_gw);
if (router_ifinfo)
batadv_neigh_ifinfo_put(router_ifinfo);
if (router)
#include "debugfs.h"
#include "main.h"
+#include <linux/dcache.h>
#include <linux/debugfs.h>
#include <linux/err.h>
#include <linux/errno.h>
return -ENOMEM;
}
+/**
+ * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif
+ * @hard_iface: hard interface which was renamed
+ */
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+ const char *name = hard_iface->net_dev->name;
+ struct dentry *dir;
+ struct dentry *d;
+
+ dir = hard_iface->debug_dir;
+ if (!dir)
+ return;
+
+ d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+ if (!d)
+ pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
/**
* batadv_debugfs_del_hardif() - delete the base directory for a hard interface
* in debugfs.
return -ENOMEM;
}
+/**
+ * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif
+ * @dev: net_device which was renamed
+ */
+void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+ struct batadv_priv *bat_priv = netdev_priv(dev);
+ const char *name = dev->name;
+ struct dentry *dir;
+ struct dentry *d;
+
+ dir = bat_priv->debug_dir;
+ if (!dir)
+ return;
+
+ d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+ if (!d)
+ pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
/**
* batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries
* @dev: netdev struct of the soft interface
void batadv_debugfs_init(void);
void batadv_debugfs_destroy(void);
int batadv_debugfs_add_meshif(struct net_device *dev);
+void batadv_debugfs_rename_meshif(struct net_device *dev);
void batadv_debugfs_del_meshif(struct net_device *dev);
int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface);
void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
#else
return 0;
}
+static inline void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+}
+
static inline void batadv_debugfs_del_meshif(struct net_device *dev)
{
}
return 0;
}
+static inline
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+}
+
static inline
void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
{
rtnl_unlock();
}
+/**
+ * batadv_hard_if_event_softif() - Handle events for soft interfaces
+ * @event: NETDEV_* event to handle
+ * @net_dev: net_device which generated an event
+ *
+ * Return: NOTIFY_* result
+ */
+static int batadv_hard_if_event_softif(unsigned long event,
+ struct net_device *net_dev)
+{
+ struct batadv_priv *bat_priv;
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ batadv_sysfs_add_meshif(net_dev);
+ bat_priv = netdev_priv(net_dev);
+ batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
+ break;
+ case NETDEV_CHANGENAME:
+ batadv_debugfs_rename_meshif(net_dev);
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
static int batadv_hard_if_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct batadv_hard_iface *primary_if = NULL;
struct batadv_priv *bat_priv;
- if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) {
- batadv_sysfs_add_meshif(net_dev);
- bat_priv = netdev_priv(net_dev);
- batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
- return NOTIFY_DONE;
- }
+ if (batadv_softif_is_valid(net_dev))
+ return batadv_hard_if_event_softif(event, net_dev);
hard_iface = batadv_hardif_get_by_netdev(net_dev);
if (!hard_iface && (event == NETDEV_REGISTER ||
if (batadv_is_wifi_hardif(hard_iface))
hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
break;
+ case NETDEV_CHANGENAME:
+ batadv_debugfs_rename_hardif(hard_iface);
+ break;
default:
break;
}
ether_addr_copy(common->addr, tt_addr);
common->vid = vid;
- common->flags = flags;
+ if (!is_multicast_ether_addr(common->addr))
+ common->flags = flags & (~BATADV_TT_SYNC_MASK);
+
tt_global_entry->roam_at = 0;
/* node must store current time in case of roaming. This is
* needed to purge this entry out on timeout (if nobody claims
* TT_CLIENT_TEMP, therefore they have to be copied in the
* client entry
*/
- common->flags |= flags & (~BATADV_TT_SYNC_MASK);
+ if (!is_multicast_ether_addr(common->addr))
+ common->flags |= flags & (~BATADV_TT_SYNC_MASK);
/* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only
* one originator left in the list and we previously received a
return 0;
}
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t bt_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
BT_DBG("sock %p, sk %p", sock, sk);
+ poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
return mask;
}
-EXPORT_SYMBOL(bt_sock_poll_mask);
+EXPORT_SYMBOL(bt_sock_poll);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
.sendmsg = hci_sock_sendmsg,
.recvmsg = hci_sock_recvmsg,
.ioctl = hci_sock_ioctl,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = hci_sock_setsockopt,
.getname = l2cap_sock_getname,
.sendmsg = l2cap_sock_sendmsg,
.recvmsg = l2cap_sock_recvmsg,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
.setsockopt = rfcomm_sock_setsockopt,
.getsockopt = rfcomm_sock_getsockopt,
.ioctl = rfcomm_sock_ioctl,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.socketpair = sock_no_socketpair,
.mmap = sock_no_mmap
};
.getname = sco_sock_getname,
.sendmsg = sco_sock_sendmsg,
.recvmsg = sco_sock_recvmsg,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
u32 size = kattr->test.data_size_in;
u32 repeat = kattr->test.repeat;
u32 retval, duration;
+ int hh_len = ETH_HLEN;
struct sk_buff *skb;
void *data;
int ret;
skb_reset_network_header(skb);
if (is_l2)
- __skb_push(skb, ETH_HLEN);
+ __skb_push(skb, hh_len);
if (is_direct_pkt_access)
bpf_compute_data_pointers(skb);
retval = bpf_test_run(prog, skb, repeat, &duration);
- if (!is_l2)
- __skb_push(skb, ETH_HLEN);
+ if (!is_l2) {
+ if (skb_headroom(skb) < hh_len) {
+ int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
+
+ if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+ }
+ memset(__skb_push(skb, hh_len), 0, hh_len);
+ }
+
size = skb->len;
/* bpf program can never convert linear skb to non-linear */
if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
--- /dev/null
+bpfilter_umh
menuconfig BPFILTER
bool "BPF based packet filtering framework (BPFILTER)"
- default n
depends on NET && BPF && INET
help
This builds experimental bpfilter framework that is aiming to
if BPFILTER
config BPFILTER_UMH
tristate "bpfilter kernel module with user mode helper"
+ depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
default m
help
This builds bpfilter kernel module with embedded user mode helper
HOSTLDFLAGS += -static
endif
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
- cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
- $(OBJCOPY) -I binary -O `$(OBJDUMP) -f $<|grep format|cut -d' ' -f8` \
- -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \
- --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
- $(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
#include <linux/file.h>
#include "msgfmt.h"
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
static struct umh_info info;
/* since ip_getsockopt() can run in parallel, serialize access to umh */
int err;
/* fork usermode process */
- err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+ err = fork_usermode_blob(&bpfilter_umh_start,
+ &bpfilter_umh_end - &bpfilter_umh_start,
+ &info);
if (err)
return err;
pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+ .section .init.rodata, "a"
+ .global bpfilter_umh_start
+bpfilter_umh_start:
+ .incbin "net/bpfilter/bpfilter_umh"
+ .global bpfilter_umh_end
+bpfilter_umh_end:
watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0);
if (IS_ERR(watcher))
return PTR_ERR(watcher);
+
+ if (watcher->family != NFPROTO_BRIDGE) {
+ module_put(watcher->me);
+ return -ENOENT;
+ }
+
w->u.watcher = watcher;
par->target = watcher;
}
i = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
+ memset(&tgpar, 0, sizeof(tgpar));
mtpar.net = tgpar.net = net;
mtpar.table = tgpar.table = name;
mtpar.entryinfo = tgpar.entryinfo = e;
goto cleanup_watchers;
}
+ /* Reject UNSPEC, xtables verdicts/return values are incompatible */
+ if (target->family != NFPROTO_BRIDGE) {
+ module_put(target->me);
+ ret = -ENOENT;
+ goto cleanup_watchers;
+ }
+
t->u.target = target;
if (t->u.target == &ebt_standard_target) {
if (gap < sizeof(struct ebt_standard_target)) {
compat_uptr_t ptr;
} u;
compat_uint_t match_size;
- compat_uint_t data[0];
+ compat_uint_t data[0] __attribute__ ((aligned (__alignof__(struct compat_ebt_replace))));
};
/* account for possible padding between match_size and ->data */
static int ebt_compat_entry_padsize(void)
{
- BUILD_BUG_ON(XT_ALIGN(sizeof(struct ebt_entry_match)) <
- COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt)));
- return (int) XT_ALIGN(sizeof(struct ebt_entry_match)) -
- COMPAT_XT_ALIGN(sizeof(struct compat_ebt_entry_mwt));
+ BUILD_BUG_ON(sizeof(struct ebt_entry_match) <
+ sizeof(struct compat_ebt_entry_mwt));
+ return (int) sizeof(struct ebt_entry_match) -
+ sizeof(struct compat_ebt_entry_mwt);
}
static int ebt_compat_match_offset(const struct xt_match *match,
if (!reject6_br_csum_ok(oldskb, hook))
return;
- nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) +
+ nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
LL_MAX_HEADER + len, GFP_ATOMIC);
if (!nskb)
return;
caifd = caif_get(skb->dev);
WARN_ON(caifd == NULL);
- if (caifd == NULL)
+ if (!caifd) {
+ rcu_read_unlock();
return;
+ }
caifd_hold(caifd);
rcu_read_unlock();
}
/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t caif_poll(struct file *file,
+ struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
+ __poll_t mask;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- __poll_t mask = 0;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = caif_poll_mask,
+ .poll = caif_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = caif_poll_mask,
+ .poll = caif_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = raw_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
static struct lock_class_key socket_class;
#endif
-/*
- * When skipping (ignoring) a block of input we read it into a "skip
- * buffer," which is this many bytes in size.
- */
-#define SKIP_BUF_SIZE 1024
-
static void queue_con(struct ceph_connection *con);
static void cancel_con(struct ceph_connection *con);
static void ceph_con_workfn(struct work_struct *);
return 0;
}
+/*
+ * If @buf is NULL, discard up to @len bytes.
+ */
static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
{
struct kvec iov = {buf, len};
struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
int r;
+ if (!buf)
+ msg.msg_flags |= MSG_TRUNC;
+
iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len);
r = sock_recvmsg(sock, &msg, msg.msg_flags);
if (r == -EAGAIN)
con->state != CON_STATE_OPEN)
return 0;
-more:
- dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
-
/* open the socket first? */
if (con->state == CON_STATE_PREOPEN) {
BUG_ON(con->sock);
}
}
-more_kvec:
+more:
+ dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
BUG_ON(!con->sock);
/* kvec data queued? */
ret = write_partial_message_data(con);
if (ret == 1)
- goto more_kvec; /* we need to send the footer, too! */
+ goto more; /* we need to send the footer, too! */
if (ret == 0)
goto out;
if (ret < 0) {
return ret;
}
-
-
/*
* Read what we can from the socket.
*/
if (con->in_base_pos < 0) {
/*
* skipping + discarding content.
- *
- * FIXME: there must be a better way to do this!
*/
- static char buf[SKIP_BUF_SIZE];
- int skip = min((int) sizeof (buf), -con->in_base_pos);
-
- dout("skipping %d / %d bytes\n", skip, -con->in_base_pos);
- ret = ceph_tcp_recvmsg(con->sock, buf, skip);
+ ret = ceph_tcp_recvmsg(con->sock, NULL, -con->in_base_pos);
if (ret <= 0)
goto out;
+ dout("skipped %d / %d bytes\n", ret, -con->in_base_pos);
con->in_base_pos += ret;
if (con->in_base_pos)
goto more;
}
EXPORT_SYMBOL(osd_req_op_extent_dup_last);
-void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
+int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
u16 opcode, const char *class, const char *method)
{
struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
BUG_ON(opcode != CEPH_OSD_OP_CALL);
pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
- BUG_ON(!pagelist);
+ if (!pagelist)
+ return -ENOMEM;
+
ceph_pagelist_init(pagelist);
op->cls.class_name = class;
osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
op->indata_len = payload_len;
+ return 0;
}
EXPORT_SYMBOL(osd_req_op_cls_init);
truncate_size, truncate_seq);
}
- req->r_abort_on_full = true;
req->r_flags = flags;
req->r_base_oloc.pool = layout->pool_id;
req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node)
DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node)
+/*
+ * Call @fn on each OSD request as long as @fn returns 0.
+ */
+static void for_each_request(struct ceph_osd_client *osdc,
+ int (*fn)(struct ceph_osd_request *req, void *arg),
+ void *arg)
+{
+ struct rb_node *n, *p;
+
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+ for (p = rb_first(&osd->o_requests); p; ) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ p = rb_next(p);
+ if (fn(req, arg))
+ return;
+ }
+ }
+
+ for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ p = rb_next(p);
+ if (fn(req, arg))
+ return;
+ }
+}
+
static bool osd_homeless(struct ceph_osd *osd)
{
return osd->o_osd == CEPH_HOMELESS_OSD;
bool recovery_deletes = ceph_osdmap_flag(osdc,
CEPH_OSDMAP_RECOVERY_DELETES);
enum calc_target_result ct_res;
- int ret;
t->epoch = osdc->osdmap->epoch;
pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool);
}
}
- ret = __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc,
- &pgid);
- if (ret) {
- WARN_ON(ret != -ENOENT);
- t->osd = CEPH_HOMELESS_OSD;
- ct_res = CALC_TARGET_POOL_DNE;
- goto out;
- }
+ __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc, &pgid);
last_pgid.pool = pgid.pool;
last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask);
struct ceph_osd_client *osdc = req->r_osdc;
struct ceph_osd *osd;
enum calc_target_result ct_res;
+ int err = 0;
bool need_send = false;
bool promoted = false;
- bool need_abort = false;
WARN_ON(req->r_tid);
dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
goto promote;
}
- if (osdc->osdmap->epoch < osdc->epoch_barrier) {
+ if (osdc->abort_err) {
+ dout("req %p abort_err %d\n", req, osdc->abort_err);
+ err = osdc->abort_err;
+ } else if (osdc->osdmap->epoch < osdc->epoch_barrier) {
dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch,
osdc->epoch_barrier);
req->r_t.paused = true;
(ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
pool_full(osdc, req->r_t.base_oloc.pool))) {
dout("req %p full/pool_full\n", req);
- pr_warn_ratelimited("FULL or reached pool quota\n");
- req->r_t.paused = true;
- maybe_request_map(osdc);
- if (req->r_abort_on_full)
- need_abort = true;
+ if (osdc->abort_on_full) {
+ err = -ENOSPC;
+ } else {
+ pr_warn_ratelimited("FULL or reached pool quota\n");
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ }
} else if (!osd_homeless(osd)) {
need_send = true;
} else {
link_request(osd, req);
if (need_send)
send_request(req);
- else if (need_abort)
- complete_request(req, -ENOSPC);
+ else if (err)
+ complete_request(req, err);
mutex_unlock(&osd->lock);
- if (ct_res == CALC_TARGET_POOL_DNE)
+ if (!err && ct_res == CALC_TARGET_POOL_DNE)
send_map_check(req);
if (promoted)
static void __complete_request(struct ceph_osd_request *req)
{
- if (req->r_callback) {
- dout("%s req %p tid %llu cb %pf result %d\n", __func__, req,
- req->r_tid, req->r_callback, req->r_result);
+ dout("%s req %p tid %llu cb %pf result %d\n", __func__, req,
+ req->r_tid, req->r_callback, req->r_result);
+
+ if (req->r_callback)
req->r_callback(req);
- }
+ complete_all(&req->r_completion);
+ ceph_osdc_put_request(req);
+}
+
+static void complete_request_workfn(struct work_struct *work)
+{
+ struct ceph_osd_request *req =
+ container_of(work, struct ceph_osd_request, r_complete_work);
+
+ __complete_request(req);
}
/*
req->r_result = err;
finish_request(req);
- __complete_request(req);
- complete_all(&req->r_completion);
- ceph_osdc_put_request(req);
+
+ INIT_WORK(&req->r_complete_work, complete_request_workfn);
+ queue_work(req->r_osdc->completion_wq, &req->r_complete_work);
}
static void cancel_map_check(struct ceph_osd_request *req)
complete_request(req, err);
}
+static int abort_fn(struct ceph_osd_request *req, void *arg)
+{
+ int err = *(int *)arg;
+
+ abort_request(req, err);
+ return 0; /* continue iteration */
+}
+
+/*
+ * Abort all in-flight requests with @err and arrange for all future
+ * requests to be failed immediately.
+ */
+void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err)
+{
+ dout("%s osdc %p err %d\n", __func__, osdc, err);
+ down_write(&osdc->lock);
+ for_each_request(osdc, abort_fn, &err);
+ osdc->abort_err = err;
+ up_write(&osdc->lock);
+}
+EXPORT_SYMBOL(ceph_osdc_abort_requests);
+
static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
{
if (likely(eb > osdc->epoch_barrier)) {
}
EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier);
+/*
+ * We can end up releasing caps as a result of abort_request().
+ * In that case, we probably want to ensure that the cap release message
+ * has an updated epoch barrier in it, so set the epoch barrier prior to
+ * aborting the first request.
+ */
+static int abort_on_full_fn(struct ceph_osd_request *req, void *arg)
+{
+ struct ceph_osd_client *osdc = req->r_osdc;
+ bool *victims = arg;
+
+ if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+ (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ pool_full(osdc, req->r_t.base_oloc.pool))) {
+ if (!*victims) {
+ update_epoch_barrier(osdc, osdc->osdmap->epoch);
+ *victims = true;
+ }
+ abort_request(req, -ENOSPC);
+ }
+
+ return 0; /* continue iteration */
+}
+
/*
* Drop all pending requests that are stalled waiting on a full condition to
* clear, and complete them with ENOSPC as the return code. Set the
*/
static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc)
{
- struct rb_node *n;
bool victims = false;
- dout("enter abort_on_full\n");
-
- if (!ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) && !have_pool_full(osdc))
- goto out;
-
- /* Scan list and see if there is anything to abort */
- for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
- struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
- struct rb_node *m;
-
- m = rb_first(&osd->o_requests);
- while (m) {
- struct ceph_osd_request *req = rb_entry(m,
- struct ceph_osd_request, r_node);
- m = rb_next(m);
-
- if (req->r_abort_on_full) {
- victims = true;
- break;
- }
- }
- if (victims)
- break;
- }
-
- if (!victims)
- goto out;
-
- /*
- * Update the barrier to current epoch if it's behind that point,
- * since we know we have some calls to be aborted in the tree.
- */
- update_epoch_barrier(osdc, osdc->osdmap->epoch);
-
- for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
- struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
- struct rb_node *m;
-
- m = rb_first(&osd->o_requests);
- while (m) {
- struct ceph_osd_request *req = rb_entry(m,
- struct ceph_osd_request, r_node);
- m = rb_next(m);
-
- if (req->r_abort_on_full &&
- (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
- pool_full(osdc, req->r_t.target_oloc.pool)))
- abort_request(req, -ENOSPC);
- }
- }
-out:
- dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier);
+ if (osdc->abort_on_full &&
+ (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc)))
+ for_each_request(osdc, abort_on_full_fn, &victims);
}
static void check_pool_dne(struct ceph_osd_request *req)
up_read(&osdc->lock);
__complete_request(req);
- complete_all(&req->r_completion);
- ceph_osdc_put_request(req);
return;
fail_request:
if (ret)
goto out_put_req;
- osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+ ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+ if (ret)
+ goto out_put_req;
+
if (req_page)
osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
0, false, false);
if (!osdc->notify_wq)
goto out_msgpool_reply;
+ osdc->completion_wq = create_singlethread_workqueue("ceph-completion");
+ if (!osdc->completion_wq)
+ goto out_notify_wq;
+
schedule_delayed_work(&osdc->timeout_work,
osdc->client->options->osd_keepalive_timeout);
schedule_delayed_work(&osdc->osds_timeout_work,
return 0;
+out_notify_wq:
+ destroy_workqueue(osdc->notify_wq);
out_msgpool_reply:
ceph_msgpool_destroy(&osdc->msgpool_op_reply);
out_msgpool:
void ceph_osdc_stop(struct ceph_osd_client *osdc)
{
- flush_workqueue(osdc->notify_wq);
+ destroy_workqueue(osdc->completion_wq);
destroy_workqueue(osdc->notify_wq);
cancel_delayed_work_sync(&osdc->timeout_work);
cancel_delayed_work_sync(&osdc->osds_timeout_work);
* Should only be called with target_oid and target_oloc (as opposed to
* base_oid and base_oloc), since tiering isn't taken into account.
*/
-int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
- const struct ceph_object_id *oid,
- const struct ceph_object_locator *oloc,
- struct ceph_pg *raw_pgid)
+void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
+ const struct ceph_object_id *oid,
+ const struct ceph_object_locator *oloc,
+ struct ceph_pg *raw_pgid)
{
WARN_ON(pi->id != oloc->pool);
int nsl = oloc->pool_ns->len;
size_t total = nsl + 1 + oid->name_len;
- if (total > sizeof(stack_buf)) {
- buf = kmalloc(total, GFP_NOIO);
- if (!buf)
- return -ENOMEM;
- }
+ if (total > sizeof(stack_buf))
+ buf = kmalloc(total, GFP_NOIO | __GFP_NOFAIL);
memcpy(buf, oloc->pool_ns->str, nsl);
buf[nsl] = '\037';
memcpy(buf + nsl + 1, oid->name, oid->name_len);
oid->name, nsl, oloc->pool_ns->str,
raw_pgid->pool, raw_pgid->seed);
}
- return 0;
}
int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
if (!pi)
return -ENOENT;
- return __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid);
+ __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid);
+ return 0;
}
EXPORT_SYMBOL(ceph_object_locator_to_pg);
/**
* datagram_poll - generic datagram poll
+ * @file: file struct
* @sock: socket
- * @events to wait for
+ * @wait: poll table
*
* Datagram poll: Again totally generic. This also handles
* sequenced packet sockets providing the socket receive queue
* and you use a different write policy from sock_writeable()
* then please supply your own write_space callback.
*/
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
return mask;
}
-EXPORT_SYMBOL(datagram_poll_mask);
+EXPORT_SYMBOL(datagram_poll);
dev->tx_queue_len = new_len;
res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
res = notifier_to_errno(res);
- if (res) {
- netdev_err(dev,
- "refused to change device tx_queue_len\n");
- dev->tx_queue_len = orig_len;
- return res;
- }
- return dev_qdisc_change_tx_queue_len(dev);
+ if (res)
+ goto err_rollback;
+ res = dev_qdisc_change_tx_queue_len(dev);
+ if (res)
+ goto err_rollback;
}
return 0;
+
+err_rollback:
+ netdev_err(dev, "refused to change device tx_queue_len\n");
+ dev->tx_queue_len = orig_len;
+ return res;
}
/**
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (dev_get_valid_name(net, dev, pat) < 0)
+ err = dev_get_valid_name(net, dev, pat);
+ if (err < 0)
goto out;
}
dev_close(dev);
/* And unlink it from device chain */
- err = -ENODEV;
unlist_netdevice(dev);
synchronize_net();
if (ifr->ifr_qlen < 0)
return -EINVAL;
if (dev->tx_queue_len ^ ifr->ifr_qlen) {
- unsigned int orig_len = dev->tx_queue_len;
-
- dev->tx_queue_len = ifr->ifr_qlen;
- err = call_netdevice_notifiers(
- NETDEV_CHANGE_TX_QUEUE_LEN, dev);
- err = notifier_to_errno(err);
- if (err) {
- dev->tx_queue_len = orig_len;
+ err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+ if (err)
return err;
- }
}
return 0;
if (rule->mark && r->mark != rule->mark)
continue;
+ if (rule->suppress_ifgroup != -1 &&
+ r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (rule->suppress_prefixlen != -1 &&
+ r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
+ if (rule->proto && r->proto != rule->proto)
+ continue;
+
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
return err;
}
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
+ if (r->ip_proto != rule->ip_proto)
+ continue;
+
+ if (r->proto != rule->proto)
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->sport_range,
+ &rule->sport_range))
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->dport_range,
+ &rule->dport_range))
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
- rule_find(ops, frh, tb, rule, user_priority)) {
+ rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
(!unaligned_ok && offset >= 0 &&
offset + ip_align >= 0 &&
offset + ip_align % size == 0))) {
+ bool ldx_off_ok = offset <= S16_MAX;
+
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
- *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
- *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
- offset);
+ *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
+ size, 2 + endian + (!ldx_off_ok * 2));
+ if (ldx_off_ok) {
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+ BPF_REG_D, offset);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+ BPF_REG_TMP, 0);
+ }
if (endian)
*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
*insn++ = BPF_JMP_A(8);
BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
u32, offset, void *, to, u32, len, u32, start_header)
{
+ u8 *end = skb_tail_pointer(skb);
+ u8 *net = skb_network_header(skb);
+ u8 *mac = skb_mac_header(skb);
u8 *ptr;
- if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+ if (unlikely(offset > 0xffff || len > (end - mac)))
goto err_clear;
switch (start_header) {
case BPF_HDR_START_MAC:
- ptr = skb_mac_header(skb) + offset;
+ ptr = mac + offset;
break;
case BPF_HDR_START_NET:
- ptr = skb_network_header(skb) + offset;
+ ptr = net + offset;
break;
default:
goto err_clear;
}
- if (likely(ptr >= skb_mac_header(skb) &&
- ptr + len <= skb_tail_pointer(skb))) {
+ if (likely(ptr >= mac && ptr + len <= end)) {
memcpy(to, ptr, len);
return 0;
}
.arg2_type = ARG_ANYTHING,
};
+static inline int sk_skb_try_make_writable(struct sk_buff *skb,
+ unsigned int write_len)
+{
+ int err = __bpf_try_make_writable(skb, write_len);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return err;
+}
+
+BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
+{
+ /* Idea is the following: should the needed direct read/write
+ * test fail during runtime, we can pull in more data and redo
+ * again, since implicitly, we invalidate previous checks here.
+ *
+ * Or, since we know how much we need to make read/writeable,
+ * this can be done once at the program beginning for direct
+ * access case. By this we overcome limitations of only current
+ * headroom being accessible.
+ */
+ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
+}
+
+static const struct bpf_func_proto sk_skb_pull_data_proto = {
+ .func = sk_skb_pull_data,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
u64, from, u64, to, u64, flags)
{
static u32 __bpf_skb_max_len(const struct sk_buff *skb)
{
- return skb->dev->mtu + skb->dev->hard_header_len;
+ return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
+ SKB_MAX_ALLOC;
}
static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
return __skb_trim_rcsum(skb, new_len);
}
-BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
- u64, flags)
+static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
+ u64 flags)
{
u32 max_len = __bpf_skb_max_len(skb);
u32 min_len = __bpf_skb_min_len(skb);
if (!ret && skb_is_gso(skb))
skb_gso_reset(skb);
}
+ return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_tail(skb, new_len, flags);
bpf_compute_data_pointers(skb);
return ret;
.arg3_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
u64, flags)
+{
+ int ret = __bpf_skb_change_tail(skb, new_len, flags);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_tail_proto = {
+ .func = sk_skb_change_tail,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
+ u64 flags)
{
u32 max_len = __bpf_skb_max_len(skb);
u32 new_len = skb->len + head_room;
skb_reset_mac_header(skb);
}
+ return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_head(skb, head_room, flags);
+
bpf_compute_data_pointers(skb);
- return 0;
+ return ret;
}
static const struct bpf_func_proto bpf_skb_change_head_proto = {
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_head(skb, head_room, flags);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_head_proto = {
+ .func = sk_skb_change_head,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
{
return xdp_data_meta_unsupported(xdp) ? 0 :
u32 index)
{
struct xdp_frame *xdpf;
- int sent;
+ int err, sent;
if (!dev->netdev_ops->ndo_xdp_xmit) {
return -EOPNOTSUPP;
}
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
-{
- unsigned int len;
-
- if (unlikely(!(fwd->flags & IFF_UP)))
- return -ENETDOWN;
-
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len)
- return -EMSGSIZE;
-
- return 0;
-}
-
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
}
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
- if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ struct bpf_dtab_netdev *dst = fwd;
+
+ err = dev_map_generic_redirect(dst, skb, xdp_prog);
+ if (unlikely(err))
goto err;
- skb->dev = fwd;
- generic_xdp_tx(skb, xdp_prog);
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
struct xdp_sock *xs = fwd;
goto err;
}
- if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ err = xdp_ok_fwd_dev(fwd, skb->len);
+ if (unlikely(err))
goto err;
skb->dev = fwd;
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
+ params->ifindex = dev->ifindex;
- return dev->ifindex;
+ return 0;
}
#endif
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl4.flowi4_iif = 1;
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
} else {
err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
}
- if (err || res.type != RTN_UNICAST)
- return 0;
+ if (err) {
+ /* map fib lookup errors to RTN_ type */
+ if (err == -EINVAL)
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ if (err == -EHOSTUNREACH)
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ if (err == -EACCES)
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+
+ if (res.type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (res.fi->fib_nhs > 1)
fib_select_path(net, &res, &fl4, NULL);
if (check_mtu) {
mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
nh = &res.fi->fib_nh[res.nh_sel];
/* do not handle lwt encaps right now */
if (nh->nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
dev = nh->nh_dev;
- if (unlikely(!dev))
- return 0;
-
if (nh->nh_gw)
params->ipv4_dst = nh->nh_gw;
* rcu_read_lock_bh is not needed here
*/
neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
/* link local addresses are never forwarded */
if (rt6_need_strict(dst) || rt6_need_strict(src))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
dev = dev_get_by_index_rcu(net, params->ifindex);
if (unlikely(!dev))
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl6.flowi6_iif = 1;
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
} else {
}
if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+ switch (f6i->fib6_type) {
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+ }
- if (unlikely(f6i->fib6_flags & RTF_REJECT ||
- f6i->fib6_type != RTN_UNICAST))
- return 0;
+ if (f6i->fib6_type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
if (check_mtu) {
mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
if (f6i->fib6_nh.nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
if (f6i->fib6_flags & RTF_GATEWAY)
*dst = f6i->fib6_nh.nh_gw;
*/
neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
ndisc_hashfn, dst, dev);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
- int index = -EAFNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (plen < sizeof(*params))
return -EINVAL;
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- index = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, params, flags, false);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- index = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, params, flags, false);
break;
#endif
}
- if (index > 0) {
+ if (!rc) {
struct net_device *dev;
- dev = dev_get_by_index_rcu(net, index);
+ dev = dev_get_by_index_rcu(net, params->ifindex);
if (!is_skb_forwardable(dev, skb))
- index = 0;
+ rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- return index;
+ return rc;
}
static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
.arg4_type = ARG_CONST_SIZE
};
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
const void *, from, u32, len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
void *srh_tlvs, *srh_end, *ptr;
memcpy(skb->data + offset, from, len);
return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
u32, action, void *, param, u32, param_len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
struct ipv6_sr_hdr *srh;
default:
return -EINVAL;
}
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
s32, len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
void *srh_end, *srh_tlvs, *ptr;
srh_state->hdrlen += len;
srh_state->valid = 0;
return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
+#endif /* CONFIG_IPV6_SEG6_BPF */
bool bpf_helper_changes_pkt_data(void *func)
{
func == bpf_skb_store_bytes ||
func == bpf_skb_change_proto ||
func == bpf_skb_change_head ||
+ func == sk_skb_change_head ||
func == bpf_skb_change_tail ||
+ func == sk_skb_change_tail ||
func == bpf_skb_adjust_room ||
func == bpf_skb_pull_data ||
+ func == sk_skb_pull_data ||
func == bpf_clone_redirect ||
func == bpf_l3_csum_replace ||
func == bpf_l4_csum_replace ||
func == bpf_xdp_adjust_meta ||
func == bpf_msg_pull_data ||
func == bpf_xdp_adjust_tail ||
- func == bpf_lwt_push_encap ||
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
func == bpf_lwt_seg6_store_bytes ||
func == bpf_lwt_seg6_adjust_srh ||
- func == bpf_lwt_seg6_action
- )
+ func == bpf_lwt_seg6_action ||
+#endif
+ func == bpf_lwt_push_encap)
return true;
return false;
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
case BPF_FUNC_skb_pull_data:
- return &bpf_skb_pull_data_proto;
+ return &sk_skb_pull_data_proto;
case BPF_FUNC_skb_change_tail:
- return &bpf_skb_change_tail_proto;
+ return &sk_skb_change_tail_proto;
case BPF_FUNC_skb_change_head:
- return &bpf_skb_change_head_proto;
+ return &sk_skb_change_head_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
case BPF_FUNC_lwt_seg6_store_bytes:
return &bpf_lwt_seg6_store_bytes_proto;
case BPF_FUNC_lwt_seg6_action:
return &bpf_lwt_seg6_action_proto;
case BPF_FUNC_lwt_seg6_adjust_srh:
return &bpf_lwt_seg6_adjust_srh_proto;
+#endif
default:
return lwt_out_func_proto(func_id, prog);
}
d->lock = lock;
spin_lock_bh(lock);
}
- if (d->tail)
- return gnet_stats_copy(d, type, NULL, 0, padattr);
+ if (d->tail) {
+ int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+ /* The initial attribute added in gnet_stats_copy() may be
+ * preceded by a padding attribute, in which case d->tail will
+ * end up pointing at the padding instead of the real attribute.
+ * Fix this so gnet_stats_finish_copy() adjusts the length of
+ * the right attribute.
+ */
+ if (ret == 0 && d->tail->nla_type == padattr)
+ d->tail = (struct nlattr *)((char *)d->tail +
+ NLA_ALIGN(d->tail->nla_len));
+ return ret;
+ }
return 0;
}
if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
return -EINVAL;
- prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
+ prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC);
if (!prog->name)
return -ENOMEM;
EXPORT_SYMBOL(neigh_rand_reach_time);
-static bool neigh_del(struct neighbour *n, __u8 state,
+static bool neigh_del(struct neighbour *n, __u8 state, __u8 flags,
struct neighbour __rcu **np, struct neigh_table *tbl)
{
bool retval = false;
write_lock(&n->lock);
- if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state)) {
+ if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state) &&
+ !(n->flags & flags)) {
struct neighbour *neigh;
neigh = rcu_dereference_protected(n->next,
while ((n = rcu_dereference_protected(*np,
lockdep_is_held(&tbl->lock)))) {
if (n == ndel)
- return neigh_del(n, 0, np, tbl);
+ return neigh_del(n, 0, 0, np, tbl);
np = &n->next;
}
return false;
* - nobody refers to it.
* - it is not permanent
*/
- if (neigh_del(n, NUD_PERMANENT, np, tbl)) {
+ if (neigh_del(n, NUD_PERMANENT, NTF_EXT_LEARNED, np,
+ tbl)) {
shrunk = 1;
continue;
}
struct page *page;
/* Empty recycle ring */
- while ((page = ptr_ring_consume(&pool->ring))) {
+ while ((page = ptr_ring_consume_bh(&pool->ring))) {
/* Verify the refcnt invariant of cached pages */
if (!(page_ref_count(page) == 1))
pr_crit("%s() page_pool refcnt %d violation\n",
return err;
}
- dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
- __dev_notify_flags(dev, old_flags, ~0U);
+ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+ __dev_notify_flags(dev, old_flags, 0U);
+ } else {
+ dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+ __dev_notify_flags(dev, old_flags, ~0U);
+ }
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
n->cloned = 1;
n->nohdr = 0;
n->peeked = 0;
+ C(pfmemalloc);
n->destructor = NULL;
C(tail);
C(end);
net_warn_ratelimited(
"skb_segment: too many frags: %u %u\n",
pos, mss);
+ err = -EINVAL;
goto err;
}
perform_csum_check:
if (!csum) {
- if (skb_has_shared_frag(nskb)) {
- err = __skb_linearize(nskb);
- if (err)
- goto err;
- }
+ if (skb_has_shared_frag(nskb) &&
+ __skb_linearize(nskb))
+ goto err;
+
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
if (npages >= 1 << order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
+ __GFP_NOWARN,
order);
if (page)
goto fill_page;
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
- val = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
- if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) &&
- inet_sk(sk)->inet_num &&
- (sk->sk_reuse != val)) {
- ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN;
- break;
- }
- sk->sk_reuse = val;
+ sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_REUSEPORT:
- if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) &&
- inet_sk(sk)->inet_num &&
- (sk->sk_reuseport != valbool)) {
- ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN;
- break;
- }
sk->sk_reuseport = valbool;
break;
case SO_TYPE:
pfrag->offset += use;
sge = sg + sg_curr - 1;
- if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
- sg->offset + sg->length == orig_offset) {
- sg->length += use;
+ if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+ sge->offset + sge->length == orig_offset) {
+ sge->length += use;
} else {
sge = sg + sg_curr;
sg_unmark_end(sge);
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- prot->slab_flags, NULL);
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+ prot->slab_flags,
prot->useroffset, prot->usersize,
NULL);
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
+ SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
rcu_read_lock();
/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
- xa->zc_alloc->free(xa->zc_alloc, handle);
+ if (!WARN_ON_ONCE(!xa))
+ xa->zc_alloc->free(xa->zc_alloc, handle);
rcu_read_unlock();
default:
/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
u32 cwnd = hc->tx_cwnd, restart_cwnd,
iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
+ s32 delta = now - hc->tx_lsndtime;
hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
/* don't reduce cwnd below the initial window (IW) */
restart_cwnd = min(cwnd, iwnd);
- cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
- hc->tx_cwnd = max(cwnd, restart_cwnd);
+ while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
+ cwnd >>= 1;
+ hc->tx_cwnd = max(cwnd, restart_cwnd);
hc->tx_cwnd_stamp = now;
hc->tx_cwnd_used = 0;
{
struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
- ktime_t now = ktime_get_real();
+ ktime_t now = ktime_get();
s64 delta = 0;
switch (fbtype) {
case CCID3_FBACK_PERIODIC:
delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
if (delta <= 0)
- DCCP_BUG("delta (%ld) <= 0", (long)delta);
- else
- hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
+ delta = 1;
+ hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
break;
default:
return;
}
- ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta,
+ ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
hc->rx_x_recv, hc->rx_pinv);
hc->rx_tstamp_last_feedback = now;
static u32 ccid3_first_li(struct sock *sk)
{
struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
- u32 x_recv, p, delta;
+ u32 x_recv, p;
+ s64 delta;
u64 fval;
if (hc->rx_rtt == 0) {
hc->rx_rtt = DCCP_FALLBACK_RTT;
}
- delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback));
+ delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
+ if (delta <= 0)
+ delta = 1;
x_recv = scaled_div32(hc->rx_bytes_recv, delta);
if (x_recv == 0) { /* would also trigger divide-by-zero */
DCCP_WARN("X_recv==0\n");
int flags, int *addr_len);
void dccp_shutdown(struct sock *sk, int how);
int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void dccp_req_err(struct sock *sk, u64 seq);
.accept = inet_accept,
.getname = inet_getname,
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
- .poll_mask = dccp_poll_mask,
+ .poll = dccp_poll,
.ioctl = inet_ioctl,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet6_getname,
- .poll_mask = dccp_poll_mask,
+ .poll = dccp_poll,
.ioctl = inet6_ioctl,
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
EXPORT_SYMBOL_GPL(dccp_disconnect);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
+/*
+ * Wait for a DCCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
+ */
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
__poll_t mask;
struct sock *sk = sock->sk;
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
return mask;
}
-EXPORT_SYMBOL_GPL(dccp_poll_mask);
+EXPORT_SYMBOL_GPL(dccp_poll);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
}
-static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
struct dn_scp *scp = DN_SK(sk);
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
if (!skb_queue_empty(&scp->other_receive_queue))
mask |= EPOLLRDBAND;
.socketpair = sock_no_socketpair,
.accept = dn_accept,
.getname = dn_getname,
- .poll_mask = dn_poll_mask,
+ .poll = dn_poll,
.ioctl = dn_ioctl,
.listen = dn_listen,
.shutdown = dn_shutdown,
opt++;
kdebug("options: '%s'", opt);
do {
+ int opt_len, opt_nlen;
const char *eq;
- int opt_len, opt_nlen, opt_vlen, tmp;
+ char optval[128];
next_opt = memchr(opt, '#', end - opt) ?: end;
opt_len = next_opt - opt;
- if (opt_len <= 0 || opt_len > 128) {
+ if (opt_len <= 0 || opt_len > sizeof(optval)) {
pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
opt_len);
return -EINVAL;
}
- eq = memchr(opt, '=', opt_len) ?: end;
- opt_nlen = eq - opt;
- eq++;
- opt_vlen = next_opt - eq; /* will be -1 if no value */
+ eq = memchr(opt, '=', opt_len);
+ if (eq) {
+ opt_nlen = eq - opt;
+ eq++;
+ memcpy(optval, eq, next_opt - eq);
+ optval[next_opt - eq] = '\0';
+ } else {
+ opt_nlen = opt_len;
+ optval[0] = '\0';
+ }
- tmp = opt_vlen >= 0 ? opt_vlen : 0;
- kdebug("option '%*.*s' val '%*.*s'",
- opt_nlen, opt_nlen, opt, tmp, tmp, eq);
+ kdebug("option '%*.*s' val '%s'",
+ opt_nlen, opt_nlen, opt, optval);
/* see if it's an error number representing a DNS error
* that's to be recorded as the result in this key */
if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 &&
memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) {
kdebug("dns error number option");
- if (opt_vlen <= 0)
- goto bad_option_value;
- ret = kstrtoul(eq, 10, &derrno);
+ ret = kstrtoul(optval, 10, &derrno);
if (ret < 0)
goto bad_option_value;
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev)
+ if (!dev->phydev && !dp->pl)
return -ENODEV;
if (!ds->ops->set_mac_eee)
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev)
+ if (!dev->phydev && !dp->pl)
return -ENODEV;
if (!ds->ops->get_mac_eee)
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+ if (!netif_running(slave_dev))
+ return 0;
+
netif_device_detach(slave_dev);
rtnl_lock();
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+ if (!netif_running(slave_dev))
+ return 0;
+
netif_device_attach(slave_dev);
rtnl_lock();
if (!skb->dev)
return NULL;
- pskb_trim_rcsum(skb, skb->len - 4);
+ if (pskb_trim_rcsum(skb, skb->len - 4))
+ return NULL;
return skb;
}
return 0;
}
+static int lowpan_get_iflink(const struct net_device *dev)
+{
+ return lowpan_802154_dev(dev)->wdev->ifindex;
+}
+
static const struct net_device_ops lowpan_netdev_ops = {
.ndo_init = lowpan_dev_init,
.ndo_start_xmit = lowpan_xmit,
.ndo_open = lowpan_open,
.ndo_stop = lowpan_stop,
.ndo_neigh_construct = lowpan_neigh_construct,
+ .ndo_get_iflink = lowpan_get_iflink,
};
static void lowpan_setup(struct net_device *ldev)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
- .poll_mask = tcp_poll_mask,
+ .poll = tcp_poll,
.ioctl = inet_ioctl,
.listen = inet_listen,
.shutdown = inet_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll_mask = udp_poll_mask,
+ .poll = udp_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
/*
* For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll_mask
+ * udp_poll
*/
static const struct proto_ops inet_sockraw_ops = {
.family = PF_INET,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
return ip_hdr(skb)->daddr;
in_dev = __in_dev_get_rcu(dev);
- BUG_ON(!in_dev);
net = dev_net(dev);
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
+ bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
struct flowi4 fl4 = {
.flowi4_iif = LOOPBACK_IFINDEX,
+ .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
.daddr = ip_hdr(skb)->saddr,
.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
.flowi4_scope = scope,
- .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+ .flowi4_mark = vmark ? skb->mark : 0,
};
if (!fib_lookup(net, &fl4, &res, 0))
return FIB_RES_PREFSRC(net, res);
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
spin_lock_bh(&im->lock);
if (pmc) {
im->interface = pmc->interface;
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- im->sfmode = pmc->sfmode;
- if (pmc->sfmode == MCAST_INCLUDE) {
+ if (im->sfmode == MCAST_INCLUDE) {
im->tomb = pmc->tomb;
im->sources = pmc->sources;
for (psf = im->sources; psf; psf = psf->sf_next)
- psf->sf_crcount = im->crcount;
+ psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ } else {
+ im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
}
in_dev_put(pmc->interface);
kfree(pmc);
#endif
}
-static void igmp_group_added(struct ip_mc_list *im)
+static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
{
struct in_device *in_dev = im->interface;
#ifdef CONFIG_IP_MULTICAST
}
/* else, v3 */
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should
+ * not send filter-mode change record as the mode should be from
+ * IN() to IN(A).
+ */
+ if (mode == MCAST_EXCLUDE)
+ im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+
igmp_ifc_event(in_dev);
#endif
}
/*
* A socket has joined a multicast group on device dev.
*/
-
-void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
+ unsigned int mode)
{
struct ip_mc_list *im;
#ifdef CONFIG_IP_MULTICAST
for_each_pmc_rtnl(in_dev, im) {
if (im->multiaddr == addr) {
im->users++;
- ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0);
+ ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0);
goto out;
}
}
in_dev_hold(in_dev);
im->multiaddr = addr;
/* initial mode is (EX, empty) */
- im->sfmode = MCAST_EXCLUDE;
- im->sfcount[MCAST_EXCLUDE] = 1;
+ im->sfmode = mode;
+ im->sfcount[mode] = 1;
refcount_set(&im->refcnt, 1);
spin_lock_init(&im->lock);
#ifdef CONFIG_IP_MULTICAST
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, im);
#endif
- igmp_group_added(im);
+ igmp_group_added(im, mode);
if (!in_dev->dead)
ip_rt_multicast_event(in_dev);
out:
return;
}
+
+void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+{
+ __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+}
EXPORT_SYMBOL(ip_mc_inc_group);
static int ip_mc_check_iphdr(struct sk_buff *skb)
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, pmc);
#endif
- igmp_group_added(pmc);
+ igmp_group_added(pmc, pmc->sfmode);
}
}
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, pmc);
#endif
- igmp_group_added(pmc);
+ igmp_group_added(pmc, pmc->sfmode);
}
}
/* Join a multicast group
*/
-
-int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
+ unsigned int mode)
{
__be32 addr = imr->imr_multiaddr.s_addr;
struct ip_mc_socklist *iml, *i;
memcpy(&iml->multi, imr, sizeof(*imr));
iml->next_rcu = inet->mc_list;
iml->sflist = NULL;
- iml->sfmode = MCAST_EXCLUDE;
+ iml->sfmode = mode;
rcu_assign_pointer(inet->mc_list, iml);
- ip_mc_inc_group(in_dev, addr);
+ __ip_mc_inc_group(in_dev, addr, mode);
err = 0;
done:
return err;
}
+
+/* Join ASM (Any-Source Multicast) group
+ */
+int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+{
+ return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE);
+}
EXPORT_SYMBOL(ip_mc_join_group);
+/* Join SSM (Source-Specific Multicast) group
+ */
+int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+ unsigned int mode)
+{
+ return __ip_mc_join_group(sk, imr, mode);
+}
+
static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
struct in_device *in_dev)
{
void inet_frags_exit_net(struct netns_frags *nf)
{
- nf->low_thresh = 0; /* prevent creation of new frags */
+ nf->high_thresh = 0; /* prevent creation of new frags */
rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
{
struct inet_frag_queue *q;
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
- return NULL;
-
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
return NULL;
{
struct inet_frag_queue *fq;
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+ return NULL;
+
rcu_read_lock();
fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score += 4;
}
if (sk->sk_incoming_cpu == raw_smp_processor_id())
int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
if (i < next->len) {
+ int delta = -next->truesize;
+
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
+ delta += next->truesize;
+ if (delta)
+ add_frag_mem_limit(qp->q.net, delta);
next->ip_defrag_offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
to->dev = from->dev;
to->mark = from->mark;
+ skb_copy_hash(to, from);
+
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;
cork->fragsize = ip_sk_use_pmtu(sk) ?
dst_mtu(&rt->dst) : rt->dst.dev->mtu;
- cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0;
+ cork->gso_size = sk->sk_type == SOCK_DGRAM &&
+ sk->sk_protocol == IPPROTO_UDP ? ipc->gso_size : 0;
cork->dst = &rt->dst;
cork->length = 0;
cork->ttl = ipc->ttl;
{
struct sockaddr_in sin;
const struct iphdr *iph = ip_hdr(skb);
- __be16 *ports = (__be16 *)skb_transport_header(skb);
+ __be16 *ports;
+ int end;
- if (skb_transport_offset(skb) + 4 > (int)skb->len)
+ end = skb_transport_offset(skb) + 4;
+ if (end > 0 && !pskb_may_pull(skb, end))
return;
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = iph->daddr;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
- err = ip_mc_join_group(sk, &mreq);
+ err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
- err = ip_mc_join_group(sk, &mreq);
+ err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
return -ENOMEM;
j = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ip;
.checkentry = icmp_checkentry,
.proto = IPPROTO_ICMP,
.family = NFPROTO_IPV4,
+ .me = THIS_MODULE,
},
};
* to a listener socket if there's one */
struct sock *sk2;
- sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+ sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
iph->saddr, laddr ? laddr : iph->daddr,
hp->source, lport ? lport : hp->dest,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
const enum nf_tproxy_lookup_t lookup_type)
{
struct sock *sk;
- struct tcphdr *tcph;
switch (protocol) {
- case IPPROTO_TCP:
+ case IPPROTO_TCP: {
+ struct tcphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, ip_hdrlen(skb),
+ sizeof(struct tcphdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
switch (lookup_type) {
case NF_TPROXY_LOOKUP_LISTENER:
- tcph = hp;
sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
ip_hdrlen(skb) +
- __tcp_hdrlen(tcph),
+ __tcp_hdrlen(hp),
saddr, sport,
daddr, dport,
in->ifindex, 0);
BUG();
}
break;
+ }
case IPPROTO_UDP:
sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
if (write && ret == 0) {
low = make_kgid(user_ns, urange[0]);
high = make_kgid(user_ns, urange[1]);
- if (!gid_valid(low) || !gid_valid(high) ||
- (urange[1] < urange[0]) || gid_lt(high, low)) {
+ if (!gid_valid(low) || !gid_valid(high))
+ return -EINVAL;
+ if (urange[1] < urange[0] || gid_lt(high, low)) {
low = make_kgid(&init_user_ns, 1);
high = make_kgid(&init_user_ns, 0);
}
ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
- int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+ __le32 key[4];
+ int ret, i;
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
rcu_read_lock();
ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
- memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
- memset(user_key, 0, sizeof(user_key));
+ memset(key, 0, sizeof(key));
rcu_read_unlock();
+ for (i = 0; i < ARRAY_SIZE(key); i++)
+ user_key[i] = le32_to_cpu(key[i]);
+
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
ret = -EINVAL;
goto bad_key;
}
- tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+ for (i = 0; i < ARRAY_SIZE(user_key); i++)
+ key[i] = cpu_to_le32(user_key[i]);
+
+ tcp_fastopen_reset_cipher(net, NULL, key,
TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
- user_key[0], user_key[1], user_key[2], user_key[3],
+ user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
}
/*
- * Socket is not locked. We are protected from async events by poll logic and
- * correct handling of state changes made by other threads is impossible in
- * any case.
+ * Wait for a TCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
*/
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
+ __poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
- __poll_t mask = 0;
int state;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
+ /* Socket is not locked. We are protected from async events
+ * by poll logic and correct handling of state changes
+ * made by other threads is impossible in any case.
+ */
+
+ mask = 0;
+
/*
* EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
return mask;
}
-EXPORT_SYMBOL(tcp_poll_mask);
+EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
* shouldn't happen.
*/
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
- "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
flags))
break;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
- "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
+ tp->copied_seq = tp->rcv_nxt;
+ tp->urg_data = 0;
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
skb_rbtree_purge(&tp->out_of_order_queue);
case TCP_REPAIR:
if (!tcp_can_repair_sock(sk))
err = -EPERM;
- else if (val == 1) {
+ else if (val == TCP_REPAIR_ON) {
tp->repair = 1;
sk->sk_reuse = SK_FORCE_REUSE;
tp->repair_queue = TCP_NO_QUEUE;
- } else if (val == 0) {
+ } else if (val == TCP_REPAIR_OFF) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
tcp_send_window_probe(sk);
+ } else if (val == TCP_REPAIR_OFF_NO_WP) {
+ tp->repair = 0;
+ sk->sk_reuse = SK_NO_REUSE;
} else
err = -EINVAL;
struct request_sock *req = inet_reqsk(sk);
local_bh_disable();
- inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
- req);
+ inet_csk_reqsk_queue_drop(req->rsk_listener, req);
local_bh_enable();
return 0;
}
/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
cwnd = (cwnd + 1) & ~1U;
+ /* Ensure gain cycling gets inflight above BDP even for small BDPs. */
+ if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+ cwnd += 2;
+
return cwnd;
}
u32 dctcp_alpha;
u32 next_seq;
u32 ce_state;
- u32 delayed_ack_reserved;
u32 loss_cwnd;
};
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
- ca->delayed_ack_reserved = 0;
ca->loss_cwnd = 0;
ca->ce_state = 0;
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=0 to CE=1 and delayed
- * ACK has not sent yet.
- */
- if (!ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=0. */
- tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (!ca->ce_state) {
+ /* State has changed from CE=0 to CE=1, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=1 to CE=0 and delayed
- * ACK has not sent yet.
- */
- if (ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=1. */
- tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (ca->ce_state) {
+ /* State has changed from CE=1 to CE=0, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
}
}
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
- struct dctcp *ca = inet_csk_ca(sk);
-
- switch (ev) {
- case CA_EVENT_DELAYED_ACK:
- if (!ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 1;
- break;
- case CA_EVENT_NON_DELAYED_ACK:
- if (ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 0;
- break;
- default:
- /* Don't care for the rest. */
- break;
- }
-}
-
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
switch (ev) {
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
- case CA_EVENT_DELAYED_ACK:
- case CA_EVENT_NON_DELAYED_ACK:
- dctcp_update_ack_reserved(sk, ev);
- break;
default:
/* Don't care for the rest. */
break;
icsk->icsk_ack.quick = quickacks;
}
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
{
- if (tcp_hdr(skb)->cwr)
+ if (tcp_hdr(skb)->cwr) {
tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+
+ /* If the sender is telling us it has entered CWR, then its
+ * cwnd may be very low (even just 1 packet), so we should ACK
+ * immediately.
+ */
+ tcp_enter_quickack_mode((struct sock *)tp, 2);
+ }
}
static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
* it is probably a retransmit.
*/
if (tp->ecn_flags & TCP_ECN_SEEN)
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
break;
case INET_ECN_CE:
if (tcp_ca_needs_ecn(sk))
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN;
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
+
+ /* If any of the cumulatively ACKed segments was
+ * retransmitted, non-SACK case cannot confirm that
+ * progress was due to original transmission due to
+ * lack of TCPCB_SACKED_ACKED bits even if some of
+ * the packets may have been never retransmitted.
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
int delta;
return true;
}
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+ struct sk_buff *to,
+ struct sk_buff *from,
+ bool *fragstolen)
+{
+ bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+ /* In case tcp_drop() is called later, update to->gso_segs */
+ if (res) {
+ u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+ max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+ skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+ }
+ return res;
+}
+
static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
sk_drops_add(sk, skb);
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, tp->ooo_last_skb,
- skb, &fragstolen)) {
+ if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+ skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
kfree_skb_partial(skb, fragstolen);
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb);
+ tcp_drop(sk, skb);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb1);
+ tcp_drop(sk, skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, skb1,
- skb, &fragstolen)) {
+ } else if (tcp_ooo_try_coalesce(sk, skb1,
+ skb, &fragstolen)) {
goto coalesce_done;
}
p = &parent->rb_right;
static void tcp_collapse_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 range_truesize, sum_tiny = 0;
struct sk_buff *skb, *head;
u32 start, end;
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
+ range_truesize = skb->truesize;
for (head = skb;;) {
skb = skb_rb_next(skb);
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, NULL, &tp->out_of_order_queue,
- head, skb, start, end);
+ /* Do not attempt collapsing tiny skbs */
+ if (range_truesize != head->truesize ||
+ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+ tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+ head, skb, start, end);
+ } else {
+ sum_tiny += range_truesize;
+ if (sum_tiny > sk->sk_rcvbuf >> 3)
+ return;
+ }
goto new_range;
}
+ range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
+ int goal;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;
NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+ goal = sk->sk_rcvbuf >> 3;
node = &tp->ooo_last_skb->rbnode;
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
+ goal -= rb_to_skb(node)->truesize;
tcp_drop(sk, rb_to_skb(node));
- sk_mem_reclaim(sk);
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !tcp_under_memory_pressure(sk))
- break;
+ if (!prev || goal <= 0) {
+ sk_mem_reclaim(sk);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ !tcp_under_memory_pressure(sk))
+ break;
+ goal = sk->sk_rcvbuf >> 3;
+ }
node = prev;
} while (node);
tp->ooo_last_skb = rb_to_skb(prev);
else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+ return 0;
+
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
*/
if (tcptw->tw_ts_recent_stamp &&
(!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
- tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
- tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
- tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ /* In case of repair and re-using TIME-WAIT sockets we still
+ * want to be sure that it is safe as above but honor the
+ * sequence numbers and time stamps set as part of the repair
+ * process.
+ *
+ * Without this check re-using a TIME-WAIT socket with TCP
+ * repair would accumulate a -1 on the repair assigned
+ * sequence number. The first time it is reused the sequence
+ * is -1, the second time -2, etc. This fixes that issue
+ * without appearing to create any others.
+ */
+ if (likely(!tp->repair)) {
+ tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+ if (tp->write_seq == 0)
+ tp->write_seq = 1;
+ tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+ tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ }
sock_hold(sktw);
return 1;
}
reqsk_put(req);
goto discard_it;
}
+ if (tcp_checksum_complete(skb)) {
+ reqsk_put(req);
+ goto csum_error;
+ }
if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
goto out_check_final;
}
- p = *head;
- th2 = tcp_hdr(p);
tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
out_check_final:
}
/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+ u32 rcv_nxt)
{
struct tcp_sock *tp = tcp_sk(sk);
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
}
+
+ if (unlikely(rcv_nxt != tp->rcv_nxt))
+ return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
- gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+ int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
- th->ack_seq = htonl(tp->rcv_nxt);
+ th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);
icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
return err;
}
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+ gfp_t gfp_mask)
+{
+ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+ tcp_sk(sk)->rcv_nxt);
+}
+
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
- tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
}
/* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;
if (sk->sk_state == TCP_CLOSE)
return;
- tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
skb_set_tcp_pure_ack(buff);
/* Send it off, this clears delayed acks for us. */
- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
-EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
* udp_poll - wait for a UDP event.
* @file - file struct
* @sock - socket
- * @events - events to wait for
+ * @wait - poll table
*
* This is same as datagram poll, except for the special case of
* blocking sockets. If application is using a blocking fd
* but then block when reading it. Add special case code
* to work around these arguably broken applications.
*/
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
- if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
+ if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
return mask;
}
-EXPORT_SYMBOL(udp_poll_mask);
+EXPORT_SYMBOL(udp_poll);
int udp_abort(struct sock *sk, int err)
{
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
config IPV6_ILA
tristate "IPv6: Identifier Locator Addressing (ILA)"
depends on NETFILTER
+ select DST_CACHE
select LWTUNNEL
---help---
Support for IPv6 Identifier Locator Addressing (ILA).
}
}
+ memset(&cfg, 0, sizeof(cfg));
cfg.valid_lft = min_t(__u32, ifp->valid_lft,
idev->cnf.temp_valid_lft + age);
cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor;
cfg.pfx = &addr;
cfg.scope = ipv6_addr_scope(cfg.pfx);
- cfg.rt_priority = 0;
ift = ipv6_add_addr(idev, &cfg, block, NULL);
if (IS_ERR(ift)) {
continue;
if ((rt->fib6_flags & noflags) != 0)
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
break;
}
out:
unsigned long expires, u32 flags)
{
struct fib6_info *f6i;
+ u32 prio;
f6i = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
if (!f6i)
return -ENOENT;
- if (f6i->fib6_metric != ifp->rt_priority) {
+ prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+ if (f6i->fib6_metric != prio) {
+ /* delete old one */
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
/* add new one */
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
- /* delete old one */
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
} else {
if (!expires)
fib6_clean_expires(f6i);
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = inet_accept, /* ok */
.getname = inet6_getname,
- .poll_mask = tcp_poll_mask, /* ok */
+ .poll = tcp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll_mask = udp_poll_mask, /* ok */
+ .poll = udp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
{
struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts;
- txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS,
- hop, hop ? ipv6_optlen(hop) : 0);
+ txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop);
txopt_put(old);
if (IS_ERR(txopts))
return PTR_ERR(txopts);
if (IS_ERR(new))
return PTR_ERR(new);
- txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
- new, new ? ipv6_optlen(new) : 0);
+ txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
kfree(new);
if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new))
return; /* Nothing to do */
- txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
- new, new ? ipv6_optlen(new) : 0);
+ txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
if (!IS_ERR(txopts)) {
txopts = xchg(&req_inet->ipv6_opt, txopts);
}
if (np->rxopt.bits.rxorigdstaddr) {
struct sockaddr_in6 sin6;
- __be16 *ports = (__be16 *) skb_transport_header(skb);
+ __be16 *ports;
+ int end;
- if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+ end = skb_transport_offset(skb) + 4;
+ if (end <= 0 || pskb_may_pull(skb, end)) {
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);
sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
sg_init_table(sg, nfrags);
ret = skb_to_sgvec(skb, sg, 0, skb->len);
- if (unlikely(ret < 0))
+ if (unlikely(ret < 0)) {
+ kfree(tmp);
goto out;
+ }
skb->ip_summed = CHECKSUM_NONE;
}
EXPORT_SYMBOL_GPL(ipv6_dup_options);
-static int ipv6_renew_option(void *ohdr,
- struct ipv6_opt_hdr __user *newopt, int newoptlen,
- int inherit,
- struct ipv6_opt_hdr **hdr,
- char **p)
+static void ipv6_renew_option(int renewtype,
+ struct ipv6_opt_hdr **dest,
+ struct ipv6_opt_hdr *old,
+ struct ipv6_opt_hdr *new,
+ int newtype, char **p)
{
- if (inherit) {
- if (ohdr) {
- memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr));
- *hdr = (struct ipv6_opt_hdr *)*p;
- *p += CMSG_ALIGN(ipv6_optlen(*hdr));
- }
- } else {
- if (newopt) {
- if (copy_from_user(*p, newopt, newoptlen))
- return -EFAULT;
- *hdr = (struct ipv6_opt_hdr *)*p;
- if (ipv6_optlen(*hdr) > newoptlen)
- return -EINVAL;
- *p += CMSG_ALIGN(newoptlen);
- }
- }
- return 0;
+ struct ipv6_opt_hdr *src;
+
+ src = (renewtype == newtype ? new : old);
+ if (!src)
+ return;
+
+ memcpy(*p, src, ipv6_optlen(src));
+ *dest = (struct ipv6_opt_hdr *)*p;
+ *p += CMSG_ALIGN(ipv6_optlen(*dest));
}
/**
*/
struct ipv6_txoptions *
ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
- int newtype,
- struct ipv6_opt_hdr __user *newopt, int newoptlen)
+ int newtype, struct ipv6_opt_hdr *newopt)
{
int tot_len = 0;
char *p;
struct ipv6_txoptions *opt2;
- int err;
if (opt) {
if (newtype != IPV6_HOPOPTS && opt->hopopt)
tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
}
- if (newopt && newoptlen)
- tot_len += CMSG_ALIGN(newoptlen);
+ if (newopt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(newopt));
if (!tot_len)
return NULL;
opt2->tot_len = tot_len;
p = (char *)(opt2 + 1);
- err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen,
- newtype != IPV6_HOPOPTS,
- &opt2->hopopt, &p);
- if (err)
- goto out;
-
- err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen,
- newtype != IPV6_RTHDRDSTOPTS,
- &opt2->dst0opt, &p);
- if (err)
- goto out;
-
- err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen,
- newtype != IPV6_RTHDR,
- (struct ipv6_opt_hdr **)&opt2->srcrt, &p);
- if (err)
- goto out;
-
- err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen,
- newtype != IPV6_DSTOPTS,
- &opt2->dst1opt, &p);
- if (err)
- goto out;
+ ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt,
+ (opt ? opt->hopopt : NULL),
+ newopt, newtype, &p);
+ ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt,
+ (opt ? opt->dst0opt : NULL),
+ newopt, newtype, &p);
+ ipv6_renew_option(IPV6_RTHDR,
+ (struct ipv6_opt_hdr **)&opt2->srcrt,
+ (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL),
+ newopt, newtype, &p);
+ ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt,
+ (opt ? opt->dst1opt : NULL),
+ newopt, newtype, &p);
opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
(opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);
return opt2;
-out:
- sock_kfree_s(sk, opt2, opt2->tot_len);
- return ERR_PTR(err);
-}
-
-/**
- * ipv6_renew_options_kern - replace a specific ext hdr with a new one.
- *
- * @sk: sock from which to allocate memory
- * @opt: original options
- * @newtype: option type to replace in @opt
- * @newopt: new option of type @newtype to replace (kernel-mem)
- * @newoptlen: length of @newopt
- *
- * See ipv6_renew_options(). The difference is that @newopt is
- * kernel memory, rather than user memory.
- */
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt,
- int newtype, struct ipv6_opt_hdr *newopt,
- int newoptlen)
-{
- struct ipv6_txoptions *ret_val;
- const mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
- ret_val = ipv6_renew_options(sk, opt, newtype,
- (struct ipv6_opt_hdr __user *)newopt,
- newoptlen);
- set_fs(old_fs);
- return ret_val;
}
struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
/* for local traffic to local address, skb dev is the loopback
* device. Check if there is a dst attached to the skb and if so
- * get the real device index.
+ * get the real device index. Same is needed for replies to a link
+ * local address on a device enslaved to an L3 master device
*/
- if (unlikely(iif == LOOPBACK_IFINDEX)) {
+ if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
if (rt6)
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score++;
}
if (sk->sk_incoming_cpu == raw_smp_processor_id())
return f6i;
}
-void fib6_info_destroy(struct fib6_info *f6i)
+void fib6_info_destroy_rcu(struct rcu_head *head)
{
+ struct fib6_info *f6i = container_of(head, struct fib6_info, rcu);
struct rt6_exception_bucket *bucket;
struct dst_metrics *m;
kfree(f6i);
}
-EXPORT_SYMBOL_GPL(fib6_info_destroy);
+EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu);
static struct fib6_node *node_alloc(struct net *net)
{
{
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&rt->fib6_table->tb6_lock));
- struct fib6_info *iter = NULL, *match = NULL;
+ struct fib6_info *iter = NULL;
struct fib6_info __rcu **ins;
+ struct fib6_info __rcu **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
- int append = (info->nlh &&
- (info->nlh->nlmsg_flags & NLM_F_APPEND));
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
+ bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
u16 nlflags = NLM_F_EXCL;
int err;
- if (append)
+ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
nlflags |= NLM_F_APPEND;
ins = &fn->leaf;
nlflags &= ~NLM_F_EXCL;
if (replace) {
- found++;
- break;
+ if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+ found++;
+ break;
+ }
+ if (rt_can_ecmp)
+ fallback_ins = fallback_ins ?: ins;
+ goto next_iter;
}
if (rt6_duplicate_nexthop(iter, rt)) {
fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
return -EEXIST;
}
-
- /* first route that matches */
- if (!match)
- match = iter;
+ /* If we have the same destination and the same metric,
+ * but not the same gateway, then the route we try to
+ * add is sibling to this route, increment our counter
+ * of siblings, and later we will add our route to the
+ * list.
+ * Only static routes (which don't have flag
+ * RTF_EXPIRES) are used for ECMPv6.
+ *
+ * To avoid long list, we only had siblings if the
+ * route have a gateway.
+ */
+ if (rt_can_ecmp &&
+ rt6_qualify_for_ecmp(iter))
+ rt->fib6_nsiblings++;
}
if (iter->fib6_metric > rt->fib6_metric)
break;
+next_iter:
ins = &iter->fib6_next;
}
+ if (fallback_ins && !found) {
+ /* No ECMP-able route found, replace first non-ECMP one */
+ ins = fallback_ins;
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
+ found++;
+ }
+
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
/* Link this route to others same route. */
- if (append && match) {
+ if (rt->fib6_nsiblings) {
+ unsigned int fib6_nsiblings;
struct fib6_info *sibling, *temp_sibling;
- if (rt->fib6_flags & RTF_REJECT) {
- NL_SET_ERR_MSG(extack,
- "Can not append a REJECT route");
- return -EINVAL;
- } else if (match->fib6_flags & RTF_REJECT) {
- NL_SET_ERR_MSG(extack,
- "Can not append to a REJECT route");
- return -EINVAL;
+ /* Find the first route that have the same metric */
+ sibling = leaf;
+ while (sibling) {
+ if (sibling->fib6_metric == rt->fib6_metric &&
+ rt6_qualify_for_ecmp(sibling)) {
+ list_add_tail(&rt->fib6_siblings,
+ &sibling->fib6_siblings);
+ break;
+ }
+ sibling = rcu_dereference_protected(sibling->fib6_next,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
}
- rt->fib6_nsiblings = match->fib6_nsiblings;
- list_add_tail(&rt->fib6_siblings, &match->fib6_siblings);
- match->fib6_nsiblings++;
-
/* For each sibling in the list, increment the counter of
* siblings. BUG() if counters does not match, list of siblings
* is broken!
*/
+ fib6_nsiblings = 0;
list_for_each_entry_safe(sibling, temp_sibling,
- &match->fib6_siblings, fib6_siblings) {
+ &rt->fib6_siblings, fib6_siblings) {
sibling->fib6_nsiblings++;
- BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings);
+ BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
+ fib6_nsiblings++;
}
-
- rt6_multipath_rebalance(match);
+ BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+ rt6_multipath_rebalance(temp_sibling);
}
/*
* insert node
*/
if (!replace) {
- enum fib_event_type event;
-
if (!add)
pr_warn("NLM_F_CREATE should be set when creating new route\n");
add:
nlflags |= NLM_F_CREATE;
- event = append ? FIB_EVENT_ENTRY_APPEND : FIB_EVENT_ENTRY_ADD;
- err = call_fib6_entry_notifiers(info->nl_net, event, rt,
- extack);
+ err = call_fib6_entry_notifiers(info->nl_net,
+ FIB_EVENT_ENTRY_ADD,
+ rt, extack);
if (err)
return err;
}
} else {
- struct fib6_info *tmp;
+ int nsiblings;
if (!found) {
if (add)
if (err)
return err;
- /* if route being replaced has siblings, set tmp to
- * last one, otherwise tmp is current route. this is
- * used to set fib6_next for new route
- */
- if (iter->fib6_nsiblings)
- tmp = list_last_entry(&iter->fib6_siblings,
- struct fib6_info,
- fib6_siblings);
- else
- tmp = iter;
-
- /* insert new route */
atomic_inc(&rt->fib6_ref);
rcu_assign_pointer(rt->fib6_node, fn);
- rt->fib6_next = tmp->fib6_next;
+ rt->fib6_next = iter->fib6_next;
rcu_assign_pointer(*ins, rt);
-
if (!info->skip_notify)
inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ nsiblings = iter->fib6_nsiblings;
+ iter->fib6_node = NULL;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ if (rcu_access_pointer(fn->rr_ptr) == iter)
+ fn->rr_ptr = NULL;
+ fib6_info_release(iter);
- /* delete old route */
- rt = iter;
-
- if (rt->fib6_nsiblings) {
- struct fib6_info *tmp;
-
+ if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
- list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings,
- fib6_siblings) {
- iter->fib6_node = NULL;
- fib6_purge_rt(iter, fn, info->nl_net);
- if (rcu_access_pointer(fn->rr_ptr) == iter)
- fn->rr_ptr = NULL;
- fib6_info_release(iter);
-
- rt->fib6_nsiblings--;
- info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+ ins = &rt->fib6_next;
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
+ while (iter) {
+ if (iter->fib6_metric > rt->fib6_metric)
+ break;
+ if (rt6_qualify_for_ecmp(iter)) {
+ *ins = iter->fib6_next;
+ iter->fib6_node = NULL;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ if (rcu_access_pointer(fn->rr_ptr) == iter)
+ fn->rr_ptr = NULL;
+ fib6_info_release(iter);
+ nsiblings--;
+ info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+ } else {
+ ins = &iter->fib6_next;
+ }
+ iter = rcu_dereference_protected(*ins,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
}
+ WARN_ON(nsiblings != 0);
}
-
- WARN_ON(rt->fib6_nsiblings != 0);
-
- rt->fib6_node = NULL;
- fib6_purge_rt(rt, fn, info->nl_net);
- if (rcu_access_pointer(fn->rr_ptr) == rt)
- fn->rr_ptr = NULL;
- fib6_info_release(rt);
}
return 0;
static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ip6_tnl *t = netdev_priv(dev);
struct dst_entry *dst = skb_dst(skb);
struct net_device_stats *stats;
goto tx_err;
}
} else {
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
switch (skb->protocol) {
case htons(ETH_P_IP):
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
to->dev = from->dev;
to->mark = from->mark;
+ skb_copy_hash(to, from);
+
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
if (mtu < IPV6_MIN_MTU)
return -EINVAL;
cork->base.fragsize = mtu;
- cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0;
+ cork->base.gso_size = sk->sk_type == SOCK_DGRAM &&
+ sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0;
if (dst_allfrag(xfrm_dst_path(&rt->dst)))
cork->base.flags |= IPCORK_ALLFRAG;
max_headroom += 8;
mtu -= 8;
}
- if (skb->protocol == htons(ETH_P_IPV6)) {
- if (mtu < IPV6_MIN_MTU)
- mtu = IPV6_MIN_MTU;
- } else if (mtu < 576) {
- mtu = 576;
- }
+ mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
+ IPV6_MIN_MTU : IPV4_MIN_MTU);
skb_dst_update_pmtu(skb, mtu);
if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
goto tx_err_dst_release;
}
- skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
- skb_dst_set(skb, dst);
- skb->dev = skb_dst(skb)->dev;
-
mtu = dst_mtu(dst);
if (!skb->ignore_df && skb->len > mtu) {
skb_dst_update_pmtu(skb, mtu);
htonl(mtu));
}
- return -EMSGSIZE;
+ err = -EMSGSIZE;
+ goto tx_err_dst_release;
}
+ skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+ skb_dst_set(skb, dst);
+ skb->dev = skb_dst(skb)->dev;
+
err = dst_output(t->net, skb->sk, skb);
if (net_xmit_eval(err) == 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
+ struct ipv6_opt_hdr *new = NULL;
+
+ /* hop-by-hop / destination options are privileged option */
+ retv = -EPERM;
+ if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+ break;
/* remove any sticky options header with a zero option
* length, per RFC3542.
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
-
- /* hop-by-hop / destination options are privileged option */
- retv = -EPERM;
- if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
- break;
+ else {
+ new = memdup_user(optval, optlen);
+ if (IS_ERR(new)) {
+ retv = PTR_ERR(new);
+ break;
+ }
+ if (unlikely(ipv6_optlen(new) > optlen)) {
+ kfree(new);
+ goto e_inval;
+ }
+ }
opt = rcu_dereference_protected(np->opt,
lockdep_sock_is_held(sk));
- opt = ipv6_renew_options(sk, opt, optname,
- (struct ipv6_opt_hdr __user *)optval,
- optlen);
+ opt = ipv6_renew_options(sk, opt, optname, new);
+ kfree(new);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
- retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
- &psin6->sin6_addr);
+ retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface,
+ &psin6->sin6_addr,
+ MCAST_INCLUDE);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
int delta);
static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
struct inet6_dev *idev);
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+ const struct in6_addr *addr, unsigned int mode);
#define MLD_QRV_DEFAULT 2
/* RFC3810, 9.2. Query Interval */
return iv > 0 ? iv : 1;
}
-int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+static int __ipv6_sock_mc_join(struct sock *sk, int ifindex,
+ const struct in6_addr *addr, unsigned int mode)
{
struct net_device *dev = NULL;
struct ipv6_mc_socklist *mc_lst;
}
mc_lst->ifindex = dev->ifindex;
- mc_lst->sfmode = MCAST_EXCLUDE;
+ mc_lst->sfmode = mode;
rwlock_init(&mc_lst->sflock);
mc_lst->sflist = NULL;
* now add/increase the group membership on the device
*/
- err = ipv6_dev_mc_inc(dev, addr);
+ err = __ipv6_dev_mc_inc(dev, addr, mode);
if (err) {
sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
return 0;
}
+
+int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+ return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE);
+}
EXPORT_SYMBOL(ipv6_sock_mc_join);
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+ const struct in6_addr *addr, unsigned int mode)
+{
+ return __ipv6_sock_mc_join(sk, ifindex, addr, mode);
+}
+
/*
* socket leave on multicast group
*/
return rv;
}
-static void igmp6_group_added(struct ifmcaddr6 *mc)
+static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
{
struct net_device *dev = mc->idev->dev;
char buf[MAX_ADDR_LEN];
}
/* else v2 */
- mc->mca_crcount = mc->idev->mc_qrv;
+ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we
+ * should not send filter-mode change record as the mode
+ * should be from IN() to IN(A).
+ */
+ if (mode == MCAST_EXCLUDE)
+ mc->mca_crcount = mc->idev->mc_qrv;
+
mld_ifc_event(mc->idev);
}
spin_lock_bh(&im->mca_lock);
if (pmc) {
im->idev = pmc->idev;
- im->mca_crcount = idev->mc_qrv;
- im->mca_sfmode = pmc->mca_sfmode;
- if (pmc->mca_sfmode == MCAST_INCLUDE) {
+ if (im->mca_sfmode == MCAST_INCLUDE) {
im->mca_tomb = pmc->mca_tomb;
im->mca_sources = pmc->mca_sources;
for (psf = im->mca_sources; psf; psf = psf->sf_next)
- psf->sf_crcount = im->mca_crcount;
+ psf->sf_crcount = idev->mc_qrv;
+ } else {
+ im->mca_crcount = idev->mc_qrv;
}
in6_dev_put(pmc->idev);
kfree(pmc);
}
static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
- const struct in6_addr *addr)
+ const struct in6_addr *addr,
+ unsigned int mode)
{
struct ifmcaddr6 *mc;
refcount_set(&mc->mca_refcnt, 1);
spin_lock_init(&mc->mca_lock);
- /* initial mode is (EX, empty) */
- mc->mca_sfmode = MCAST_EXCLUDE;
- mc->mca_sfcount[MCAST_EXCLUDE] = 1;
+ mc->mca_sfmode = mode;
+ mc->mca_sfcount[mode] = 1;
if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
/*
* device multicast group inc (add if not found)
*/
-int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+ const struct in6_addr *addr, unsigned int mode)
{
struct ifmcaddr6 *mc;
struct inet6_dev *idev;
if (ipv6_addr_equal(&mc->mca_addr, addr)) {
mc->mca_users++;
write_unlock_bh(&idev->lock);
- ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0,
- NULL, 0);
+ ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0);
in6_dev_put(idev);
return 0;
}
}
- mc = mca_alloc(idev, addr);
+ mc = mca_alloc(idev, addr, mode);
if (!mc) {
write_unlock_bh(&idev->lock);
in6_dev_put(idev);
write_unlock_bh(&idev->lock);
mld_del_delrec(idev, mc);
- igmp6_group_added(mc);
+ igmp6_group_added(mc, mode);
ma_put(mc);
return 0;
}
+int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+{
+ return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE);
+}
+
/*
* device multicast group del
*/
psf_next = psf->sf_next;
- if (!is_in(pmc, psf, type, gdeleted, sdeleted)) {
+ if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) {
psf_prev = psf;
continue;
}
if (pmc->mca_sfcount[MCAST_EXCLUDE])
type = MLD2_CHANGE_TO_EXCLUDE;
else
- type = MLD2_CHANGE_TO_INCLUDE;
+ type = MLD2_ALLOW_NEW_SOURCES;
skb = add_grec(skb, pmc, type, 0, 0, 1);
spin_unlock_bh(&pmc->mca_lock);
}
mld_send_initial_cr(idev);
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
}
if (idev->mc_dad_count) {
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
if (idev->mc_ifc_count) {
idev->mc_ifc_count--;
if (idev->mc_ifc_count)
- mld_ifc_start_timer(idev, idev->mc_maxdelay);
+ mld_ifc_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
ipv6_mc_reset(idev);
for (i = idev->mc_list; i; i = i->next) {
mld_del_delrec(idev, i);
- igmp6_group_added(i);
+ igmp6_group_added(i, i->mca_sfmode);
}
read_unlock_bh(&idev->lock);
}
return;
}
}
- if (ndopts.nd_opts_nonce)
+ if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
inc = ipv6_addr_is_multicast(daddr);
return -ENOMEM;
j = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ipv6;
.checkentry = icmp6_checkentry,
.proto = IPPROTO_ICMPV6,
.family = NFPROTO_IPV6,
+ .me = THIS_MODULE,
},
};
if (hdr == NULL)
goto err_reg;
- net->nf_frag.sysctl.frags_hdr = hdr;
+ net->nf_frag_frags_hdr = hdr;
return 0;
err_reg:
{
struct ctl_table *table;
- table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
- unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+ table = net->nf_frag_frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->nf_frag_frags_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
fq->q.meat == fq->q.len &&
nf_ct_frag6_reasm(fq, skb, dev))
ret = 0;
+ else
+ skb_dst_drop(skb);
out_unlock:
spin_unlock_bh(&fq->q.lock);
* to a listener socket if there's one */
struct sock *sk2;
- sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto,
+ sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto,
&iph->saddr,
nf_tproxy_laddr6(skb, laddr, &iph->daddr),
hp->source,
EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6);
struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
const u8 protocol,
const struct in6_addr *saddr, const struct in6_addr *daddr,
const __be16 sport, const __be16 dport,
const enum nf_tproxy_lookup_t lookup_type)
{
struct sock *sk;
- struct tcphdr *tcph;
switch (protocol) {
- case IPPROTO_TCP:
+ case IPPROTO_TCP: {
+ struct tcphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, thoff,
+ sizeof(struct tcphdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
switch (lookup_type) {
case NF_TPROXY_LOOKUP_LISTENER:
- tcph = hp;
sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
- thoff + __tcp_hdrlen(tcph),
+ thoff + __tcp_hdrlen(hp),
saddr, sport,
daddr, ntohs(dport),
in->ifindex, 0);
BUG();
}
break;
+ }
case IPPROTO_UDP:
sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
}
#endif /* CONFIG_PROC_FS */
-/* Same as inet6_dgram_ops, sans udp_poll_mask. */
+/* Same as inet6_dgram_ops, sans udp_poll. */
const struct proto_ops inet6_sockraw_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll_mask = datagram_poll_mask, /* ok */
+ .poll = datagram_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
rt->dst.lastuse = jiffies;
}
+/* Caller must already hold reference to @from */
static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
- fib6_info_hold(from);
rcu_assign_pointer(rt->from, from);
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
- if (from->fib6_metrics != &dst_default_metrics) {
- rt->dst._metrics |= DST_METRICS_REFCOUNTED;
- refcount_inc(&from->fib6_metrics->refcnt);
- }
}
+/* Caller must already hold reference to @ort */
static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
{
struct net_device *dev = fib6_info_nh_dev(ort);
struct net_device *dev = rt->fib6_nh.nh_dev;
struct rt6_info *nrt;
+ if (!fib6_info_hold_safe(rt))
+ return NULL;
+
nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (nrt)
ip6_rt_copy_init(nrt, rt);
+ else
+ fib6_info_release(rt);
return nrt;
}
* Clone the route.
*/
+ if (!fib6_info_hold_safe(ort))
+ return NULL;
+
dev = ip6_rt_get_dev_rcu(ort);
rt = ip6_dst_alloc(dev_net(dev), dev, 0);
- if (!rt)
+ if (!rt) {
+ fib6_info_release(ort);
return NULL;
+ }
ip6_rt_copy_init(rt, ort);
rt->rt6i_flags |= RTF_CACHE;
struct net_device *dev;
struct rt6_info *pcpu_rt;
+ if (!fib6_info_hold_safe(rt))
+ return NULL;
+
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(rt);
pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
- if (!pcpu_rt)
+ if (!pcpu_rt) {
+ fib6_info_release(rt);
return NULL;
+ }
ip6_rt_copy_init(pcpu_rt, rt);
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
const struct in6_addr *daddr, *saddr;
struct rt6_info *rt6 = (struct rt6_info *)dst;
- if (rt6->rt6i_flags & RTF_LOCAL)
- return;
-
if (dst_metric_locked(dst, RTAX_MTU))
return;
out:
if (ret)
- dst_hold(&ret->dst);
+ ip6_hold_safe(net, &ret, true);
else
ret = ip6_create_rt_rcu(rt);
continue;
if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
rcu_read_unlock();
/* if gateway was specified only delete the one hop */
rcu_read_lock();
from = rcu_dereference(rt->from);
+ /* This fib6_info_hold() is safe here because we hold reference to rt
+ * and rt already holds reference to fib6_info.
+ */
fib6_info_hold(from);
rcu_read_unlock();
continue;
if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
break;
}
out:
ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
break;
}
- if (rt)
- fib6_info_hold(rt);
+ if (rt && !fib6_info_hold_safe(rt))
+ rt = NULL;
rcu_read_unlock();
return rt;
}
struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL;
if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!idev || idev->cnf.accept_ra != 2)) {
- fib6_info_hold(rt);
+ (!idev || idev->cnf.accept_ra != 2) &&
+ fib6_info_hold_safe(rt)) {
rcu_read_unlock();
ip6_del_rt(net, rt);
goto restart;
lockdep_is_held(&rt->fib6_table->tb6_lock));
while (iter) {
if (iter->fib6_metric == rt->fib6_metric &&
- iter->fib6_nsiblings)
+ rt6_qualify_for_ecmp(iter))
return iter;
iter = rcu_dereference_protected(iter->fib6_next,
lockdep_is_held(&rt->fib6_table->tb6_lock));
rt = NULL;
goto cleanup;
}
+ if (!rt6_qualify_for_ecmp(rt)) {
+ err = -EINVAL;
+ NL_SET_ERR_MSG(extack,
+ "Device only routes can not be added for IPv6 using the multipath API.");
+ fib6_info_release(rt);
+ goto cleanup;
+ }
rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
NLM_F_REPLACE);
- cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND;
nhn++;
}
return -ENOMEM;
for_each_possible_cpu(cpu) {
- tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ tfm = crypto_alloc_shash(algo->name, 0, 0);
if (IS_ERR(tfm))
return PTR_ERR(tfm);
p_tfm = per_cpu_ptr(algo->tfms, cpu);
if (do_flowlabel > 0) {
hash = skb_get_hash(skb);
- rol32(hash, 16);
+ hash = rol32(hash, 16);
flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
} else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) {
flowlabel = ip6_flowlabel(inner_hdr);
&tcp_hashinfo, NULL, 0,
&ipv6h->saddr,
th->source, &ipv6h->daddr,
- ntohs(th->source), tcp_v6_iif(skb),
+ ntohs(th->source),
+ tcp_v6_iif_l3_slave(skb),
tcp_v6_sdif(skb));
if (!sk1)
goto out;
reqsk_put(req);
goto discard_it;
}
+ if (tcp_checksum_complete(skb)) {
+ reqsk_put(req);
+ goto csum_error;
+ }
if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
skb, __tcp_hdrlen(th),
&ipv6_hdr(skb)->saddr, th->source,
&ipv6_hdr(skb)->daddr,
- ntohs(th->dest), tcp_v6_iif(skb),
+ ntohs(th->dest),
+ tcp_v6_iif_l3_slave(skb),
sdif);
if (sk2) {
struct inet_timewait_sock *tw = inet_twsk(sk);
return 0;
}
-static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == IUCV_LISTEN)
return iucv_accept_poll(sk);
.getname = iucv_sock_getname,
.sendmsg = iucv_sock_sendmsg,
.recvmsg = iucv_sock_recvmsg,
- .poll_mask = iucv_sock_poll_mask,
+ .poll = iucv_sock_poll,
.ioctl = sock_no_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
struct list_head *head;
int index = 0;
- /* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
- * so we set sk_state, otherwise epoll_wait always returns right away
- * with EPOLLHUP
+ /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
+ * we set sk_state, otherwise epoll_wait always returns right away with
+ * EPOLLHUP
*/
kcm->sk.sk_state = TCP_ESTABLISHED;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
/* Now the operations that really occur. */
.release = pfkey_release,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.sendmsg = pfkey_sendmsg,
.recvmsg = pfkey_recvmsg,
};
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip6_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet6_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
goto out_tunnel;
}
+ /* L2TPv2 only accepts PPP pseudo-wires */
+ if (tunnel->version == 2 && cfg.pw_type != L2TP_PWTYPE_PPP) {
+ ret = -EPROTONOSUPPORT;
+ goto out_tunnel;
+ }
+
if (tunnel->version > 2) {
if (info->attrs[L2TP_ATTR_DATA_SEQ])
cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]);
u32 session_id, peer_session_id;
bool drop_refcnt = false;
bool drop_tunnel = false;
+ bool new_session = false;
+ bool new_tunnel = false;
int ver = 2;
int fd;
.encap = L2TP_ENCAPTYPE_UDP,
.debug = 0,
};
+
+ /* Prevent l2tp_tunnel_register() from trying to set up
+ * a kernel socket.
+ */
+ if (fd < 0) {
+ error = -EBADF;
+ goto end;
+ }
+
error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
if (error < 0)
goto end;
goto end;
}
drop_tunnel = true;
+ new_tunnel = true;
}
} else {
/* Error if we can't find the tunnel */
session = l2tp_session_get(sock_net(sk), tunnel, session_id);
if (session) {
drop_refcnt = true;
+
+ if (session->pwtype != L2TP_PWTYPE_PPP) {
+ error = -EPROTOTYPE;
+ goto end;
+ }
+
ps = l2tp_session_priv(session);
/* Using a pre-existing session is fine as long as it hasn't
/* Default MTU must allow space for UDP/L2TP/PPP headers */
cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
cfg.mru = cfg.mtu;
+ cfg.pw_type = L2TP_PWTYPE_PPP;
session = l2tp_session_create(sizeof(struct pppol2tp_session),
tunnel, session_id,
goto end;
}
drop_refcnt = true;
+ new_session = true;
}
/* Special case: if source & dest session_id == 0x0000, this
session->name);
end:
+ if (error) {
+ if (new_session)
+ l2tp_session_delete(session);
+ if (new_tunnel)
+ l2tp_tunnel_delete(tunnel);
+ }
if (drop_refcnt)
l2tp_session_dec_refcount(session);
if (drop_tunnel)
l2tp_session_get(sock_net(sk), tunnel,
stats.session_id);
- if (session) {
- err = pppol2tp_session_ioctl(session, cmd,
- arg);
+ if (!session) {
+ err = -EBADR;
+ break;
+ }
+ if (session->pwtype != L2TP_PWTYPE_PPP) {
l2tp_session_dec_refcount(session);
- } else {
err = -EBADR;
+ break;
}
+
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+ l2tp_session_dec_refcount(session);
break;
}
#ifdef CONFIG_XFRM
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppol2tp_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = pppol2tp_setsockopt,
.socketpair = sock_no_socketpair,
.accept = llc_ui_accept,
.getname = llc_ui_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = llc_ui_ioctl,
.listen = llc_ui_listen,
.shutdown = llc_ui_shutdown,
rcu_read_lock_bh();
sap = __llc_sap_find(sap_value);
- if (sap)
- llc_sap_hold(sap);
+ if (!sap || !llc_sap_hold_safe(sap))
+ sap = NULL;
rcu_read_unlock_bh();
return sap;
}
ieee80211_led_init(local);
+ result = ieee80211_txq_setup_flows(local);
+ if (result)
+ goto fail_flows;
+
rtnl_lock();
result = ieee80211_init_rate_ctrl_alg(local,
rtnl_unlock();
- result = ieee80211_txq_setup_flows(local);
- if (result)
- goto fail_flows;
-
#ifdef CONFIG_INET
local->ifa_notifier.notifier_call = ieee80211_ifa_changed;
result = register_inetaddr_notifier(&local->ifa_notifier);
#if defined(CONFIG_INET) || defined(CONFIG_IPV6)
fail_ifa:
#endif
- ieee80211_txq_teardown_flows(local);
- fail_flows:
rtnl_lock();
rate_control_deinitialize(local);
ieee80211_remove_interfaces(local);
rtnl_unlock();
ieee80211_led_exit(local);
ieee80211_wep_free(local);
+ ieee80211_txq_teardown_flows(local);
+ fail_flows:
destroy_workqueue(local->workqueue);
fail_workqueue:
wiphy_unregister(local->hw.wiphy);
sdata->control_port_over_nl80211)) {
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
- struct ethhdr *ehdr = eth_hdr(skb);
- cfg80211_rx_control_port(dev, skb->data, skb->len,
- ehdr->h_source,
- be16_to_cpu(skb->protocol), noencrypt);
+ cfg80211_rx_control_port(dev, skb, noencrypt);
dev_kfree_skb(skb);
} else {
/* deliver to local stack */
skb_reset_network_header(skb);
skb_reset_mac_header(skb);
+ local_bh_disable();
__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+ local_bh_enable();
return 0;
}
if (!sta->uploaded)
continue;
- if (sta->sdata->vif.type != NL80211_IFTYPE_AP)
+ if (sta->sdata->vif.type != NL80211_IFTYPE_AP &&
+ sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
continue;
for (state = IEEE80211_STA_NOTEXIST;
ncm->data[2] = data;
ncm->data[4] = ntohl(lsc->oem_status);
- netdev_info(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
- nc->id, data & 0x1 ? "up" : "down");
+ netdev_dbg(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
+ nc->id, data & 0x1 ? "up" : "down");
chained = !list_empty(&nc->link);
state = nc->state;
hncdsc = (struct ncsi_aen_hncdsc_pkt *)h;
ncm->data[3] = ntohl(hncdsc->status);
spin_unlock_irqrestore(&nc->lock, flags);
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: host driver %srunning on channel %u\n",
- ncm->data[3] & 0x1 ? "" : "not ", nc->id);
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: host driver %srunning on channel %u\n",
+ ncm->data[3] & 0x1 ? "" : "not ", nc->id);
return 0;
}
}
break;
case ncsi_dev_state_config_done:
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: channel %u config done\n", nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n",
+ nc->id);
spin_lock_irqsave(&nc->lock, flags);
if (nc->reconfigure_needed) {
/* This channel's configuration has been updated
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_printk(KERN_DEBUG, dev,
- "Dirty NCSI channel state reset\n");
+ netdev_dbg(dev, "Dirty NCSI channel state reset\n");
ncsi_process_next_channel(ndp);
break;
}
} else {
hot_nc = NULL;
nc->state = NCSI_CHANNEL_INACTIVE;
- netdev_warn(ndp->ndev.dev,
- "NCSI: channel %u link down after config\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: channel %u link down after config\n",
+ nc->id);
}
spin_unlock_irqrestore(&nc->lock, flags);
}
ncm = &found->modes[NCSI_MODE_LINK];
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: Channel %u added to queue (link %s)\n",
- found->id, ncm->data[2] & 0x1 ? "up" : "down");
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: Channel %u added to queue (link %s)\n",
+ found->id, ncm->data[2] & 0x1 ? "up" : "down");
out:
spin_lock_irqsave(&ndp->lock, flags);
switch (old_state) {
case NCSI_CHANNEL_INACTIVE:
ndp->ndev.state = ncsi_dev_state_config;
- netdev_info(ndp->ndev.dev, "NCSI: configuring channel %u\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: configuring channel %u\n",
+ nc->id);
ncsi_configure_channel(ndp);
break;
case NCSI_CHANNEL_ACTIVE:
ndp->ndev.state = ncsi_dev_state_suspend;
- netdev_info(ndp->ndev.dev, "NCSI: suspending channel %u\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: suspending channel %u\n",
+ nc->id);
ncsi_suspend_channel(ndp);
break;
default:
return ncsi_choose_active_channel(ndp);
}
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: No more channels to process\n");
ncsi_report_link(ndp, false);
return -ENODEV;
}
if ((ndp->ndev.state & 0xff00) ==
ncsi_dev_state_config ||
!list_empty(&nc->link)) {
- netdev_printk(KERN_DEBUG, nd->dev,
- "NCSI: channel %p marked dirty\n",
- nc);
+ netdev_dbg(nd->dev,
+ "NCSI: channel %p marked dirty\n",
+ nc);
nc->reconfigure_needed = true;
}
spin_unlock_irqrestore(&nc->lock, flags);
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_printk(KERN_DEBUG, nd->dev,
- "NCSI: kicked channel %p\n", nc);
+ netdev_dbg(nd->dev, "NCSI: kicked channel %p\n", nc);
n++;
}
}
list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) {
n_vids++;
if (vlan->vid == vid) {
- netdev_printk(KERN_DEBUG, dev,
- "NCSI: vid %u already registered\n", vid);
+ netdev_dbg(dev, "NCSI: vid %u already registered\n",
+ vid);
return 0;
}
}
vlan->vid = vid;
list_add_rcu(&vlan->list, &ndp->vlan_vids);
- netdev_printk(KERN_DEBUG, dev, "NCSI: Added new vid %u\n", vid);
+ netdev_dbg(dev, "NCSI: Added new vid %u\n", vid);
found = ncsi_kick_channels(ndp) != 0;
/* Remove the VLAN id from our internal list */
list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list)
if (vlan->vid == vid) {
- netdev_printk(KERN_DEBUG, dev,
- "NCSI: vid %u found, removing\n", vid);
+ netdev_dbg(dev, "NCSI: vid %u found, removing\n", vid);
list_del_rcu(&vlan->list);
found = true;
kfree(vlan);
}
}
- netdev_printk(KERN_DEBUG, ndp->ndev.dev, "NCSI: Stopping device\n");
+ netdev_dbg(ndp->ndev.dev, "NCSI: Stopping device\n");
ncsi_report_link(ndp, true);
}
EXPORT_SYMBOL_GPL(ncsi_stop_dev);
if NF_TABLES
+config NF_TABLES_SET
+ tristate "Netfilter nf_tables set infrastructure"
+ help
+ This option enables the nf_tables set infrastructure that allows to
+ look up for elements in a set and to build one-way mappings between
+ matchings and actions.
+
config NF_TABLES_INET
depends on IPV6
select NF_TABLES_IPV4
This option adds the "flow_offload" expression that you can use to
choose what flows are placed into the hardware.
-config NFT_SET_RBTREE
- tristate "Netfilter nf_tables rbtree set module"
- help
- This option adds the "rbtree" set type (Red Black tree) that is used
- to build interval-based sets.
-
-config NFT_SET_HASH
- tristate "Netfilter nf_tables hash set module"
- help
- This option adds the "hash" set type that is used to build one-way
- mappings between matchings and actions.
-
-config NFT_SET_BITMAP
- tristate "Netfilter nf_tables bitmap set module"
- help
- This option adds the "bitmap" set type that is used to build sets
- whose keys are smaller or equal to 16 bits.
-
config NFT_COUNTER
tristate "Netfilter nf_tables counter module"
help
nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
+nf_tables_set-objs := nf_tables_set_core.o \
+ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
+
obj-$(CONFIG_NF_TABLES) += nf_tables.o
+obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o
obj-$(CONFIG_NFT_COMPAT) += nft_compat.o
obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o
obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o
obj-$(CONFIG_NFT_QUOTA) += nft_quota.o
obj-$(CONFIG_NFT_REJECT) += nft_reject.o
obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
-obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o
-obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o
-obj-$(CONFIG_NFT_SET_BITMAP) += nft_set_bitmap.o
obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
obj-$(CONFIG_NFT_LOG) += nft_log.o
obj-$(CONFIG_NFT_MASQ) += nft_masq.o
pr_debug("Create set %s with family %s\n",
set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
-#ifndef IP_SET_PROTO_UNDEF
+#ifdef IP_SET_PROTO_UNDEF
+ if (set->family != NFPROTO_UNSPEC)
+ return -IPSET_ERR_INVALID_FAMILY;
+#else
if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
return -IPSET_ERR_INVALID_FAMILY;
#endif
* For now only for NAT!
*/
ip_vs_rs_hash(ipvs, dest);
+ /* FTP-NAT requires conntrack for mangling */
+ if (svc->port == FTPPORT)
+ ip_vs_register_conntrack(svc);
}
atomic_set(&dest->conn_flags, conn_flags);
*/
static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
{
+ ip_vs_unregister_conntrack(svc);
/* Hold svc to avoid double release from dest_trash */
atomic_inc(&svc->refcnt);
/*
bool new_rt_is_local)
{
bool rt_mode_allow_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
- bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
+ bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_NON_LOCAL);
bool rt_mode_allow_redirect = !!(rt_mode & IP_VS_RT_MODE_RDR);
bool source_is_loopback;
bool old_rt_is_local;
struct nf_conncount_tuple {
struct hlist_node node;
struct nf_conntrack_tuple tuple;
+ struct nf_conntrack_zone zone;
+ int cpu;
+ u32 jiffies32;
};
struct nf_conncount_rb {
}
bool nf_conncount_add(struct hlist_head *head,
- const struct nf_conntrack_tuple *tuple)
+ const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_zone *zone)
{
struct nf_conncount_tuple *conn;
if (conn == NULL)
return false;
conn->tuple = *tuple;
+ conn->zone = *zone;
+ conn->cpu = raw_smp_processor_id();
+ conn->jiffies32 = (u32)jiffies;
hlist_add_head(&conn->node, head);
return true;
}
EXPORT_SYMBOL_GPL(nf_conncount_add);
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ unsigned long a, b;
+ int cpu = raw_smp_processor_id();
+ __s32 age;
+
+ found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+ if (found)
+ return found;
+ b = conn->jiffies32;
+ a = (u32)jiffies;
+
+ /* conn might have been added just before by another cpu and
+ * might still be unconfirmed. In this case, nf_conntrack_find()
+ * returns no result. Thus only evict if this cpu added the
+ * stale entry or if the entry is older than two jiffies.
+ */
+ age = a - b;
+ if (conn->cpu == cpu || age >= 2) {
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return ERR_PTR(-EAGAIN);
+}
+
unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_zone *zone,
{
const struct nf_conntrack_tuple_hash *found;
struct nf_conncount_tuple *conn;
- struct hlist_node *n;
struct nf_conn *found_ct;
+ struct hlist_node *n;
unsigned int length = 0;
*addit = tuple ? true : false;
/* check the saved connections */
hlist_for_each_entry_safe(conn, n, head, node) {
- found = nf_conntrack_find_get(net, zone, &conn->tuple);
- if (found == NULL) {
- hlist_del(&conn->node);
- kmem_cache_free(conncount_conn_cachep, conn);
+ found = find_or_evict(net, conn);
+ if (IS_ERR(found)) {
+ /* Not found, but might be about to be confirmed */
+ if (PTR_ERR(found) == -EAGAIN) {
+ length++;
+ if (!tuple)
+ continue;
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+ nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+ nf_ct_zone_id(zone, zone->dir))
+ *addit = false;
+ }
continue;
}
found_ct = nf_ct_tuplehash_to_ctrack(found);
- if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple)) {
+ if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
+ nf_ct_zone_equal(found_ct, zone, zone->dir)) {
/*
* Just to be sure we have it only once in the list.
* We should not see tuples twice unless someone hooks
if (!addit)
return count;
- if (!nf_conncount_add(&rbconn->hhead, tuple))
+ if (!nf_conncount_add(&rbconn->hhead, tuple, zone))
return 0; /* hotdrop */
return count + 1;
}
conn->tuple = *tuple;
+ conn->zone = *zone;
memcpy(rbconn->key, key, sizeof(u32) * keylen);
INIT_HLIST_HEAD(&rbconn->hhead);
return -EOPNOTSUPP;
/* On boot, we can set this without any fancy locking. */
- if (!nf_conntrack_htable_size)
+ if (!nf_conntrack_hash)
return param_set_uint(val, kp);
rc = kstrtouint(val, 0, &hashsize);
nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
nf_ct_iterate_destroy(unhelp, me);
+
+ /* Maybe someone has gotten the helper already when unhelp above.
+ * So need to wait it.
+ */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
}
nfnl_lock(NFNL_SUBSYS_CTNETLINK);
rcu_read_lock();
- if (nat_hook->parse_nat_setup)
+ nat_hook = rcu_dereference(nf_nat_hook);
+ if (nat_hook)
return -EAGAIN;
#endif
return -EOPNOTSUPP;
* We currently ignore Sync packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
[DCCP_PKT_SYNCACK] = {
/*
* We currently ignore SyncAck packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
},
[CT_DCCP_ROLE_SERVER] = {
* We currently ignore Sync packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
[DCCP_PKT_SYNCACK] = {
/*
* We currently ignore SyncAck packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
},
};
if (write) {
struct ctl_table tmp = *table;
+ /* proc_dostring() can append to existing strings, so we need to
+ * initialize it as an empty string.
+ */
+ buf[0] = '\0';
tmp.data = buf;
r = proc_dostring(&tmp, write, buffer, lenp, ppos);
if (r)
rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
mutex_unlock(&nf_log_mutex);
} else {
+ struct ctl_table tmp = *table;
+
+ tmp.data = buf;
mutex_lock(&nf_log_mutex);
logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
- table->data = "NONE";
+ strlcpy(buf, "NONE", sizeof(buf));
else
- table->data = logger->name;
- r = proc_dostring(table, write, buffer, lenp, ppos);
+ strlcpy(buf, logger->name, sizeof(buf));
mutex_unlock(&nf_log_mutex);
+ r = proc_dostring(&tmp, write, buffer, lenp, ppos);
}
return r;
{
ctx->net = net;
ctx->family = family;
+ ctx->level = 0;
ctx->table = table;
ctx->chain = chain;
ctx->nla = nla;
struct nft_base_chain *basechain;
struct nft_stats *stats = NULL;
struct nft_chain_hook hook;
- const struct nlattr *name;
struct nf_hook_ops *ops;
struct nft_trans *trans;
int err;
return PTR_ERR(stats);
}
+ err = -ENOMEM;
trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
sizeof(struct nft_trans_chain));
- if (trans == NULL) {
- free_percpu(stats);
- return -ENOMEM;
- }
+ if (trans == NULL)
+ goto err;
nft_trans_chain_stats(trans) = stats;
nft_trans_chain_update(trans) = true;
else
nft_trans_chain_policy(trans) = -1;
- name = nla[NFTA_CHAIN_NAME];
- if (nla[NFTA_CHAIN_HANDLE] && name) {
- nft_trans_chain_name(trans) =
- nla_strdup(name, GFP_KERNEL);
- if (!nft_trans_chain_name(trans)) {
- kfree(trans);
- free_percpu(stats);
- return -ENOMEM;
+ if (nla[NFTA_CHAIN_HANDLE] &&
+ nla[NFTA_CHAIN_NAME]) {
+ struct nft_trans *tmp;
+ char *name;
+
+ err = -ENOMEM;
+ name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+ if (!name)
+ goto err;
+
+ err = -EEXIST;
+ list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) {
+ if (tmp->msg_type == NFT_MSG_NEWCHAIN &&
+ tmp->ctx.table == table &&
+ nft_trans_chain_update(tmp) &&
+ nft_trans_chain_name(tmp) &&
+ strcmp(name, nft_trans_chain_name(tmp)) == 0) {
+ kfree(name);
+ goto err;
+ }
}
+
+ nft_trans_chain_name(trans) = name;
}
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
+err:
+ free_percpu(stats);
+ kfree(trans);
+ return err;
}
static int nf_tables_newchain(struct net *net, struct sock *nlsk,
return skb->len;
}
+static int nf_tables_dump_rules_start(struct netlink_callback *cb)
+{
+ const struct nlattr * const *nla = cb->data;
+ struct nft_rule_dump_ctx *ctx = NULL;
+
+ if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
+ ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (nla[NFTA_RULE_TABLE]) {
+ ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
+ GFP_ATOMIC);
+ if (!ctx->table) {
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ }
+ if (nla[NFTA_RULE_CHAIN]) {
+ ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
+ GFP_ATOMIC);
+ if (!ctx->chain) {
+ kfree(ctx->table);
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ }
+ }
+
+ cb->data = ctx;
+ return 0;
+}
+
static int nf_tables_dump_rules_done(struct netlink_callback *cb)
{
struct nft_rule_dump_ctx *ctx = cb->data;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start= nf_tables_dump_rules_start,
.dump = nf_tables_dump_rules,
.done = nf_tables_dump_rules_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
- struct nft_rule_dump_ctx *ctx;
-
- ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
- if (!ctx)
- return -ENOMEM;
-
- if (nla[NFTA_RULE_TABLE]) {
- ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
- GFP_ATOMIC);
- if (!ctx->table) {
- kfree(ctx);
- return -ENOMEM;
- }
- }
- if (nla[NFTA_RULE_CHAIN]) {
- ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
- GFP_ATOMIC);
- if (!ctx->chain) {
- kfree(ctx->table);
- kfree(ctx);
- return -ENOMEM;
- }
- }
- c.data = ctx;
- }
-
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
struct nft_rule *rule;
int err;
+ if (ctx->level == NFT_JUMP_STACK_SIZE)
+ return -EMLINK;
+
list_for_each_entry(rule, &chain->rules, list) {
if (!nft_is_active_next(ctx->net, rule))
continue;
u32 id = ntohl(nla_get_be32(nla));
list_for_each_entry(trans, &net->nft.commit_list, list) {
- struct nft_set *set = nft_trans_set(trans);
+ if (trans->msg_type == NFT_MSG_NEWSET) {
+ struct nft_set *set = nft_trans_set(trans);
- if (trans->msg_type == NFT_MSG_NEWSET &&
- id == nft_trans_set_id(trans) &&
- nft_active_genmask(set, genmask))
- return set;
+ if (id == nft_trans_set_id(trans) &&
+ nft_active_genmask(set, genmask))
+ return set;
+ }
}
return ERR_PTR(-ENOENT);
}
return skb->len;
}
+static int nf_tables_dump_sets_start(struct netlink_callback *cb)
+{
+ struct nft_ctx *ctx_dump = NULL;
+
+ ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC);
+ if (ctx_dump == NULL)
+ return -ENOMEM;
+
+ cb->data = ctx_dump;
+ return 0;
+}
+
static int nf_tables_dump_sets_done(struct netlink_callback *cb)
{
kfree(cb->data);
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_sets_start,
.dump = nf_tables_dump_sets,
.done = nf_tables_dump_sets_done,
+ .data = &ctx,
.module = THIS_MODULE,
};
- struct nft_ctx *ctx_dump;
-
- ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC);
- if (ctx_dump == NULL)
- return -ENOMEM;
-
- *ctx_dump = ctx;
- c.data = ctx_dump;
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
return -ENOSPC;
}
+static int nf_tables_dump_set_start(struct netlink_callback *cb)
+{
+ struct nft_set_dump_ctx *dump_ctx = cb->data;
+
+ cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC);
+
+ return cb->data ? 0 : -ENOMEM;
+}
+
static int nf_tables_dump_set_done(struct netlink_callback *cb)
{
kfree(cb->data);
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_set_start,
.dump = nf_tables_dump_set,
.done = nf_tables_dump_set_done,
.module = THIS_MODULE,
};
- struct nft_set_dump_ctx *dump_ctx;
-
- dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC);
- if (!dump_ctx)
- return -ENOMEM;
-
- dump_ctx->set = set;
- dump_ctx->ctx = ctx;
+ struct nft_set_dump_ctx dump_ctx = {
+ .set = set,
+ .ctx = ctx,
+ };
- c.data = dump_ctx;
+ c.data = &dump_ctx;
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
return skb->len;
}
-static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+static int nf_tables_dump_obj_start(struct netlink_callback *cb)
{
- struct nft_obj_filter *filter = cb->data;
+ const struct nlattr * const *nla = cb->data;
+ struct nft_obj_filter *filter = NULL;
- if (filter) {
- kfree(filter->table);
- kfree(filter);
+ if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) {
+ filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+ if (!filter)
+ return -ENOMEM;
+
+ if (nla[NFTA_OBJ_TABLE]) {
+ filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
+ if (!filter->table) {
+ kfree(filter);
+ return -ENOMEM;
+ }
+ }
+
+ if (nla[NFTA_OBJ_TYPE])
+ filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
}
+ cb->data = filter;
return 0;
}
-static struct nft_obj_filter *
-nft_obj_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_obj_done(struct netlink_callback *cb)
{
- struct nft_obj_filter *filter;
-
- filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
- if (!filter)
- return ERR_PTR(-ENOMEM);
+ struct nft_obj_filter *filter = cb->data;
- if (nla[NFTA_OBJ_TABLE]) {
- filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
- if (!filter->table) {
- kfree(filter);
- return ERR_PTR(-ENOMEM);
- }
+ if (filter) {
+ kfree(filter->table);
+ kfree(filter);
}
- if (nla[NFTA_OBJ_TYPE])
- filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- return filter;
+ return 0;
}
/* called with rcu_read_lock held */
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_obj_start,
.dump = nf_tables_dump_obj,
.done = nf_tables_dump_obj_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_OBJ_TABLE] ||
- nla[NFTA_OBJ_TYPE]) {
- struct nft_obj_filter *filter;
-
- filter = nft_obj_filter_alloc(nla);
- if (IS_ERR(filter))
- return -ENOMEM;
-
- c.data = filter;
- }
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
flowtable->ops[i].priv = &flowtable->data;
flowtable->ops[i].hook = flowtable->data.type->hook;
flowtable->ops[i].dev = dev_array[i];
- flowtable->dev_name[i] = kstrdup(dev_array[i]->name,
- GFP_KERNEL);
}
return err;
err6:
i = flowtable->ops_len;
err5:
- for (k = i - 1; k >= 0; k--) {
- kfree(flowtable->dev_name[k]);
+ for (k = i - 1; k >= 0; k--)
nf_unregister_net_hook(net, &flowtable->ops[k]);
- }
kfree(flowtable->ops);
err4:
goto nla_put_failure;
for (i = 0; i < flowtable->ops_len; i++) {
- if (flowtable->dev_name[i][0] &&
- nla_put_string(skb, NFTA_DEVICE_NAME,
- flowtable->dev_name[i]))
+ const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev);
+
+ if (dev &&
+ nla_put_string(skb, NFTA_DEVICE_NAME, dev->name))
goto nla_put_failure;
}
nla_nest_end(skb, nest_devs);
return skb->len;
}
-static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
+static int nf_tables_dump_flowtable_start(struct netlink_callback *cb)
{
- struct nft_flowtable_filter *filter = cb->data;
+ const struct nlattr * const *nla = cb->data;
+ struct nft_flowtable_filter *filter = NULL;
- if (!filter)
- return 0;
+ if (nla[NFTA_FLOWTABLE_TABLE]) {
+ filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+ if (!filter)
+ return -ENOMEM;
- kfree(filter->table);
- kfree(filter);
+ filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
+ GFP_ATOMIC);
+ if (!filter->table) {
+ kfree(filter);
+ return -ENOMEM;
+ }
+ }
+ cb->data = filter;
return 0;
}
-static struct nft_flowtable_filter *
-nft_flowtable_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
{
- struct nft_flowtable_filter *filter;
+ struct nft_flowtable_filter *filter = cb->data;
- filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
if (!filter)
- return ERR_PTR(-ENOMEM);
+ return 0;
- if (nla[NFTA_FLOWTABLE_TABLE]) {
- filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
- GFP_ATOMIC);
- if (!filter->table) {
- kfree(filter);
- return ERR_PTR(-ENOMEM);
- }
- }
- return filter;
+ kfree(filter->table);
+ kfree(filter);
+
+ return 0;
}
/* called with rcu_read_lock held */
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_flowtable_start,
.dump = nf_tables_dump_flowtable,
.done = nf_tables_dump_flowtable_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_FLOWTABLE_TABLE]) {
- struct nft_flowtable_filter *filter;
-
- filter = nft_flowtable_filter_alloc(nla);
- if (IS_ERR(filter))
- return -ENOMEM;
-
- c.data = filter;
- }
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
kfree(flowtable->name);
flowtable->data.type->free(&flowtable->data);
module_put(flowtable->data.type->owner);
+ kfree(flowtable);
}
static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
continue;
nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
- flowtable->dev_name[i][0] = '\0';
flowtable->ops[i].dev = NULL;
break;
}
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct nft_flowtable *flowtable;
struct nft_table *table;
+ struct net *net;
if (event != NETDEV_UNREGISTER)
return 0;
+ net = maybe_get_net(dev_net(dev));
+ if (!net)
+ return 0;
+
nfnl_lock(NFNL_SUBSYS_NFTABLES);
- list_for_each_entry(table, &dev_net(dev)->nft.tables, list) {
+ list_for_each_entry(table, &net->nft.tables, list) {
list_for_each_entry(flowtable, &table->flowtables, list) {
nft_flowtable_event(event, dev, flowtable);
}
}
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-
+ put_net(net);
return NOTIFY_DONE;
}
case NFT_MSG_DELTABLE:
nf_tables_table_destroy(&trans->ctx);
break;
+ case NFT_MSG_NEWCHAIN:
+ kfree(nft_trans_chain_name(trans));
+ break;
case NFT_MSG_DELCHAIN:
nf_tables_chain_destroy(&trans->ctx);
break;
nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
break;
case NFT_MSG_NEWCHAIN:
- if (nft_trans_chain_update(trans))
+ if (nft_trans_chain_update(trans)) {
nft_chain_commit_update(trans);
- else
+ nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+ /* trans destroyed after rcu grace period */
+ } else {
nft_clear(net, trans->ctx.chain);
-
- nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
- nft_trans_destroy(trans);
+ nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+ nft_trans_destroy(trans);
+ }
break;
case NFT_MSG_DELCHAIN:
nft_chain_del(trans->ctx.chain);
kfree(trans);
}
-static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+static int __nf_tables_abort(struct net *net)
{
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
case NFT_MSG_NEWCHAIN:
if (nft_trans_chain_update(trans)) {
free_percpu(nft_trans_chain_stats(trans));
-
+ kfree(nft_trans_chain_name(trans));
nft_trans_destroy(trans);
} else {
trans->ctx.table->use--;
nft_validate_state_update(net, NFT_VALIDATE_SKIP);
}
+static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+{
+ return __nf_tables_abort(net);
+}
+
static bool nf_tables_valid_genid(struct net *net, u32 genid)
{
return net->nft.base_seq == genid;
err = nf_tables_check_loops(ctx, data->verdict.chain);
if (err < 0)
return err;
-
- if (ctx->chain->level + 1 >
- data->verdict.chain->level) {
- if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
- return -EMLINK;
- data->verdict.chain->level = ctx->chain->level + 1;
- }
}
return 0;
static void __net_exit nf_tables_exit_net(struct net *net)
{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ if (!list_empty(&net->nft.commit_list))
+ __nf_tables_abort(net);
__nft_release_tables(net);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
WARN_ON_ONCE(!list_empty(&net->nft.tables));
- WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
}
static struct pernet_operations nf_tables_net_ops = {
static void __exit nf_tables_module_exit(void)
{
- unregister_pernet_subsys(&nf_tables_net_ops);
nfnetlink_subsys_unregister(&nf_tables_subsys);
unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
+ nft_chain_filter_fini();
+ unregister_pernet_subsys(&nf_tables_net_ops);
rcu_barrier();
nf_tables_core_module_exit();
kfree(info);
- nft_chain_filter_fini();
}
module_init(nf_tables_module_init);
switch (regs.verdict.code) {
case NFT_JUMP:
- BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
+ if (WARN_ON_ONCE(stackptr >= NFT_JUMP_STACK_SIZE))
+ return NF_DROP;
jumpstack[stackptr].chain = chain;
jumpstack[stackptr].rules = rules + 1;
stackptr++;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <net/netfilter/nf_tables_core.h>
+
+static int __init nf_tables_set_module_init(void)
+{
+ nft_register_set(&nft_set_hash_fast_type);
+ nft_register_set(&nft_set_hash_type);
+ nft_register_set(&nft_set_rhash_type);
+ nft_register_set(&nft_set_bitmap_type);
+ nft_register_set(&nft_set_rbtree_type);
+
+ return 0;
+}
+
+static void __exit nf_tables_set_module_exit(void)
+{
+ nft_unregister_set(&nft_set_rbtree_type);
+ nft_unregister_set(&nft_set_bitmap_type);
+ nft_unregister_set(&nft_set_rhash_type);
+ nft_unregister_set(&nft_set_hash_type);
+ nft_unregister_set(&nft_set_hash_fast_type);
+}
+
+module_init(nf_tables_set_module_init);
+module_exit(nf_tables_set_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFT_SET();
*/
if (err == -EAGAIN) {
status |= NFNL_BATCH_REPLAY;
- goto next;
+ goto done;
}
}
ack:
if (err)
status |= NFNL_BATCH_FAILURE;
}
-next:
+
msglen = NLMSG_ALIGN(nlh->nlmsg_len);
if (msglen > skb->len)
msglen = skb->len;
}
done:
if (status & NFNL_BATCH_REPLAY) {
- ss->abort(net, oskb);
+ const struct nfnetlink_subsystem *ss2;
+
+ ss2 = nfnl_dereference_protected(subsys_id);
+ if (ss2 == ss)
+ ss->abort(net, oskb);
nfnl_err_reset(&err_list);
nfnl_unlock(subsys_id);
kfree_skb(skb);
static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
[NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) },
[NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) },
+ [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 },
+ [NFQA_CFG_MASK] = { .type = NLA_U32 },
+ [NFQA_CFG_FLAGS] = { .type = NLA_U32 },
};
static const struct nf_queue_handler nfqh = {
event != NETDEV_CHANGENAME)
return NOTIFY_DONE;
+ ctx.net = maybe_get_net(ctx.net);
+ if (!ctx.net)
+ return NOTIFY_DONE;
+
nfnl_lock(NFNL_SUBSYS_NFTABLES);
list_for_each_entry(table, &ctx.net->nft.tables, list) {
if (table->family != NFPROTO_NETDEV)
}
}
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ put_net(ctx.net);
return NOTIFY_DONE;
}
rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV]));
family = ctx->family;
+ if (strcmp(tg_name, XT_ERROR_TARGET) == 0 ||
+ strcmp(tg_name, XT_STANDARD_TARGET) == 0 ||
+ strcmp(tg_name, "standard") == 0)
+ return ERR_PTR(-EINVAL);
+
/* Re-use the existing target if it's already loaded. */
list_for_each_entry(nft_target, &nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
+ if (!target->target)
+ continue;
+
if (nft_target_cmp(target, tg_name, rev, family))
return &nft_target->ops;
}
if (IS_ERR(target))
return ERR_PTR(-ENOENT);
+ if (!target->target) {
+ err = -EINVAL;
+ goto err;
+ }
+
if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) {
err = -EINVAL;
goto err;
if (!addit)
goto out;
- if (!nf_conncount_add(&priv->hhead, tuple_ptr)) {
+ if (!nf_conncount_add(&priv->hhead, tuple_ptr, zone)) {
regs->verdict.code = NF_DROP;
spin_unlock_bh(&priv->lock);
return;
goto err1;
set->ops->gc_init(set);
}
-
- } else if (set->flags & NFT_SET_EVAL)
- return -EINVAL;
+ }
nft_set_ext_prepare(&priv->tmpl);
nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen);
const struct nft_data **d)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ struct nft_ctx *pctx = (struct nft_ctx *)ctx;
const struct nft_data *data;
int err;
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
+ pctx->level++;
err = nft_chain_validate(ctx, data->verdict.chain);
if (err < 0)
return err;
+ pctx->level--;
break;
default:
break;
struct nft_set_elem *elem)
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+ struct nft_ctx *pctx = (struct nft_ctx *)ctx;
const struct nft_data *data;
+ int err;
if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
*nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
- return nft_chain_validate(ctx, data->verdict.chain);
+ pctx->level++;
+ err = nft_chain_validate(ctx, data->verdict.chain);
+ if (err < 0)
+ return err;
+ pctx->level--;
+ break;
default:
- return 0;
+ break;
}
+
+ return 0;
}
static int nft_lookup_validate(const struct nft_ctx *ctx,
return true;
}
-static struct nft_set_type nft_bitmap_type __read_mostly = {
+struct nft_set_type nft_set_bitmap_type __read_mostly = {
.owner = THIS_MODULE,
.ops = {
.privsize = nft_bitmap_privsize,
.get = nft_bitmap_get,
},
};
-
-static int __init nft_bitmap_module_init(void)
-{
- return nft_register_set(&nft_bitmap_type);
-}
-
-static void __exit nft_bitmap_module_exit(void)
-{
- nft_unregister_set(&nft_bitmap_type);
-}
-
-module_init(nft_bitmap_module_init);
-module_exit(nft_bitmap_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
-MODULE_ALIAS_NFT_SET();
struct nft_rhash *priv = nft_set_priv(set);
cancel_delayed_work_sync(&priv->gc_work);
+ rcu_barrier();
rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
(void *)set);
}
return true;
}
-static struct nft_set_type nft_rhash_type __read_mostly = {
+struct nft_set_type nft_set_rhash_type __read_mostly = {
.owner = THIS_MODULE,
.features = NFT_SET_MAP | NFT_SET_OBJECT |
NFT_SET_TIMEOUT | NFT_SET_EVAL,
},
};
-static struct nft_set_type nft_hash_type __read_mostly = {
+struct nft_set_type nft_set_hash_type __read_mostly = {
.owner = THIS_MODULE,
.features = NFT_SET_MAP | NFT_SET_OBJECT,
.ops = {
},
};
-static struct nft_set_type nft_hash_fast_type __read_mostly = {
+struct nft_set_type nft_set_hash_fast_type __read_mostly = {
.owner = THIS_MODULE,
.features = NFT_SET_MAP | NFT_SET_OBJECT,
.ops = {
.get = nft_hash_get,
},
};
-
-static int __init nft_hash_module_init(void)
-{
- if (nft_register_set(&nft_hash_fast_type) ||
- nft_register_set(&nft_hash_type) ||
- nft_register_set(&nft_rhash_type))
- return 1;
- return 0;
-}
-
-static void __exit nft_hash_module_exit(void)
-{
- nft_unregister_set(&nft_rhash_type);
- nft_unregister_set(&nft_hash_type);
- nft_unregister_set(&nft_hash_fast_type);
-}
-
-module_init(nft_hash_module_init);
-module_exit(nft_hash_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
parent = rcu_dereference_raw(parent->rb_left);
if (interval &&
nft_rbtree_equal(set, this, interval) &&
- nft_rbtree_interval_end(this) &&
+ nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(interval))
continue;
interval = rbe;
gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
if (!gcb)
- goto out;
+ break;
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
rbe = rb_entry(prev, struct nft_rbtree_elem, node);
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
+ prev = NULL;
}
node = rb_next(node);
+ if (!node)
+ break;
}
-out:
if (gcb) {
for (i = 0; i < gcb->head.cnt; i++) {
rbe = gcb->elems[i];
struct rb_node *node;
cancel_delayed_work_sync(&priv->gc_work);
+ rcu_barrier();
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
return true;
}
-static struct nft_set_type nft_rbtree_type __read_mostly = {
+struct nft_set_type nft_set_rbtree_type __read_mostly = {
.owner = THIS_MODULE,
.features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
.ops = {
.get = nft_rbtree_get,
},
};
-
-static int __init nft_rbtree_module_init(void)
-{
- return nft_register_set(&nft_rbtree_type);
-}
-
-static void __exit nft_rbtree_module_exit(void)
-{
- nft_unregister_set(&nft_rbtree_type);
-}
-
-module_init(nft_rbtree_module_init);
-module_exit(nft_rbtree_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Máté Eckl");
MODULE_DESCRIPTION("nf_tables socket match module");
+MODULE_ALIAS_NFT_EXPR("socket");
}
if (info->helper[0]) {
+ if (strnlen(info->helper, sizeof(info->helper)) == sizeof(info->helper)) {
+ ret = -ENAMETOOLONG;
+ goto err3;
+ }
+
ret = xt_ct_set_helper(ct, info->helper, par);
if (ret < 0)
goto err3;
}
if (info->timeout[0]) {
+ if (strnlen(info->timeout, sizeof(info->timeout)) == sizeof(info->timeout)) {
+ ret = -ENAMETOOLONG;
+ goto err4;
+ }
+
ret = xt_ct_set_timeout(ct, par, info->timeout);
if (ret < 0)
goto err4;
* addresses, this happens if the redirect already happened
* and the current packet belongs to an already established
* connection */
- sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
iph->saddr, iph->daddr,
hp->source, hp->dest,
skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
else if (!sk)
/* no, there's no established connection, check if
* there's a listener on the redirected addr/port */
- sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
iph->saddr, laddr,
hp->source, lport,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
* addresses, this happens if the redirect already happened
* and the current packet belongs to an already established
* connection */
- sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
+ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto,
&iph->saddr, &iph->daddr,
hp->source, hp->dest,
xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED);
else if (!sk)
/* no there's no established connection, check if
* there's a listener on the redirected addr/port */
- sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp,
+ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff,
tproto, &iph->saddr, laddr,
hp->source, lport,
xt_in(par), NF_TPROXY_LOOKUP_LISTENER);
static void __exit connmark_mt_exit(void)
{
xt_unregister_match(&connmark_mt_reg);
- xt_unregister_target(connmark_tg_reg);
+ xt_unregister_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg));
}
module_init(connmark_mt_init);
/* Normalize to fit into jiffies */
if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
- add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC)
- add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC;
+ add_opt.ext.timeout > IPSET_MAX_TIMEOUT)
+ add_opt.ext.timeout = IPSET_MAX_TIMEOUT;
if (info->add_set.index != IPSET_INVALID_ID)
ip_set_add(info->add_set.index, skb, par, &add_opt);
if (info->del_set.index != IPSET_INVALID_ID)
/* Normalize to fit into jiffies */
if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
- add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC)
- add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC;
+ add_opt.ext.timeout > IPSET_MAX_TIMEOUT)
+ add_opt.ext.timeout = IPSET_MAX_TIMEOUT;
if (info->add_set.index != IPSET_INVALID_ID)
ip_set_add(info->add_set.index, skb, par, &add_opt);
if (info->del_set.index != IPSET_INVALID_ID)
}
if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) |
(info->flags & IPSET_FLAG_MAP_SKBQUEUE)) &&
- !(par->hook_mask & (1 << NF_INET_FORWARD |
+ (par->hook_mask & ~(1 << NF_INET_FORWARD |
1 << NF_INET_LOCAL_OUT |
1 << NF_INET_POST_ROUTING))) {
pr_info_ratelimited("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n");
#include <linux/hash.h>
#include <linux/genetlink.h>
#include <linux/net_namespace.h>
+#include <linux/nospec.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
if (protocol < 0 || protocol >= MAX_LINKS)
return -EPROTONOSUPPORT;
+ protocol = array_index_nospec(protocol, MAX_LINKS);
netlink_lock_table();
#ifdef CONFIG_MODULES
return err;
}
+ if (nlk->ngroups == 0)
+ groups = 0;
+ else if (nlk->ngroups < 8*sizeof(groups))
+ groups &= (1UL << nlk->ngroups) - 1;
+
bound = nlk->bound;
if (bound) {
/* Ensure nlk->portid is up-to-date. */
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = netlink_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = nr_accept,
.getname = nr_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = nr_ioctl,
.listen = nr_listen,
.shutdown = sock_no_shutdown,
pr_debug("Fragment %zd bytes remaining %zd",
frag_len, remaining_len);
- pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT,
+ pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0,
frag_len + LLCP_HEADER_SIZE, &err);
if (pdu == NULL) {
- pr_err("Could not allocate PDU\n");
- continue;
+ pr_err("Could not allocate PDU (error=%d)\n", err);
+ len -= remaining_len;
+ if (len == 0)
+ len = err;
+ break;
}
pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI);
return 0;
}
-static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
pr_debug("%p\n", sk);
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == LLCP_LISTEN)
return llcp_accept_poll(sk);
.socketpair = sock_no_socketpair,
.accept = llcp_sock_accept,
.getname = llcp_sock_getname,
- .poll_mask = llcp_sock_poll_mask,
+ .poll = llcp_sock_poll,
.ioctl = sock_no_ioctl,
.listen = llcp_sock_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = llcp_sock_getname,
- .poll_mask = llcp_sock_poll_mask,
+ .poll = llcp_sock_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
__skb_pull(skb, nsh_len);
skb_reset_mac_header(skb);
- skb_reset_mac_len(skb);
+ skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0;
skb->protocol = proto;
features &= NETIF_F_SG;
if (!meter)
return ERR_PTR(-ENOMEM);
+ meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]);
meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
u32 meter_id;
bool failed;
+ if (!a[OVS_METER_ATTR_ID]) {
+ return -ENODEV;
+ }
+
meter = dp_meter_create(a);
if (IS_ERR_OR_NULL(meter))
return PTR_ERR(meter);
goto exit_unlock;
}
- if (!a[OVS_METER_ATTR_ID]) {
- err = -ENODEV;
- goto exit_unlock;
- }
-
meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
/* Cannot fail after this. */
if (po->stats.stats1.tp_drops)
status |= TP_STATUS_LOSING;
}
+
+ if (do_vnet &&
+ virtio_net_hdr_from_skb(skb, h.raw + macoff -
+ sizeof(struct virtio_net_hdr),
+ vio_le(), true, 0))
+ goto drop_n_account;
+
po->stats.stats1.tp_packets++;
if (copy_skb) {
status |= TP_STATUS_COPY;
}
spin_unlock(&sk->sk_receive_queue.lock);
- if (do_vnet) {
- if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
- sizeof(struct virtio_net_hdr),
- vio_le(), true, 0)) {
- spin_lock(&sk->sk_receive_queue.lock);
- goto drop_n_account;
- }
- }
-
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
goto out_free;
} else if (reserve) {
skb_reserve(skb, -reserve);
+ if (len < reserve)
+ skb_reset_network_header(skb);
}
/* Returns -EFAULT on error */
return 0;
}
-static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t packet_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
spin_lock_bh(&sk->sk_receive_queue.lock);
if (po->rx_ring.pg_vec) {
}
if (req->tp_block_nr) {
+ unsigned int min_frame_size;
+
/* Sanity tests and some calculations */
err = -EBUSY;
if (unlikely(rb->pg_vec))
goto out;
if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
goto out;
+ min_frame_size = po->tp_hdrlen + po->tp_reserve;
if (po->tp_version >= TPACKET_V3 &&
- req->tp_block_size <=
- BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
+ req->tp_block_size <
+ BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size)
goto out;
- if (unlikely(req->tp_frame_size < po->tp_hdrlen +
- po->tp_reserve))
+ if (unlikely(req->tp_frame_size < min_frame_size))
goto out;
if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
goto out;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname_spkt,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname,
- .poll_mask = packet_poll_mask,
+ .poll = packet_poll,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
return sizeof(struct sockaddr_pn);
}
-static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct pep_sock *pn = pep_sk(sk);
__poll_t mask = 0;
+ poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == TCP_CLOSE)
return EPOLLERR;
if (!skb_queue_empty(&sk->sk_receive_queue))
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pn_socket_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = pn_socket_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = pn_socket_accept,
.getname = pn_socket_getname,
- .poll_mask = pn_socket_poll_mask,
+ .poll = pn_socket_poll,
.ioctl = pn_socket_ioctl,
.listen = pn_socket_listen,
.shutdown = sock_no_shutdown,
hdr->type = cpu_to_le32(type);
hdr->src_node_id = cpu_to_le32(from->sq_node);
hdr->src_port_id = cpu_to_le32(from->sq_port);
- hdr->dst_node_id = cpu_to_le32(to->sq_node);
- hdr->dst_port_id = cpu_to_le32(to->sq_port);
+ if (to->sq_port == QRTR_PORT_CTRL) {
+ hdr->dst_node_id = cpu_to_le32(node->nid);
+ hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+ } else {
+ hdr->dst_node_id = cpu_to_le32(to->sq_node);
+ hdr->dst_port_id = cpu_to_le32(to->sq_port);
+ }
hdr->size = cpu_to_le32(len);
hdr->confirm_rx = 0;
node = NULL;
if (addr->sq_node == QRTR_NODE_BCAST) {
enqueue_fn = qrtr_bcast_enqueue;
+ if (addr->sq_port != QRTR_PORT_CTRL) {
+ release_sock(sk);
+ return -ENOTCONN;
+ }
} else if (addr->sq_node == ipc->us.sq_node) {
enqueue_fn = qrtr_local_enqueue;
} else {
.recvmsg = qrtr_recvmsg,
.getname = qrtr_getname,
.ioctl = qrtr_ioctl,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
int rds_conn_init(void)
{
+ int ret;
+
+ ret = rds_loop_net_init(); /* register pernet callback */
+ if (ret)
+ return ret;
+
rds_conn_slab = kmem_cache_create("rds_connection",
sizeof(struct rds_connection),
0, 0, NULL);
- if (!rds_conn_slab)
+ if (!rds_conn_slab) {
+ rds_loop_net_exit();
return -ENOMEM;
+ }
rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
rds_info_register_func(RDS_INFO_SEND_MESSAGES,
void rds_conn_exit(void)
{
+ rds_loop_net_exit(); /* unregister pernet callback */
rds_loop_exit();
WARN_ON(!hlist_empty(rds_conn_hash));
struct rds_ib_frmr *frmr;
int ret;
+ if (!ic) {
+ /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
do {
if (ibmr)
rds_ib_free_frmr(ibmr, true);
struct rds_info_rdma_connection *iinfo);
void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
- struct rds_sock *rs, u32 *key_ret);
+ struct rds_sock *rs, u32 *key_ret,
+ struct rds_connection *conn);
void rds_ib_sync_mr(void *trans_private, int dir);
void rds_ib_free_mr(void *trans_private, int invalidate);
void rds_ib_flush_mrs(void);
}
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
- struct rds_sock *rs, u32 *key_ret)
+ struct rds_sock *rs, u32 *key_ret,
+ struct rds_connection *conn)
{
struct rds_ib_device *rds_ibdev;
struct rds_ib_mr *ibmr = NULL;
- struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
+ struct rds_ib_connection *ic = NULL;
int ret;
rds_ibdev = rds_ib_get_device(rs->rs_bound_addr);
goto out;
}
+ if (conn)
+ ic = conn->c_transport_data;
+
if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
ret = -ENODEV;
goto out;
ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret);
else
ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret);
- if (ibmr)
- rds_ibdev = NULL;
-
- out:
- if (!ibmr)
+ if (IS_ERR(ibmr)) {
+ ret = PTR_ERR(ibmr);
pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret);
+ } else {
+ return ibmr;
+ }
+ out:
if (rds_ibdev)
rds_ib_dev_put(rds_ibdev);
- return ibmr;
+ return ERR_PTR(ret);
}
void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool)
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "rds_single_path.h"
#include "rds.h"
static DEFINE_SPINLOCK(loop_conns_lock);
static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+ atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+ return atomic_read(&rds_loop_unloading) != 0;
+}
/*
* This 'loopback' transport is a special case for flows that originate
struct rds_loop_connection *lc, *_lc;
LIST_HEAD(tmp_list);
+ rds_loop_set_unloading();
+ synchronize_rcu();
/* avoid calling conn_destroy with irqs off */
spin_lock_irq(&loop_conns_lock);
list_splice(&loop_conns, &tmp_list);
}
}
+static void rds_loop_kill_conns(struct net *net)
+{
+ struct rds_loop_connection *lc, *_lc;
+ LIST_HEAD(tmp_list);
+
+ spin_lock_irq(&loop_conns_lock);
+ list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) {
+ struct net *c_net = read_pnet(&lc->conn->c_net);
+
+ if (net != c_net)
+ continue;
+ list_move_tail(&lc->loop_node, &tmp_list);
+ }
+ spin_unlock_irq(&loop_conns_lock);
+
+ list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+ WARN_ON(lc->conn->c_passive);
+ rds_conn_destroy(lc->conn);
+ }
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+ rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+ .exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+ return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+ unregister_pernet_device(&rds_loop_net_ops);
+}
+
/*
* This is missing .xmit_* because loop doesn't go through generic
* rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and
.inc_copy_to_user = rds_message_inc_copy_to_user,
.inc_free = rds_loop_inc_free,
.t_name = "loopback",
+ .t_type = RDS_TRANS_LOOP,
+ .t_unloading = rds_loop_is_unloading,
};
/* loop.c */
extern struct rds_transport rds_loop_transport;
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
void rds_loop_exit(void);
#endif
}
static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
- u64 *cookie_ret, struct rds_mr **mr_ret)
+ u64 *cookie_ret, struct rds_mr **mr_ret,
+ struct rds_conn_path *cp)
{
struct rds_mr *mr = NULL, *found;
unsigned int nr_pages;
* Note that dma_map() implies that pending writes are
* flushed to RAM, so no dma_sync is needed here. */
trans_private = rs->rs_transport->get_mr(sg, nents, rs,
- &mr->r_key);
+ &mr->r_key,
+ cp ? cp->cp_conn : NULL);
if (IS_ERR(trans_private)) {
for (i = 0 ; i < nents; i++)
sizeof(struct rds_get_mr_args)))
return -EFAULT;
- return __rds_rdma_map(rs, &args, NULL, NULL);
+ return __rds_rdma_map(rs, &args, NULL, NULL, NULL);
}
int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
new_args.cookie_addr = args.cookie_addr;
new_args.flags = args.flags;
- return __rds_rdma_map(rs, &new_args, NULL, NULL);
+ return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL);
}
/*
rm->m_rdma_cookie != 0)
return -EINVAL;
- return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr);
+ return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie,
+ &rm->rdma.op_rdma_mr, rm->m_conn_path);
}
/*
struct scatterlist *op_sg;
} data;
};
+
+ struct rds_conn_path *m_conn_path;
};
/*
int n_status;
};
+/* Available as part of RDS core, so doesn't need to participate
+ * in get_preferred transport etc
+ */
+#define RDS_TRANS_LOOP 3
+
/**
* struct rds_transport - transport specific behavioural hooks
*
unsigned int avail);
void (*exit)(void);
void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg,
- struct rds_sock *rs, u32 *key_ret);
+ struct rds_sock *rs, u32 *key_ret,
+ struct rds_connection *conn);
void (*sync_mr)(void *trans_private, int direction);
void (*free_mr)(void *trans_private, int invalidate);
void (*flush_mrs)(void);
rds_stats_add(s_recv_bytes_added_to_socket, delta);
else
rds_stats_add(s_recv_bytes_removed_from_socket, -delta);
+
+ /* loop transport doesn't send/recv congestion updates */
+ if (rs->rs_transport->t_type == RDS_TRANS_LOOP)
+ return;
+
now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs);
rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d "
rs->rs_conn = conn;
}
+ if (conn->c_trans->t_mp_capable)
+ cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
+ else
+ cpath = &conn->c_path[0];
+
+ rm->m_conn_path = cpath;
+
/* Parse any control messages the user may have included. */
ret = rds_cmsg_send(rs, rm, msg, &allocated_mr);
if (ret) {
goto out;
}
- if (conn->c_trans->t_mp_capable)
- cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
- else
- cpath = &conn->c_path[0];
-
if (rds_destroy_pending(conn)) {
ret = -EAGAIN;
goto out;
.socketpair = sock_no_socketpair,
.accept = rose_accept,
.getname = rose_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = rose_ioctl,
.listen = rose_listen,
.shutdown = sock_no_shutdown,
/*
* permit an RxRPC socket to be polled
*/
-static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct rxrpc_sock *rx = rxrpc_sk(sk);
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
* queue */
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = rxrpc_poll_mask,
+ .poll = rxrpc_poll,
.ioctl = sock_no_ioctl,
.listen = rxrpc_listen,
.shutdown = rxrpc_shutdown,
#define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
u8 peer_keepalive_cursor;
- ktime_t peer_keepalive_base;
- struct hlist_head peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
- struct hlist_head peer_keepalive_new;
+ time64_t peer_keepalive_base;
+ struct list_head peer_keepalive[32];
+ struct list_head peer_keepalive_new;
struct timer_list peer_keepalive_timer;
struct work_struct peer_keepalive_work;
};
struct hlist_head error_targets; /* targets for net error distribution */
struct work_struct error_distributor;
struct rb_root service_conns; /* Service connections */
- struct hlist_node keepalive_link; /* Link in net->peer_keepalive[] */
+ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */
time64_t last_tx_at; /* Last time packet sent here */
seqlock_t service_conn_lock;
spinlock_t lock; /* access lock */
while (*pp) {
parent = *pp;
xcall = rb_entry(parent, struct rxrpc_call, sock_node);
- if (user_call_ID < call->user_call_ID)
+ if (user_call_ID < xcall->user_call_ID)
pp = &(*pp)->rb_left;
- else if (user_call_ID > call->user_call_ID)
+ else if (user_call_ID > xcall->user_call_ID)
pp = &(*pp)->rb_right;
else
goto id_in_use;
bool rxrpc_queue_call(struct rxrpc_call *call)
{
const void *here = __builtin_return_address(0);
- int n = __atomic_add_unless(&call->usage, 1, 0);
+ int n = atomic_fetch_add_unless(&call->usage, 1, 0);
if (n == 0)
return false;
if (rxrpc_queue_work(&call->processor))
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
rxrpc_tx_fail_call_final_resend);
return -EAGAIN;
}
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
_leave(" = 0");
return 0;
bool rxrpc_queue_conn(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
- int n = __atomic_add_unless(&conn->usage, 1, 0);
+ int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
if (n == 0)
return false;
if (rxrpc_queue_work(&conn->processor))
const void *here = __builtin_return_address(0);
if (conn) {
- int n = __atomic_add_unless(&conn->usage, 1, 0);
+ int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
if (n > 0)
trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
else
const void *here = __builtin_return_address(0);
if (local) {
- int n = __atomic_add_unless(&local->usage, 1, 0);
+ int n = atomic_fetch_add_unless(&local->usage, 1, 0);
if (n > 0)
trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
else
hash_init(rxnet->peer_hash);
spin_lock_init(&rxnet->peer_hash_lock);
for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
- INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
- INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+ INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
+ INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
timer_setup(&rxnet->peer_keepalive_timer,
rxrpc_peer_keepalive_timeout, 0);
INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
- rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
+ rxnet->peer_keepalive_base = ktime_get_seconds();
ret = -ENOMEM;
rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
now = ktime_get_real();
if (ping)
call->ping_time = now;
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_fail_call_ack);
ret = kernel_sendmsg(conn->params.local->socket,
&msg, iov, 1, sizeof(pkt));
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_fail_call_abort);
* message and update the peer record
*/
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
up_read(&conn->params.local->defrag_sem);
if (ret < 0)
if (ret == 0) {
ret = kernel_sendmsg(conn->params.local->socket, &msg,
iov, 2, len);
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
opt = IP_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket, SOL_IP,
if (ret == 0) {
ret = kernel_sendmsg(conn->params.local->socket, &msg,
iov, 2, len);
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
opt = IPV6_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket,
trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
rxrpc_tx_fail_version_keepalive);
- peer->last_tx_at = ktime_get_real();
+ peer->last_tx_at = ktime_get_seconds();
_leave("");
}
}
/*
- * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ * Perform keep-alive pings.
*/
-void rxrpc_peer_keepalive_worker(struct work_struct *work)
+static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
+ struct list_head *collector,
+ time64_t base,
+ u8 cursor)
{
- struct rxrpc_net *rxnet =
- container_of(work, struct rxrpc_net, peer_keepalive_work);
struct rxrpc_peer *peer;
- unsigned long delay;
- ktime_t base, now = ktime_get_real();
- s64 diff;
- u8 cursor, slot;
+ const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+ time64_t keepalive_at;
+ int slot;
- base = rxnet->peer_keepalive_base;
- cursor = rxnet->peer_keepalive_cursor;
+ spin_lock_bh(&rxnet->peer_hash_lock);
- _enter("%u,%lld", cursor, ktime_sub(now, base));
+ while (!list_empty(collector)) {
+ peer = list_entry(collector->next,
+ struct rxrpc_peer, keepalive_link);
-next_bucket:
- diff = ktime_to_ns(ktime_sub(now, base));
- if (diff < 0)
- goto resched;
+ list_del_init(&peer->keepalive_link);
+ if (!rxrpc_get_peer_maybe(peer))
+ continue;
- _debug("at %u", cursor);
- spin_lock_bh(&rxnet->peer_hash_lock);
-next_peer:
- if (!rxnet->live) {
spin_unlock_bh(&rxnet->peer_hash_lock);
- goto out;
- }
- /* Everything in the bucket at the cursor is processed this second; the
- * bucket at cursor + 1 goes now + 1s and so on...
- */
- if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
- if (hlist_empty(&rxnet->peer_keepalive_new)) {
- spin_unlock_bh(&rxnet->peer_hash_lock);
- goto emptied_bucket;
+ keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+ slot = keepalive_at - base;
+ _debug("%02x peer %u t=%d {%pISp}",
+ cursor, peer->debug_id, slot, &peer->srx.transport);
+
+ if (keepalive_at <= base ||
+ keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+ rxrpc_send_keepalive(peer);
+ slot = RXRPC_KEEPALIVE_TIME;
}
- hlist_move_list(&rxnet->peer_keepalive_new,
- &rxnet->peer_keepalive[cursor]);
+ /* A transmission to this peer occurred since last we examined
+ * it so put it into the appropriate future bucket.
+ */
+ slot += cursor;
+ slot &= mask;
+ spin_lock_bh(&rxnet->peer_hash_lock);
+ list_add_tail(&peer->keepalive_link,
+ &rxnet->peer_keepalive[slot & mask]);
+ rxrpc_put_peer(peer);
}
- peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
- struct rxrpc_peer, keepalive_link);
- hlist_del_init(&peer->keepalive_link);
- if (!rxrpc_get_peer_maybe(peer))
- goto next_peer;
-
spin_unlock_bh(&rxnet->peer_hash_lock);
+}
- _debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+ struct rxrpc_net *rxnet =
+ container_of(work, struct rxrpc_net, peer_keepalive_work);
+ const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+ time64_t base, now, delay;
+ u8 cursor, stop;
+ LIST_HEAD(collector);
-recalc:
- diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
- if (diff < -30 || diff > 30)
- goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
- diff += RXRPC_KEEPALIVE_TIME - 1;
- if (diff < 0)
- goto send;
+ now = ktime_get_seconds();
+ base = rxnet->peer_keepalive_base;
+ cursor = rxnet->peer_keepalive_cursor;
+ _enter("%lld,%u", base - now, cursor);
- slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
- if (slot == 0)
- goto send;
+ if (!rxnet->live)
+ return;
- /* A transmission to this peer occurred since last we examined it so
- * put it into the appropriate future bucket.
+ /* Remove to a temporary list all the peers that are currently lodged
+ * in expired buckets plus all new peers.
+ *
+ * Everything in the bucket at the cursor is processed this
+ * second; the bucket at cursor + 1 goes at now + 1s and so
+ * on...
*/
- slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
spin_lock_bh(&rxnet->peer_hash_lock);
- hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
- rxrpc_put_peer(peer);
- goto next_peer;
-
-send:
- rxrpc_send_keepalive(peer);
- now = ktime_get_real();
- goto recalc;
+ list_splice_init(&rxnet->peer_keepalive_new, &collector);
+
+ stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
+ while (base <= now && (s8)(cursor - stop) < 0) {
+ list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
+ &collector);
+ base++;
+ cursor++;
+ }
-emptied_bucket:
- cursor++;
- if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
- cursor = 0;
- base = ktime_add_ns(base, NSEC_PER_SEC);
- goto next_bucket;
+ base = now;
+ spin_unlock_bh(&rxnet->peer_hash_lock);
-resched:
rxnet->peer_keepalive_base = base;
rxnet->peer_keepalive_cursor = cursor;
- delay = nsecs_to_jiffies(-diff) + 1;
- timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
-out:
+ rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
+ ASSERT(list_empty(&collector));
+
+ /* Schedule the timer for the next occupied timeslot. */
+ cursor = rxnet->peer_keepalive_cursor;
+ stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
+ for (; (s8)(cursor - stop) < 0; cursor++) {
+ if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
+ break;
+ base++;
+ }
+
+ now = ktime_get_seconds();
+ delay = base - now;
+ if (delay < 1)
+ delay = 1;
+ delay *= HZ;
+ if (rxnet->live)
+ timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+
_leave("");
}
if (!peer) {
peer = prealloc;
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
- hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
+ list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
}
spin_unlock(&rxnet->peer_hash_lock);
if (!peer) {
hash_add_rcu(rxnet->peer_hash,
&candidate->hash_link, hash_key);
- hlist_add_head(&candidate->keepalive_link,
- &rxnet->peer_keepalive_new);
+ list_add_tail(&candidate->keepalive_link,
+ &rxnet->peer_keepalive_new);
}
spin_unlock_bh(&rxnet->peer_hash_lock);
const void *here = __builtin_return_address(0);
if (peer) {
- int n = __atomic_add_unless(&peer->usage, 1, 0);
+ int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
if (n > 0)
trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
else
spin_lock_bh(&rxnet->peer_hash_lock);
hash_del_rcu(&peer->hash_link);
- hlist_del_init(&peer->keepalive_link);
+ list_del_init(&peer->keepalive_link);
spin_unlock_bh(&rxnet->peer_hash_lock);
kfree_rcu(peer, rcu);
return -EAGAIN;
}
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
_leave(" = 0");
return 0;
}
return -EAGAIN;
}
- conn->params.peer->last_tx_at = ktime_get_real();
+ conn->params.peer->last_tx_at = ktime_get_seconds();
_leave(" = 0");
return 0;
}
}
params_old = rtnl_dereference(p->params);
- params_new->action = parm->action;
+ p->tcf_action = parm->action;
params_new->update_flags = parm->update_flags;
rcu_assign_pointer(p->params, params_new);
if (params_old)
tcf_lastuse_update(&p->tcf_tm);
bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
- action = params->action;
+ action = READ_ONCE(p->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
goto drop_stats;
.index = p->tcf_index,
.refcnt = p->tcf_refcnt - ref,
.bindcnt = p->tcf_bindcnt - bind,
+ .action = p->tcf_action,
};
struct tcf_t t;
params = rtnl_dereference(p->params);
- opt.action = params->action;
opt.update_flags = params->update_flags;
if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
spin_unlock_bh(&ife->tcf_lock);
p = rcu_dereference_protected(ife->params, 1);
- kfree_rcu(p, rcu);
+ if (p)
+ kfree_rcu(p, rcu);
}
/* under ife->tcf_lock for existing action */
saddr = nla_data(tb[TCA_IFE_SMAC]);
}
- ife->tcf_action = parm->action;
-
if (parm->flags & IFE_ENCODE) {
if (daddr)
ether_addr_copy(p->eth_dst, daddr);
NULL, NULL);
if (err) {
metadata_parse_err:
- if (exists)
- tcf_idr_release(*a, bind);
if (ret == ACT_P_CREATED)
- _tcf_ife_cleanup(*a);
+ tcf_idr_release(*a, bind);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
err = use_all_metadata(ife);
if (err) {
if (ret == ACT_P_CREATED)
- _tcf_ife_cleanup(*a);
+ tcf_idr_release(*a, bind);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
}
}
+ ife->tcf_action = parm->action;
if (exists)
spin_unlock_bh(&ife->tcf_lock);
tcf_lastuse_update(&t->tcf_tm);
bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
- action = params->action;
+ action = READ_ONCE(t->tcf_action);
switch (params->tcft_action) {
case TCA_TUNNEL_KEY_ACT_RELEASE:
params_old = rtnl_dereference(t->params);
- params_new->action = parm->action;
+ t->tcf_action = parm->action;
params_new->tcft_action = parm->t_action;
params_new->tcft_enc_metadata = metadata;
.index = t->tcf_index,
.refcnt = t->tcf_refcnt - ref,
.bindcnt = t->tcf_bindcnt - bind,
+ .action = t->tcf_action,
};
struct tcf_t tm;
params = rtnl_dereference(t->params);
opt.t_action = params->tcft_action;
- opt.action = params->action;
if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
for (tp = rtnl_dereference(chain->filter_chain);
tp; tp = rtnl_dereference(tp->next))
tfilter_notify(net, oskb, n, tp, block,
- q, parent, 0, event, false);
+ q, parent, NULL, event, false);
}
static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (cb->args[1] == 0) {
- if (tcf_fill_node(net, skb, tp, block, q, parent, 0,
+ if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER) <= 0)
struct rhashtable_params filter_ht_params;
struct flow_dissector dissector;
struct list_head filters;
- struct rcu_head rcu;
+ struct rcu_work rwork;
struct list_head list;
};
return rhashtable_init(&head->ht, &mask_ht_params);
}
+static void fl_mask_free(struct fl_flow_mask *mask)
+{
+ rhashtable_destroy(&mask->ht);
+ kfree(mask);
+}
+
+static void fl_mask_free_work(struct work_struct *work)
+{
+ struct fl_flow_mask *mask = container_of(to_rcu_work(work),
+ struct fl_flow_mask, rwork);
+
+ fl_mask_free(mask);
+}
+
static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
bool async)
{
return false;
rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
- rhashtable_destroy(&mask->ht);
list_del_rcu(&mask->list);
if (async)
- kfree_rcu(mask, rcu);
+ tcf_queue_work(&mask->rwork, fl_mask_free_work);
else
- kfree(mask);
+ fl_mask_free(mask);
return true;
}
struct sk_buff **to_free)
{
qdisc_drop(skb, sch, to_free);
- return NET_XMIT_SUCCESS;
+ return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)
q->cparams.mtu = psched_mtu(qdisc_dev(sch));
if (opt) {
- int err = fq_codel_change(sch, opt, extack);
+ err = fq_codel_change(sch, opt, extack);
if (err)
- return err;
+ goto init_failure;
}
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
if (err)
- return err;
+ goto init_failure;
if (!q->flows) {
q->flows = kvcalloc(q->flows_cnt,
sizeof(struct fq_codel_flow),
GFP_KERNEL);
- if (!q->flows)
- return -ENOMEM;
+ if (!q->flows) {
+ err = -ENOMEM;
+ goto init_failure;
+ }
q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL);
- if (!q->backlogs)
- return -ENOMEM;
+ if (!q->backlogs) {
+ err = -ENOMEM;
+ goto alloc_failure;
+ }
for (i = 0; i < q->flows_cnt; i++) {
struct fq_codel_flow *flow = q->flows + i;
else
sch->flags &= ~TCQ_F_CAN_BYPASS;
return 0;
+
+alloc_failure:
+ kvfree(q->flows);
+ q->flows = NULL;
+init_failure:
+ q->flows_cnt = 0;
+ return err;
}
static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
if (next_time == 0 || next_time > q->root.cl_cfmin)
next_time = q->root.cl_cfmin;
}
- WARN_ON(next_time == 0);
- qdisc_watchdog_schedule(&q->watchdog, next_time);
+ if (next_time)
+ qdisc_watchdog_schedule(&q->watchdog, next_time);
}
static int
/* Account for a different sized first fragment */
if (msg_len >= first_len) {
msg->can_delay = 0;
- SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS);
+ if (msg_len > first_len)
+ SCTP_INC_STATS(sock_net(asoc->base.sk),
+ SCTP_MIB_FRAGUSRMSGS);
} else {
/* Which may be the only one... */
first_len = msg_len;
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = sctp_getname,
- .poll_mask = sctp_poll_mask,
+ .poll = sctp_poll,
.ioctl = inet6_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
refcount_inc(&sk->sk_wmem_alloc);
}
+static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
+{
+ if (SCTP_OUTPUT_CB(head)->last == head)
+ skb_shinfo(head)->frag_list = skb;
+ else
+ SCTP_OUTPUT_CB(head)->last->next = skb;
+ SCTP_OUTPUT_CB(head)->last = skb;
+
+ head->truesize += skb->truesize;
+ head->data_len += skb->len;
+ head->len += skb->len;
+
+ __skb_header_release(skb);
+}
+
static int sctp_packet_pack(struct sctp_packet *packet,
struct sk_buff *head, int gso, gfp_t gfp)
{
if (gso) {
skb_shinfo(head)->gso_type = sk->sk_gso_type;
- NAPI_GRO_CB(head)->last = head;
+ SCTP_OUTPUT_CB(head)->last = head;
} else {
nskb = head;
pkt_size = packet->size;
&packet->chunk_list);
}
- if (gso) {
- if (skb_gro_receive(&head, nskb)) {
- kfree_skb(nskb);
- return 0;
- }
- if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >=
- sk->sk_gso_max_segs))
- return 0;
- }
+ if (gso)
+ sctp_packet_gso_append(head, nskb);
pkt_count++;
} while (!list_empty(&packet->chunk_list));
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname, /* Semantics are different. */
- .poll_mask = sctp_poll_mask,
+ .poll = sctp_poll,
.ioctl = inet_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
* here, again, by modeling the current TCP/UDP code. We don't have
* a good way to test with it yet.
*/
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
struct sctp_sock *sp = sctp_sk(sk);
__poll_t mask;
+ poll_wait(file, sk_sleep(sk), wait);
+
sock_rps_record_flow(sk);
/* A TCP-style listening socket becomes readable when the accept queue
if (dst) {
/* Re-fetch, as under layers may have a higher minimum size */
- pmtu = SCTP_TRUNC4(dst_mtu(dst));
+ pmtu = sctp_dst_mtu(dst);
change = t->pathmtu != pmtu;
}
t->pathmtu = pmtu;
*/
static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
static void smc_set_keepalive(struct sock *sk, int val)
{
goto out;
smc = smc_sk(sk);
+
+ /* cleanup for a dangling non-blocking connect */
+ flush_work(&smc->connect_work);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
* sock lock for child sockets again
smc->clcsock = NULL;
}
if (smc->use_fallback) {
- sock_put(sk); /* passive closing */
+ if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+ sock_put(sk); /* passive closing */
sk->sk_state = SMC_CLOSED;
sk->sk_state_change(sk);
}
sk->sk_protocol = protocol;
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+ INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
spin_lock_init(&smc->accept_q_lock);
{
int rc;
- if (reason_code < 0) /* error, fallback is not possible */
+ if (reason_code < 0) { /* error, fallback is not possible */
+ if (smc->sk.sk_state == SMC_INIT)
+ sock_put(&smc->sk); /* passive closing */
return reason_code;
+ }
if (reason_code != SMC_CLC_DECL_REPLY) {
rc = smc_clc_send_decline(smc, reason_code);
- if (rc < 0)
+ if (rc < 0) {
+ if (smc->sk.sk_state == SMC_INIT)
+ sock_put(&smc->sk); /* passive closing */
return rc;
+ }
}
return smc_connect_fallback(smc);
}
smc_lgr_forget(smc->conn.lgr);
mutex_unlock(&smc_create_lgr_pending);
smc_conn_free(&smc->conn);
- if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
- sock_put(&smc->sk); /* passive closing */
return reason_code;
}
return 0;
}
+static void smc_connect_work(struct work_struct *work)
+{
+ struct smc_sock *smc = container_of(work, struct smc_sock,
+ connect_work);
+ int rc;
+
+ lock_sock(&smc->sk);
+ rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+ smc->connect_info->alen, smc->connect_info->flags);
+ if (smc->clcsock->sk->sk_err) {
+ smc->sk.sk_err = smc->clcsock->sk->sk_err;
+ goto out;
+ }
+ if (rc < 0) {
+ smc->sk.sk_err = -rc;
+ goto out;
+ }
+
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ smc->sk.sk_err = -rc;
+
+out:
+ smc->sk.sk_state_change(&smc->sk);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+ release_sock(&smc->sk);
+}
+
static int smc_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
+ if (flags & O_NONBLOCK) {
+ if (smc->connect_info) {
+ rc = -EALREADY;
+ goto out;
+ }
+ smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+ if (!smc->connect_info) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ smc->connect_info->alen = alen;
+ smc->connect_info->flags = flags ^ O_NONBLOCK;
+ memcpy(&smc->connect_info->addr, addr, alen);
+ schedule_work(&smc->connect_work);
+ rc = -EINPROGRESS;
+ } else {
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc)
+ goto out;
- rc = __smc_connect(smc);
- if (rc < 0)
- goto out;
- else
- rc = 0; /* success cases including fallback */
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ goto out;
+ else
+ rc = 0; /* success cases including fallback */
+ }
out:
release_sock(sk);
sock_hold(lsk); /* sock_put in smc_listen_work */
INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
smc_copy_sock_settings_to_smc(new_smc);
+ new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+ new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
sock_hold(&new_smc->sk); /* sock_put in passive closing */
if (!schedule_work(&new_smc->smc_listen_work))
sock_put(&new_smc->sk);
struct sock *sk = sock->sk;
__poll_t mask = 0;
struct smc_sock *smc;
- int rc;
if (!sk)
return EPOLLNVAL;
smc = smc_sk(sock->sk);
- sock_hold(sk);
- lock_sock(sk);
if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
/* delegate to CLC child sock */
- release_sock(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
- lock_sock(sk);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
+ if (sk->sk_err)
mask |= EPOLLERR;
- } else {
- /* if non-blocking connect finished ... */
- if (sk->sk_state == SMC_INIT &&
- mask & EPOLLOUT &&
- smc->clcsock->sk->sk_state != TCP_CLOSE) {
- rc = __smc_connect(smc);
- if (rc < 0)
- mask |= EPOLLERR;
- /* success cases including fallback */
- mask |= EPOLLOUT | EPOLLWRNORM;
- }
- }
} else {
- if (sk->sk_state != SMC_CLOSED) {
- release_sock(sk);
+ if (sk->sk_state != SMC_CLOSED)
sock_poll_wait(file, sk_sleep(sk), wait);
- lock_sock(sk);
- }
if (sk->sk_err)
mask |= EPOLLERR;
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
}
if (smc->conn.urg_state == SMC_URG_VALID)
mask |= EPOLLPRI;
-
}
- release_sock(sk);
- sock_put(sk);
return mask;
}
lock_sock(sk);
rc = -ENOTCONN;
- if ((sk->sk_state != SMC_LISTEN) &&
- (sk->sk_state != SMC_ACTIVE) &&
+ if ((sk->sk_state != SMC_ACTIVE) &&
(sk->sk_state != SMC_PEERCLOSEWAIT1) &&
(sk->sk_state != SMC_PEERCLOSEWAIT2) &&
(sk->sk_state != SMC_APPCLOSEWAIT1) &&
if (optlen < sizeof(int))
return -EINVAL;
- get_user(val, (int __user *)optval);
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
lock_sock(sk);
switch (optname) {
smc = smc_sk(sock->sk);
conn = &smc->conn;
+ lock_sock(&smc->sk);
if (smc->use_fallback) {
- if (!smc->clcsock)
+ if (!smc->clcsock) {
+ release_sock(&smc->sk);
return -EBADF;
- return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+ }
+ answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+ release_sock(&smc->sk);
+ return answ;
}
switch (cmd) {
case SIOCINQ: /* same as FIONREAD */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
break;
case SIOCOUTQ:
/* output queue size (not send + not acked) */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
break;
case SIOCOUTQNSD:
/* output queue size (not send only) */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
answ = smc_tx_prepared_sends(&smc->conn);
break;
case SIOCATMARK:
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED) {
answ = 0;
}
break;
default:
+ release_sock(&smc->sk);
return -ENOIOCTLCMD;
}
+ release_sock(&smc->sk);
return put_user(answ, (int __user *)arg);
}
struct work_struct close_work; /* peer sent some closing */
};
+struct smc_connect_info {
+ int flags;
+ int alen;
+ struct sockaddr addr;
+};
+
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
+ struct smc_connect_info *connect_info; /* connect address & flags */
+ struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
struct list_head accept_q; /* sockets to be accepted */
/* force immediate tx of current consumer cursor, but
* under send_lock to guarantee arrival in seqno-order
*/
- smc_tx_sndbuf_nonempty(conn);
+ if (smc->sk.sk_state != SMC_INIT)
+ smc_tx_sndbuf_nonempty(conn);
}
}
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type)
{
+ long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
struct sock *clc_sk = smc->clcsock->sk;
struct smc_clc_msg_hdr *clcm = buf;
struct msghdr msg = {NULL, 0};
memset(&msg, 0, sizeof(struct msghdr));
iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
krflags = MSG_WAITALL;
- smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
smc->sk.sk_err = EPROTO;
}
out:
+ smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
return reason_code;
}
}
switch (sk->sk_state) {
case SMC_INIT:
+ sk->sk_state = SMC_PEERABORTWAIT;
+ break;
case SMC_ACTIVE:
sk->sk_state = SMC_PEERABORTWAIT;
release_sock(sk);
void smc_tx_consumer_update(struct smc_connection *conn, bool force)
{
- union smc_host_cursor cfed, cons;
+ union smc_host_cursor cfed, cons, prod;
+ int sender_free = conn->rmb_desc->len;
int to_confirm;
smc_curs_write(&cons,
smc_curs_read(&conn->rx_curs_confirmed, conn),
conn);
to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+ if (to_confirm > conn->rmbe_update_limit) {
+ smc_curs_write(&prod,
+ smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+ conn);
+ sender_free = conn->rmb_desc->len -
+ smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+ }
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
force ||
((to_confirm > conn->rmbe_update_limit) &&
- ((to_confirm > (conn->rmb_desc->len / 2)) ||
+ ((sender_free <= (conn->rmb_desc->len / 2)) ||
conn->local_rx_ctrl.prod_flags.write_blocked))) {
if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
conn->alert_token_local) { /* connection healthy */
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/nospec.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
static int sock_mmap(struct file *file, struct vm_area_struct *vma);
static int sock_close(struct inode *inode, struct file *file);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
- __poll_t events);
-static __poll_t sock_poll_mask(struct file *file, __poll_t);
-static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
+static __poll_t sock_poll(struct file *file,
+ struct poll_table_struct *wait);
static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
.llseek = no_llseek,
.read_iter = sock_read_iter,
.write_iter = sock_write_iter,
- .get_poll_head = sock_get_poll_head,
- .poll_mask = sock_poll_mask,
.poll = sock_poll,
.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
- struct qstr name = { .name = "" };
- struct path path;
struct file *file;
- if (dname) {
- name.name = dname;
- name.len = strlen(name.name);
- } else if (sock->sk) {
- name.name = sock->sk->sk_prot_creator->name;
- name.len = strlen(name.name);
- }
- path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
- if (unlikely(!path.dentry)) {
- sock_release(sock);
- return ERR_PTR(-ENOMEM);
- }
- path.mnt = mntget(sock_mnt);
+ if (!dname)
+ dname = sock->sk ? sock->sk->sk_prot_creator->name : "";
- d_instantiate(path.dentry, SOCK_INODE(sock));
-
- file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
- &socket_file_ops);
+ file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
+ O_RDWR | (flags & O_NONBLOCK),
+ &socket_file_ops);
if (IS_ERR(file)) {
- /* drop dentry, keep inode for a bit */
- ihold(d_inode(path.dentry));
- path_put(&path);
- /* ... and now kill it properly */
sock_release(sock);
return file;
}
sock->file = file;
- file->f_flags = O_RDWR | (flags & O_NONBLOCK);
file->private_data = sock;
return file;
}
}
EXPORT_SYMBOL(sock_create_lite);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
- __poll_t events)
-{
- struct socket *sock = file->private_data;
-
- if (!sock->ops->poll_mask)
- return NULL;
- sock_poll_busy_loop(sock, events);
- return sk_sleep(sock->sk);
-}
-
-static __poll_t sock_poll_mask(struct file *file, __poll_t events)
-{
- struct socket *sock = file->private_data;
-
- /*
- * We need to be sure we are in sync with the socket flags modification.
- *
- * This memory barrier is paired in the wq_has_sleeper.
- */
- smp_mb();
-
- /* this socket can poll_ll so tell the system call */
- return sock->ops->poll_mask(sock, events) |
- (sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
-}
-
/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
struct socket *sock = file->private_data;
- __poll_t events = poll_requested_events(wait), mask = 0;
-
- if (sock->ops->poll) {
- sock_poll_busy_loop(sock, events);
- mask = sock->ops->poll(file, sock, wait);
- } else if (sock->ops->poll_mask) {
- sock_poll_wait(file, sock_get_poll_head(file, events), wait);
- mask = sock->ops->poll_mask(sock, events);
- }
+ __poll_t events = poll_requested_events(wait);
- return mask | sock_poll_busy_flag(sock);
+ sock_poll_busy_loop(sock, events);
+ if (!sock->ops->poll)
+ return 0;
+ return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
if (call < 1 || call > SYS_SENDMMSG)
return -EINVAL;
+ call = array_index_nospec(call, SYS_SENDMMSG + 1);
len = nargs[call];
if (len > sizeof(a))
bool sock_is_registered(int family)
{
- return family < NPROTO && rcu_access_pointer(net_families[family]);
+ return family < NPROTO &&
+ rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]);
}
static int __init sock_init(void)
*/
struct strp_msg strp;
int accum_len;
- int early_eaten;
};
static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
head = strp->skb_head;
if (head) {
/* Message already in progress */
-
- stm = _strp_msg(head);
- if (unlikely(stm->early_eaten)) {
- /* Already some number of bytes on the receive sock
- * data saved in skb_head, just indicate they
- * are consumed.
- */
- eaten = orig_len <= stm->early_eaten ?
- orig_len : stm->early_eaten;
- stm->early_eaten -= eaten;
-
- return eaten;
- }
-
if (unlikely(orig_offset)) {
/* Getting data with a non-zero offset when a message is
* in progress is not expected. If it does happen, we
}
stm->accum_len += cand_len;
+ eaten += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
break;
/* Lower sock lock held */
void strp_data_ready(struct strparser *strp)
{
- if (unlikely(strp->stopped))
+ if (unlikely(strp->stopped) || strp->paused)
return;
/* This check is needed to synchronize with do_strp_work.
return;
}
- if (strp->paused)
- return;
-
if (strp->need_bytes) {
if (strp_peek_len(strp) < strp->need_bytes)
return;
task->tk_status = -EAGAIN;
goto out_unlock;
}
- if (!bc_prealloc(req) && !req->rq_xmit_bytes_sent)
- req->rq_xid = xprt_alloc_xid(xprt);
ret = true;
out_unlock:
spin_unlock_bh(&xprt->transport_lock);
static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
{
- return (__force __be32)xprt->xid++;
+ __be32 xid;
+
+ spin_lock(&xprt->reserve_lock);
+ xid = (__force __be32)xprt->xid++;
+ spin_unlock(&xprt->reserve_lock);
+ return xid;
}
static inline void xprt_init_xid(struct rpc_xprt *xprt)
req->rq_task = task;
req->rq_xprt = xprt;
req->rq_buffer = NULL;
+ req->rq_xid = xprt_alloc_xid(xprt);
req->rq_connect_cookie = xprt->connect_cookie - 1;
req->rq_bytes_sent = 0;
req->rq_snd_buf.len = 0;
}
/* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer
+ * Returns true if message should be dropped by caller, i.e., if it is a
+ * trial message or we are inside trial period. Otherwise false.
*/
static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
struct tipc_media_addr *maddr,
msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
}
+ /* Accept regular link requests/responses only after trial period */
if (mtyp != DSC_TRIAL_MSG)
- return false;
+ return trial;
sugg_addr = tipc_node_try_addr(net, peer_id, src);
if (sugg_addr)
{
struct tipc_discoverer *d = from_timer(d, t, timer);
struct tipc_net *tn = tipc_net(d->net);
- u32 self = tipc_own_addr(d->net);
struct tipc_media_addr maddr;
struct sk_buff *skb = NULL;
struct net *net = d->net;
goto exit;
}
- /* Did we just leave the address trial period ? */
- if (!self && !time_before(jiffies, tn->addr_trial_end)) {
- self = tn->trial_addr;
- tipc_net_finalize(net, self);
- msg_set_prevnode(buf_msg(d->skb), self);
+ /* Trial period over ? */
+ if (!time_before(jiffies, tn->addr_trial_end)) {
+ /* Did we just leave it ? */
+ if (!tipc_own_addr(net))
+ tipc_net_finalize(net, tn->trial_addr);
+
msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+ msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
}
/* Adjust timeout interval according to discovery phase */
void tipc_net_finalize(struct net *net, u32 addr)
{
- tipc_set_node_addr(net, addr);
- smp_mb();
- tipc_named_reinit(net);
- tipc_sk_reinit(net);
- tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
- TIPC_CLUSTER_SCOPE, 0, addr);
+ struct tipc_net *tn = tipc_net(net);
+
+ if (!cmpxchg(&tn->node_addr, 0, addr)) {
+ tipc_set_node_addr(net, addr);
+ tipc_named_reinit(net);
+ tipc_sk_reinit(net);
+ tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+ TIPC_CLUSTER_SCOPE, 0, addr);
+ }
}
void tipc_net_stop(struct net *net)
}
/* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not
+ * Returns suggested address if any, otherwise 0
*/
u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
{
if (n) {
addr = n->addr;
tipc_node_put(n);
+ return addr;
}
- /* Even this node may be in trial phase */
+
+ /* Even this node may be in conflict */
if (tn->trial_addr == addr)
return tipc_node_suggest_addr(net, addr);
- return addr;
+ return 0;
}
void tipc_node_check_dest(struct net *net, u32 addr,
}
/**
- * tipc_poll - read pollmask
+ * tipc_poll - read and possibly block on pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
+ * @wait: ???
*
* Returns pollmask value
*
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
-static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t tipc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
__poll_t revents = 0;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
.socketpair = tipc_socketpair,
.accept = sock_no_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = sock_no_listen,
.shutdown = tipc_shutdown,
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
}
static int tls_do_encryption(struct tls_context *tls_ctx,
- struct tls_sw_context_tx *ctx, size_t data_len,
- gfp_t flags)
+ struct tls_sw_context_tx *ctx,
+ struct aead_request *aead_req,
+ size_t data_len)
{
- unsigned int req_size = sizeof(struct aead_request) +
- crypto_aead_reqsize(ctx->aead_send);
- struct aead_request *aead_req;
int rc;
- aead_req = kzalloc(req_size, flags);
- if (!aead_req)
- return -ENOMEM;
-
ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size;
ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size;
ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size;
ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size;
- kfree(aead_req);
return rc;
}
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+ struct aead_request *req;
int rc;
+ req = kzalloc(sizeof(struct aead_request) +
+ crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+ if (!req)
+ return -ENOMEM;
+
sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1);
sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
tls_ctx->pending_open_record_frags = 0;
set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags);
- rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size,
- sk->sk_allocation);
+ rc = tls_do_encryption(tls_ctx, ctx, req, ctx->sg_plaintext_size);
if (rc < 0) {
/* If we are called from write_space and
* we fail, we need to set this SOCK_NOSPACE
* to trigger another write_space in the future.
*/
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- return rc;
+ goto out_req;
}
free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem,
tls_err_abort(sk, EBADMSG);
tls_advance_record_sn(sk, &tls_ctx->tx);
+out_req:
+ kfree(req);
return rc;
}
ret = tls_push_record(sk, msg->msg_flags, record_type);
if (!ret)
continue;
- if (ret == -EAGAIN)
+ if (ret < 0)
goto send_end;
copied -= try_to_copy;
return NULL;
}
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ return NULL;
+
if (sock_flag(sk, SOCK_DONE))
return NULL;
nsg = skb_to_sgvec(skb, &sgin[1],
rxm->offset + tls_ctx->rx.prepend_size,
rxm->full_len - tls_ctx->rx.prepend_size);
+ if (nsg < 0) {
+ ret = nsg;
+ goto out;
+ }
tls_make_aad(ctx->rx_aad_ciphertext,
rxm->full_len - tls_ctx->rx.overhead_size,
rxm->full_len - tls_ctx->rx.overhead_size,
skb, sk->sk_allocation);
+out:
if (sgin != &sgin_arr[0])
kfree(sgin);
struct sk_buff *skb;
ssize_t copied = 0;
bool cmsg = false;
- int err = 0;
+ int target, err = 0;
long timeo;
flags |= nonblock;
lock_sock(sk);
+ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
bool zc = false;
goto recv_end;
}
}
+ /* If we have a new message from strparser, continue now. */
+ if (copied >= target && !ctx->recv_pkt)
+ break;
} while (len);
recv_end:
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll_mask(struct socket *, __poll_t);
-static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
+static __poll_t unix_dgram_poll(struct file *, struct socket *,
+ poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll_mask = unix_poll_mask,
+ .poll = unix_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
- .poll_mask = unix_dgram_poll_mask,
+ .poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll_mask = unix_dgram_poll_mask,
+ .poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
return err;
}
-static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err)
return mask;
}
-static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk, *other;
- int writable;
- __poll_t mask = 0;
+ unsigned int writable;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
}
/* No write status requested, avoid expensive OUT tests. */
- if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+ if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
return mask;
writable = unix_writable(sk);
return transport->shutdown(vsock_sk(sk), mode);
}
-void vsock_pending_work(struct work_struct *work)
+static void vsock_pending_work(struct work_struct *work)
{
struct sock *sk;
struct sock *listener;
struct vsock_sock *vsk;
bool cleanup;
- vsk = container_of(work, struct vsock_sock, dwork.work);
+ vsk = container_of(work, struct vsock_sock, pending_work.work);
sk = sk_vsock(vsk);
listener = vsk->listener;
cleanup = true;
sock_put(sk);
sock_put(listener);
}
-EXPORT_SYMBOL_GPL(vsock_pending_work);
/**** SOCKET OPERATIONS ****/
return retval;
}
+static void vsock_connect_timeout(struct work_struct *work);
+
struct sock *__vsock_create(struct net *net,
struct socket *sock,
struct sock *parent,
vsk->sent_request = false;
vsk->ignore_connecting_rst = false;
vsk->peer_shutdown = 0;
+ INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
+ INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);
psk = parent ? vsock_sk(parent) : NULL;
if (parent) {
return err;
}
-static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t vsock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
- struct sock *sk = sock->sk;
- struct vsock_sock *vsk = vsock_sk(sk);
- __poll_t mask = 0;
+ struct sock *sk;
+ __poll_t mask;
+ struct vsock_sock *vsk;
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
if (sk->sk_err)
/* Signify that there has been an error on this socket. */
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = vsock_getname,
- .poll_mask = vsock_poll_mask,
+ .poll = vsock_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = vsock_shutdown,
struct vsock_sock *vsk;
int cancel = 0;
- vsk = container_of(work, struct vsock_sock, dwork.work);
+ vsk = container_of(work, struct vsock_sock, connect_work.work);
sk = sk_vsock(vsk);
lock_sock(sk);
* timeout fires.
*/
sock_hold(sk);
- INIT_DELAYED_WORK(&vsk->dwork,
- vsock_connect_timeout);
- schedule_delayed_work(&vsk->dwork, timeout);
+ schedule_delayed_work(&vsk->connect_work, timeout);
/* Skip ahead to preserve error code set above. */
goto out_wait;
.socketpair = sock_no_socketpair,
.accept = vsock_accept,
.getname = vsock_getname,
- .poll_mask = vsock_poll_mask,
+ .poll = vsock_poll,
.ioctl = sock_no_ioctl,
.listen = vsock_listen,
.shutdown = vsock_shutdown,
return -ENODEV;
}
- if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
+ if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
return virtio_transport_send_pkt_loopback(vsock, pkt);
if (pkt->reply)
vpending->listener = sk;
sock_hold(sk);
sock_hold(pending);
- INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work);
- schedule_delayed_work(&vpending->dwork, HZ);
+ schedule_delayed_work(&vpending->pending_work, HZ);
out:
return err;
nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
list_del_rcu(&wdev->list);
+ synchronize_rcu();
rdev->devlist_generation++;
switch (wdev->iftype) {
params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) |
BIT(NL80211_STA_FLAG_MFP) |
BIT(NL80211_STA_FLAG_AUTHORIZED);
+ break;
default:
return -EINVAL;
}
nl80211_check_s32);
/*
* Check HT operation mode based on
- * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+ * IEEE 802.11-2016 9.4.2.57 HT Operation element.
*/
if (tb[NL80211_MESHCONF_HT_OPMODE]) {
ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
return -EINVAL;
- if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
- (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
+ /* NON_HT_STA bit is reserved, but some programs set it */
+ ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
- switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
- case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
- case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
- if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
- return -EINVAL;
- break;
- case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
- case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
- if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
- break;
- }
cfg->ht_opmode = ht_opmode;
mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
}
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy,
- info->extack);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy,
+ info->extack);
+ if (err)
+ goto error;
+
err = -EINVAL;
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy, NULL);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy, NULL);
+ if (err)
+ return err;
+
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
return -EINVAL;
EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
static int __nl80211_rx_control_port(struct net_device *dev,
- const u8 *buf, size_t len,
- const u8 *addr, u16 proto,
+ struct sk_buff *skb,
bool unencrypted, gfp_t gfp)
{
struct wireless_dev *wdev = dev->ieee80211_ptr;
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+ struct ethhdr *ehdr = eth_hdr(skb);
+ const u8 *addr = ehdr->h_source;
+ u16 proto = be16_to_cpu(skb->protocol);
struct sk_buff *msg;
void *hdr;
+ struct nlattr *frame;
+
u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid);
if (!nlportid)
return -ENOENT;
- msg = nlmsg_new(100 + len, gfp);
+ msg = nlmsg_new(100 + skb->len, gfp);
if (!msg)
return -ENOMEM;
nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
NL80211_ATTR_PAD) ||
- nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) ||
(unencrypted && nla_put_flag(msg,
NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT)))
goto nla_put_failure;
+ frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len);
+ if (!frame)
+ goto nla_put_failure;
+
+ skb_copy_bits(skb, 0, nla_data(frame), skb->len);
genlmsg_end(msg, hdr);
return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
}
bool cfg80211_rx_control_port(struct net_device *dev,
- const u8 *buf, size_t len,
- const u8 *addr, u16 proto, bool unencrypted)
+ struct sk_buff *skb, bool unencrypted)
{
int ret;
- trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted);
- ret = __nl80211_rx_control_port(dev, buf, len, addr, proto,
- unencrypted, GFP_ATOMIC);
+ trace_cfg80211_rx_control_port(dev, skb, unencrypted);
+ ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC);
trace_cfg80211_return_bool(ret == 0);
return ret == 0;
}
* as some drivers used this to restore its orig_* reg domain.
*/
if (initiator == NL80211_REGDOM_SET_BY_CORE &&
- wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)
+ wiphy->regulatory_flags & REGULATORY_CUSTOM_REG &&
+ !(wiphy->regulatory_flags &
+ REGULATORY_WIPHY_SELF_MANAGED))
reg_call_notifier(wiphy, lr);
return;
}
}
}
-static bool reg_only_self_managed_wiphys(void)
-{
- struct cfg80211_registered_device *rdev;
- struct wiphy *wiphy;
- bool self_managed_found = false;
-
- ASSERT_RTNL();
-
- list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
- wiphy = &rdev->wiphy;
- if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
- self_managed_found = true;
- else
- return false;
- }
-
- /* make sure at least one self-managed wiphy exists */
- return self_managed_found;
-}
-
/*
* Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_*
* Regulatory hints come on a first come first serve basis and we
spin_unlock(®_requests_lock);
notify_self_managed_wiphys(reg_request);
- if (reg_only_self_managed_wiphys()) {
- reg_free_request(reg_request);
- return;
- }
reg_process_hint(reg_request);
);
TRACE_EVENT(cfg80211_rx_control_port,
- TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len,
- const u8 *addr, u16 proto, bool unencrypted),
- TP_ARGS(netdev, buf, len, addr, proto, unencrypted),
+ TP_PROTO(struct net_device *netdev, struct sk_buff *skb,
+ bool unencrypted),
+ TP_ARGS(netdev, skb, unencrypted),
TP_STRUCT__entry(
NETDEV_ENTRY
- MAC_ENTRY(addr)
+ __field(int, len)
+ MAC_ENTRY(from)
__field(u16, proto)
__field(bool, unencrypted)
),
TP_fast_assign(
NETDEV_ASSIGN;
- MAC_ASSIGN(addr, addr);
- __entry->proto = proto;
+ __entry->len = skb->len;
+ MAC_ASSIGN(from, eth_hdr(skb)->h_source);
+ __entry->proto = be16_to_cpu(skb->protocol);
__entry->unencrypted = unencrypted;
),
- TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s",
- NETDEV_PR_ARG, MAC_PR_ARG(addr),
+ TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s",
+ NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from),
__entry->proto, BOOL_TO_STR(__entry->unencrypted))
);
if (!rdev->ops->get_station)
return -EOPNOTSUPP;
+ memset(sinfo, 0, sizeof(*sinfo));
+
return rdev_get_station(rdev, dev, mac_addr, sinfo);
}
EXPORT_SYMBOL(cfg80211_get_station);
.socketpair = sock_no_socketpair,
.accept = x25_accept,
.getname = x25_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = x25_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_x25_ioctl,
long npgs;
int err;
- umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL);
+ umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs),
+ GFP_KERNEL | __GFP_NOWARN);
if (!umem->pgs)
return -ENOMEM;
{
int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len);
- if (err) {
- xdp_return_buff(xdp);
+ if (err)
xs->rx_dropped++;
- }
return err;
}
u64 addr;
int err;
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+ return -EINVAL;
+
if (!xskq_peek_addr(xs->umem->fq, &addr) ||
len > xs->umem->chunk_size_nohr) {
xs->rx_dropped++;
{
u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
struct xdp_sock *xs = xdp_sk(skb->sk);
+ unsigned long flags;
+ spin_lock_irqsave(&xs->tx_completion_lock, flags);
WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr));
+ spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
sock_wfree(skb);
}
struct sk_buff *skb;
int err = 0;
- if (unlikely(!xs->tx))
- return -ENOBUFS;
-
mutex_lock(&xs->mutex);
while (xskq_peek_desc(xs->tx, &desc)) {
goto out;
}
- if (xskq_reserve_addr(xs->umem->cq)) {
- err = -EAGAIN;
- goto out;
- }
-
- len = desc.len;
- if (unlikely(len > xs->dev->mtu)) {
- err = -EMSGSIZE;
+ if (xskq_reserve_addr(xs->umem->cq))
goto out;
- }
- if (xs->queue_id >= xs->dev->real_num_tx_queues) {
- err = -ENXIO;
+ if (xs->queue_id >= xs->dev->real_num_tx_queues)
goto out;
- }
+ len = desc.len;
skb = sock_alloc_send_skb(sk, len, 1, &err);
if (unlikely(!skb)) {
err = -EAGAIN;
skb->destructor = xsk_destruct_skb;
err = dev_direct_xmit(skb, xs->queue_id);
+ xskq_discard_desc(xs->tx);
/* Ignore NET_XMIT_CN as packet might have been sent */
if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
- err = -EAGAIN;
- /* SKB consumed by dev_direct_xmit() */
+ /* SKB completed but not sent */
+ err = -EBUSY;
goto out;
}
sent_frame = true;
- xskq_discard_desc(xs->tx);
}
out:
return -ENXIO;
if (unlikely(!(xs->dev->flags & IFF_UP)))
return -ENETDOWN;
+ if (unlikely(!xs->tx))
+ return -ENOBUFS;
if (need_wait)
return -EOPNOTSUPP;
return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
}
-static __poll_t xsk_poll_mask(struct socket *sock, __poll_t events)
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
{
- __poll_t mask = datagram_poll_mask(sock, events);
+ unsigned int mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
struct xdp_sock *xs = xdp_sk(sk);
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = xsk_poll_mask,
+ .poll = xsk_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
xs = xdp_sk(sk);
mutex_init(&xs->mutex);
+ spin_lock_init(&xs->tx_completion_lock);
local_bh_disable();
sock_prot_inuse_add(net, &xsk_proto, 1);
return (entries > dcnt) ? dcnt : entries;
}
-static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer)
-{
- return q->nentries - (producer - q->cons_tail);
-}
-
static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
{
- u32 free_entries = xskq_nb_free_lazy(q, producer);
+ u32 free_entries = q->nentries - (producer - q->cons_tail);
if (free_entries >= dcnt)
return free_entries;
{
struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
- if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0)
+ if (xskq_nb_free(q, q->prod_tail, 1) == 0)
return -ENOSPC;
ring->desc[q->prod_tail++ & q->ring_mask] = addr;
static inline bool xskq_empty_desc(struct xsk_queue *q)
{
- return xskq_nb_free(q, q->prod_tail, 1) == q->nentries;
+ return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries;
}
void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props);
if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
return make_blackhole(net, dst_orig->ops->family, dst_orig);
+ if (IS_ERR(dst))
+ dst_release(dst_orig);
+
return dst;
}
EXPORT_SYMBOL(xfrm_lookup_route);
{
struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
- if (nlsk)
- return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
- else
- return -1;
+ if (!nlsk) {
+ kfree_skb(skb);
+ return -EPIPE;
+ }
+
+ return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
}
static inline unsigned int xfrm_spdinfo_msgsize(void)
#ifdef CONFIG_XFRM_SUB_POLICY
static int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
{
- struct xfrm_userpolicy_type upt = {
- .type = type,
- };
+ struct xfrm_userpolicy_type upt;
+
+ /* Sadly there are two holes in struct xfrm_userpolicy_type */
+ memset(&upt, 0, sizeof(upt));
+ upt.type = type;
return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt);
}
--- /dev/null
+cpustat
+fds_example
+lathist
+load_sock_ops
+lwt_len_hist
+map_perf_test
+offwaketime
+per_socket_stats_example
+sampleip
+sock_example
+sockex1
+sockex2
+sockex3
+spintest
+syscall_nrs.h
+syscall_tp
+task_fd_query
+tc_l2_redirect
+test_cgrp2_array_pin
+test_cgrp2_attach
+test_cgrp2_attach2
+test_cgrp2_sock
+test_cgrp2_sock2
+test_current_task_under_cgroup
+test_lru_dist
+test_map_in_map
+test_overhead
+test_probe_write_user
+trace_event
+trace_output
+tracex1
+tracex2
+tracex3
+tracex4
+tracex5
+tracex6
+tracex7
+xdp1
+xdp2
+xdp_adjust_tail
+xdp_fwd
+xdp_monitor
+xdp_redirect
+xdp_redirect_cpu
+xdp_redirect_map
+xdp_router_ipv4
+xdp_rxq_info
+xdp_tx_iptunnel
+xdpsock
*/
#define KBUILD_MODNAME "foo"
#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
return 0;
}
-struct vlan_hdr {
- uint16_t h_vlan_TCI;
- uint16_t h_vlan_encapsulated_proto;
-};
-
SEC("varlen")
int handle_ingress(struct __sk_buff *skb)
{
*/
#define _GNU_SOURCE
#include <sched.h>
+#include <errno.h>
#include <stdio.h>
#include <sys/types.h>
#include <asm/unistd.h>
exit(1);
}
start_time = time_get_ns();
- for (i = 0; i < MAX_CNT; i++)
- write(fd, buf, sizeof(buf));
+ for (i = 0; i < MAX_CNT; i++) {
+ if (write(fd, buf, sizeof(buf)) < 0) {
+ printf("task rename failed: %s\n", strerror(errno));
+ close(fd);
+ return;
+ }
+ }
printf("task_rename:%d: %lld events per sec\n",
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
close(fd);
exit(1);
}
start_time = time_get_ns();
- for (i = 0; i < MAX_CNT; i++)
- read(fd, buf, sizeof(buf));
+ for (i = 0; i < MAX_CNT; i++) {
+ if (read(fd, buf, sizeof(buf)) < 0) {
+ printf("failed to read from /dev/urandom: %s\n", strerror(errno));
+ close(fd);
+ return;
+ }
+ }
printf("urandom_read:%d: %lld events per sec\n",
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
close(fd);
}
}
+static inline int generate_load(void)
+{
+ if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) {
+ printf("failed to generate some load with dd: %s\n", strerror(errno));
+ return -1;
+ }
+
+ return 0;
+}
+
static void test_perf_event_all_cpu(struct perf_event_attr *attr)
{
int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0);
}
- system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+ if (generate_load() < 0) {
+ error = 1;
+ goto all_cpu_err;
+ }
print_stacks();
all_cpu_err:
for (i--; i >= 0; i--) {
static void test_perf_event_task(struct perf_event_attr *attr)
{
- int pmu_fd;
+ int pmu_fd, error = 0;
/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
* Enabling inherit will cause bpf_perf_prog_read_time helper failure.
}
assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0);
- system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+ if (generate_load() < 0) {
+ error = 1;
+ goto err;
+ }
print_stacks();
+err:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
close(pmu_fd);
+ if (error)
+ int_exit(0);
}
static void test_bpf_perf_event(void)
BPF_FILE=xdp2skb_meta_kern.o
DIR=$(dirname $0)
-export TC=/usr/sbin/tc
-export IP=/usr/sbin/ip
+[ -z "$TC" ] && TC=tc
+[ -z "$IP" ] && IP=ip
function usage() {
echo ""
local allow_fail="$2"
shift 2
if [[ -n "$VERBOSE" ]]; then
- echo "$(basename $cmd) $@"
+ echo "$cmd $@"
fi
if [[ -n "$DRYRUN" ]]; then
return
struct ethhdr *eth = data;
struct ipv6hdr *ip6h;
struct iphdr *iph;
- int out_index;
u16 h_proto;
u64 nh_off;
+ int rc;
nh_off = sizeof(*eth);
if (data + nh_off > data_end)
fib_params.ifindex = ctx->ingress_ifindex;
- out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+ rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
/* verify egress index has xdp support
* TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
* NOTE: without verification that egress index supports XDP
* forwarding packets are dropped.
*/
- if (out_index > 0) {
+ if (rc == 0) {
if (h_proto == htons(ETH_P_IP))
ip_decrease_ttl(iph);
else if (h_proto == htons(ETH_P_IPV6))
memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
- return bpf_redirect_map(&tx_port, out_index, 0);
+ return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
}
return XDP_PASS;
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
-#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+#define MAX_CPUS 64 /* WARNING - sync with _user.c */
/* Special map type that can XDP_REDIRECT frames to another CPU */
struct bpf_map_def SEC("maps") cpu_map = {
#include <arpa/inet.h>
#include <linux/if_link.h>
-#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+#define MAX_CPUS 64 /* WARNING - sync with _kern.c */
/* How many xdp_progs are defined in _kern.c */
#define MAX_PROG 5
* procedure.
*/
create_cpu_entry(1, 1024, 0, false);
- create_cpu_entry(1, 128, 0, false);
+ create_cpu_entry(1, 8, 0, false);
create_cpu_entry(1, 16000, 0, false);
}
int ret;
ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
- if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN)
+ if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY)
return;
lassert(0);
}
return "(invalid)";
}
+static struct page *__mbochs_get_page(struct mdev_state *mdev_state,
+ pgoff_t pgoff);
static struct page *mbochs_get_page(struct mdev_state *mdev_state,
pgoff_t pgoff);
MBOCHS_MEMORY_BAR_OFFSET + mdev_state->memsize) {
pos -= MBOCHS_MMIO_BAR_OFFSET;
poff = pos & ~PAGE_MASK;
- pg = mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
+ pg = __mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
map = kmap(pg);
if (is_write)
memcpy(map + poff, buf, count);
dev_dbg(dev, "%s: %d pages released\n", __func__, count);
}
-static int mbochs_region_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_region_vm_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mdev_state *mdev_state = vma->vm_private_data;
return 0;
}
-static int mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mbochs_dmabuf *dmabuf = vma->vm_private_data;
mutex_unlock(&mdev_state->ops_lock);
}
-static void *mbochs_kmap_atomic_dmabuf(struct dma_buf *buf,
- unsigned long page_num)
+static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
{
struct mbochs_dmabuf *dmabuf = buf->priv;
struct page *page = dmabuf->pages[page_num];
- return kmap_atomic(page);
+ return kmap(page);
}
-static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
+static void mbochs_kunmap_dmabuf(struct dma_buf *buf, unsigned long page_num,
+ void *vaddr)
{
- struct mbochs_dmabuf *dmabuf = buf->priv;
- struct page *page = dmabuf->pages[page_num];
-
- return kmap(page);
+ kunmap(vaddr);
}
static struct dma_buf_ops mbochs_dmabuf_ops = {
.map_dma_buf = mbochs_map_dmabuf,
.unmap_dma_buf = mbochs_unmap_dmabuf,
.release = mbochs_release_dmabuf,
- .map_atomic = mbochs_kmap_atomic_dmabuf,
.map = mbochs_kmap_dmabuf,
+ .unmap = mbochs_kunmap_dmabuf,
.mmap = mbochs_mmap_dmabuf,
};
# Prefix -I with $(srctree) if it is not an absolute path.
# skip if -I has no parameter
addtree = $(if $(patsubst -I%,%,$(1)), \
-$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)))
+$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)),$(1))
# Find all -I options and call addtree
flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o)))
"$(CC_FLAGS_FTRACE)" ]; then \
$(sub_cmd_record_mcount) \
fi;
+endif # -record-mcount
endif # CONFIG_FTRACE_MCOUNT_RECORD
ifdef CONFIG_STACK_VALIDATION
objtool_args += --retpoline
endif
endif
-endif
ifdef CONFIG_MODVERSIONS
# We never want them to be removed automatically.
.SECONDARY: $(targets)
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable se we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
$(subdir-ymn):
$(Q)$(MAKE) $(clean)=$@
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable se we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
$(subdir-ym):
$(Q)$(MAKE) $(modbuiltin)=$@
-
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable se we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
$(modules):
$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
-
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable so we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
include $(cmd_files)
endif
-
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable se we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
$(modules):
$(call cmd,sign_ko,$(MODLIB)/$(modinst_dir))
-# Declare the contents of the .PHONY variable as phony. We keep that
-# information in a variable se we can use it in if_changed and friends.
-
.PHONY: $(PHONY)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=alignment)
endif
-ifdef CONFIG_UBSAN_NULL
- CFLAGS_UBSAN += $(call cc-option, -fsanitize=null)
-endif
-
# -fsanitize=* options makes GCC less smart than usual and
# increase number of 'maybe-uninitialized false-positives
CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized)
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1
#include <stdio.h>
int main(void)
{
"A patch subject line should describe the change not the tool that found it\n" . $herecurr);
}
-# Check for old stable address
- if ($line =~ /^\s*cc:\s*.*<?\bstable\@kernel\.org\b>?.*$/i) {
- ERROR("STABLE_ADDRESS",
- "The 'stable' address should be 'stable\@vger.kernel.org'\n" . $herecurr);
- }
-
# Check for unwanted Gerrit info
if ($in_commit_log && $line =~ /^\s*change-id:/i) {
ERROR("GERRIT_CHANGE_ID",
defined $stat &&
$stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s &&
$1 !~ /^_*volatile_*$/) {
- my $specifier;
- my $extension;
- my $bad_specifier = "";
my $stat_real;
my $lc = $stat =~ tr@\n@@;
$lc = $lc + $linenr;
for (my $count = $linenr; $count <= $lc; $count++) {
+ my $specifier;
+ my $extension;
+ my $bad_specifier = "";
my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
$fmt =~ s/%%//g;
);
if ($help != 0) {
- print "$scriptname [--help] [--fix-rst]\n";
+ print "$scriptname [--help] [--fix]\n";
exit -1;
}
my $f = $1;
my $ln = $2;
- # Makefiles contain nasty expressions to parse docs
- next if ($f =~ m/Makefile/);
+ # Makefiles and scripts contain nasty expressions to parse docs
+ next if ($f =~ m/Makefile/ || $f =~ m/\.sh$/);
+
# Skip this script
next if ($f eq $scriptname);
- if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*+-]*),) {
+ if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*\[\]\?+-]*)(.*),) {
my $prefix = $1;
my $ref = $2;
my $base = $2;
+ my $extra = $3;
+
+ # some file references are like:
+ # /usr/src/linux/Documentation/DMA-{API,mapping}.txt
+ # For now, ignore them
+ next if ($extra =~ m/^{/);
+
+ # Remove footnotes at the end like:
+ # Documentation/devicetree/dt-object-internal.txt[1]
+ $ref =~ s/(txt|rst)\[\d+]$/$1/;
+
+ # Remove ending ']' without any '['
+ $ref =~ s/\].*// if (!($ref =~ m/\[/));
+ # Remove puntuation marks at the end
$ref =~ s/[\,\.]+$//;
my $fulref = "$prefix$ref";
# Check if exists, evaluating wildcards
next if (grep -e, glob("$ref $fulref"));
+ # Accept relative Documentation patches for tools/
+ if ($f =~ m/tools/) {
+ my $path = $f;
+ $path =~ s,(.*)/.*,$1,;
+ next if (grep -e, glob("$path/$ref $path/$fulref"));
+ }
+
if ($fix) {
- if (!($ref =~ m/(devicetree|scripts|Kconfig|Kbuild)/)) {
+ if (!($ref =~ m/(scripts|Kconfig|Kbuild)/)) {
$broken_ref{$ref}++;
}
} else {
# get just the basename
$new =~ s,.*/,,;
- # Seek for the same name on another place, as it may have been moved
my $f="";
- $f = qx(find . -iname $new) if ($new);
+ # usual reason for breakage: DT file moved around
+ if ($ref =~ /devicetree/) {
+ my $search = $new;
+ $search =~ s,^.*/,,;
+ $f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search);
+ if (!$f) {
+ # Manufacturer name may have changed
+ $search =~ s/^.*,//;
+ $f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search);
+ }
+ }
# usual reason for breakage: file renamed to .rst
if (!$f) {
$f=qx(find . -iname $new) if ($new);
}
+ # usual reason for breakage: use dash or underline
+ if (!$f) {
+ $new =~ s/[-_]/[-_]/g;
+ $f=qx(find . -iname $new) if ($new);
+ }
+
+ # Wild guess: seek for the same name on another place
+ if (!$f) {
+ $f = qx(find . -iname $new) if ($new);
+ }
+
my @find = split /\s+/, $f;
if (!$f) {
try_decompress 'BZh' xy bunzip2
try_decompress '\135\0\0\0' xxx unlzma
try_decompress '\211\114\132' xy 'lzop -d'
+try_decompress '\002!L\030' xxx 'lz4 -d'
+try_decompress '(\265/\375' xxx unzstd
# Bail out:
echo "$me: Cannot find vmlinux." >&2
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
* config BAZ
* int "BAZ Value"
* range 1..255
+ *
+ * Please, also check zconf.y:print_symbol() when modifying the
+ * list of property types!
*/
enum prop_type {
P_UNKNOWN,
nread--;
/* remove trailing new lines */
- while (buf[nread - 1] == '\n')
+ while (nread > 0 && buf[nread - 1] == '\n')
nread--;
buf[nread] = 0;
static struct menu *current_menu, *current_entry;
%}
-%expect 32
+%expect 31
%union
{
/* if entry */
-if_entry: T_IF expr nl
+if_entry: T_IF expr T_EOL
{
printd(DEBUG_PARSE, "%s:%d:if\n", zconf_curname(), zconf_lineno());
menu_add_entry(NULL);
print_quoted_string(out, prop->text);
fputc('\n', out);
break;
+ case P_SYMBOL:
+ fputs( " symbol ", out);
+ fprintf(out, "%s\n", prop->sym->name);
+ break;
default:
fprintf(out, " unknown prop %d!\n", prop->type);
break;
)
regex_c=(
'/^SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/sys_\1/'
+ '/^BPF_CALL_[0-9](\([[:alnum:]_]*\).*/\1/'
'/^COMPAT_SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/compat_sys_\1/'
'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1/'
'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1_rcuidle/'
{
setup_regex exuberant asm c
all_target_sources | xargs $1 -a \
- -I __initdata,__exitdata,__initconst, \
+ -I __initdata,__exitdata,__initconst,__ro_after_init \
-I __initdata_memblock \
-I __refdata,__attribute,__maybe_unused,__always_unused \
-I __acquires,__releases,__deprecated \
config PAGE_TABLE_ISOLATION
bool "Remove the kernel mapping in user mode"
default y
- depends on X86_64 && !UML
+ depends on X86 && !UML
help
This feature reduces the number of hardware side channels by
ensuring that the majority of kernel addresses are not mapped
return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR);
}
-static int apparmor_file_open(struct file *file, const struct cred *cred)
+static int apparmor_file_open(struct file *file)
{
struct aa_file_ctx *fctx = file_ctx(file);
struct aa_label *label;
return 0;
}
- label = aa_get_newest_cred_label(cred);
+ label = aa_get_newest_cred_label(file->f_cred);
if (!unconfined(label)) {
struct inode *inode = file_inode(file);
struct path_cond cond = { inode->i_uid, inode->i_mode };
* This is one of the three key functions for hierarchy implementation.
* This function is responsible for re-evaluating all the cgroup's active
* exceptions due to a parent's exception change.
- * Refer to Documentation/cgroups/devices.txt for more details.
+ * Refer to Documentation/cgroup-v1/devices.txt for more details.
*/
static void revalidate_active_exceptions(struct dev_cgroup *devcg)
{
struct integrity_iint_cache *iint,
struct file *file, const unsigned char *filename,
struct evm_ima_xattr_data *xattr_value,
- int xattr_len, int opened);
+ int xattr_len);
int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
struct file *file,
const unsigned char *filename,
struct evm_ima_xattr_data *xattr_value,
- int xattr_len, int opened)
+ int xattr_len)
{
return INTEGRITY_UNKNOWN;
}
struct integrity_iint_cache *iint,
struct file *file, const unsigned char *filename,
struct evm_ima_xattr_data *xattr_value,
- int xattr_len, int opened)
+ int xattr_len)
{
static const char op[] = "appraise_data";
const char *cause = "unknown";
cause = iint->flags & IMA_DIGSIG_REQUIRED ?
"IMA-signature-required" : "missing-hash";
status = INTEGRITY_NOLABEL;
- if (opened & FILE_CREATED)
+ if (file->f_mode & FMODE_CREATED)
iint->flags |= IMA_NEW_FILE;
if ((iint->flags & IMA_NEW_FILE) &&
(!(iint->flags & IMA_DIGSIG_REQUIRED) ||
static int process_measurement(struct file *file, const struct cred *cred,
u32 secid, char *buf, loff_t size, int mask,
- enum ima_hooks func, int opened)
+ enum ima_hooks func)
{
struct inode *inode = file_inode(file);
struct integrity_iint_cache *iint = NULL;
if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
inode_lock(inode);
rc = ima_appraise_measurement(func, iint, file, pathname,
- xattr_value, xattr_len, opened);
+ xattr_value, xattr_len);
inode_unlock(inode);
}
if (action & IMA_AUDIT)
if (file && (prot & PROT_EXEC)) {
security_task_getsecid(current, &secid);
return process_measurement(file, current_cred(), secid, NULL,
- 0, MAY_EXEC, MMAP_CHECK, 0);
+ 0, MAY_EXEC, MMAP_CHECK);
}
return 0;
security_task_getsecid(current, &secid);
ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0,
- MAY_EXEC, BPRM_CHECK, 0);
+ MAY_EXEC, BPRM_CHECK);
if (ret)
return ret;
security_cred_getsecid(bprm->cred, &secid);
return process_measurement(bprm->file, bprm->cred, secid, NULL, 0,
- MAY_EXEC, CREDS_CHECK, 0);
+ MAY_EXEC, CREDS_CHECK);
}
/**
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
-int ima_file_check(struct file *file, int mask, int opened)
+int ima_file_check(struct file *file, int mask)
{
u32 secid;
security_task_getsecid(current, &secid);
return process_measurement(file, current_cred(), secid, NULL, 0,
mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
- MAY_APPEND), FILE_CHECK, opened);
+ MAY_APPEND), FILE_CHECK);
}
EXPORT_SYMBOL_GPL(ima_file_check);
func = read_idmap[read_id] ?: FILE_CHECK;
security_task_getsecid(current, &secid);
return process_measurement(file, current_cred(), secid, buf, size,
- MAY_READ, func, 0);
+ MAY_READ, func);
}
static int __init init_ima(void)
* The src pointer is defined as Z || other info where Z is the shared secret
* from DH and other info is an arbitrary string (see SP800-56A section
* 5.8.1.2).
+ *
+ * 'dlen' must be a multiple of the digest size.
*/
static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
u8 *dst, unsigned int dlen, unsigned int zlen)
{
uint8_t *outbuf = NULL;
int ret;
- size_t outbuf_len = round_up(buflen,
- crypto_shash_digestsize(sdesc->shash.tfm));
+ size_t outbuf_len = roundup(buflen,
+ crypto_shash_digestsize(sdesc->shash.tfm));
outbuf = kmalloc(outbuf_len, GFP_KERNEL);
if (!outbuf) {
return call_int_hook(file_receive, 0, file);
}
-int security_file_open(struct file *file, const struct cred *cred)
+int security_file_open(struct file *file)
{
int ret;
- ret = call_int_hook(file_open, 0, file, cred);
+ ret = call_int_hook(file_open, 0, file);
if (ret)
return ret;
return file_has_perm(cred, file, file_to_av(file));
}
-static int selinux_file_open(struct file *file, const struct cred *cred)
+static int selinux_file_open(struct file *file)
{
struct file_security_struct *fsec;
struct inode_security_struct *isec;
* new inode label or new policy.
* This check is not redundant - do not remove.
*/
- return file_path_has_perm(cred, file, open_file_to_av(file));
+ return file_path_has_perm(file->f_cred, file, open_file_to_av(file));
}
/* task security operations */
}
/* This supports connect(2) and SCTP connect services such as sctp_connectx(3)
- * and sctp_sendmsg(3) as described in Documentation/security/LSM-sctp.txt
+ * and sctp_sendmsg(3) as described in Documentation/security/LSM-sctp.rst
*/
static int selinux_socket_connect_helper(struct socket *sock,
struct sockaddr *address, int addrlen)
static ssize_t sel_read_policy(struct file *filp, char __user *buf,
size_t count, loff_t *ppos)
{
- struct selinux_fs_info *fsi = file_inode(filp)->i_sb->s_fs_info;
struct policy_load_memory *plm = filp->private_data;
int ret;
- mutex_lock(&fsi->mutex);
-
ret = avc_has_perm(&selinux_state,
current_sid(), SECINITSID_SECURITY,
SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL);
if (ret)
- goto out;
+ return ret;
- ret = simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
-out:
- mutex_unlock(&fsi->mutex);
- return ret;
+ return simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
}
static vm_fault_t sel_mmap_policy_fault(struct vm_fault *vmf)
ret = -EINVAL;
if (index >= fsi->bool_num || strcmp(name,
fsi->bool_pending_names[index]))
- goto out;
+ goto out_unlock;
ret = -ENOMEM;
page = (char *)get_zeroed_page(GFP_KERNEL);
if (!page)
- goto out;
+ goto out_unlock;
cur_enforcing = security_get_bool_value(fsi->state, index);
if (cur_enforcing < 0) {
ret = cur_enforcing;
- goto out;
+ goto out_unlock;
}
length = scnprintf(page, PAGE_SIZE, "%d %d", cur_enforcing,
fsi->bool_pending_values[index]);
- ret = simple_read_from_buffer(buf, count, ppos, page, length);
-out:
mutex_unlock(&fsi->mutex);
+ ret = simple_read_from_buffer(buf, count, ppos, page, length);
+out_free:
free_page((unsigned long)page);
return ret;
+
+out_unlock:
+ mutex_unlock(&fsi->mutex);
+ goto out_free;
}
static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK;
const char *name = filep->f_path.dentry->d_name.name;
+ if (count >= PAGE_SIZE)
+ return -ENOMEM;
+
+ /* No partial writes. */
+ if (*ppos != 0)
+ return -EINVAL;
+
+ page = memdup_user_nul(buf, count);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
mutex_lock(&fsi->mutex);
length = avc_has_perm(&selinux_state,
fsi->bool_pending_names[index]))
goto out;
- length = -ENOMEM;
- if (count >= PAGE_SIZE)
- goto out;
-
- /* No partial writes. */
- length = -EINVAL;
- if (*ppos != 0)
- goto out;
-
- page = memdup_user_nul(buf, count);
- if (IS_ERR(page)) {
- length = PTR_ERR(page);
- page = NULL;
- goto out;
- }
-
length = -EINVAL;
if (sscanf(page, "%d", &new_value) != 1)
goto out;
ssize_t length;
int new_value;
+ if (count >= PAGE_SIZE)
+ return -ENOMEM;
+
+ /* No partial writes. */
+ if (*ppos != 0)
+ return -EINVAL;
+
+ page = memdup_user_nul(buf, count);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
mutex_lock(&fsi->mutex);
length = avc_has_perm(&selinux_state,
if (length)
goto out;
- length = -ENOMEM;
- if (count >= PAGE_SIZE)
- goto out;
-
- /* No partial writes. */
- length = -EINVAL;
- if (*ppos != 0)
- goto out;
-
- page = memdup_user_nul(buf, count);
- if (IS_ERR(page)) {
- length = PTR_ERR(page);
- page = NULL;
- goto out;
- }
-
length = -EINVAL;
if (sscanf(page, "%d", &new_value) != 1)
goto out;
*
* Returns 0
*/
-static int smack_file_open(struct file *file, const struct cred *cred)
+static int smack_file_open(struct file *file)
{
- struct task_smack *tsp = cred->security;
+ struct task_smack *tsp = file->f_cred->security;
struct inode *inode = file_inode(file);
struct smk_audit_info ad;
int rc;
smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
smk_ad_setfield_u_fs_path(&ad, file->f_path);
rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
- rc = smk_bu_credfile(cred, file, MAY_READ, rc);
+ rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
return rc;
}
struct smack_known *skp = smk_of_task_struct(p);
isp->smk_inode = skp;
+ isp->smk_flags |= SMK_INODE_INSTANT;
}
/*
*
* Returns 0 on success, negative value otherwise.
*/
-static int tomoyo_file_open(struct file *f, const struct cred *cred)
+static int tomoyo_file_open(struct file *f)
{
int flags = f->f_flags;
/* Don't check read permission here if called from do_execve(). */
depends on SND_OSSEMUL
help
To enable OSS mixer API emulation (/dev/mixer*), say Y here
- and read <file:Documentation/sound/alsa/OSS-Emulation.txt>.
+ and read <file:Documentation/sound/designs/oss-emulation.rst>.
Many programs still use the OSS API, so say Y.
select SND_PCM
help
To enable OSS digital audio (PCM) emulation (/dev/dsp*), say Y
- here and read <file:Documentation/sound/alsa/OSS-Emulation.txt>.
+ here and read <file:Documentation/sound/designs/oss-emulation.rst>.
Many programs still use the OSS API, so say Y.
int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
struct snd_rawmidi_params * params)
{
- char *newbuf;
+ char *newbuf, *oldbuf;
struct snd_rawmidi_runtime *runtime = substream->runtime;
if (substream->append && substream->use_count > 1)
return -EINVAL;
}
if (params->buffer_size != runtime->buffer_size) {
- newbuf = krealloc(runtime->buffer, params->buffer_size,
- GFP_KERNEL);
+ newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
if (!newbuf)
return -ENOMEM;
+ spin_lock_irq(&runtime->lock);
+ oldbuf = runtime->buffer;
runtime->buffer = newbuf;
runtime->buffer_size = params->buffer_size;
runtime->avail = runtime->buffer_size;
+ runtime->appl_ptr = runtime->hw_ptr = 0;
+ spin_unlock_irq(&runtime->lock);
+ kfree(oldbuf);
}
runtime->avail_min = params->avail_min;
substream->active_sensing = !params->no_active_sensing;
int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
struct snd_rawmidi_params * params)
{
- char *newbuf;
+ char *newbuf, *oldbuf;
struct snd_rawmidi_runtime *runtime = substream->runtime;
snd_rawmidi_drain_input(substream);
return -EINVAL;
}
if (params->buffer_size != runtime->buffer_size) {
- newbuf = krealloc(runtime->buffer, params->buffer_size,
- GFP_KERNEL);
+ newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
if (!newbuf)
return -ENOMEM;
+ spin_lock_irq(&runtime->lock);
+ oldbuf = runtime->buffer;
runtime->buffer = newbuf;
runtime->buffer_size = params->buffer_size;
+ runtime->appl_ptr = runtime->hw_ptr = 0;
+ spin_unlock_irq(&runtime->lock);
+ kfree(oldbuf);
}
runtime->avail_min = params->avail_min;
return 0;
struct snd_seq_client *cptr = NULL;
/* search for next client */
- info->client++;
+ if (info->client < INT_MAX)
+ info->client++;
if (info->client < 0)
info->client = 0;
for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) {
} else {
if (id.subdevice < 0)
id.subdevice = 0;
- else
+ else if (id.subdevice < INT_MAX)
id.subdevice++;
}
}
select SND_RAWMIDI
help
To include support for MIDI serial port interfaces, say Y here
- and read <file:Documentation/sound/alsa/serial-u16550.txt>.
+ and read <file:Documentation/sound/cards/serial-u16550.rst>.
This driver works with serial UARTs 16550 and better.
This driver accesses the serial port hardware directly, so
the device frequently. A value of 10 seconds would be a
good choice for normal operations.
- See Documentation/sound/alsa/powersave.txt for more details.
+ See Documentation/sound/designs/powersave.rst for more details.
config SND_AC97_POWER_SAVE_DEFAULT
int "Default time-out for AC97 power-save mode"
help
If you want to record audio from TV cards based on
Brooktree Bt878/Bt879 chips, say Y here and read
- <file:Documentation/sound/alsa/Bt87x.txt>.
+ <file:Documentation/sound/cards/bt87x.rst>.
To compile this driver as a module, choose M here: the module
will be called snd-bt87x.
help
If you want to use soundcards based on C-Media CMI8338, CMI8738,
CMI8768 or CMI8770 chips, say Y here and read
- <file:Documentation/sound/alsa/CMIPCI.txt>.
+ <file:Documentation/sound/cards/cmipci.rst>.
To compile this driver as a module, choose M here: the module
will be called snd-cmipci.
Audigy and E-mu APS (partially supported) soundcards.
The confusing multitude of mixer controls is documented in
- <file:Documentation/sound/alsa/SB-Live-mixer.txt> and
- <file:Documentation/sound/alsa/Audigy-mixer.txt>.
+ <file:Documentation/sound/cards/sb-live-mixer.rst> and
+ <file:Documentation/sound/cards/audigy-mixer.rst>.
To compile this driver as a module, choose M here: the module
will be called snd-emu10k1.
select SND_PCM
help
If you want to use Digigram miXart soundcards, say Y here and
- read <file:Documentation/sound/alsa/MIXART.txt>.
+ read <file:Documentation/sound/cards/mixart.rst>.
To compile this driver as a module, choose M here: the module
will be called snd-mixart.
if (!kctl)
return -ENOMEM;
kctl->id.device = device;
- snd_ctl_add(emu->card, kctl);
+ err = snd_ctl_add(emu->card, kctl);
+ if (err < 0)
+ return err;
snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(emu->pci), 64*1024, 64*1024);
if ((err = snd_ac97_mixer(chip->ac97_bus, &ac97, &chip->ac97_sec)) < 0)
return err;
}
- for (i = 0; i < FM801_CONTROLS; i++)
- snd_ctl_add(chip->card, snd_ctl_new1(&snd_fm801_controls[i], chip));
+ for (i = 0; i < FM801_CONTROLS; i++) {
+ err = snd_ctl_add(chip->card,
+ snd_ctl_new1(&snd_fm801_controls[i], chip));
+ if (err < 0)
+ return err;
+ }
if (chip->multichannel) {
- for (i = 0; i < FM801_CONTROLS_MULTI; i++)
- snd_ctl_add(chip->card, snd_ctl_new1(&snd_fm801_controls_multi[i], chip));
+ for (i = 0; i < FM801_CONTROLS_MULTI; i++) {
+ err = snd_ctl_add(chip->card,
+ snd_ctl_new1(&snd_fm801_controls_multi[i], chip));
+ if (err < 0)
+ return err;
+ }
}
return 0;
}
list_for_each_entry(pcm, &codec->pcm_list_head, list)
snd_pcm_suspend_all(pcm->pcm);
state = hda_call_codec_suspend(codec);
- if (codec_has_clkstop(codec) && codec_has_epss(codec) &&
- (state & AC_PWRST_CLK_STOP_OK))
+ if (codec->link_down_at_suspend ||
+ (codec_has_clkstop(codec) && codec_has_epss(codec) &&
+ (state & AC_PWRST_CLK_STOP_OK)))
snd_hdac_codec_link_down(&codec->core);
snd_hdac_link_power(&codec->core, false);
return 0;
unsigned int power_save_node:1; /* advanced PM for each widget */
unsigned int auto_runtime_pm:1; /* enable automatic codec runtime pm */
unsigned int force_pin_prefix:1; /* Add location prefix */
+ unsigned int link_down_at_suspend:1; /* link down at runtime suspend */
#ifdef CONFIG_PM
unsigned long power_on_acct;
unsigned long power_off_acct;
enum {
QUIRK_NONE,
QUIRK_ALIENWARE,
+ QUIRK_ALIENWARE_M17XR4,
QUIRK_SBZ,
QUIRK_R3DI,
};
};
static const struct snd_pci_quirk ca0132_quirks[] = {
+ SND_PCI_QUIRK(0x1028, 0x057b, "Alienware M17x R4", QUIRK_ALIENWARE_M17XR4),
SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ),
SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ),
SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
- SND_PCI_QUIRK(0x1458, 0xA036, "Recon3Di", QUIRK_R3DI),
+ SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
+ SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI),
{}
};
* I think this has to do with the pin for rear surround being 0x11,
* and the center/lfe being 0x10. Usually the pin order is the opposite.
*/
-const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
+static const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
{ .channels = 2,
.map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR } },
{ .channels = 4,
info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[0];
/* With the DSP enabled, desktops don't use this ADC. */
- if (spec->use_alt_functions) {
+ if (!spec->use_alt_functions) {
info = snd_hda_codec_pcm_new(codec, "CA0132 Analog Mic-In2");
if (!info)
return -ENOMEM;
* Bit 6: set to select Data2, clear for Data1
* Bit 7: set to enable DMic, clear for AMic
*/
- val = 0x23;
+ if (spec->quirk == QUIRK_ALIENWARE_M17XR4)
+ val = 0x33;
+ else
+ val = 0x23;
/* keep a copy of dmic ctl val for enable/disable dmic purpuse */
spec->dmic_ctl = val;
snd_hda_codec_write(codec, spec->input_pins[0], 0,
snd_hda_sequence_write(codec, spec->base_init_verbs);
- if (spec->quirk != QUIRK_NONE)
+ if (spec->use_alt_functions)
ca0132_alt_init(codec);
ca0132_download_dsp(codec);
case QUIRK_R3DI:
r3di_setup_defaults(codec);
break;
- case QUIRK_NONE:
- case QUIRK_ALIENWARE:
+ case QUIRK_SBZ:
+ break;
+ default:
ca0132_setup_defaults(codec);
ca0132_init_analog_mic2(codec);
ca0132_init_dmic(codec);
static void ca0132_config(struct hda_codec *codec)
{
struct ca0132_spec *spec = codec->spec;
- struct auto_pin_cfg *cfg = &spec->autocfg;
spec->dacs[0] = 0x2;
spec->dacs[1] = 0x3;
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
spec->dig_in = 0x09;
- cfg->dig_in_pin = 0x0e;
- cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
break;
case QUIRK_R3DI:
codec_dbg(codec, "%s: QUIRK_R3DI applied.\n", __func__);
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
break;
default:
spec->num_outputs = 2;
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
spec->dig_in = 0x09;
- cfg->dig_in_pin = 0x0e;
- cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
break;
}
}
static int ca0132_prepare_verbs(struct hda_codec *codec)
{
/* Verbs + terminator (an empty element) */
-#define NUM_SPEC_VERBS 4
+#define NUM_SPEC_VERBS 2
struct ca0132_spec *spec = codec->spec;
spec->chip_init_verbs = ca0132_init_verbs0;
if (!spec->spec_init_verbs)
return -ENOMEM;
- /* HP jack autodetection */
- spec->spec_init_verbs[0].nid = spec->unsol_tag_hp;
- spec->spec_init_verbs[0].param = AC_VERB_SET_UNSOLICITED_ENABLE;
- spec->spec_init_verbs[0].verb = AC_USRSP_EN | spec->unsol_tag_hp;
-
- /* MIC1 jack autodetection */
- spec->spec_init_verbs[1].nid = spec->unsol_tag_amic1;
- spec->spec_init_verbs[1].param = AC_VERB_SET_UNSOLICITED_ENABLE;
- spec->spec_init_verbs[1].verb = AC_USRSP_EN | spec->unsol_tag_amic1;
-
/* config EAPD */
- spec->spec_init_verbs[2].nid = 0x0b;
- spec->spec_init_verbs[2].param = 0x78D;
- spec->spec_init_verbs[2].verb = 0x00;
+ spec->spec_init_verbs[0].nid = 0x0b;
+ spec->spec_init_verbs[0].param = 0x78D;
+ spec->spec_init_verbs[0].verb = 0x00;
/* Previously commented configuration */
/*
- spec->spec_init_verbs[3].nid = 0x0b;
- spec->spec_init_verbs[3].param = AC_VERB_SET_EAPD_BTLENABLE;
+ spec->spec_init_verbs[2].nid = 0x0b;
+ spec->spec_init_verbs[2].param = AC_VERB_SET_EAPD_BTLENABLE;
+ spec->spec_init_verbs[2].verb = 0x02;
+
+ spec->spec_init_verbs[3].nid = 0x10;
+ spec->spec_init_verbs[3].param = 0x78D;
spec->spec_init_verbs[3].verb = 0x02;
spec->spec_init_verbs[4].nid = 0x10;
- spec->spec_init_verbs[4].param = 0x78D;
+ spec->spec_init_verbs[4].param = AC_VERB_SET_EAPD_BTLENABLE;
spec->spec_init_verbs[4].verb = 0x02;
-
- spec->spec_init_verbs[5].nid = 0x10;
- spec->spec_init_verbs[5].param = AC_VERB_SET_EAPD_BTLENABLE;
- spec->spec_init_verbs[5].verb = 0x02;
*/
/* Terminator: spec->spec_init_verbs[NUM_SPEC_VERBS-1] */
SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK),
SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK),
+ SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK),
+ SND_PCI_QUIRK(0x103c, 0x83d3, "HP ProBook 640 G4", CXT_FIXUP_HP_DOCK),
SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+ SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO),
SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/pm_runtime.h>
#include <sound/core.h>
#include <sound/jack.h>
#include <sound/asoundef.h>
if (pin_idx < 0)
return;
+ mutex_lock(&spec->pcm_lock);
if (hdmi_present_sense(get_pin(spec, pin_idx), 1))
snd_hda_jack_report_sync(codec);
+ mutex_unlock(&spec->pcm_lock);
}
static void jack_callback(struct hda_codec *codec,
static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
{
struct hda_codec *codec = per_pin->codec;
- struct hdmi_spec *spec = codec->spec;
int ret;
/* no temporary power up/down needed for component notifier */
- if (!codec_has_acomp(codec))
- snd_hda_power_up_pm(codec);
+ if (!codec_has_acomp(codec)) {
+ ret = snd_hda_power_up_pm(codec);
+ if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) {
+ snd_hda_power_down_pm(codec);
+ return false;
+ }
+ }
- mutex_lock(&spec->pcm_lock);
if (codec_has_acomp(codec)) {
sync_eld_via_acomp(codec, per_pin);
ret = false; /* don't call snd_hda_jack_report_sync() */
} else {
ret = hdmi_present_sense_via_verbs(per_pin, repoll);
}
- mutex_unlock(&spec->pcm_lock);
if (!codec_has_acomp(codec))
snd_hda_power_down_pm(codec);
{
struct hdmi_spec_per_pin *per_pin =
container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
+ struct hda_codec *codec = per_pin->codec;
+ struct hdmi_spec *spec = codec->spec;
if (per_pin->repoll_count++ > 6)
per_pin->repoll_count = 0;
+ mutex_lock(&spec->pcm_lock);
if (hdmi_present_sense(per_pin, per_pin->repoll_count))
snd_hda_jack_report_sync(per_pin->codec);
+ mutex_unlock(&spec->pcm_lock);
}
static void intel_haswell_fixup_connect_list(struct hda_codec *codec,
spec->chmap.channels_max = max(spec->chmap.channels_max, 8u);
+ /* AMD GPUs have neither EPSS nor CLKSTOP bits, hence preventing
+ * the link-down as is. Tell the core to allow it.
+ */
+ codec->link_down_at_suspend = 1;
+
return 0;
}
{
struct alc_spec *spec = codec->spec;
+ if (!snd_hda_get_bool_hint(codec, "shutup"))
+ return; /* disabled explicitly by hints */
+
if (spec && spec->shutup)
spec->shutup(codec);
else
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
SND_PCI_QUIRK(0x10cf, 0x1397, "Fujitsu Lifebook S7110", ALC262_FIXUP_FSC_S7110),
SND_PCI_QUIRK(0x10cf, 0x142d, "Fujitsu Lifebook E8410", ALC262_FIXUP_BENQ),
SND_PCI_QUIRK(0x10f1, 0x2915, "Tyan Thunder n6650W", ALC262_FIXUP_TYAN),
+ SND_PCI_QUIRK(0x1734, 0x1141, "FSC ESPRIMO U9210", ALC262_FIXUP_FSC_H270),
SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", ALC262_FIXUP_FSC_H270),
SND_PCI_QUIRK(0x17aa, 0x384e, "Lenovo 3000", ALC262_FIXUP_LENOVO_3000),
SND_PCI_QUIRK(0x17ff, 0x0560, "Benq ED8", ALC262_FIXUP_BENQ),
struct alc_spec *spec = codec->spec;
if (action == HDA_FIXUP_ACT_PRE_PROBE) {
- spec->shutup = alc_no_shutup; /* reduce click noise */
spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */
spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
codec->power_save_node = 0; /* avoid click noises */
/* for hda_fixup_thinkpad_acpi() */
#include "thinkpad_helper.c"
+static void alc_fixup_thinkpad_acpi(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc_fixup_no_shutup(codec, fix, action); /* reduce click noise */
+ hda_fixup_thinkpad_acpi(codec, fix, action);
+}
+
/* for dell wmi mic mute led */
#include "dell_wmi_helper.c"
},
[ALC269_FIXUP_THINKPAD_ACPI] = {
.type = HDA_FIXUP_FUNC,
- .v.func = hda_fixup_thinkpad_acpi,
+ .v.func = alc_fixup_thinkpad_acpi,
.chained = true,
.chain_id = ALC269_FIXUP_SKU_IGNORE,
},
SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC),
SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
+ SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
- SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
{0x14, 0x90170110},
{0x19, 0x02a11030},
{0x21, 0x02211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11030},
+ {0x1a, 0x02a11040},
+ {0x1b, 0x01014020},
+ {0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11020},
+ {0x1a, 0x02a11030},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60140},
{0x14, 0x90170110},
/* dsp port */
chip->port_dsp_bar = pci_ioremap_bar(pci, 2);
+ if (!chip->port_dsp_bar) {
+ dev_err(card->dev, "cannot remap PCI memory region\n");
+ err = -ENOMEM;
+ goto remap_pci_failed;
+ }
err = request_threaded_irq(pci->irq, lx_interrupt, lx_threaded_irq,
IRQF_SHARED, KBUILD_MODNAME, chip);
free_irq(pci->irq, chip);
request_irq_failed:
+ iounmap(chip->port_dsp_bar);
+
+remap_pci_failed:
pci_release_regions(pci);
request_regions_failed:
static int snd_sonicvibes_create_gameport(struct sonicvibes *sonic)
{
struct gameport *gp;
+ int err;
sonic->gameport = gp = gameport_allocate_port();
if (!gp) {
gameport_register_port(gp);
- snd_ctl_add(sonic->card, snd_ctl_new1(&snd_sonicvibes_game_control, sonic));
+ err = snd_ctl_add(sonic->card,
+ snd_ctl_new1(&snd_sonicvibes_game_control, sonic));
+ if (err < 0)
+ return err;
return 0;
}
return err;
}
- snd_sonicvibes_create_gameport(sonic);
+ err = snd_sonicvibes_create_gameport(sonic);
+ if (err < 0) {
+ snd_card_free(card);
+ return err;
+ }
if ((err = snd_card_register(card)) < 0) {
snd_card_free(card);
struct snd_pcm_chmap_elem *chmap; /* (optional) channel map */
bool dsd_dop; /* add DOP headers in case of DSD samples */
bool dsd_bitrev; /* reverse the bits of each DSD sample */
+ bool dsd_raw; /* altsetting is raw DSD */
};
struct snd_usb_substream;
sample_width = fmt->bBitResolution;
sample_bytes = fmt->bSubslotSize;
- if (format & UAC2_FORMAT_TYPE_I_RAW_DATA)
+ if (format & UAC2_FORMAT_TYPE_I_RAW_DATA) {
pcm_formats |= SNDRV_PCM_FMTBIT_SPECIAL;
+ /* flag potentially raw DSD capable altsettings */
+ fp->dsd_raw = true;
+ }
format <<= 1;
break;
NULL, NULL, unitid, 0, 0);
}
-static void get_connector_control_name(struct mixer_build *state,
+static void get_connector_control_name(struct usb_mixer_interface *mixer,
struct usb_audio_term *term,
bool is_input, char *name, int name_size)
{
- int name_len = get_term_name(state->chip, term, name, name_size, 0);
+ int name_len = get_term_name(mixer->chip, term, name, name_size, 0);
if (name_len == 0)
strlcpy(name, "Unknown", name_size);
}
/* Build a mixer control for a UAC connector control (jack-detect) */
-static void build_connector_control(struct mixer_build *state,
+static void build_connector_control(struct usb_mixer_interface *mixer,
struct usb_audio_term *term, bool is_input)
{
struct snd_kcontrol *kctl;
cval = kzalloc(sizeof(*cval), GFP_KERNEL);
if (!cval)
return;
- snd_usb_mixer_elem_init_std(&cval->head, state->mixer, term->id);
+ snd_usb_mixer_elem_init_std(&cval->head, mixer, term->id);
/*
* UAC2: The first byte from reading the UAC2_TE_CONNECTOR control returns the
* number of channels connected.
* This boolean ctl will simply report if any channels are connected
* or not.
*/
- if (state->mixer->protocol == UAC_VERSION_2)
+ if (mixer->protocol == UAC_VERSION_2)
cval->control = UAC2_TE_CONNECTOR;
else /* UAC_VERSION_3 */
cval->control = UAC3_TE_INSERTION;
cval->max = 1;
kctl = snd_ctl_new1(&usb_connector_ctl_ro, cval);
if (!kctl) {
- usb_audio_err(state->chip, "cannot malloc kcontrol\n");
+ usb_audio_err(mixer->chip, "cannot malloc kcontrol\n");
kfree(cval);
return;
}
- get_connector_control_name(state, term, is_input, kctl->id.name,
+ get_connector_control_name(mixer, term, is_input, kctl->id.name,
sizeof(kctl->id.name));
kctl->private_free = snd_usb_mixer_elem_free;
snd_usb_mixer_add_control(&cval->head, kctl);
/* Check for jack detection. */
if (uac_v2v3_control_is_readable(bmctls, control))
- build_connector_control(state, &iterm, true);
+ build_connector_control(state->mixer, &iterm, true);
return 0;
}
UAC3_BADD_FU_ID7, map->map);
}
+ /* Insertion Control */
+ if (f->subclass == UAC3_FUNCTION_SUBCLASS_HEADSET_ADAPTER) {
+ struct usb_audio_term iterm, oterm;
+
+ /* Input Term - Insertion control */
+ memset(&iterm, 0, sizeof(iterm));
+ iterm.id = UAC3_BADD_IT_ID4;
+ iterm.type = UAC_BIDIR_TERMINAL_HEADSET;
+ build_connector_control(mixer, &iterm, true);
+
+ /* Output Term - Insertion control */
+ memset(&oterm, 0, sizeof(oterm));
+ oterm.id = UAC3_BADD_OT_ID3;
+ oterm.type = UAC_BIDIR_TERMINAL_HEADSET;
+ build_connector_control(mixer, &oterm, false);
+ }
+
return 0;
}
if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
UAC2_TE_CONNECTOR)) {
- build_connector_control(&state, &state.oterm,
+ build_connector_control(state.mixer, &state.oterm,
false);
}
} else { /* UAC_VERSION_3 */
if (uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
UAC3_TE_INSERTION)) {
- build_connector_control(&state, &state.oterm,
+ build_connector_control(state.mixer, &state.oterm,
false);
}
}
err = snd_usb_mixer_controls(mixer);
if (err < 0)
goto _error;
- err = snd_usb_mixer_status_create(mixer);
- if (err < 0)
- goto _error;
}
+
+ err = snd_usb_mixer_status_create(mixer);
+ if (err < 0)
+ goto _error;
+
err = create_keep_iface_ctl(mixer);
if (err < 0)
goto _error;
}
},
+/* disabled due to regression for other devices;
+ * see https://bugzilla.kernel.org/show_bug.cgi?id=199905
+ */
+#if 0
{
/*
* Nura's first gen headphones use Cambridge Silicon Radio's vendor
}
}
},
+#endif /* disabled */
{
/*
case USB_ID(0x1511, 0x0037): /* AURALiC VEGA */
case USB_ID(0x20b1, 0x0002): /* Wyred 4 Sound DAC-2 DSD */
case USB_ID(0x20b1, 0x2004): /* Matrix Audio X-SPDIF 2 */
- case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */
case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */
case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */
case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */
case USB_ID(0x22d9, 0x0436): /* OPPO Sonica */
case USB_ID(0x22d9, 0x0461): /* OPPO UDP-205 */
case USB_ID(0x2522, 0x0012): /* LH Labs VI DAC Infinity */
- case USB_ID(0x25ce, 0x001f): /* Mytek Brooklyn DAC */
- case USB_ID(0x25ce, 0x0021): /* Mytek Manhattan DAC */
- case USB_ID(0x25ce, 0x8025): /* Mytek Brooklyn DAC+ */
case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */
if (fp->altsetting == 2)
return SNDRV_PCM_FMTBIT_DSD_U32_BE;
case USB_ID(0x20b1, 0x3021): /* Eastern El. MiniMax Tube DAC Supreme */
case USB_ID(0x20b1, 0x3023): /* Aune X1S 32BIT/384 DSD DAC */
case USB_ID(0x20b1, 0x302d): /* Unison Research Unico CD Due */
- case USB_ID(0x20b1, 0x3036): /* Holo Springs Level 3 R2R DAC */
case USB_ID(0x20b1, 0x307b): /* CH Precision C1 DAC */
case USB_ID(0x20b1, 0x3086): /* Singxer F-1 converter board */
case USB_ID(0x22d9, 0x0426): /* OPPO HA-2 */
return SNDRV_PCM_FMTBIT_DSD_U32_BE;
}
+ /* Mostly generic method to detect many DSD-capable implementations -
+ * from XMOS/Thesycon
+ */
+ switch (USB_ID_VENDOR(chip->usb_id)) {
+ case 0x20b1: /* XMOS based devices */
+ case 0x25ce: /* Mytek devices */
+ if (fp->dsd_raw)
+ return SNDRV_PCM_FMTBIT_DSD_U32_BE;
+ break;
+ default:
+ break;
+
+ }
+
return 0;
}
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
#define ELOOP 249 /* Too many symbolic links encountered */
#define ENOSYS 251 /* Function not implemented */
-#define ENOTSUP 252 /* Function not implemented (POSIX.4 / HPUX) */
#define ECANCELLED 253 /* aio request was canceled before complete (POSIX.4 / HPUX) */
#define ECANCELED ECANCELLED /* SuSv3 and Solaris wants one 'L' */
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
#define __NR_pkey_alloc 384
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
+#define __NR_rseq 387
+#define __NR_io_pgetevents 388
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* _MCSAFE_TEST_H_ */
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
#include <asm/alternative-asm.h>
#include <asm/export.h>
ENDPROC(memcpy_orig)
#ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
/*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
* Note that we only catch machine checks when reading the source addresses.
* Writes to target are posted and don't generate machine checks.
*/
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
subl $8, %ecx
negl %ecx
subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
movb (%rsi), %al
+ MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+ MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
- jnz .L_copy_leading_bytes
+ jnz .L_read_leading_bytes
.L_8byte_aligned:
- /* Figure out how many whole cache lines (64-bytes) to copy */
- movl %edx, %ecx
- andl $63, %edx
- shrl $6, %ecx
- jz .L_no_whole_cache_lines
-
- /* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
- movq %r8, (%rdi)
- movq %r9, 1*8(%rdi)
- movq %r10, 2*8(%rdi)
- movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
- movq %r8, 4*8(%rdi)
- movq %r9, 5*8(%rdi)
- movq %r10, 6*8(%rdi)
- movq %r11, 7*8(%rdi)
- leaq 64(%rsi), %rsi
- leaq 64(%rdi), %rdi
- decl %ecx
- jnz .L_cache_w0
-
- /* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
movl %edx, %ecx
andl $7, %edx
shrl $3, %ecx
jz .L_no_whole_words
- /* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
movq (%rsi), %r8
- mov %r8, (%rdi)
- leaq 8(%rsi), %rsi
- leaq 8(%rdi), %rdi
+ MCSAFE_TEST_SRC %rsi 8 .E_read_words
+ MCSAFE_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+ movq %r8, (%rdi)
+ addq $8, %rsi
+ addq $8, %rdi
decl %ecx
- jnz .L_copy_trailing_words
+ jnz .L_read_words
/* Any trailing bytes? */
.L_no_whole_words:
/* Copy trailing bytes */
movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
movb (%rsi), %al
+ MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+ MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
- jnz .L_copy_trailing_bytes
+ jnz .L_read_trailing_bytes
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorq %rax, %rax
ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
.section .fixup, "ax"
- /* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
- mov $-EFAULT, %rax
+ /*
+ * Return number of bytes not copied for any failure. Note that
+ * there is no "tail" handling since the source buffer is 8-byte
+ * aligned and poison is cacheline aligned.
+ */
+.E_read_words:
+ shll $3, %ecx
+.E_leading_bytes:
+ addl %edx, %ecx
+.E_trailing_bytes:
+ mov %ecx, %eax
ret
+ /*
+ * For write fault handling, given the destination is unaligned,
+ * we handle faults on multi-byte writes with a byte-by-byte
+ * copy up to the write-protected page.
+ */
+.E_write_words:
+ shll $3, %ecx
+ addl %edx, %ecx
+ movl %ecx, %edx
+ jmp mcsafe_handle_tail
+
.previous
- _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+ _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+ _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+ _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+ _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+ _ASM_EXTABLE(.L_write_words, .E_write_words)
+ _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
#endif
int err;
int fd;
+ if (argc < 3) {
+ p_err("too few arguments, id ID and FILE path is required");
+ return -1;
+ } else if (argc > 3) {
+ p_err("too many arguments");
+ return -1;
+ }
+
if (!is_prefix(*argv, "id")) {
p_err("expected 'id' got %s", *argv);
return -1;
}
NEXT_ARG();
- if (argc != 1)
- usage();
-
fd = get_fd_by_id(id);
if (fd < 0) {
p_err("can't get prog by id (%u): %s", id, strerror(errno));
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
+#include <linux/kernel.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
static void *alloc_value(struct bpf_map_info *info)
{
if (map_is_per_cpu(info->type))
- return malloc(info->value_size * get_possible_cpus());
+ return malloc(round_up(info->value_size, 8) *
+ get_possible_cpus());
else
return malloc(info->value_size);
}
jsonw_name(json_wtr, "value");
print_hex_data_json(value, info->value_size);
} else {
- unsigned int i, n;
+ unsigned int i, n, step;
n = get_possible_cpus();
+ step = round_up(info->value_size, 8);
jsonw_name(json_wtr, "key");
print_hex_data_json(key, info->key_size);
jsonw_int_field(json_wtr, "cpu", i);
jsonw_name(json_wtr, "value");
- print_hex_data_json(value + i * info->value_size,
+ print_hex_data_json(value + i * step,
info->value_size);
jsonw_end_object(json_wtr);
printf("\n");
} else {
- unsigned int i, n;
+ unsigned int i, n, step;
n = get_possible_cpus();
+ step = round_up(info->value_size, 8);
printf("key:\n");
fprint_hex(stdout, key, info->key_size, " ");
for (i = 0; i < n; i++) {
printf("value (CPU %02d):%c",
i, info->value_size > 16 ? '\n' : ' ');
- fprint_hex(stdout, value + i * info->value_size,
+ fprint_hex(stdout, value + i * step,
info->value_size, " ");
printf("\n");
}
if (perf_query_supported)
goto out;
- fd = open(bin_name, O_RDONLY);
+ fd = open("/", O_RDONLY);
if (fd < 0) {
- p_err("perf_query_support: %s", strerror(errno));
+ p_err("perf_query_support: cannot open directory \"/\" (%s)",
+ strerror(errno));
goto out;
}
}
wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
- nsecs / 1000000000;
+ (real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+ 1000000000;
+
if (!localtime_r(&wallclock_secs, &load_tm)) {
snprintf(buf, size, "%llu", nsecs / 1000000000);
return -1;
}
- if (do_pin_fd(prog_fd, argv[1])) {
- p_err("failed to pin program");
- return -1;
- }
+ if (do_pin_fd(prog_fd, argv[1]))
+ goto err_close_obj;
if (json_output)
jsonw_null(json_wtr);
+ bpf_object__close(obj);
+
return 0;
+
+err_close_obj:
+ bpf_object__close(obj);
+ return -1;
}
static int do_help(int argc, char **argv)
$(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp; \
rm -f $(depfile); \
mv -f $(dot-target).tmp $(dot-target).cmd, \
- printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
- printf '\# using basic dep data\n\n' >> $(dot-target).cmd; \
+ printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
+ printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd; \
cat $(depfile) >> $(dot-target).cmd; \
printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
###
## HOSTCC C flags
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
$(Q)$(MAKE) $(build)=fixdep
$(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
- $(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $<
+ $(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
FORCE:
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+ compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+ compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+ compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+ compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+ compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+ compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+ compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+ compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+ compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+ compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+ compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+ compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+ compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+ compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+ compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+ compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+ compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+ compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at 264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+ compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+ compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+ compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx, sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
*/
#define DRM_CLIENT_CAP_ATOMIC 3
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO 4
+
/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
struct drm_set_client_cap {
__u64 capability;
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
- * is set to metric from route (IPv4/IPv6 only).
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
- * Egress device index on success, 0 if packet needs to continue
- * up the stack for further processing or a negative error in case
- * of failure.
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
- __u32 ifindex; /* L3 device index for lookup */
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
union {
/* inputs to lookup */
__u8 tos; /* AF_INET */
- __be32 flowlabel; /* AF_INET6 */
+ __be32 flowinfo; /* AF_INET6, flow_label + priority */
/* output: metric of fib result (IPv4/IPv6 only) */
__u32 rt_metric;
*/
#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24)
#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff)
+#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff)
/* Attributes stored in the BTF_INT_ENCODING */
#define BTF_INT_SIGNED (1 << 0)
IFLA_BRPORT_BCAST_FLOOD,
IFLA_BRPORT_GROUP_FWD_MASK,
IFLA_BRPORT_NEIGH_SUPPRESS,
+ IFLA_BRPORT_ISOLATED,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
IFLA_VXLAN_COLLECT_METADATA,
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
+ IFLA_VXLAN_TTL_INHERIT,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions of the Internet Protocol.
+ *
+ * Version: @(#)in.h 1.0.1 04/21/93
+ *
+ * Authors: Original taken from the GNU Project <netinet/in.h> file.
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols. */
+enum {
+ IPPROTO_IP = 0, /* Dummy protocol for TCP */
+#define IPPROTO_IP IPPROTO_IP
+ IPPROTO_ICMP = 1, /* Internet Control Message Protocol */
+#define IPPROTO_ICMP IPPROTO_ICMP
+ IPPROTO_IGMP = 2, /* Internet Group Management Protocol */
+#define IPPROTO_IGMP IPPROTO_IGMP
+ IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP IPPROTO_IPIP
+ IPPROTO_TCP = 6, /* Transmission Control Protocol */
+#define IPPROTO_TCP IPPROTO_TCP
+ IPPROTO_EGP = 8, /* Exterior Gateway Protocol */
+#define IPPROTO_EGP IPPROTO_EGP
+ IPPROTO_PUP = 12, /* PUP protocol */
+#define IPPROTO_PUP IPPROTO_PUP
+ IPPROTO_UDP = 17, /* User Datagram Protocol */
+#define IPPROTO_UDP IPPROTO_UDP
+ IPPROTO_IDP = 22, /* XNS IDP protocol */
+#define IPPROTO_IDP IPPROTO_IDP
+ IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */
+#define IPPROTO_TP IPPROTO_TP
+ IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP IPPROTO_DCCP
+ IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */
+#define IPPROTO_IPV6 IPPROTO_IPV6
+ IPPROTO_RSVP = 46, /* RSVP Protocol */
+#define IPPROTO_RSVP IPPROTO_RSVP
+ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */
+#define IPPROTO_GRE IPPROTO_GRE
+ IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP IPPROTO_ESP
+ IPPROTO_AH = 51, /* Authentication Header protocol */
+#define IPPROTO_AH IPPROTO_AH
+ IPPROTO_MTP = 92, /* Multicast Transport Protocol */
+#define IPPROTO_MTP IPPROTO_MTP
+ IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */
+#define IPPROTO_BEETPH IPPROTO_BEETPH
+ IPPROTO_ENCAP = 98, /* Encapsulation Header */
+#define IPPROTO_ENCAP IPPROTO_ENCAP
+ IPPROTO_PIM = 103, /* Protocol Independent Multicast */
+#define IPPROTO_PIM IPPROTO_PIM
+ IPPROTO_COMP = 108, /* Compression Header Protocol */
+#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
+#define IPPROTO_SCTP IPPROTO_SCTP
+ IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
+#define IPPROTO_UDPLITE IPPROTO_UDPLITE
+ IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */
+#define IPPROTO_MPLS IPPROTO_MPLS
+ IPPROTO_RAW = 255, /* Raw IP packets */
+#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+ __be32 s_addr;
+};
+#endif
+
+#define IP_TOS 1
+#define IP_TTL 2
+#define IP_HDRINCL 3
+#define IP_OPTIONS 4
+#define IP_ROUTER_ALERT 5
+#define IP_RECVOPTS 6
+#define IP_RETOPTS 7
+#define IP_PKTINFO 8
+#define IP_PKTOPTIONS 9
+#define IP_MTU_DISCOVER 10
+#define IP_RECVERR 11
+#define IP_RECVTTL 12
+#define IP_RECVTOS 13
+#define IP_MTU 14
+#define IP_FREEBIND 15
+#define IP_IPSEC_POLICY 16
+#define IP_XFRM_POLICY 17
+#define IP_PASSSEC 18
+#define IP_TRANSPARENT 19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR 20
+#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR
+
+#define IP_MINTTL 21
+#define IP_NODEFRAG 22
+#define IP_CHECKSUM 23
+#define IP_BIND_ADDRESS_NO_PORT 24
+#define IP_RECVFRAGSIZE 25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
+#define IP_PMTUDISC_WANT 1 /* Use per route hints */
+#define IP_PMTUDISC_DO 2 /* Always DF */
+#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE 4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT 5
+
+#define IP_MULTICAST_IF 32
+#define IP_MULTICAST_TTL 33
+#define IP_MULTICAST_LOOP 34
+#define IP_ADD_MEMBERSHIP 35
+#define IP_DROP_MEMBERSHIP 36
+#define IP_UNBLOCK_SOURCE 37
+#define IP_BLOCK_SOURCE 38
+#define IP_ADD_SOURCE_MEMBERSHIP 39
+#define IP_DROP_SOURCE_MEMBERSHIP 40
+#define IP_MSFILTER 41
+#define MCAST_JOIN_GROUP 42
+#define MCAST_BLOCK_SOURCE 43
+#define MCAST_UNBLOCK_SOURCE 44
+#define MCAST_LEAVE_GROUP 45
+#define MCAST_JOIN_SOURCE_GROUP 46
+#define MCAST_LEAVE_SOURCE_GROUP 47
+#define MCAST_MSFILTER 48
+#define IP_MULTICAST_ALL 49
+#define IP_UNICAST_IF 50
+
+#define MCAST_EXCLUDE 0
+#define MCAST_INCLUDE 1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL 1
+#define IP_DEFAULT_MULTICAST_LOOP 1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_interface; /* local IP address of interface */
+};
+
+struct ip_mreqn {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_address; /* local IP address of interface */
+ int imr_ifindex; /* Interface index */
+};
+
+struct ip_mreq_source {
+ __be32 imr_multiaddr;
+ __be32 imr_interface;
+ __be32 imr_sourceaddr;
+};
+
+struct ip_msfilter {
+ __be32 imsf_multiaddr;
+ __be32 imsf_interface;
+ __u32 imsf_fmode;
+ __u32 imsf_numsrc;
+ __be32 imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+ (sizeof(struct ip_msfilter) - sizeof(__u32) \
+ + (numsrc) * sizeof(__u32))
+
+struct group_req {
+ __u32 gr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gr_group; /* group address */
+};
+
+struct group_source_req {
+ __u32 gsr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gsr_group; /* group address */
+ struct __kernel_sockaddr_storage gsr_source; /* source address */
+};
+
+struct group_filter {
+ __u32 gf_interface; /* interface index */
+ struct __kernel_sockaddr_storage gf_group; /* multicast address */
+ __u32 gf_fmode; /* filter mode */
+ __u32 gf_numsrc; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+ (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+ + (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+ int ipi_ifindex;
+ struct in_addr ipi_spec_dst;
+ struct in_addr ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_in {
+ __kernel_sa_family_t sin_family; /* Address family */
+ __be16 sin_port; /* Port number */
+ struct in_addr sin_addr; /* Internet address */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) -
+ sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero __pad /* for BSD UNIX comp. -FvK */
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0)
+#define IN_CLASSA_NET 0xff000000
+#define IN_CLASSA_NSHIFT 24
+#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET)
+#define IN_CLASSA_MAX 128
+
+#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define IN_CLASSB_NET 0xffff0000
+#define IN_CLASSB_NSHIFT 16
+#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET)
+#define IN_CLASSB_MAX 65536
+
+#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define IN_CLASSC_NET 0xffffff00
+#define IN_CLASSC_NSHIFT 8
+#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET)
+
+#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define IN_MULTICAST(a) IN_CLASSD(a)
+#define IN_MULTICAST_NET 0xF0000000
+
+#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_BADCLASS(a) IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define INADDR_ANY ((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define INADDR_BROADCAST ((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define INADDR_NONE ((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define IN_LOOPBACKNET 127
+
+/* Address to loopback in software to local host. */
+#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */
+#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h>
+
+
+#endif /* _UAPI_LINUX_IN_H */
#define KVM_CAP_S390_BPB 152
#define KVM_CAP_GET_MSR_FEATURES 153
#define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
#ifdef KVM_CAP_IRQ_ROUTING
PERF_SAMPLE_PHYS_ADDR = 1U << 19,
PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
+
+ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63,
};
/*
* asking selinux for a specific new context (e.g. with runcon) will result
* in execve returning -EPERM.
*
- * See Documentation/prctl/no_new_privs.txt for more details.
+ * See Documentation/userspace-api/no_new_privs.rst for more details.
*/
#define PR_SET_NO_NEW_PRIVS 38
#define PR_GET_NO_NEW_PRIVS 39
/*
* Check for "NAME_PATH" environment variable to override fs location (for
- * testing). This matches the recommendation in Documentation/sysfs-rules.txt
+ * testing). This matches the recommendation in Documentation/admin-guide/sysfs-rules.rst
* for SYSFS_PATH.
*/
static bool fs__env_override(struct fs *fs)
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: LGPL-2.1
/* Copyright (c) 2018 Facebook */
#include <stdlib.h>
-#include <stdint.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
struct btf_type **types;
const char *strings;
void *nohdr_data;
- uint32_t nr_types;
- uint32_t types_size;
- uint32_t data_size;
+ __u32 nr_types;
+ __u32 types_size;
+ __u32 data_size;
int fd;
};
-static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
+static const char *btf_name_by_offset(const struct btf *btf, __u32 offset)
{
if (offset < btf->hdr->str_len)
return &btf->strings[offset];
{
if (btf->types_size - btf->nr_types < 2) {
struct btf_type **new_types;
- u32 expand_by, new_size;
+ __u32 expand_by, new_size;
if (btf->types_size == BTF_MAX_NR_TYPES)
return -E2BIG;
static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
{
const struct btf_header *hdr = btf->hdr;
- u32 meta_left;
+ __u32 meta_left;
if (btf->data_size < sizeof(struct btf_header)) {
elog("BTF header not found\n");
while (next_type < end_type) {
struct btf_type *t = next_type;
- uint16_t vlen = BTF_INFO_VLEN(t->info);
+ __u16 vlen = BTF_INFO_VLEN(t->info);
int err;
next_type += sizeof(*t);
return 0;
}
-static const struct btf_type *btf_type_by_id(const struct btf *btf,
- uint32_t type_id)
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
{
if (type_id > btf->nr_types)
return NULL;
return !t || btf_type_is_void(t);
}
-static int64_t btf_type_size(const struct btf_type *t)
+static __s64 btf_type_size(const struct btf_type *t)
{
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_INT:
#define MAX_RESOLVE_DEPTH 32
-int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
+__s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
{
const struct btf_array *array;
const struct btf_type *t;
- uint32_t nelems = 1;
- int64_t size = -1;
+ __u32 nelems = 1;
+ __s64 size = -1;
int i;
- t = btf_type_by_id(btf, type_id);
+ t = btf__type_by_id(btf, type_id);
for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
i++) {
size = btf_type_size(t);
return -EINVAL;
}
- t = btf_type_by_id(btf, type_id);
+ t = btf__type_by_id(btf, type_id);
}
if (size < 0)
return nelems * size;
}
-int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
+__s32 btf__find_by_name(const struct btf *btf, const char *type_name)
{
- uint32_t i;
+ __u32 i;
if (!strcmp(type_name, "void"))
return 0;
free(btf);
}
-struct btf *btf__new(uint8_t *data, uint32_t size,
- btf_print_fn_t err_log)
+struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
{
- uint32_t log_buf_size = 0;
+ __u32 log_buf_size = 0;
char *log_buf = NULL;
struct btf *btf;
int err;
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: LGPL-2.1 */
/* Copyright (c) 2018 Facebook */
#ifndef __BPF_BTF_H
#define __BPF_BTF_H
-#include <stdint.h>
+#include <linux/types.h>
#define BTF_ELF_SEC ".BTF"
struct btf;
+struct btf_type;
typedef int (*btf_print_fn_t)(const char *, ...)
__attribute__((format(printf, 1, 2)));
void btf__free(struct btf *btf);
-struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
-int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
-int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+__s32 btf__find_by_name(const struct btf *btf, const char *type_name);
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
+__s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
int btf__fd(const struct btf *btf);
#endif
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/list.h>
#include <linux/limits.h>
#include <sys/stat.h>
size_t offset;
int map_ifindex;
struct bpf_map_def def;
- uint32_t btf_key_type_id;
- uint32_t btf_value_type_id;
+ __u32 btf_key_type_id;
+ __u32 btf_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
};
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
+ const struct btf_type *container_type;
+ const struct btf_member *key, *value;
struct bpf_map_def *def = &map->def;
const size_t max_name = 256;
- int64_t key_size, value_size;
- int32_t key_id, value_id;
- char name[max_name];
+ char container_name[max_name];
+ __s64 key_size, value_size;
+ __s32 container_id;
- /* Find key type by name from BTF */
- if (snprintf(name, max_name, "%s_key", map->name) == max_name) {
- pr_warning("map:%s length of BTF key_type:%s_key is too long\n",
+ if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
+ max_name) {
+ pr_warning("map:%s length of '____btf_map_%s' is too long\n",
map->name, map->name);
return -EINVAL;
}
- key_id = btf__find_by_name(btf, name);
- if (key_id < 0) {
- pr_debug("map:%s key_type:%s cannot be found in BTF\n",
- map->name, name);
- return key_id;
+ container_id = btf__find_by_name(btf, container_name);
+ if (container_id < 0) {
+ pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
+ map->name, container_name);
+ return container_id;
}
- key_size = btf__resolve_size(btf, key_id);
- if (key_size < 0) {
- pr_warning("map:%s key_type:%s cannot get the BTF type_size\n",
- map->name, name);
- return key_size;
+ container_type = btf__type_by_id(btf, container_id);
+ if (!container_type) {
+ pr_warning("map:%s cannot find BTF type for container_id:%u\n",
+ map->name, container_id);
+ return -EINVAL;
}
- if (def->key_size != key_size) {
- pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n",
- map->name, name, (unsigned int)key_size, def->key_size);
+ if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
+ BTF_INFO_VLEN(container_type->info) < 2) {
+ pr_warning("map:%s container_name:%s is an invalid container struct\n",
+ map->name, container_name);
return -EINVAL;
}
- /* Find value type from BTF */
- if (snprintf(name, max_name, "%s_value", map->name) == max_name) {
- pr_warning("map:%s length of BTF value_type:%s_value is too long\n",
- map->name, map->name);
- return -EINVAL;
+ key = (struct btf_member *)(container_type + 1);
+ value = key + 1;
+
+ key_size = btf__resolve_size(btf, key->type);
+ if (key_size < 0) {
+ pr_warning("map:%s invalid BTF key_type_size\n",
+ map->name);
+ return key_size;
}
- value_id = btf__find_by_name(btf, name);
- if (value_id < 0) {
- pr_debug("map:%s value_type:%s cannot be found in BTF\n",
- map->name, name);
- return value_id;
+ if (def->key_size != key_size) {
+ pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
+ map->name, (__u32)key_size, def->key_size);
+ return -EINVAL;
}
- value_size = btf__resolve_size(btf, value_id);
+ value_size = btf__resolve_size(btf, value->type);
if (value_size < 0) {
- pr_warning("map:%s value_type:%s cannot get the BTF type_size\n",
- map->name, name);
+ pr_warning("map:%s invalid BTF value_type_size\n", map->name);
return value_size;
}
if (def->value_size != value_size) {
- pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n",
- map->name, name, (unsigned int)value_size, def->value_size);
+ pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
+ map->name, (__u32)value_size, def->value_size);
return -EINVAL;
}
- map->btf_key_type_id = key_id;
- map->btf_value_type_id = value_id;
+ map->btf_key_type_id = key->type;
+ map->btf_value_type_id = value->type;
return 0;
}
return map ? map->name : NULL;
}
-uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map)
+__u32 bpf_map__btf_key_type_id(const struct bpf_map *map)
{
return map ? map->btf_key_type_id : 0;
}
-uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map)
+__u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
{
return map ? map->btf_value_type_id : 0;
}
volatile struct perf_event_mmap_page *header = mem;
__u64 data_tail = header->data_tail;
__u64 data_head = header->data_head;
+ int ret = LIBBPF_PERF_EVENT_ERROR;
void *base, *begin, *end;
- int ret;
asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
if (data_head == data_tail)
int bpf_map__fd(struct bpf_map *map);
const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
const char *bpf_map__name(struct bpf_map *map);
-uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map);
-uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map);
+__u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
+__u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
Second, some types of fence affect the way the memory subsystem
propagates stores. When a fence instruction is executed on CPU C:
- For each other CPU C', smb_wmb() forces all po-earlier stores
+ For each other CPU C', smp_wmb() forces all po-earlier stores
on C to propagate to C' before any po-later stores do.
For each other CPU C', any store which propagates to C before
locking will be seen as ordered by CPUs not holding that lock.
Consider this example:
- /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+ /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
void CPU0(void)
{
spin_lock(&mylock);
smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
to understand their use cases. The general approach is shown below:
- /* See MP+wmbonceonce+rmbonceonce.litmus. */
+ /* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
void CPU0(void)
{
WRITE_ONCE(x, 1);
And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
the corresponding read-side code fragment:
- cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+ cur_cycle = READ_ONCE(log->l_curr_cycle);
smp_rmb();
- cur_block = ACCESS_ONCE(log->l_curr_block);
+ cur_block = READ_ONCE(log->l_curr_block);
Alternatively, consider the following comment in function
perf_output_put_handle() in kernel/events/ring_buffer.c:
One way of avoiding the counter-intuitive outcome is through the use of a
control dependency paired with a full memory barrier:
- /* See LB+ctrlonceonce+mbonceonce.litmus. */
+ /* See LB+fencembonceonce+ctrlonceonce.litmus. */
void CPU0(void)
{
r0 = READ_ONCE(x);
while another CPU stores to the second variable and then loads from the
first. Preserving order requires nothing less than full barriers:
- /* See SB+mbonceonces.litmus. */
+ /* See SB+fencembonceonces.litmus. */
void CPU0(void)
{
WRITE_ONCE(x, 1);
The memory model is used, in conjunction with "herd7", to exhaustively
explore the state space of small litmus tests.
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
- $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+ $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
Here is the corresponding output:
- Test SB+mbonceonces Allowed
+ Test SB+fencembonceonces Allowed
States 3
0:r0=0; 1:r0=1;
0:r0=1; 1:r0=0;
Witnesses
Positive: 0 Negative: 3
Condition exists (0:r0=0 /\ 1:r0=0)
- Observation SB+mbonceonces Never 0 3
- Time SB+mbonceonces 0.01
+ Observation SB+fencembonceonces Never 0 3
+ Time SB+fencembonceonces 0.01
Hash=d66d99523e2cac6b06e66f4c995ebb48
The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
The "klitmus7" tool converts a litmus test into a Linux kernel module,
which may then be loaded and run.
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
$ mkdir mymodules
- $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+ $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
$ cd mymodules ; make
$ sudo sh run.sh
The corresponding output includes:
- Test SB+mbonceonces Allowed
+ Test SB+fencembonceonces Allowed
Histogram (3 states)
644580 :>0:r0=1; 1:r0=0;
644328 :>0:r0=0; 1:r0=1;
Positive: 0, Negative: 2000000
Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
Hash=d66d99523e2cac6b06e66f4c995ebb48
- Observation SB+mbonceonces Never 0 2000000
- Time SB+mbonceonces 0.16
+ Observation SB+fencembonceonces Never 0 2000000
+ Time SB+fencembonceonces 0.16
The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
that during two million trials, the state specified in this litmus
"Linux-kernel memory consistency model"
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
'release (*smp_store_release*) ||
'acquire (*smp_load_acquire*) ||
'noreturn (* R of non-return RMW *)
--- /dev/null
+C IRIW+fencembonceonces+OnceOnce
+
+(*
+ * Result: Never
+ *
+ * Test of independent reads from independent writes with smp_mb()
+ * between each pairs of reads. In other words, is smp_mb() sufficient to
+ * cause two different reading processes to agree on the order of a pair
+ * of writes, where each write is to a different variable by a different
+ * process? This litmus test exercises LKMM's "propagation" rule.
+ *)
+
+{}
+
+P0(int *x)
+{
+ WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+ int r1;
+
+ r0 = READ_ONCE(*x);
+ smp_mb();
+ r1 = READ_ONCE(*y);
+}
+
+P2(int *y)
+{
+ WRITE_ONCE(*y, 1);
+}
+
+P3(int *x, int *y)
+{
+ int r0;
+ int r1;
+
+ r0 = READ_ONCE(*y);
+ smp_mb();
+ r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
+++ /dev/null
-C IRIW+mbonceonces+OnceOnce
-
-(*
- * Result: Never
- *
- * Test of independent reads from independent writes with smp_mb()
- * between each pairs of reads. In other words, is smp_mb() sufficient to
- * cause two different reading processes to agree on the order of a pair
- * of writes, where each write is to a different variable by a different
- * process? This litmus test exercises LKMM's "propagation" rule.
- *)
-
-{}
-
-P0(int *x)
-{
- WRITE_ONCE(*x, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
- int r1;
-
- r0 = READ_ONCE(*x);
- smp_mb();
- r1 = READ_ONCE(*y);
-}
-
-P2(int *y)
-{
- WRITE_ONCE(*y, 1);
-}
-
-P3(int *x, int *y)
-{
- int r0;
- int r1;
-
- r0 = READ_ONCE(*y);
- smp_mb();
- r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
(*
* Result: Sometimes
+++ /dev/null
-C LB+ctrlonceonce+mbonceonce
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that lightweight ordering suffices for
- * the load-buffering pattern, in other words, preventing all processes
- * reading from the preceding process's write. In this example, the
- * combination of a control dependency and a full memory barrier are enough
- * to do the trick. (But the full memory barrier could be replaced with
- * another control dependency and order would still be maintained.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- int r0;
-
- r0 = READ_ONCE(*x);
- if (r0)
- WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
-
- r0 = READ_ONCE(*y);
- smp_mb();
- WRITE_ONCE(*x, 1);
-}
-
-exists (0:r0=1 /\ 1:r0=1)
--- /dev/null
+C LB+fencembonceonce+ctrlonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that lightweight ordering suffices for
+ * the load-buffering pattern, in other words, preventing all processes
+ * reading from the preceding process's write. In this example, the
+ * combination of a control dependency and a full memory barrier are enough
+ * to do the trick. (But the full memory barrier could be replaced with
+ * another control dependency and order would still be maintained.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ int r0;
+
+ r0 = READ_ONCE(*x);
+ if (r0)
+ WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+
+ r0 = READ_ONCE(*y);
+ smp_mb();
+ WRITE_ONCE(*x, 1);
+}
+
+exists (0:r0=1 /\ 1:r0=1)
--- /dev/null
+C MP+fencewmbonceonce+fencermbonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that smp_wmb() and smp_rmb() provide
+ * sufficient ordering for the message-passing pattern. However, it
+ * is usually better to use smp_store_release() and smp_load_acquire().
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ WRITE_ONCE(*x, 1);
+ smp_wmb();
+ WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+ int r1;
+
+ r0 = READ_ONCE(*y);
+ smp_rmb();
+ r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
+++ /dev/null
-C MP+wmbonceonce+rmbonceonce
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that smp_wmb() and smp_rmb() provide
- * sufficient ordering for the message-passing pattern. However, it
- * is usually better to use smp_store_release() and smp_load_acquire().
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- WRITE_ONCE(*x, 1);
- smp_wmb();
- WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
- int r1;
-
- r0 = READ_ONCE(*y);
- smp_rmb();
- r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 1:r1=0)
--- /dev/null
+C R+fencembonceonces
+
+(*
+ * Result: Never
+ *
+ * This is the fully ordered (via smp_mb()) version of one of the classic
+ * counterintuitive litmus tests that illustrates the effects of store
+ * propagation delays. Note that weakening either of the barriers would
+ * cause the resulting test to be allowed.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ WRITE_ONCE(*x, 1);
+ smp_mb();
+ WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+
+ WRITE_ONCE(*y, 2);
+ smp_mb();
+ r0 = READ_ONCE(*x);
+}
+
+exists (y=2 /\ 1:r0=0)
+++ /dev/null
-C R+mbonceonces
-
-(*
- * Result: Never
- *
- * This is the fully ordered (via smp_mb()) version of one of the classic
- * counterintuitive litmus tests that illustrates the effects of store
- * propagation delays. Note that weakening either of the barriers would
- * cause the resulting test to be allowed.
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- WRITE_ONCE(*x, 1);
- smp_mb();
- WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
-
- WRITE_ONCE(*y, 2);
- smp_mb();
- r0 = READ_ONCE(*x);
-}
-
-exists (y=2 /\ 1:r0=0)
Test of write-write coherence, that is, whether or not two
successive writes to the same variable are ordered.
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
Test of independent reads from independent writes with smp_mb()
between each pairs of reads. In other words, is smp_mb()
sufficient to cause two different reading processes to agree on
Can a release-acquire chain order a prior store against
a later load?
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
Does a control dependency and an smp_mb() suffice for the
load-buffering litmus test, where each process reads from one
of two variables then writes to the other?
As below, but with the first access of the writer process
and the second access of reader process protected by a lock.
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
Does a smp_wmb() (between the stores) and an smp_rmb() (between
the loads) suffice for the message-passing litmus test, where one
process writes data and then a flag, and the other process reads
the flag and then the data. (This is similar to the ISA2 tests,
but with two processes instead of three.)
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
This is the fully ordered (via smp_mb()) version of one of
the classic counterintuitive litmus tests that illustrates the
effects of store propagation delays.
R+poonceonces.litmus
As above, but without the smp_mb() invocations.
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
This is the fully ordered (again, via smp_mb() version of store
buffering, which forms the core of Dekker's mutual-exclusion
algorithm.
SB+poonceonces.litmus
As above, but without the smp_mb() invocations.
+SB+rfionceonce-poonceonces.litmus
+ This litmus test demonstrates that LKMM is not fully multicopy
+ atomic. (Neither is it other multicopy atomic.) This litmus test
+ also demonstrates the "locations" debugging aid, which designates
+ additional registers and locations to be printed out in the dump
+ of final states in the herd7 output. Without the "locations"
+ statement, only those registers and locations mentioned in the
+ "exists" clause will be printed.
+
S+poonceonces.litmus
As below, but without the smp_wmb() and acquire load.
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
Can a smp_wmb(), instead of a release, and an acquire order
a prior store against a subsequent store?
WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
These two are members of an extension of the MP litmus-test
class in which the first write is moved to a separate process.
The second is forbidden because smp_store_release() is
As above, but with smp_mb__after_spinlock() immediately
following the spin_lock().
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
Is the ordering provided by a release-acquire chain sufficient
to make ordering apparent to accesses by a process that does
not participate in that release-acquire chain?
--- /dev/null
+C S+fencewmbonceonce+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * Can a smp_wmb(), instead of a release, and an acquire order a prior
+ * store against a subsequent store?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ WRITE_ONCE(*x, 2);
+ smp_wmb();
+ WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+
+ r0 = smp_load_acquire(y);
+ WRITE_ONCE(*x, 1);
+}
+
+exists (x=2 /\ 1:r0=1)
+++ /dev/null
-C S+wmbonceonce+poacquireonce
-
-(*
- * Result: Never
- *
- * Can a smp_wmb(), instead of a release, and an acquire order a prior
- * store against a subsequent store?
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- WRITE_ONCE(*x, 2);
- smp_wmb();
- WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
-
- r0 = smp_load_acquire(y);
- WRITE_ONCE(*x, 1);
-}
-
-exists (x=2 /\ 1:r0=1)
--- /dev/null
+C SB+fencembonceonces
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that full memory barriers suffice to
+ * order the store-buffering pattern, where each process writes to the
+ * variable that the preceding process reads. (Locking and RCU can also
+ * suffice, but not much else.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ int r0;
+
+ WRITE_ONCE(*x, 1);
+ smp_mb();
+ r0 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+
+ WRITE_ONCE(*y, 1);
+ smp_mb();
+ r0 = READ_ONCE(*x);
+}
+
+exists (0:r0=0 /\ 1:r0=0)
+++ /dev/null
-C SB+mbonceonces
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that full memory barriers suffice to
- * order the store-buffering pattern, where each process writes to the
- * variable that the preceding process reads. (Locking and RCU can also
- * suffice, but not much else.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- int r0;
-
- WRITE_ONCE(*x, 1);
- smp_mb();
- r0 = READ_ONCE(*y);
-}
-
-P1(int *x, int *y)
-{
- int r0;
-
- WRITE_ONCE(*y, 1);
- smp_mb();
- r0 = READ_ONCE(*x);
-}
-
-exists (0:r0=0 /\ 1:r0=0)
--- /dev/null
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ int r1;
+ int r2;
+
+ WRITE_ONCE(*x, 1);
+ r1 = READ_ONCE(*x);
+ r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+ int r3;
+ int r4;
+
+ WRITE_ONCE(*y, 1);
+ r3 = READ_ONCE(*y);
+ r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
--- /dev/null
+C WRC+pooncerelease+fencermbonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * This litmus test is an extension of the message-passing pattern, where
+ * the first write is moved to a separate process. Because it features
+ * a release and a read memory barrier, it should be forbidden. More
+ * specifically, this litmus test is forbidden because smp_store_release()
+ * is A-cumulative in LKMM.
+ *)
+
+{}
+
+P0(int *x)
+{
+ WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+ int r0;
+
+ r0 = READ_ONCE(*x);
+ smp_store_release(y, 1);
+}
+
+P2(int *x, int *y)
+{
+ int r0;
+ int r1;
+
+ r0 = READ_ONCE(*y);
+ smp_rmb();
+ r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
+++ /dev/null
-C WRC+pooncerelease+rmbonceonce+Once
-
-(*
- * Result: Never
- *
- * This litmus test is an extension of the message-passing pattern, where
- * the first write is moved to a separate process. Because it features
- * a release and a read memory barrier, it should be forbidden. More
- * specifically, this litmus test is forbidden because smp_store_release()
- * is A-cumulative in LKMM.
- *)
-
-{}
-
-P0(int *x)
-{
- WRITE_ONCE(*x, 1);
-}
-
-P1(int *x, int *y)
-{
- int r0;
-
- r0 = READ_ONCE(*x);
- smp_store_release(y, 1);
-}
-
-P2(int *x, int *y)
-{
- int r0;
- int r1;
-
- r0 = READ_ONCE(*y);
- smp_rmb();
- r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
--- /dev/null
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test shows that a release-acquire chain, while sufficient
+ * when there is but one non-reads-from (AKA non-rf) link, does not suffice
+ * if there is more than one. Of the three processes, only P1() reads from
+ * P0's write, which means that there are two non-rf links: P1() to P2()
+ * is a write-to-write link (AKA a "coherence" or just "co" link) and P2()
+ * to P0() is a read-to-write link (AKA a "from-reads" or just "fr" link).
+ * When there are two or more non-rf links, you typically will need one
+ * full barrier for each non-rf link. (Exceptions include some cases
+ * involving locking.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+ WRITE_ONCE(*x, 1);
+ smp_store_release(y, 1);
+}
+
+P1(int *y, int *z)
+{
+ int r0;
+
+ r0 = smp_load_acquire(y);
+ smp_store_release(z, 1);
+}
+
+P2(int *x, int *z)
+{
+ int r1;
+
+ WRITE_ONCE(*z, 2);
+ smp_mb();
+ r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ z=2 /\ 2:r1=0)
+++ /dev/null
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
-
-(*
- * Result: Sometimes
- *
- * This litmus test shows that a release-acquire chain, while sufficient
- * when there is but one non-reads-from (AKA non-rf) link, does not suffice
- * if there is more than one. Of the three processes, only P1() reads from
- * P0's write, which means that there are two non-rf links: P1() to P2()
- * is a write-to-write link (AKA a "coherence" or just "co" link) and P2()
- * to P0() is a read-to-write link (AKA a "from-reads" or just "fr" link).
- * When there are two or more non-rf links, you typically will need one
- * full barrier for each non-rf link. (Exceptions include some cases
- * involving locking.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
- WRITE_ONCE(*x, 1);
- smp_store_release(y, 1);
-}
-
-P1(int *y, int *z)
-{
- int r0;
-
- r0 = smp_load_acquire(y);
- smp_store_release(z, 1);
-}
-
-P2(int *x, int *z)
-{
- int r1;
-
- WRITE_ONCE(*z, 2);
- smp_mb();
- r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ z=2 /\ 2:r1=0)
# appended.
#
# Usage:
-# sh checkalllitmus.sh [ directory ]
+# checkalllitmus.sh [ directory ]
#
# The LINUX_HERD_OPTIONS environment variable may be used to specify
# arguments to herd, whose default is defined by the checklitmus.sh script.
# with ".out" appended.
#
# Usage:
-# sh checklitmus.sh file.litmus
+# checklitmus.sh file.litmus
#
# The LINUX_HERD_OPTIONS environment variable may be used to specify
# arguments to herd, which default to "-conf linux-kernel.cfg". Thus,
unsigned sp_reg:4;
unsigned bp_reg:4;
unsigned type:2;
+ unsigned end:1;
} __packed;
/*
s16 sp_offset;
u8 sp_reg;
u8 type;
+ u8 end;
};
#endif /* __ASSEMBLY__ */
"lbug_with_loc",
"fortify_panic",
"usercopy_abort",
+ "machine_real_restart",
};
if (func->bind == STB_WEAK)
cfa->offset = hint->sp_offset;
insn->state.type = hint->type;
+ insn->state.end = hint->end;
}
return 0;
int stack_size;
unsigned char type;
bool bp_scratch;
- bool drap;
+ bool drap, end;
int drap_reg, drap_offset;
struct cfi_reg vals[CFI_NUM_REGS];
};
continue;
sym->pfunc = sym->cfunc = sym;
coldstr = strstr(sym->name, ".cold.");
- if (coldstr) {
- coldstr[0] = '\0';
- pfunc = find_symbol_by_name(elf, sym->name);
- coldstr[0] = '.';
-
- if (!pfunc) {
- WARN("%s(): can't find parent function",
- sym->name);
- goto err;
- }
-
- sym->pfunc = pfunc;
- pfunc->cfunc = sym;
+ if (!coldstr)
+ continue;
+
+ coldstr[0] = '\0';
+ pfunc = find_symbol_by_name(elf, sym->name);
+ coldstr[0] = '.';
+
+ if (!pfunc) {
+ WARN("%s(): can't find parent function",
+ sym->name);
+ goto err;
+ }
+
+ sym->pfunc = pfunc;
+ pfunc->cfunc = sym;
+
+ /*
+ * Unfortunately, -fnoreorder-functions puts the child
+ * inside the parent. Remove the overlap so we can
+ * have sane assumptions.
+ *
+ * Note that pfunc->len now no longer matches
+ * pfunc->sym.st_size.
+ */
+ if (sym->sec == pfunc->sec &&
+ sym->offset >= pfunc->offset &&
+ sym->offset + sym->len == pfunc->offset + pfunc->len) {
+ pfunc->len -= sym->len;
}
}
}
sec->sh.sh_flags = SHF_ALLOC;
- /* Add section name to .shstrtab */
+ /* Add section name to .shstrtab (or .strtab for Clang) */
shstrtab = find_section_by_name(elf, ".shstrtab");
+ if (!shstrtab)
+ shstrtab = find_section_by_name(elf, ".strtab");
if (!shstrtab) {
- WARN("can't find .shstrtab section");
+ WARN("can't find .shstrtab or .strtab section");
return NULL;
}
print_reg(orc[i].bp_reg, orc[i].bp_offset);
- printf(" type:%s\n", orc_type_name(orc[i].type));
+ printf(" type:%s end:%d\n",
+ orc_type_name(orc[i].type), orc[i].end);
}
elf_end(elf);
struct cfi_reg *cfa = &insn->state.cfa;
struct cfi_reg *bp = &insn->state.regs[CFI_BP];
+ orc->end = insn->state.end;
+
if (cfa->base == CFI_UNDEFINED) {
orc->sp_reg = ORC_REG_UNDEFINED;
continue;
OPTIONS
-------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
--no-desc::
Don't print descriptions.
--long-desc::
Print longer event descriptions.
+--debug::
+Enable debugging output.
+
--details::
Print how named events are resolved internally into perf events, and also
any extra expressions computed by perf stat.
-
[[EVENT_MODIFIERS]]
EVENT MODIFIERS
---------------
perf record -e '{cycles,instructions}:S' ...
perf report --group
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
the first event (the leader) samples, and it only reads the values of the
other events in the group.
"perf report" to view group events together.
--filter=<filter>::
- Event filter. This option should follow a event selector (-e) which
+ Event filter. This option should follow an event selector (-e) which
selects either tracepoint event(s) or a hardware trace PMU
(e.g. Intel PT or CoreSight).
--exclude-perf::
Don't record events issued by perf itself. This option should follow
- a event selector (-e) which selects tracepoint event(s). It adds a
+ an event selector (-e) which selects tracepoint event(s). It adds a
filter expression 'common_pid != $PERFPID' to filters. If other
'--filter' exists, the new filter expression will be combined with
them by '&&'.
This option should be used together with "-I" option.
example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
+--interval-clear::
+Clear the screen before next interval.
+
--timeout msecs::
Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
This option is not supported with the "-I" option.
ifeq ($(SRCARCH),arm64)
NO_PERF_REGS := 0
+ NO_SYSCALL_TABLE := 0
+ CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
endif
PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
- PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
- PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+ PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
endif
mandir = share/man
infodir = share/info
perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
sharedir = $(prefix)/share
template_dir = share/perf-core/templates
STRACE_GROUPS_DIR = share/perf-core/strace/groups
SHELL = $(SHELL_PATH)
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
beauty_outdir := $(OUTPUT)trace/beauty/generated
beauty_ioctl_outdir := $(beauty_outdir)/ioctl
drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
$(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+ $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
$(sndrv_ctl_ioctl_array) \
$(kcmp_type_array) \
$(kvm_ioctl_array) \
+ $(socket_ipproto_array) \
$(vhost_virtio_ioctl_array) \
$(madvise_behavior_array) \
$(perf_ioctl_array) \
$(OUTPUT)$(sndrv_pcm_ioctl_array) \
$(OUTPUT)$(kvm_ioctl_array) \
$(OUTPUT)$(kcmp_type_array) \
+ $(OUTPUT)$(socket_ipproto_array) \
$(OUTPUT)$(vhost_virtio_ioctl_array) \
$(OUTPUT)$(perf_ioctl_array) \
$(OUTPUT)$(prctl_option_array) \
endif
PERF_HAVE_JITDUMP := 1
PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+ $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+ $(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+ echo "Could not read input file" >&2
+ exit 1
+fi
+
+create_table_from_c()
+{
+ local sc nr last_sc
+
+ create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+ {
+
+ cat <<-_EoHEADER
+ #include <stdio.h>
+ #define __ARCH_WANT_RENAMEAT
+ #include "$input"
+ int main(int argc, char *argv[])
+ {
+ _EoHEADER
+
+ while read sc nr; do
+ printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+ last_sc=$sc
+ done
+
+ printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+ printf "}\n"
+
+ } | $hostcc -o $create_table_exe -x c -
+
+ $create_table_exe
+
+ rm -f $create_table_exe
+}
+
+create_table()
+{
+ echo "static const char *syscalltbl_arm64[] = {"
+ create_table_from_c
+ echo "};"
+}
+
+$gcc -E -dM -x c $input \
+ |sed -ne 's/^#define __NR_//p' \
+ |sort -t' ' -k2 -nu \
+ |create_table
}
/*
- * Check if return address is on the stack.
+ * Check if return address is on the stack. If return address
+ * is in a register (typically R0), it is yet to be saved on
+ * the stack.
*/
- if (nops != 0 || ops != NULL)
+ if ((nops != 0 || ops != NULL) &&
+ !(nops == 1 && ops[0].atom == DW_OP_regx &&
+ ops[0].number2 == 0 && ops[0].offset == 0))
return 0;
/*
u64 ip;
u64 skip_slot = -1;
- if (chain->nr < 3)
+ if (!chain || chain->nr < 3)
return skip_slot;
- ip = chain->ips[2];
+ ip = chain->ips[1];
thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
{
- if (strstr(cpuid, "IBM/S390")) {
+ if (strstr(cpuid, "IBM")) {
kvm->exit_reasons = sie_exit_reasons;
kvm->exit_reasons_isa = "SIE";
} else
330 common pkey_alloc __x64_sys_pkey_alloc
331 common pkey_free __x64_sys_pkey_free
332 common statx __x64_sys_statx
+333 common io_pgetevents __x64_sys_io_pgetevents
+334 common rseq __x64_sys_rseq
#
# x32-specific system call numbers start at 512 to avoid cache impact
else if (rm[2].rm_so != rm[2].rm_eo)
prefix[0] = '+';
else
- strncpy(prefix, "+0", 2);
+ scnprintf(prefix, sizeof(prefix), "+0");
}
/* Rename register */
// SPDX-License-Identifier: GPL-2.0
#include <string.h>
+#include <linux/stddef.h>
#include <linux/perf_event.h>
#include "../../util/intel-pt.h"
#include <stdbool.h>
#include <errno.h>
+#include <linux/stddef.h>
#include <linux/perf_event.h>
#include "../../perf.h"
perf-y += futex-requeue.o
perf-y += futex-lock-pi.o
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
#define altinstr_replacement text
#define globl p2align 4; .globl
#define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
#include "../../arch/x86/lib/memcpy_64.S"
/*
--- /dev/null
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+ for (; len; --len, to++, from++) {
+ /*
+ * Call the assembly routine back directly since
+ * memcpy_mcsafe() may silently fallback to memcpy.
+ */
+ unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+ if (rem)
+ break;
+ }
+ return len;
+}
u8 *global_data;
u8 *process_data;
u8 *thread_data;
- u64 bytes_done;
+ u64 bytes_done, secs;
long work_done;
u32 l;
struct rusage rusage;
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
- td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+ secs = td->runtime_ns / NSEC_PER_SEC;
+ td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
getrusage(RUSAGE_THREAD, &rusage);
td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
return ret;
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
static int hist_entry__tty_annotate(struct hist_entry *he,
struct perf_evsel *evsel,
struct perf_annotate *ann)
.attr = perf_event__process_attr,
.build_id = perf_event__process_build_id,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
struct compute_stats cstats;
+ unsigned long paddr;
+ unsigned long paddr_cnt;
+ bool paddr_zero;
+ char *nodestr;
+
/*
* must be at the end,
* because of its callchain dynamic entry
*/
struct hist_entry he;
-
- unsigned long paddr;
- unsigned long paddr_cnt;
- bool paddr_zero;
- char *nodestr;
};
static char const *coalesce_default = "pid,iaddr";
fprintf(out, "%s\n", bf);
fprintf(out, " -------------------------------------------------------------\n");
- hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+ hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
}
static void print_pareto(FILE *out)
fprintf(out, "=================================================\n");
fprintf(out, "#\n");
- hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+ hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
fprintf(out, "\n");
fprintf(out, "=================================================\n");
" s Toggle full length of symbol and source line columns \n"
" q Return back to cacheline list \n";
+ if (!he)
+ return 0;
+
/* Display compact version first. */
c2c.symbol_full = false;
hists__output_resort(hists, NULL);
hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
- symbol_conf.use_callchain);
+ !symbol_conf.use_callchain);
}
static void data__fprintf(void)
}
/*
- * All features are received, we can force the
+ * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+ * means all features are received, now we can force the
* group if needed.
*/
setup_forced_leader(rep, session->evlist);
hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
- symbol_conf.use_callchain ||
- symbol_conf.show_branchflag_count);
+ !(symbol_conf.use_callchain ||
+ symbol_conf.show_branchflag_count));
fprintf(stdout, "\n\n");
}
PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
},
+ [PERF_TYPE_HW_CACHE] = {
+ .user_set = false,
+
+ .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+ PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+ PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
+
+ .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+ },
+
[PERF_TYPE_RAW] = {
.user_set = false,
struct perf_evlist *evlist;
struct perf_evsel *evsel, *pos;
int err;
+ static struct perf_evsel_script *es;
err = perf_event__process_attr(tool, event, pevlist);
if (err)
evlist = *pevlist;
evsel = perf_evlist__last(*pevlist);
+ if (!evsel->priv) {
+ if (scr->per_event_dump) {
+ evsel->priv = perf_evsel_script__new(evsel,
+ scr->session->data);
+ } else {
+ es = zalloc(sizeof(*es));
+ if (!es)
+ return -ENOMEM;
+ es->fp = stdout;
+ evsel->priv = es;
+ }
+ }
+
if (evsel->attr.type >= PERF_TYPE_MAX &&
evsel->attr.type != PERF_TYPE_SYNTH)
return 0;
return set_maps(script);
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
#ifdef HAVE_AUXTRACE_SUPPORT
static int perf_script__process_auxtrace_info(struct perf_tool *tool,
union perf_event *event,
.attr = process_attr,
.event_update = perf_event__process_event_update,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.build_id = perf_event__process_build_id,
.id_index = perf_event__process_id_index,
.auxtrace_info = perf_script__process_auxtrace_info,
"+field to add and -field to remove."
"Valid types: hw,sw,trace,raw,synth. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+ "addr,symoff,srcline,period,iregs,uregs,brstack,"
+ "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+ "callindent,insn,insnlen,synth,phys_addr,metric,misc",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
#include "util/tool.h"
#include "util/string2.h"
#include "util/metricgroup.h"
+#include "util/top.h"
#include "asm/bug.h"
#include <linux/time64.h>
typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
+#define METRIC_ONLY_LEN 20
+
static int run_count = 1;
static bool no_inherit = false;
static volatile pid_t child_pid = -1;
static aggr_get_id_t aggr_get_id;
static bool append_file;
static bool interval_count;
+static bool interval_clear;
static const char *output_name;
static int output_fd;
static int print_free_counters_hint;
static u64 *walltime_run;
static bool ru_display = false;
static struct rusage ru_data;
+static unsigned int metric_only_len = METRIC_ONLY_LEN;
struct perf_stat {
bool record;
return perf_evsel__open_per_thread(evsel, evsel_list->threads);
}
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
- if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
- perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
- return 1;
-
- return 0;
-}
-
static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
}
-#define METRIC_ONLY_LEN 20
-
/* Filter out some columns that don't work well in metrics only mode */
static bool valid_only_metric(const char *unit)
{
struct outstate *os = ctx;
FILE *out = os->fh;
- int n;
- char buf[1024];
- unsigned mlen = METRIC_ONLY_LEN;
+ char buf[1024], str[1024];
+ unsigned mlen = metric_only_len;
if (!valid_only_metric(unit))
return;
unit = fixunit(buf, os->evsel, unit);
- if (color)
- n = color_fprintf(out, color, fmt, val);
- else
- n = fprintf(out, fmt, val);
- if (n > METRIC_ONLY_LEN)
- n = METRIC_ONLY_LEN;
if (mlen < strlen(unit))
mlen = strlen(unit) + 1;
- fprintf(out, "%*s", mlen - n, "");
+
+ if (color)
+ mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+ color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+ fprintf(out, "%*s ", mlen, str);
}
static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
if (csv_output)
fprintf(os->fh, "%s%s", unit, csv_sep);
else
- fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
-}
-
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
- FILE *output = stat_config.output;
- double msecs = avg / NSEC_PER_MSEC;
- const char *fmt_v, *fmt_n;
- char name[25];
-
- fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
- fmt_n = csv_output ? "%s" : "%-25s";
-
- aggr_printout(evsel, id, nr);
-
- scnprintf(name, sizeof(name), "%s%s",
- perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
- fprintf(output, fmt_v, msecs, csv_sep);
-
- if (csv_output)
- fprintf(output, "%s%s", evsel->unit, csv_sep);
- else
- fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
- fprintf(output, fmt_n, name);
-
- if (evsel->cgrp)
- fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+ fprintf(os->fh, "%*s ", metric_only_len, unit);
}
static int first_shadow_cpu(struct perf_evsel *evsel, int id)
return;
}
- if (metric_only)
- /* nothing */;
- else if (nsec_counter(counter))
- nsec_printout(id, nr, counter, uval);
- else
+ if (!metric_only)
abs_printout(id, nr, counter, uval);
out.print_metric = pm;
alias->scale != counter->scale ||
alias->cgrp != counter->cgrp ||
strcmp(alias->unit, counter->unit) ||
- nsec_counter(alias) != nsec_counter(counter))
+ perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
break;
alias->merged_stat = true;
cb(alias, data, false);
FILE *output = stat_config.output;
static int num_print_interval;
+ if (interval_clear)
+ puts(CONSOLE_CLEAR);
+
sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
- if (num_print_interval == 0 && !csv_output) {
+ if ((num_print_interval == 0 && !csv_output) || interval_clear) {
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
fprintf(output, "# time socket cpus");
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_NONE:
- fprintf(output, "# time CPU");
+ fprintf(output, "# time CPU ");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
}
}
- if (num_print_interval == 0 && metric_only)
+ if ((num_print_interval == 0 || interval_clear) && metric_only)
print_metric_headers(" ", true);
if (++num_print_interval == 25)
num_print_interval = 0;
"(overhead is possible for values <= 100ms)"),
OPT_INTEGER(0, "interval-count", &stat_config.times,
"print counts for fixed number of times"),
+ OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+ "clear screen in between new interval"),
OPT_UINTEGER(0, "timeout", &stat_config.timeout,
"stop workload and print counts after a timeout period in ms (>= 10ms)"),
OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
+ struct parse_events_error errinfo;
/* Set attrs if no event is selected and !null_run: */
if (null_run)
return 0;
if (transaction_run) {
- struct parse_events_error errinfo;
+ /* Handle -T as -M transaction. Once platform specific metrics
+ * support has been added to the json files, all archictures
+ * will use this approach. To determine transaction support
+ * on an architecture test for such a metric name.
+ */
+ if (metricgroup__has_metric("transaction")) {
+ struct option opt = { .value = &evsel_list };
+
+ return metricgroup__parse_groups(&opt, "transaction",
+ &metric_events);
+ }
if (pmu_have_event("cpu", "cycles-ct") &&
pmu_have_event("cpu", "el-start"))
&errinfo);
if (err) {
fprintf(stderr, "Cannot set up transaction events\n");
+ parse_events_print_error(&errinfo, transaction_attrs);
return -1;
}
return 0;
pmu_have_event("msr", "smi")) {
if (!force_metric_only)
metric_only = true;
- err = parse_events(evsel_list, smi_cost_attrs, NULL);
+ err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
} else {
fprintf(stderr, "To measure SMI cost, it needs "
"msr/aperf/, msr/smi/ and cpu/cycles/ support\n");
+ parse_events_print_error(&errinfo, smi_cost_attrs);
return -1;
}
if (err) {
if (topdown_attrs[0] && str) {
if (warn)
arch_topdown_group_warn();
- err = parse_events(evsel_list, str, NULL);
+ err = parse_events(evsel_list, str, &errinfo);
if (err) {
fprintf(stderr,
"Cannot set up top down events %s: %d\n",
str, err);
free(str);
+ parse_events_print_error(&errinfo, str);
return -1;
}
} else {
hists__output_recalc_col_len(hists, top->print_entries - printed);
putchar('\n');
hists__fprintf(hists, false, top->print_entries - printed, win_width,
- top->min_percent, stdout, symbol_conf.use_callchain);
+ top->min_percent, stdout, !symbol_conf.use_callchain);
}
static void prompt_integer(int *target, const char *msg)
{
int idx = val - sa->offset;
- if (idx < 0 || idx >= sa->nr_entries)
+ if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
return scnprintf(bf, size, intfmt, val);
return scnprintf(bf, size, "%s", sa->entries[idx]);
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
{ .name = "socket",
.arg = { [0] = STRARRAY(family, socket_families),
- [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+ [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+ [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "socketpair",
.arg = { [0] = STRARRAY(family, socket_families),
- [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+ [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+ [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "stat", .alias = "newstat", },
{ .name = "statx",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ },
if (trace__validate_ev_qualifier(trace))
goto out;
+ trace->trace_syscalls = true;
}
err = 0;
},
.output = stderr,
.show_comm = true,
- .trace_syscalls = true,
+ .trace_syscalls = false,
.kernel_syscallchains = false,
.max_stack = UINT_MAX,
};
if (!trace.trace_syscalls && !trace.trace_pgfaults &&
trace.evlist->nr_entries == 0 /* Was --events used? */) {
- pr_err("Please specify something to trace.\n");
- return -1;
- }
-
- if (!trace.trace_syscalls && trace.ev_qualifier) {
- pr_err("The -e option can't be used with --no-syscalls.\n");
- goto out;
+ trace.trace_syscalls = true;
}
if (output_name != NULL) {
include/uapi/linux/fcntl.h
include/uapi/linux/kcmp.h
include/uapi/linux/kvm.h
+include/uapi/linux/in.h
include/uapi/linux/perf_event.h
include/uapi/linux/prctl.h
include/uapi/linux/sched.h
arch/s390/include/uapi/asm/sie.h
arch/arm/include/uapi/asm/kvm.h
arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
arch/alpha/include/uapi/asm/errno.h
arch/mips/include/asm/errno.h
arch/mips/include/uapi/asm/errno.h
include/uapi/asm-generic/errno-base.h
include/uapi/asm-generic/ioctls.h
include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
'
check_2 () {
// SPDX-License-Identifier: GPL-2.0
#ifndef _PERF_BPF_H
#define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
#define SEC(NAME) __attribute__((section(NAME), used))
#define probe(function, vars) \
#include <sys/mman.h>
#include <syscall.h> /* for gettid() */
#include <err.h>
+#include <linux/kernel.h>
#include "jvmti_agent.h"
#include "../util/jitdump.h"
/*
* jitdump file name
*/
- snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+ scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
if (fd == -1)
#include <time.h>
#include <stdbool.h>
#include <linux/types.h>
+#include <linux/stddef.h>
#include <linux/perf_event.h>
extern bool test_attr__enabled;
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
+#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 1024
+#endif
extern const char *input_name;
extern bool perf_host, perf_guest;
hostprogs := jevents
jevents-y += json.o jsmn.o jevents.o
-CHOSTFLAGS_jevents.o = -I$(srctree)/tools/include
+HOSTCFLAGS_jevents.o = -I$(srctree)/tools/include
pmu-events-y += pmu-events.o
JDIR = pmu-events/arch/$(SRCARCH)
JSON = $(shell [ -d $(JDIR) ] && \
{
"ArchStdEvent": "L1D_CACHE_REFILL_WR",
},
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+ },
+ {
+ "ArchStdEvent": "L1D_CACHE_INVAL",
+ },
{
"ArchStdEvent": "L1D_TLB_REFILL_RD",
},
{
"ArchStdEvent": "L1D_TLB_WR",
},
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_RD",
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_REFILL_WR",
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_RD",
+ },
+ {
+ "ArchStdEvent": "L2D_TLB_WR",
+ },
{
"ArchStdEvent": "BUS_ACCESS_RD",
- },
- {
+ },
+ {
"ArchStdEvent": "BUS_ACCESS_WR",
- }
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_RD",
+ },
+ {
+ "ArchStdEvent": "MEM_ACCESS_WR",
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LD_SPEC",
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_ST_SPEC",
+ },
+ {
+ "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+ },
+ {
+ "ArchStdEvent": "EXC_UNDEF",
+ },
+ {
+ "ArchStdEvent": "EXC_SVC",
+ },
+ {
+ "ArchStdEvent": "EXC_PABORT",
+ },
+ {
+ "ArchStdEvent": "EXC_DABORT",
+ },
+ {
+ "ArchStdEvent": "EXC_IRQ",
+ },
+ {
+ "ArchStdEvent": "EXC_FIQ",
+ },
+ {
+ "ArchStdEvent": "EXC_SMC",
+ },
+ {
+ "ArchStdEvent": "EXC_HVC",
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_PABORT",
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_DABORT",
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_OTHER",
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_IRQ",
+ },
+ {
+ "ArchStdEvent": "EXC_TRAP_FIQ",
+ }
]
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "0",
"EventName": "CPU_CYCLES",
"BriefDescription": "CPU Cycles",
"PublicDescription": "Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "1",
"EventName": "INSTRUCTIONS",
"BriefDescription": "Instructions",
"PublicDescription": "Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "2",
"EventName": "L1I_DIR_WRITES",
"BriefDescription": "L1I Directory Writes",
"PublicDescription": "Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "3",
"EventName": "L1I_PENALTY_CYCLES",
"BriefDescription": "L1I Penalty Cycles",
"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "4",
"EventName": "L1D_DIR_WRITES",
"BriefDescription": "L1D Directory Writes",
"PublicDescription": "Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "5",
"EventName": "L1D_PENALTY_CYCLES",
"BriefDescription": "L1D Penalty Cycles",
"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "32",
"EventName": "PROBLEM_STATE_CPU_CYCLES",
"BriefDescription": "Problem-State CPU Cycles",
"PublicDescription": "Problem-State Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "33",
"EventName": "PROBLEM_STATE_INSTRUCTIONS",
"BriefDescription": "Problem-State Instructions",
"PublicDescription": "Problem-State Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "34",
"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
"BriefDescription": "Problem-State L1I Directory Writes",
"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "35",
"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1I Penalty Cycles",
"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "36",
"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
"BriefDescription": "Problem-State L1D Directory Writes",
"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "37",
"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1D Penalty Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "64",
"EventName": "PRNG_FUNCTIONS",
"BriefDescription": "PRNG Functions",
"PublicDescription": "Total number of the PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "65",
"EventName": "PRNG_CYCLES",
"BriefDescription": "PRNG Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "66",
"EventName": "PRNG_BLOCKED_FUNCTIONS",
"BriefDescription": "PRNG Blocked Functions",
"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "67",
"EventName": "PRNG_BLOCKED_CYCLES",
"BriefDescription": "PRNG Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "68",
"EventName": "SHA_FUNCTIONS",
"BriefDescription": "SHA Functions",
"PublicDescription": "Total number of SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "69",
"EventName": "SHA_CYCLES",
"BriefDescription": "SHA Cycles",
"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "70",
"EventName": "SHA_BLOCKED_FUNCTIONS",
"BriefDescription": "SHA Blocked Functions",
"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "71",
"EventName": "SHA_BLOCKED_CYCLES",
"BriefDescription": "SHA Bloced Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "72",
"EventName": "DEA_FUNCTIONS",
"BriefDescription": "DEA Functions",
"PublicDescription": "Total number of the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "73",
"EventName": "DEA_CYCLES",
"BriefDescription": "DEA Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "74",
"EventName": "DEA_BLOCKED_FUNCTIONS",
"BriefDescription": "DEA Blocked Functions",
"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "75",
"EventName": "DEA_BLOCKED_CYCLES",
"BriefDescription": "DEA Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "76",
"EventName": "AES_FUNCTIONS",
"BriefDescription": "AES Functions",
"PublicDescription": "Total number of AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "77",
"EventName": "AES_CYCLES",
"BriefDescription": "AES Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "78",
"EventName": "AES_BLOCKED_FUNCTIONS",
"BriefDescription": "AES Blocked Functions",
"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "79",
"EventName": "AES_BLOCKED_CYCLES",
"BriefDescription": "AES Blocked Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "128",
"EventName": "L1I_L2_SOURCED_WRITES",
"BriefDescription": "L1I L2 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "129",
"EventName": "L1D_L2_SOURCED_WRITES",
"BriefDescription": "L1D L2 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "130",
"EventName": "L1I_L3_LOCAL_WRITES",
"BriefDescription": "L1I L3 Local Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "131",
"EventName": "L1D_L3_LOCAL_WRITES",
"BriefDescription": "L1D L3 Local Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "132",
"EventName": "L1I_L3_REMOTE_WRITES",
"BriefDescription": "L1I L3 Remote Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "133",
"EventName": "L1D_L3_REMOTE_WRITES",
"BriefDescription": "L1D L3 Remote Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "134",
"EventName": "L1D_LMEM_SOURCED_WRITES",
"BriefDescription": "L1D Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "135",
"EventName": "L1I_LMEM_SOURCED_WRITES",
"BriefDescription": "L1I Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "136",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "137",
"EventName": "L1I_CACHELINE_INVALIDATES",
"BriefDescription": "L1I Cacheline Invalidates",
"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "138",
"EventName": "ITLB1_WRITES",
"BriefDescription": "ITLB1 Writes",
"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "139",
"EventName": "DTLB1_WRITES",
"BriefDescription": "DTLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "140",
"EventName": "TLB2_PTE_WRITES",
"BriefDescription": "TLB2 PTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "141",
"EventName": "TLB2_CRSTE_WRITES",
"BriefDescription": "TLB2 CRSTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "142",
"EventName": "TLB2_CRSTE_HPAGE_WRITES",
"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "145",
"EventName": "ITLB1_MISSES",
"BriefDescription": "ITLB1 Misses",
"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "146",
"EventName": "DTLB1_MISSES",
"BriefDescription": "DTLB1 Misses",
"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "147",
"EventName": "L2C_STORES_SENT",
"BriefDescription": "L2C Stores Sent",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "0",
"EventName": "CPU_CYCLES",
"BriefDescription": "CPU Cycles",
"PublicDescription": "Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "1",
"EventName": "INSTRUCTIONS",
"BriefDescription": "Instructions",
"PublicDescription": "Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "2",
"EventName": "L1I_DIR_WRITES",
"BriefDescription": "L1I Directory Writes",
"PublicDescription": "Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "3",
"EventName": "L1I_PENALTY_CYCLES",
"BriefDescription": "L1I Penalty Cycles",
"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "4",
"EventName": "L1D_DIR_WRITES",
"BriefDescription": "L1D Directory Writes",
"PublicDescription": "Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "5",
"EventName": "L1D_PENALTY_CYCLES",
"BriefDescription": "L1D Penalty Cycles",
"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "32",
"EventName": "PROBLEM_STATE_CPU_CYCLES",
"BriefDescription": "Problem-State CPU Cycles",
"PublicDescription": "Problem-State Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "33",
"EventName": "PROBLEM_STATE_INSTRUCTIONS",
"BriefDescription": "Problem-State Instructions",
"PublicDescription": "Problem-State Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "34",
"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
"BriefDescription": "Problem-State L1I Directory Writes",
"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "35",
"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1I Penalty Cycles",
"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "36",
"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
"BriefDescription": "Problem-State L1D Directory Writes",
"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "37",
"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1D Penalty Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "64",
"EventName": "PRNG_FUNCTIONS",
"BriefDescription": "PRNG Functions",
"PublicDescription": "Total number of the PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "65",
"EventName": "PRNG_CYCLES",
"BriefDescription": "PRNG Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "66",
"EventName": "PRNG_BLOCKED_FUNCTIONS",
"BriefDescription": "PRNG Blocked Functions",
"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "67",
"EventName": "PRNG_BLOCKED_CYCLES",
"BriefDescription": "PRNG Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "68",
"EventName": "SHA_FUNCTIONS",
"BriefDescription": "SHA Functions",
"PublicDescription": "Total number of SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "69",
"EventName": "SHA_CYCLES",
"BriefDescription": "SHA Cycles",
"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "70",
"EventName": "SHA_BLOCKED_FUNCTIONS",
"BriefDescription": "SHA Blocked Functions",
"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "71",
"EventName": "SHA_BLOCKED_CYCLES",
"BriefDescription": "SHA Bloced Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "72",
"EventName": "DEA_FUNCTIONS",
"BriefDescription": "DEA Functions",
"PublicDescription": "Total number of the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "73",
"EventName": "DEA_CYCLES",
"BriefDescription": "DEA Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "74",
"EventName": "DEA_BLOCKED_FUNCTIONS",
"BriefDescription": "DEA Blocked Functions",
"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "75",
"EventName": "DEA_BLOCKED_CYCLES",
"BriefDescription": "DEA Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "76",
"EventName": "AES_FUNCTIONS",
"BriefDescription": "AES Functions",
"PublicDescription": "Total number of AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "77",
"EventName": "AES_CYCLES",
"BriefDescription": "AES Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "78",
"EventName": "AES_BLOCKED_FUNCTIONS",
"BriefDescription": "AES Blocked Functions",
"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "79",
"EventName": "AES_BLOCKED_CYCLES",
"BriefDescription": "AES Blocked Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "128",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "129",
"EventName": "DTLB1_WRITES",
"BriefDescription": "DTLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "130",
"EventName": "DTLB1_MISSES",
"BriefDescription": "DTLB1 Misses",
"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "131",
"EventName": "DTLB1_HPAGE_WRITES",
"BriefDescription": "DTLB1 One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "132",
"EventName": "DTLB1_GPAGE_WRITES",
"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
"PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "133",
"EventName": "L1D_L2D_SOURCED_WRITES",
"BriefDescription": "L1D L2D Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "134",
"EventName": "ITLB1_WRITES",
"BriefDescription": "ITLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "135",
"EventName": "ITLB1_MISSES",
"BriefDescription": "ITLB1 Misses",
"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "136",
"EventName": "L1I_L2I_SOURCED_WRITES",
"BriefDescription": "L1I L2I Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "137",
"EventName": "TLB2_PTE_WRITES",
"BriefDescription": "TLB2 PTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "138",
"EventName": "TLB2_CRSTE_HPAGE_WRITES",
"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "139",
"EventName": "TLB2_CRSTE_WRITES",
"BriefDescription": "TLB2 CRSTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "140",
"EventName": "TX_C_TEND",
"BriefDescription": "Completed TEND instructions in constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "141",
"EventName": "TX_NC_TEND",
"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "143",
"EventName": "L1C_TLB1_MISSES",
"BriefDescription": "L1C TLB1 Misses",
"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "144",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "145",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "146",
"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
"BriefDescription": "L1D On-Node L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "147",
"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "148",
"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Node L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "149",
"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "150",
"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "151",
"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "152",
"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "153",
"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "154",
"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "155",
"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "156",
"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "157",
"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "158",
"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
"BriefDescription": "L1D On-Node Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "159",
"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "160",
"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "161",
"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "162",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "163",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "164",
"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "165",
"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "166",
"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Node L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "167",
"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "168",
"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "169",
"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "170",
"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "171",
"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "172",
"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "173",
"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "174",
"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "175",
"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "176",
"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
"BriefDescription": "L1I On-Node Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "177",
"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "178",
"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "179",
"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "218",
"EventName": "TX_NC_TABORT",
"BriefDescription": "Aborted transactions in non-constrained TX mode",
"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "219",
"EventName": "TX_C_TABORT_NO_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "220",
"EventName": "TX_C_TABORT_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "448",
"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
"BriefDescription": "Cycle count with one thread active",
"PublicDescription": "Cycle count with one thread active"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "449",
"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
"BriefDescription": "Cycle count with two threads active",
--- /dev/null
+[
+ {
+ "BriefDescription": "Transaction count",
+ "MetricName": "transaction",
+ "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+ }
+]
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "0",
"EventName": "CPU_CYCLES",
"BriefDescription": "CPU Cycles",
"PublicDescription": "Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "1",
"EventName": "INSTRUCTIONS",
"BriefDescription": "Instructions",
"PublicDescription": "Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "2",
"EventName": "L1I_DIR_WRITES",
"BriefDescription": "L1I Directory Writes",
"PublicDescription": "Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "3",
"EventName": "L1I_PENALTY_CYCLES",
"BriefDescription": "L1I Penalty Cycles",
"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "4",
"EventName": "L1D_DIR_WRITES",
"BriefDescription": "L1D Directory Writes",
"PublicDescription": "Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "5",
"EventName": "L1D_PENALTY_CYCLES",
"BriefDescription": "L1D Penalty Cycles",
"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "32",
"EventName": "PROBLEM_STATE_CPU_CYCLES",
"BriefDescription": "Problem-State CPU Cycles",
"PublicDescription": "Problem-State Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "33",
"EventName": "PROBLEM_STATE_INSTRUCTIONS",
"BriefDescription": "Problem-State Instructions",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "64",
"EventName": "PRNG_FUNCTIONS",
"BriefDescription": "PRNG Functions",
"PublicDescription": "Total number of the PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "65",
"EventName": "PRNG_CYCLES",
"BriefDescription": "PRNG Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "66",
"EventName": "PRNG_BLOCKED_FUNCTIONS",
"BriefDescription": "PRNG Blocked Functions",
"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "67",
"EventName": "PRNG_BLOCKED_CYCLES",
"BriefDescription": "PRNG Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "68",
"EventName": "SHA_FUNCTIONS",
"BriefDescription": "SHA Functions",
"PublicDescription": "Total number of SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "69",
"EventName": "SHA_CYCLES",
"BriefDescription": "SHA Cycles",
"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "70",
"EventName": "SHA_BLOCKED_FUNCTIONS",
"BriefDescription": "SHA Blocked Functions",
"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "71",
"EventName": "SHA_BLOCKED_CYCLES",
"BriefDescription": "SHA Bloced Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "72",
"EventName": "DEA_FUNCTIONS",
"BriefDescription": "DEA Functions",
"PublicDescription": "Total number of the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "73",
"EventName": "DEA_CYCLES",
"BriefDescription": "DEA Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "74",
"EventName": "DEA_BLOCKED_FUNCTIONS",
"BriefDescription": "DEA Blocked Functions",
"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "75",
"EventName": "DEA_BLOCKED_CYCLES",
"BriefDescription": "DEA Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "76",
"EventName": "AES_FUNCTIONS",
"BriefDescription": "AES Functions",
"PublicDescription": "Total number of AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "77",
"EventName": "AES_CYCLES",
"BriefDescription": "AES Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "78",
"EventName": "AES_BLOCKED_FUNCTIONS",
"BriefDescription": "AES Blocked Functions",
"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "79",
"EventName": "AES_BLOCKED_CYCLES",
"BriefDescription": "AES Blocked Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "128",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
"PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "129",
"EventName": "DTLB2_WRITES",
"BriefDescription": "DTLB2 Writes",
"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "130",
"EventName": "DTLB2_MISSES",
"BriefDescription": "DTLB2 Misses",
"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "131",
"EventName": "DTLB2_HPAGE_WRITES",
"BriefDescription": "DTLB2 One-Megabyte Page Writes",
"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "132",
"EventName": "DTLB2_GPAGE_WRITES",
"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "133",
"EventName": "L1D_L2D_SOURCED_WRITES",
"BriefDescription": "L1D L2D Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "134",
"EventName": "ITLB2_WRITES",
"BriefDescription": "ITLB2 Writes",
"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "135",
"EventName": "ITLB2_MISSES",
"BriefDescription": "ITLB2 Misses",
"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "136",
"EventName": "L1I_L2I_SOURCED_WRITES",
"BriefDescription": "L1I L2I Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "137",
"EventName": "TLB2_PTE_WRITES",
"BriefDescription": "TLB2 PTE Writes",
"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "138",
"EventName": "TLB2_CRSTE_WRITES",
"BriefDescription": "TLB2 CRSTE Writes",
"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "139",
"EventName": "TLB2_ENGINES_BUSY",
"BriefDescription": "TLB2 Engines Busy",
"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "140",
"EventName": "TX_C_TEND",
"BriefDescription": "Completed TEND instructions in constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "141",
"EventName": "TX_NC_TEND",
"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "143",
"EventName": "L1C_TLB2_MISSES",
"BriefDescription": "L1C TLB2 Misses",
"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "144",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "145",
"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "146",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "147",
"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "148",
"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "149",
"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "150",
"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "151",
"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "152",
"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "153",
"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "154",
"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "155",
"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "156",
"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "157",
"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "158",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "162",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "163",
"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "164",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "165",
"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "166",
"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "167",
"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "168",
"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "169",
"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "170",
"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "171",
"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "172",
"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "173",
"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "174",
"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "175",
"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "224",
"EventName": "BCD_DFP_EXECUTION_SLOTS",
"BriefDescription": "BCD DFP Execution Slots",
"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "225",
"EventName": "VX_BCD_EXECUTION_SLOTS",
"BriefDescription": "VX BCD Execution Slots",
"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "226",
"EventName": "DECIMAL_INSTRUCTIONS",
"BriefDescription": "Decimal Instructions",
"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "232",
"EventName": "LAST_HOST_TRANSLATIONS",
"BriefDescription": "Last host translation done",
"PublicDescription": "Last Host Translation done"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "243",
"EventName": "TX_NC_TABORT",
"BriefDescription": "Aborted transactions in non-constrained TX mode",
"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "244",
"EventName": "TX_C_TABORT_NO_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "245",
"EventName": "TX_C_TABORT_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "448",
"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
"BriefDescription": "Cycle count with one thread active",
"PublicDescription": "Cycle count with one thread active"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "449",
"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
"BriefDescription": "Cycle count with two threads active",
--- /dev/null
+[
+ {
+ "BriefDescription": "Transaction count",
+ "MetricName": "transaction",
+ "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+ }
+]
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "0",
"EventName": "CPU_CYCLES",
"BriefDescription": "CPU Cycles",
"PublicDescription": "Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "1",
"EventName": "INSTRUCTIONS",
"BriefDescription": "Instructions",
"PublicDescription": "Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "2",
"EventName": "L1I_DIR_WRITES",
"BriefDescription": "L1I Directory Writes",
"PublicDescription": "Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "3",
"EventName": "L1I_PENALTY_CYCLES",
"BriefDescription": "L1I Penalty Cycles",
"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "4",
"EventName": "L1D_DIR_WRITES",
"BriefDescription": "L1D Directory Writes",
"PublicDescription": "Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "5",
"EventName": "L1D_PENALTY_CYCLES",
"BriefDescription": "L1D Penalty Cycles",
"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "32",
"EventName": "PROBLEM_STATE_CPU_CYCLES",
"BriefDescription": "Problem-State CPU Cycles",
"PublicDescription": "Problem-State Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "33",
"EventName": "PROBLEM_STATE_INSTRUCTIONS",
"BriefDescription": "Problem-State Instructions",
"PublicDescription": "Problem-State Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "34",
"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
"BriefDescription": "Problem-State L1I Directory Writes",
"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "35",
"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1I Penalty Cycles",
"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "36",
"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
"BriefDescription": "Problem-State L1D Directory Writes",
"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "37",
"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1D Penalty Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "64",
"EventName": "PRNG_FUNCTIONS",
"BriefDescription": "PRNG Functions",
"PublicDescription": "Total number of the PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "65",
"EventName": "PRNG_CYCLES",
"BriefDescription": "PRNG Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "66",
"EventName": "PRNG_BLOCKED_FUNCTIONS",
"BriefDescription": "PRNG Blocked Functions",
"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "67",
"EventName": "PRNG_BLOCKED_CYCLES",
"BriefDescription": "PRNG Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "68",
"EventName": "SHA_FUNCTIONS",
"BriefDescription": "SHA Functions",
"PublicDescription": "Total number of SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "69",
"EventName": "SHA_CYCLES",
"BriefDescription": "SHA Cycles",
"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "70",
"EventName": "SHA_BLOCKED_FUNCTIONS",
"BriefDescription": "SHA Blocked Functions",
"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "71",
"EventName": "SHA_BLOCKED_CYCLES",
"BriefDescription": "SHA Bloced Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "72",
"EventName": "DEA_FUNCTIONS",
"BriefDescription": "DEA Functions",
"PublicDescription": "Total number of the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "73",
"EventName": "DEA_CYCLES",
"BriefDescription": "DEA Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "74",
"EventName": "DEA_BLOCKED_FUNCTIONS",
"BriefDescription": "DEA Blocked Functions",
"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "75",
"EventName": "DEA_BLOCKED_CYCLES",
"BriefDescription": "DEA Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "76",
"EventName": "AES_FUNCTIONS",
"BriefDescription": "AES Functions",
"PublicDescription": "Total number of AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "77",
"EventName": "AES_CYCLES",
"BriefDescription": "AES Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "78",
"EventName": "AES_BLOCKED_FUNCTIONS",
"BriefDescription": "AES Blocked Functions",
"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "79",
"EventName": "AES_BLOCKED_CYCLES",
"BriefDescription": "AES Blocked Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "128",
"EventName": "L1D_L2_SOURCED_WRITES",
"BriefDescription": "L1D L2 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "129",
"EventName": "L1I_L2_SOURCED_WRITES",
"BriefDescription": "L1I L2 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "130",
"EventName": "DTLB1_MISSES",
"BriefDescription": "DTLB1 Misses",
"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "131",
"EventName": "ITLB1_MISSES",
"BriefDescription": "ITLB1 Misses",
"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "133",
"EventName": "L2C_STORES_SENT",
"BriefDescription": "L2C Stores Sent",
"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "134",
"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Book L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "135",
"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1D On-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "136",
"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1I On-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "137",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "138",
"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1D Off-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "139",
"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1I Off-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "140",
"EventName": "DTLB1_HPAGE_WRITES",
"BriefDescription": "DTLB1 One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "141",
"EventName": "L1D_LMEM_SOURCED_WRITES",
"BriefDescription": "L1D Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "142",
"EventName": "L1I_LMEM_SOURCED_WRITES",
"BriefDescription": "L1I Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "143",
"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Book L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "144",
"EventName": "DTLB1_WRITES",
"BriefDescription": "DTLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "145",
"EventName": "ITLB1_WRITES",
"BriefDescription": "ITLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "146",
"EventName": "TLB2_PTE_WRITES",
"BriefDescription": "TLB2 PTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "147",
"EventName": "TLB2_CRSTE_HPAGE_WRITES",
"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "148",
"EventName": "TLB2_CRSTE_WRITES",
"BriefDescription": "TLB2 CRSTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "150",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "152",
"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "153",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "155",
"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "0",
"EventName": "CPU_CYCLES",
"BriefDescription": "CPU Cycles",
"PublicDescription": "Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "1",
"EventName": "INSTRUCTIONS",
"BriefDescription": "Instructions",
"PublicDescription": "Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "2",
"EventName": "L1I_DIR_WRITES",
"BriefDescription": "L1I Directory Writes",
"PublicDescription": "Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "3",
"EventName": "L1I_PENALTY_CYCLES",
"BriefDescription": "L1I Penalty Cycles",
"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "4",
"EventName": "L1D_DIR_WRITES",
"BriefDescription": "L1D Directory Writes",
"PublicDescription": "Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "5",
"EventName": "L1D_PENALTY_CYCLES",
"BriefDescription": "L1D Penalty Cycles",
"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "32",
"EventName": "PROBLEM_STATE_CPU_CYCLES",
"BriefDescription": "Problem-State CPU Cycles",
"PublicDescription": "Problem-State Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "33",
"EventName": "PROBLEM_STATE_INSTRUCTIONS",
"BriefDescription": "Problem-State Instructions",
"PublicDescription": "Problem-State Instruction Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "34",
"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
"BriefDescription": "Problem-State L1I Directory Writes",
"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "35",
"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1I Penalty Cycles",
"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "36",
"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
"BriefDescription": "Problem-State L1D Directory Writes",
"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "37",
"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
"BriefDescription": "Problem-State L1D Penalty Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "64",
"EventName": "PRNG_FUNCTIONS",
"BriefDescription": "PRNG Functions",
"PublicDescription": "Total number of the PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "65",
"EventName": "PRNG_CYCLES",
"BriefDescription": "PRNG Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "66",
"EventName": "PRNG_BLOCKED_FUNCTIONS",
"BriefDescription": "PRNG Blocked Functions",
"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "67",
"EventName": "PRNG_BLOCKED_CYCLES",
"BriefDescription": "PRNG Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "68",
"EventName": "SHA_FUNCTIONS",
"BriefDescription": "SHA Functions",
"PublicDescription": "Total number of SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "69",
"EventName": "SHA_CYCLES",
"BriefDescription": "SHA Cycles",
"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "70",
"EventName": "SHA_BLOCKED_FUNCTIONS",
"BriefDescription": "SHA Blocked Functions",
"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "71",
"EventName": "SHA_BLOCKED_CYCLES",
"BriefDescription": "SHA Bloced Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "72",
"EventName": "DEA_FUNCTIONS",
"BriefDescription": "DEA Functions",
"PublicDescription": "Total number of the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "73",
"EventName": "DEA_CYCLES",
"BriefDescription": "DEA Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "74",
"EventName": "DEA_BLOCKED_FUNCTIONS",
"BriefDescription": "DEA Blocked Functions",
"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "75",
"EventName": "DEA_BLOCKED_CYCLES",
"BriefDescription": "DEA Blocked Cycles",
"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "76",
"EventName": "AES_FUNCTIONS",
"BriefDescription": "AES Functions",
"PublicDescription": "Total number of AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "77",
"EventName": "AES_CYCLES",
"BriefDescription": "AES Cycles",
"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "78",
"EventName": "AES_BLOCKED_FUNCTIONS",
"BriefDescription": "AES Blocked Functions",
"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "79",
"EventName": "AES_BLOCKED_CYCLES",
"BriefDescription": "AES Blocked Cycles",
[
{
+ "Unit": "CPU-M-CF",
"EventCode": "128",
"EventName": "DTLB1_MISSES",
"BriefDescription": "DTLB1 Misses",
"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "129",
"EventName": "ITLB1_MISSES",
"BriefDescription": "ITLB1 Misses",
"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "130",
"EventName": "L1D_L2I_SOURCED_WRITES",
"BriefDescription": "L1D L2I Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "131",
"EventName": "L1I_L2I_SOURCED_WRITES",
"BriefDescription": "L1I L2I Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "132",
"EventName": "L1D_L2D_SOURCED_WRITES",
"BriefDescription": "L1D L2D Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "133",
"EventName": "DTLB1_WRITES",
"BriefDescription": "DTLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "135",
"EventName": "L1D_LMEM_SOURCED_WRITES",
"BriefDescription": "L1D Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "137",
"EventName": "L1I_LMEM_SOURCED_WRITES",
"BriefDescription": "L1I Local Memory Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "138",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "139",
"EventName": "DTLB1_HPAGE_WRITES",
"BriefDescription": "DTLB1 One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "140",
"EventName": "ITLB1_WRITES",
"BriefDescription": "ITLB1 Writes",
"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "141",
"EventName": "TLB2_PTE_WRITES",
"BriefDescription": "TLB2 PTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "142",
"EventName": "TLB2_CRSTE_HPAGE_WRITES",
"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "143",
"EventName": "TLB2_CRSTE_WRITES",
"BriefDescription": "TLB2 CRSTE Writes",
"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "144",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "145",
"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "146",
"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
"BriefDescription": "L1D Off-Book L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "147",
"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1D On-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "148",
"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1D Off-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "149",
"EventName": "TX_NC_TEND",
"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "150",
"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "151",
"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "152",
"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "153",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I On-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "154",
"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "155",
"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
"BriefDescription": "L1I Off-Book L3 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "156",
"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1I On-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "157",
"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
"BriefDescription": "L1I Off-Book L4 Sourced Writes",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "158",
"EventName": "TX_C_TEND",
"BriefDescription": "Completed TEND instructions in constrained TX mode",
"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "159",
"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "160",
"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "161",
"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "177",
"EventName": "TX_NC_TABORT",
"BriefDescription": "Aborted transactions in non-constrained TX mode",
"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "178",
"EventName": "TX_C_TABORT_NO_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
},
{
+ "Unit": "CPU-M-CF",
"EventCode": "179",
"EventName": "TX_C_TABORT_SPECIAL",
"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
--- /dev/null
+[
+ {
+ "BriefDescription": "Transaction count",
+ "MetricName": "transaction",
+ "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+ }
+]
{ "QPI LL", "uncore_qpi" },
{ "SBO", "uncore_sbox" },
{ "iMPH-U", "uncore_arb" },
+ { "CPU-M-CF", "cpum_cf" },
+ { "CPU-M-SF", "cpum_sf" },
{}
};
string = ""
if flag_fields[event_name][field_name]:
- print_delim = 0
- keys = flag_fields[event_name][field_name]['values'].keys()
- keys.sort()
- for idx in keys:
+ print_delim = 0
+ for idx in sorted(flag_fields[event_name][field_name]['values']):
if not value and not idx:
string += flag_fields[event_name][field_name]['values'][idx]
break
string = ""
if symbolic_fields[event_name][field_name]:
- keys = symbolic_fields[event_name][field_name]['values'].keys()
- keys.sort()
- for idx in keys:
+ for idx in sorted(symbolic_fields[event_name][field_name]['values']):
if not value and not idx:
- string = symbolic_fields[event_name][field_name]['values'][idx]
+ string = symbolic_fields[event_name][field_name]['values'][idx]
break
- if (value == idx):
- string = symbolic_fields[event_name][field_name]['values'][idx]
+ if (value == idx):
+ string = symbolic_fields[event_name][field_name]['values'][idx]
break
return string
string = ""
print_delim = 0
- keys = trace_flags.keys()
-
- for idx in keys:
- if not value and not idx:
- string += "NONE"
- break
-
- if idx and (value & idx) == idx:
- if print_delim:
- string += " | ";
- string += trace_flags[idx]
- print_delim = 1
- value &= ~idx
+ for idx in trace_flags:
+ if not value and not idx:
+ string += "NONE"
+ break
+
+ if idx and (value & idx) == idx:
+ if print_delim:
+ string += " | ";
+ string += trace_flags[idx]
+ print_delim = 1
+ value &= ~idx
return string
# PerfEvent is the base class for all perf event sample, PebsEvent
# is a HW base Intel x86 PEBS event, and user could add more SW/HW
# event classes based on requirements.
+from __future__ import print_function
import struct
PerfEvent.event_num += 1
def show(self):
- print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+ print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+ (self.name, self.symbol, self.comm, self.dso))
#
# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
try:
import wx
except ImportError:
- raise ImportError, "You need to install the wxpython lib for this script"
+ raise ImportError("You need to install the wxpython lib for this script")
class RootFrame(wx.Frame):
# This software may be distributed under the terms of the GNU General
# Public License ("GPL") version 2 as published by the Free Software
# Foundation.
+from __future__ import print_function
import errno, os
return str
def add_stats(dict, key, value):
- if not dict.has_key(key):
+ if key not in dict:
dict[key] = (value, value, value, 1)
else:
min, max, avg, count = dict[key]
except:
if not audit_package_warned:
audit_package_warned = True
- print "Install the audit-libs-python package to get syscall names.\n" \
- "For example:\n # apt-get install python-audit (Ubuntu)" \
- "\n # yum install audit-libs-python (Fedora)" \
- "\n etc.\n"
+ print("Install the audit-libs-python package to get syscall names.\n"
+ "For example:\n # apt-get install python-audit (Ubuntu)"
+ "\n # yum install audit-libs-python (Fedora)"
+ "\n etc.\n")
def syscall_name(id):
try:
# This software is distributed under the terms of the GNU General
# Public License ("GPL") version 2 as published by the Free Software
# Foundation.
-
+from __future__ import print_function
import os
import sys
from collections import defaultdict
-from UserList import UserList
+try:
+ from UserList import UserList
+except ImportError:
+ # Python 3: UserList moved to the collections package
+ from collections import UserList
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
if i == -1:
return
- for i in xrange(i, len(self.data)):
+ for i in range(i, len(self.data)):
timeslice = self.data[i]
if timeslice.start > end:
return
on_cpu_task = self.current_tsk[headers.cpu]
if on_cpu_task != -1 and on_cpu_task != prev_pid:
- print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
- (headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+ print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+ headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
threads[prev_pid] = prev_comm
threads[next_pid] = next_comm
if (!t->subtest.get_nr)
pr_debug("%s:", t->desc);
else
- pr_debug("%s subtest %d:", t->desc, subtest);
+ pr_debug("%s subtest %d:", t->desc, subtest + 1);
switch (err) {
case TEST_OK:
#define for_each_shell_test(dir, base, ent) \
while ((ent = readdir(dir)) != NULL) \
- if (!is_directory(base, ent))
+ if (!is_directory(base, ent) && ent->d_name[0] != '.')
static const char *shell_tests__dir(char *path, size_t size)
{
return 0;
}
+static bool test__intel_pt_valid(void)
+{
+ return !!perf_pmu__find("intel_pt");
+}
+
static int test__intel_pt(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evlist__first(evlist);
return 0;
}
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+ TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+ return 0;
+}
+
static int count_tracepoints(void)
{
struct dirent *events_ent;
const char *name;
__u32 type;
const int id;
+ bool (*valid)(void);
int (*check)(struct perf_evlist *evlist);
};
},
{
.name = "intel_pt//u",
+ .valid = test__intel_pt_valid,
.check = test__intel_pt,
.id = 52,
},
+ {
+ .name = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+ .check = test__checkevent_complex_name,
+ .id = 53
+ }
};
static struct evlist_test test__events_pmu[] = {
.check = test__checkevent_pmu_partial_time_callgraph,
.id = 2,
},
+ {
+ .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+ .check = test__checkevent_complex_name,
+ .id = 3,
+ }
};
struct terms_test {
static int test_event(struct evlist_test *e)
{
+ struct parse_events_error err = { .idx = 0, };
struct perf_evlist *evlist;
int ret;
+ if (e->valid && !e->valid()) {
+ pr_debug("... SKIP");
+ return 0;
+ }
+
evlist = perf_evlist__new();
if (evlist == NULL)
return -ENOMEM;
- ret = parse_events(evlist, e->name, NULL);
+ ret = parse_events(evlist, e->name, &err);
if (ret) {
- pr_debug("failed to parse event '%s', err %d\n",
- e->name, ret);
+ pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+ e->name, ret, err.str);
+ parse_events_print_error(&err, e->name);
} else {
ret = e->check(evlist);
}
for (i = 0; i < cnt; i++) {
struct evlist_test *e = &events[i];
- pr_debug("running test %d '%s'\n", e->id, e->name);
+ pr_debug("running test %d '%s'", e->id, e->name);
ret1 = test_event(e);
if (ret1)
ret2 = ret1;
+ pr_debug("\n");
}
return ret2;
}
while (!ret && (ent = readdir(dir))) {
- struct evlist_test e;
+ struct evlist_test e = { .id = 0, };
char name[2 * NAME_MAX + 1 + 12 + 3];
/* Names containing . are special and cannot be used directly */
libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+ event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+ grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+ if [ $? -ne 0 -o -z "$event_name" ] ; then
+ printf "FAIL: could not add event\n"
+ return 1
+ fi
+}
+
trace_libc_inet_pton_backtrace() {
- idx=0
- expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
- expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+ expected=`mktemp -u /tmp/expected.XXX`
+
+ echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
+ echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
case "$(uname -m)" in
s390x)
eventattr='call-graph=dwarf,max-stack=4'
- expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
- expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
- expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+ echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+ echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+ echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+ ;;
+ ppc64|ppc64le)
+ eventattr='max-stack=4'
+ echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+ echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+ echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
;;
*)
eventattr='max-stack=3'
- expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
- expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+ echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+ echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
;;
esac
- file=`mktemp -u /tmp/perf.data.XXX`
+ perf_data=`mktemp -u /tmp/perf.data.XXX`
+ perf_script=`mktemp -u /tmp/perf.script.XXX`
+ perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+ perf script -i $perf_data > $perf_script
- perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
- perf script -i $file | while read line ; do
+ exec 3<$perf_script
+ exec 4<$expected
+ while read line <&3 && read -r pattern <&4; do
+ [ -z "$pattern" ] && break
echo $line
- echo "$line" | egrep -q "${expected[$idx]}"
+ echo "$line" | egrep -q "$pattern"
if [ $? -ne 0 ] ; then
- printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
- exit 1
+ printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
+ return 1
fi
- let idx+=1
- [ -z "${expected[$idx]}" ] && break
done
# If any statements are executed from this point onwards,
# even if the perf script output does not match.
}
+delete_libc_inet_pton_event() {
+
+ if [ -n "$event_name" ] ; then
+ perf probe -q -d $event_name
+ fi
+}
+
# Check for IPv6 interface existence
ip a sh lo | fgrep -q inet6 || exit 2
skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
trace_libc_inet_pton_backtrace
err=$?
-rm -f ${file}
-perf probe -q -d probe_libc:inet_pton
+rm -f ${perf_data} ${perf_script} ${expected}
+delete_libc_inet_pton_event
exit $err
file=$(mktemp /tmp/temporary_file.XXXXX)
trace_open_vfs_getname() {
- evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+ evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
perf trace -e $evts touch $file 2>&1 | \
egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
}
perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
perf_header__set_feat(&session->header, HEADER_NRCPUS);
+ perf_header__set_feat(&session->header, HEADER_ARCH);
session->header.data_size += DATA_SIZE;
libperf-y += kcmp.o
libperf-y += pkey_alloc.o
libperf-y += prctl.o
+libperf-y += socket.o
libperf-y += statx.o
size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
#!/bin/sh
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
printf "#endif\n"
printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \
sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
printf "};\n"
#!/bin/sh
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *kcmp_types[] = {\n"
regex='^[[:space:]]+(KCMP_(\w+)),'
#!/bin/sh
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *kvm_ioctl_cmds[] = {\n"
regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h | \
+egrep $regex ${header_dir}/kvm.h | \
sed -r "s/$regex/\2 \1/g" | \
egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
sort | xargs printf "\t[%s] = \"%s\",\n"
#!/bin/sh
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
printf "static const char *madvise_advices[] = {\n"
regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
#!/bin/sh
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *perf_ioctl_cmds[] = {\n"
regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
#!/bin/sh
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
printf "static const char *pkey_alloc_access_rights[] = {\n"
regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
#!/bin/sh
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
printf "};\n"
#!/bin/sh
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
printf "};\n"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+ static DEFINE_STRARRAY(socket_ipproto);
+
+ return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+ int domain = syscall_arg__val(arg, 0);
+
+ if (domain == AF_INET || domain == AF_INET6)
+ return socket__scnprintf_ipproto(arg->val, bf, size);
+
+ return syscall_arg__scnprintf_int(bf, size, arg);
+}
--- /dev/null
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+ sed -r "s/$regex/\2 \1/g" | \
+ sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
#!/bin/sh
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
sed -r "s/$regex/\2 \1/g" | \
sort | xargs printf "\t[%s] = \"%s\",\n"
printf "};\n"
printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
sed -r "s/$regex/\2 \1/g" | \
sort | xargs printf "\t[%s] = \"%s\",\n"
printf "};\n"
gtk_tree_store_set(store, &iter, col_idx++, s, -1);
}
- if (hists__has_callchains(hists) &&
+ if (hist_entry__has_callchains(h) &&
symbol_conf.use_callchain && hists__has(hists, sym)) {
if (callchain_param.mode == CHAIN_GRAPH_REL)
total = symbol_conf.cumulate_callchain ?
static int hist_entry__fprintf(struct hist_entry *he, size_t size,
char *bf, size_t bfsz, FILE *fp,
- bool use_callchain)
+ bool ignore_callchains)
{
int ret;
int callchain_ret = 0;
ret = fprintf(fp, "%s\n", bf);
- if (hist_entry__has_callchains(he) && use_callchain)
+ if (hist_entry__has_callchains(he) && !ignore_callchains)
callchain_ret = hist_entry_callchain__fprintf(he, total_period,
0, fp);
size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
int max_cols, float min_pcnt, FILE *fp,
- bool use_callchain)
+ bool ignore_callchains)
{
struct rb_node *nd;
size_t ret = 0;
if (percent < min_pcnt)
continue;
- ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+ ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
if (max_rows && ++nr_rows >= max_rows)
break;
err = bpf_object__load(obj);
if (err) {
- pr_debug("bpf: load objects failed\n");
+ char bf[128];
+ libbpf_strerror(err, bf, sizeof(bf));
+ pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
return err;
}
return 0;
/*
* Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
- * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM
+ * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM
* instruction (BPF_{B,H,W,DW}).
*/
static int
raw_svector_ostream ostream(*Buffer);
legacy::PassManager PM;
- if (TargetMachine->addPassesToEmitFile(PM, ostream,
- TargetMachine::CGFT_ObjectFile)) {
+ bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+ TargetMachine::CGFT_ObjectFile);
+#else
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+ TargetMachine::CGFT_ObjectFile);
+#endif
+ if (NotAdded) {
llvm::errs() << "TargetMachine can't emit a file of this type\n";
return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
}
static struct comm_str *comm_str__get(struct comm_str *cs)
{
- if (cs)
- refcount_inc(&cs->refcnt);
- return cs;
+ if (cs && refcount_inc_not_zero(&cs->refcnt))
+ return cs;
+
+ return NULL;
}
static void comm_str__put(struct comm_str *cs)
parent = *p;
iter = rb_entry(parent, struct comm_str, rb_node);
+ /*
+ * If we race with comm_str__put, iter->refcnt is 0
+ * and it will be removed within comm_str__put call
+ * shortly, ignore it in this search.
+ */
cmp = strcmp(str, iter->str);
- if (!cmp)
- return comm_str__get(iter);
+ if (!cmp && comm_str__get(iter))
+ return iter;
if (cmp < 0)
p = &(*p)->rb_left;
#endif
#endif
+#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL
+
struct cs_etm_decoder {
void *data;
void (*packet_printer)(const char *msg);
decoder->tail = 0;
decoder->packet_count = 0;
for (i = 0; i < MAX_BUFFER; i++) {
- decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
- decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+ decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+ decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
decoder->packet_buffer[i].last_instr_taken_branch = false;
decoder->packet_buffer[i].exc = false;
decoder->packet_buffer[i].exc_ret = false;
decoder->packet_buffer[et].exc = false;
decoder->packet_buffer[et].exc_ret = false;
decoder->packet_buffer[et].cpu = *((int *)inode->priv);
- decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
- decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+ decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+ decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
if (decoder->packet_count == MAX_BUFFER - 1)
return OCSD_RESP_WAIT;
};
enum cs_etm_sample_type {
+ CS_ETM_EMPTY = 0,
CS_ETM_RANGE = 1 << 0,
CS_ETM_TRACE_ON = 1 << 1,
};
static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
{
+ /* Returns 0 for the CS_ETM_TRACE_ON packet */
+ if (packet->sample_type == CS_ETM_TRACE_ON)
+ return 0;
+
/*
* The packet records the execution range with an exclusive end address
*
return packet->end_addr - A64_INSTR_SIZE;
}
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+ /* Returns 0 for the CS_ETM_TRACE_ON packet */
+ if (packet->sample_type == CS_ETM_TRACE_ON)
+ return 0;
+
+ return packet->start_addr;
+}
+
static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
{
/*
be = &bs->entries[etmq->last_branch_pos];
be->from = cs_etm__last_executed_instr(etmq->prev_packet);
- be->to = etmq->packet->start_addr;
+ be->to = cs_etm__first_executed_instr(etmq->packet);
/* No support for mispredict */
be->flags.mispred = 0;
be->flags.predicted = 1;
sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
sample.pid = etmq->pid;
sample.tid = etmq->tid;
- sample.addr = etmq->packet->start_addr;
+ sample.addr = cs_etm__first_executed_instr(etmq->packet);
sample.id = etmq->etm->branches_id;
sample.stream_id = etmq->etm->branches_id;
sample.period = 1;
etmq->period_instructions = instrs_over;
}
- if (etm->sample_branches &&
- etmq->prev_packet &&
- etmq->prev_packet->sample_type == CS_ETM_RANGE &&
- etmq->prev_packet->last_instr_taken_branch) {
- ret = cs_etm__synth_branch_sample(etmq);
- if (ret)
- return ret;
+ if (etm->sample_branches && etmq->prev_packet) {
+ bool generate_sample = false;
+
+ /* Generate sample for tracing on packet */
+ if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+ generate_sample = true;
+
+ /* Generate sample for branch taken packet */
+ if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+ etmq->prev_packet->last_instr_taken_branch)
+ generate_sample = true;
+
+ if (generate_sample) {
+ ret = cs_etm__synth_branch_sample(etmq);
+ if (ret)
+ return ret;
+ }
}
if (etm->sample_branches || etm->synth_opts.last_branch) {
static int cs_etm__flush(struct cs_etm_queue *etmq)
{
int err = 0;
+ struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
+ if (!etmq->prev_packet)
+ return 0;
+
+ /* Handle start tracing packet */
+ if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+ goto swap_packet;
+
if (etmq->etm->synth_opts.last_branch &&
- etmq->prev_packet &&
etmq->prev_packet->sample_type == CS_ETM_RANGE) {
/*
* Generate a last branch event for the branches left in the
err = cs_etm__synth_instruction_sample(
etmq, addr,
etmq->period_instructions);
+ if (err)
+ return err;
+
etmq->period_instructions = 0;
+ }
+
+ if (etm->sample_branches &&
+ etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+ err = cs_etm__synth_branch_sample(etmq);
+ if (err)
+ return err;
+ }
+
+swap_packet:
+ if (etmq->etm->synth_opts.last_branch) {
/*
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
*/
cs_etm__flush(etmq);
break;
+ case CS_ETM_EMPTY:
+ /*
+ * Should not receive empty packet,
+ * report error.
+ */
+ pr_err("CS ETM Trace: empty packet\n");
+ return -EINVAL;
default:
break;
}
evsel->attr.sample_period = 1;
}
+ if (perf_evsel__is_clock(evsel)) {
+ /*
+ * The evsel->unit points to static alias->unit
+ * so it's ok to use static string in here.
+ */
+ static const char *unit = "msec";
+
+ evsel->unit = unit;
+ evsel->scale = 1e-6;
+ }
+
return evsel;
}
}
}
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+ return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+ (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
/*
* The enable_on_exec/disabled value strategy:
*
else
perf_evsel__reset_sample_bit(evsel, PERIOD);
}
+
+ /*
+ * For initial_delay, a dummy event is added implicitly.
+ * The software event will trigger -EOPNOTSUPP error out,
+ * if BRANCH_STACK bit is set.
+ */
+ if (opts->initial_delay && is_dummy_event(evsel))
+ perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
}
static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
{
- struct perf_event_attr *attr = &evsel->attr;
+ return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
- return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
- (attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+ return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+ perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
}
struct perf_attr_details {
int cpu_nr = ff->ph->env.nr_cpus_avail;
u64 size = 0;
struct perf_header *ph = ff->ph;
+ bool do_core_id_test = true;
ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
if (!ph->env.cpu)
return 0;
}
+ /* On s390 the socket_id number is not related to the numbers of cpus.
+ * The socket_id number might be higher than the numbers of cpus.
+ * This depends on the configuration.
+ */
+ if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+ do_core_id_test = false;
+
for (i = 0; i < (u32)cpu_nr; i++) {
if (do_read_u32(ff, &nr))
goto free_cpu;
if (do_read_u32(ff, &nr))
goto free_cpu;
- if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+ if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
pr_debug("socket_id number is too big."
"You may need to upgrade the perf tool.\n");
goto free_cpu;
FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true),
FEAT_OPN(BRANCH_STACK, branch_stack, false),
FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false),
- FEAT_OPN(GROUP_DESC, group_desc, false),
+ FEAT_OPR(GROUP_DESC, group_desc, false),
FEAT_OPN(AUXTRACE, auxtrace, false),
FEAT_OPN(STAT, stat, false),
FEAT_OPN(CACHE, cache, true),
pr_warning("invalid record type %d in pipe-mode\n", type);
return 0;
}
- if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+ if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
pr_warning("invalid record type %d in pipe-mode\n", type);
return -1;
}
#ifndef __PERF_HEADER_H
#define __PERF_HEADER_H
+#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <sys/types.h>
#include <stdbool.h>
static int hist_entry__init(struct hist_entry *he,
struct hist_entry *template,
- bool sample_self)
+ bool sample_self,
+ size_t callchain_size)
{
*he = *template;
+ he->callchain_size = callchain_size;
if (symbol_conf.cumulate_callchain) {
he->stat_acc = malloc(sizeof(he->stat));
he = ops->new(callchain_size);
if (he) {
- err = hist_entry__init(he, template, sample_self);
+ err = hist_entry__init(he, template, sample_self, callchain_size);
if (err) {
ops->free(he);
he = NULL;
.raw_data = sample->raw_data,
.raw_size = sample->raw_size,
.ops = ops,
- };
+ }, *he = hists__findnew_entry(hists, &entry, al, sample_self);
- return hists__findnew_entry(hists, &entry, al, sample_self);
+ if (!hists->has_callchains && he && he->callchain_size != 0)
+ hists->has_callchains = true;
+ return he;
}
struct hist_entry *hists__add_entry(struct hists *hists,
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
+ bool has_callchains;
int socket_filter;
struct perf_hpp_list *hpp_list;
struct list_head hpp_formats;
size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
int max_cols, float min_pcnt, FILE *fp,
- bool use_callchain);
+ bool ignore_callchains);
size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
void hists__filter_by_dso(struct hists *hists);
static __pure inline bool hists__has_callchains(struct hists *hists)
{
- const struct perf_evsel *evsel = hists_to_evsel(hists);
- return evsel__has_callchain(evsel);
+ return hists->has_callchains;
}
int hists__init(void);
if (len < offs)
return INTEL_PT_NEED_MORE_BYTES;
byte = buf[offs++];
- payload |= (byte >> 1) << shift;
+ payload |= ((uint64_t)byte >> 1) << shift;
}
packet->type = INTEL_PT_CYC;
"#!/usr/bin/env sh\n"
"if ! test -d \"$KBUILD_DIR\"\n"
"then\n"
-" exit -1\n"
+" exit 1\n"
"fi\n"
"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
"then\n"
-" exit -1\n"
+" exit 1\n"
"fi\n"
"TMPDIR=`mktemp -d`\n"
"if test -z \"$TMPDIR\"\n"
"then\n"
-" exit -1\n"
+" exit 1\n"
"fi\n"
"cat << EOF > $TMPDIR/Makefile\n"
"obj-y := dummy.o\n"
}
/*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
*/
-static struct thread *____machine__findnew_thread(struct machine *machine,
- struct threads *threads,
- pid_t pid, pid_t tid,
- bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+ int pid, int tid)
{
- struct rb_node **p = &threads->entries.rb_node;
- struct rb_node *parent = NULL;
struct thread *th;
- /*
- * Front-end cache - TID lookups come in blocks,
- * so most of the time we dont have to look up
- * the full rbtree:
- */
th = threads->last_match;
if (th != NULL) {
if (th->tid == tid) {
threads->last_match = NULL;
}
+ return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+ int pid, int tid)
+{
+ struct thread *th = NULL;
+
+ if (perf_singlethreaded)
+ th = __threads__get_last_match(threads, machine, pid, tid);
+
+ return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+ threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+ if (perf_singlethreaded)
+ __threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+ struct threads *threads,
+ pid_t pid, pid_t tid,
+ bool create)
+{
+ struct rb_node **p = &threads->entries.rb_node;
+ struct rb_node *parent = NULL;
+ struct thread *th;
+
+ th = threads__get_last_match(threads, machine, pid, tid);
+ if (th)
+ return th;
+
while (*p != NULL) {
parent = *p;
th = rb_entry(parent, struct thread, rb_node);
if (th->tid == tid) {
- threads->last_match = th;
+ threads__set_last_match(threads, th);
machine__update_thread_pid(machine, th, pid);
return thread__get(th);
}
* It is now in the rbtree, get a ref
*/
thread__get(th);
- threads->last_match = th;
+ threads__set_last_match(threads, th);
++threads->nr;
}
struct threads *threads = machine__threads(machine, th->tid);
if (threads->last_match == th)
- threads->last_match = NULL;
+ threads__set_last_match(threads, NULL);
BUG_ON(refcount_read(&th->refcnt) == 0);
if (lock)
{
struct callchain_cursor *cursor = arg;
const char *srcline = NULL;
+ u64 addr;
if (symbol_conf.hide_unresolved && entry->sym == NULL)
return 0;
if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
return 0;
- srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+ /*
+ * Convert entry->ip from a virtual address to an offset in
+ * its corresponding binary.
+ */
+ addr = map__map_ip(entry->map, entry->ip);
+
+ srcline = callchain_srcline(entry->map, entry->sym, addr);
return callchain_cursor_append(cursor, entry->ip,
entry->map, entry->sym,
false, NULL, 0, 0, 0, srcline);
if (raw)
s = (char *)pe->metric_name;
else {
- if (asprintf(&s, "%s\n\t[%s]",
- pe->metric_name, pe->desc) < 0)
+ if (asprintf(&s, "%s\n%*s%s]",
+ pe->metric_name, 8, "[", pe->desc) < 0)
return;
}
metricgroup__free_egroups(&group_list);
return ret;
}
+
+bool metricgroup__has_metric(const char *metric)
+{
+ struct pmu_events_map *map = perf_pmu__find_map(NULL);
+ struct pmu_event *pe;
+ int i;
+
+ if (!map)
+ return false;
+
+ for (i = 0; ; i++) {
+ pe = &map->table[i];
+
+ if (!pe->name && !pe->metric_group && !pe->metric_name)
+ break;
+ if (!pe->metric_expr)
+ continue;
+ if (match_metric(pe->metric_name, metric))
+ return true;
+ }
+ return false;
+}
struct rblist *metric_events);
void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
#endif
#define __PERF_NAMESPACES_H
#include <sys/types.h>
+#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <linux/refcount.h>
#include <linux/types.h>
event_pmu:
PE_NAME opt_pmu_config
{
+ struct parse_events_state *parse_state = _parse_state;
+ struct parse_events_error *error = parse_state->error;
struct list_head *list, *orig_terms, *terms;
if (parse_events_copy_term_list($2, &orig_terms))
YYABORT;
+ if (error)
+ error->idx = @1.first_column;
+
ALLOC_LIST(list);
if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
struct perf_pmu *pmu = NULL;
return 0;
}
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+ char **new_str)
+{
+ if (!*old_str)
+ goto set_new;
+
+ if (*new_str) { /* Have new string, check with old */
+ if (strcasecmp(*old_str, *new_str))
+ pr_debug("alias %s differs in field '%s'\n",
+ name, field);
+ zfree(old_str);
+ } else /* Nothing new --> keep old string */
+ return;
+set_new:
+ *old_str = *new_str;
+ *new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+ struct perf_pmu_alias *newalias)
+{
+ perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+ perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+ &newalias->long_desc);
+ perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+ perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+ &newalias->metric_expr);
+ perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+ &newalias->metric_name);
+ perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+ old->scale = newalias->scale;
+ old->per_pkg = newalias->per_pkg;
+ old->snapshot = newalias->snapshot;
+ memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+ zfree(&newalias->name);
+ zfree(&newalias->desc);
+ zfree(&newalias->long_desc);
+ zfree(&newalias->topic);
+ zfree(&newalias->str);
+ zfree(&newalias->metric_expr);
+ zfree(&newalias->metric_name);
+ parse_events_terms__purge(&newalias->terms);
+ free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+ struct list_head *alist)
+{
+ struct perf_pmu_alias *a;
+
+ list_for_each_entry(a, alist, list) {
+ if (!strcasecmp(newalias->name, a->name)) {
+ perf_pmu_update_alias(a, newalias);
+ perf_pmu_free_alias(newalias);
+ return true;
+ }
+ }
+ return false;
+}
+
static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
char *desc, char *val,
char *long_desc, char *topic,
char *metric_expr,
char *metric_name)
{
+ struct parse_events_term *term;
struct perf_pmu_alias *alias;
int ret;
int num;
+ char newval[256];
alias = malloc(sizeof(*alias));
if (!alias)
return ret;
}
+ /* Scan event and remove leading zeroes, spaces, newlines, some
+ * platforms have terms specified as
+ * event=0x0091 (read from files ../<PMU>/events/<FILE>
+ * and terms specified as event=0x91 (read from JSON files).
+ *
+ * Rebuild string to make alias->str member comparable.
+ */
+ memset(newval, 0, sizeof(newval));
+ ret = 0;
+ list_for_each_entry(term, &alias->terms, list) {
+ if (ret)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ ",");
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%#x", term->config, term->val.num);
+ else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%s", term->config, term->val.str);
+ }
+
alias->name = strdup(name);
if (dir) {
/*
snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
}
alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
- alias->str = strdup(val);
+ alias->str = strdup(newval);
- list_add_tail(&alias->list, list);
+ if (!perf_pmu_merge_alias(alias, list))
+ list_add_tail(&alias->list, list);
return 0;
}
buf[ret] = 0;
+ /* Remove trailing newline from sysfs file */
+ rtrim(buf);
+
return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
NULL, NULL, NULL);
}
if (stat(path, &st) == 0)
return 1;
- /* Look for cpu sysfs (specific to s390) */
- scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
- sysfs, name);
- if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
- return 1;
-
return 0;
}
if (_PyTuple_Resize(&t, n) == -1)
Py_FatalError("error resizing Python tuple");
- if (!dict) {
+ if (!dict)
call_object(handler, t, handler_name);
- } else {
+ else
call_object(handler, t, default_handler_name);
- Py_DECREF(dict);
- }
- Py_XDECREF(all_entries_dict);
Py_DECREF(t);
}
call_object(handler, t, handler_name);
- Py_DECREF(dict);
Py_DECREF(t);
}
fprintf(ofp, "# See the perf-script-python Documentation for the list "
"of available functions.\n\n");
+ fprintf(ofp, "from __future__ import print_function\n\n");
fprintf(ofp, "import os\n");
fprintf(ofp, "import sys\n\n");
fprintf(ofp, "from Core import *\n\n\n");
fprintf(ofp, "def trace_begin():\n");
- fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+ fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
fprintf(ofp, "def trace_end():\n");
- fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+ fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
while ((event = trace_find_next_event(pevent, event))) {
fprintf(ofp, "def %s__%s(", event->system, event->name);
"common_secs, common_nsecs,\n\t\t\t"
"common_pid, common_comm)\n\n");
- fprintf(ofp, "\t\tprint \"");
+ fprintf(ofp, "\t\tprint(\"");
not_first = 0;
count = 0;
fprintf(ofp, "%s", f->name);
}
- fprintf(ofp, ")\n\n");
+ fprintf(ofp, "))\n\n");
- fprintf(ofp, "\t\tprint 'Sample: {'+"
- "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+ fprintf(ofp, "\t\tprint('Sample: {'+"
+ "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
fprintf(ofp, "\t\tfor node in common_callchain:");
fprintf(ofp, "\n\t\t\tif 'sym' in node:");
- fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+ fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
fprintf(ofp, "\n\t\t\telse:");
- fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
- fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+ fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+ fprintf(ofp, "\t\tprint()\n\n");
}
fprintf(ofp, "def trace_unhandled(event_name, context, "
"event_fields_dict, perf_sample_dict):\n");
- fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
- fprintf(ofp, "\t\tprint 'Sample: {'+"
- "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+ fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+ fprintf(ofp, "\t\tprint('Sample: {'+"
+ "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
fprintf(ofp, "def print_header("
"event_name, cpu, secs, nsecs, pid, comm):\n"
- "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
- "(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+ "\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+ "(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
"\treturn delimiter.join"
char level;
u8 filtered;
+
+ u16 callchain_size;
union {
/*
* Since perf diff only supports the stdio output, TUI
static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
{
- return hists__has_callchains(he->hists);
+ return he->callchain_size != 0;
}
static inline bool hist_entry__has_pairs(struct hist_entry *he)
ratio = total / avg;
print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
- } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
- perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+ } else if (perf_evsel__is_clock(evsel)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
- avg / ratio);
+ avg / (ratio * evsel->scale));
else
print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
#include <asm/syscalls_32.c>
const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
#endif
struct syscall {
if (__report_module(&al, ip, ui))
return -1;
- e->ip = al.addr;
+ e->ip = ip;
e->map = al.map;
e->sym = al.sym;
struct addr_location al;
e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
- e.ip = al.addr;
+ e.ip = ip;
e.map = al.map;
pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
# example: [color=#CC00CC]
#
# arglist: A list of arguments from registers/stack addresses. See URL:
-# https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt
+# https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
#
# example: cpu=%di:s32
#
# example: [color=#CC00CC]
#
# arglist: A list of arguments from registers/stack addresses. See URL:
-# https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt
+# https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
#
# example: port=+36(%di):s32
#
.PP
\fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group.
.PP
-\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC".
The column name "all" can be used to enable all disabled-by-default built-in counters.
.PP
\fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group.
\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved.
\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters.
\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
-\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
\fBCorWatt\fP Watts consumed by the core part of the package.
\fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
\fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
-\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
+\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary.
\fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
.fi
.SH TOO MUCH INFORMATION EXAMPLE
unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int has_misc_feature_control;
+unsigned int first_counter_read = 1;
#define RAPL_PKG (1 << 0)
/* 0x610 MSR_PKG_POWER_LIMIT */
unsigned long long irq_count;
unsigned int smi_count;
unsigned int cpu_id;
+ unsigned int apic_id;
+ unsigned int x2apic_id;
unsigned int flags;
#define CPU_IS_FIRST_THREAD_IN_CORE 0x2
#define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4
}
/*
- * Each string in this array is compared in --show and --hide cmdline.
- * Thus, strings that are proper sub-sets must follow their more specific peers.
+ * This list matches the column headers, except
+ * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time
+ * 2. Core and CPU are moved to the end, we can't have strings that contain them
+ * matching on them for --show and --hide.
*/
struct msr_counter bic[] = {
{ 0x0, "usec" },
{ 0x0, "Time_Of_Day_Seconds" },
{ 0x0, "Package" },
+ { 0x0, "Node" },
{ 0x0, "Avg_MHz" },
+ { 0x0, "Busy%" },
{ 0x0, "Bzy_MHz" },
{ 0x0, "TSC_MHz" },
{ 0x0, "IRQ" },
{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
- { 0x0, "Busy%" },
+ { 0x0, "sysfs" },
{ 0x0, "CPU%c1" },
{ 0x0, "CPU%c3" },
{ 0x0, "CPU%c6" },
{ 0x0, "Cor_J" },
{ 0x0, "GFX_J" },
{ 0x0, "RAM_J" },
- { 0x0, "Core" },
- { 0x0, "CPU" },
{ 0x0, "Mod%c6" },
- { 0x0, "sysfs" },
{ 0x0, "Totl%C0" },
{ 0x0, "Any%C0" },
{ 0x0, "GFX%C0" },
{ 0x0, "CPUGFX%" },
- { 0x0, "Node%" },
+ { 0x0, "Core" },
+ { 0x0, "CPU" },
+ { 0x0, "APIC" },
+ { 0x0, "X2APIC" },
};
-
-
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
#define BIC_USEC (1ULL << 0)
#define BIC_TOD (1ULL << 1)
#define BIC_Package (1ULL << 2)
-#define BIC_Avg_MHz (1ULL << 3)
-#define BIC_Bzy_MHz (1ULL << 4)
-#define BIC_TSC_MHz (1ULL << 5)
-#define BIC_IRQ (1ULL << 6)
-#define BIC_SMI (1ULL << 7)
-#define BIC_Busy (1ULL << 8)
-#define BIC_CPU_c1 (1ULL << 9)
-#define BIC_CPU_c3 (1ULL << 10)
-#define BIC_CPU_c6 (1ULL << 11)
-#define BIC_CPU_c7 (1ULL << 12)
-#define BIC_ThreadC (1ULL << 13)
-#define BIC_CoreTmp (1ULL << 14)
-#define BIC_CoreCnt (1ULL << 15)
-#define BIC_PkgTmp (1ULL << 16)
-#define BIC_GFX_rc6 (1ULL << 17)
-#define BIC_GFXMHz (1ULL << 18)
-#define BIC_Pkgpc2 (1ULL << 19)
-#define BIC_Pkgpc3 (1ULL << 20)
-#define BIC_Pkgpc6 (1ULL << 21)
-#define BIC_Pkgpc7 (1ULL << 22)
-#define BIC_Pkgpc8 (1ULL << 23)
-#define BIC_Pkgpc9 (1ULL << 24)
-#define BIC_Pkgpc10 (1ULL << 25)
-#define BIC_CPU_LPI (1ULL << 26)
-#define BIC_SYS_LPI (1ULL << 27)
-#define BIC_PkgWatt (1ULL << 26)
-#define BIC_CorWatt (1ULL << 27)
-#define BIC_GFXWatt (1ULL << 28)
-#define BIC_PkgCnt (1ULL << 29)
-#define BIC_RAMWatt (1ULL << 30)
-#define BIC_PKG__ (1ULL << 31)
-#define BIC_RAM__ (1ULL << 32)
-#define BIC_Pkg_J (1ULL << 33)
-#define BIC_Cor_J (1ULL << 34)
-#define BIC_GFX_J (1ULL << 35)
-#define BIC_RAM_J (1ULL << 36)
-#define BIC_Core (1ULL << 37)
-#define BIC_CPU (1ULL << 38)
-#define BIC_Mod_c6 (1ULL << 39)
-#define BIC_sysfs (1ULL << 40)
-#define BIC_Totl_c0 (1ULL << 41)
-#define BIC_Any_c0 (1ULL << 42)
-#define BIC_GFX_c0 (1ULL << 43)
-#define BIC_CPUGFX (1ULL << 44)
-#define BIC_Node (1ULL << 45)
-
-#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD)
+#define BIC_Node (1ULL << 3)
+#define BIC_Avg_MHz (1ULL << 4)
+#define BIC_Busy (1ULL << 5)
+#define BIC_Bzy_MHz (1ULL << 6)
+#define BIC_TSC_MHz (1ULL << 7)
+#define BIC_IRQ (1ULL << 8)
+#define BIC_SMI (1ULL << 9)
+#define BIC_sysfs (1ULL << 10)
+#define BIC_CPU_c1 (1ULL << 11)
+#define BIC_CPU_c3 (1ULL << 12)
+#define BIC_CPU_c6 (1ULL << 13)
+#define BIC_CPU_c7 (1ULL << 14)
+#define BIC_ThreadC (1ULL << 15)
+#define BIC_CoreTmp (1ULL << 16)
+#define BIC_CoreCnt (1ULL << 17)
+#define BIC_PkgTmp (1ULL << 18)
+#define BIC_GFX_rc6 (1ULL << 19)
+#define BIC_GFXMHz (1ULL << 20)
+#define BIC_Pkgpc2 (1ULL << 21)
+#define BIC_Pkgpc3 (1ULL << 22)
+#define BIC_Pkgpc6 (1ULL << 23)
+#define BIC_Pkgpc7 (1ULL << 24)
+#define BIC_Pkgpc8 (1ULL << 25)
+#define BIC_Pkgpc9 (1ULL << 26)
+#define BIC_Pkgpc10 (1ULL << 27)
+#define BIC_CPU_LPI (1ULL << 28)
+#define BIC_SYS_LPI (1ULL << 29)
+#define BIC_PkgWatt (1ULL << 30)
+#define BIC_CorWatt (1ULL << 31)
+#define BIC_GFXWatt (1ULL << 32)
+#define BIC_PkgCnt (1ULL << 33)
+#define BIC_RAMWatt (1ULL << 34)
+#define BIC_PKG__ (1ULL << 35)
+#define BIC_RAM__ (1ULL << 36)
+#define BIC_Pkg_J (1ULL << 37)
+#define BIC_Cor_J (1ULL << 38)
+#define BIC_GFX_J (1ULL << 39)
+#define BIC_RAM_J (1ULL << 40)
+#define BIC_Mod_c6 (1ULL << 41)
+#define BIC_Totl_c0 (1ULL << 42)
+#define BIC_Any_c0 (1ULL << 43)
+#define BIC_GFX_c0 (1ULL << 44)
+#define BIC_CPUGFX (1ULL << 45)
+#define BIC_Core (1ULL << 46)
+#define BIC_CPU (1ULL << 47)
+#define BIC_APIC (1ULL << 48)
+#define BIC_X2APIC (1ULL << 49)
+
+#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
-unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
"when COMMAND completes.\n"
"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
"to print statistics, until interrupted.\n"
- "--add add a counter\n"
- " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
- "--cpu cpu-set limit output to summary plus cpu-set:\n"
- " {core | package | j,k,l..m,n-p }\n"
- "--quiet skip decoding system configuration header\n"
- "--interval sec.subsec Override default 5-second measurement interval\n"
- "--help print this help message\n"
- "--list list column headers only\n"
- "--num_iterations num number of the measurement iterations\n"
- "--out file create or truncate \"file\" for all output\n"
- "--version print version information\n"
+ " -a, --add add a counter\n"
+ " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+ " -c, --cpu cpu-set limit output to summary plus cpu-set:\n"
+ " {core | package | j,k,l..m,n-p }\n"
+ " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n"
+ " -D, --Dump displays the raw counter values\n"
+ " -e, --enable [all | column]\n"
+ " shows all or the specified disabled column\n"
+ " -H, --hide [column|column,column,...]\n"
+ " hide the specified column(s)\n"
+ " -i, --interval sec.subsec\n"
+ " Override default 5-second measurement interval\n"
+ " -J, --Joules displays energy in Joules instead of Watts\n"
+ " -l, --list list column headers only\n"
+ " -n, --num_iterations num\n"
+ " number of the measurement iterations\n"
+ " -o, --out file\n"
+ " create or truncate \"file\" for all output\n"
+ " -q, --quiet skip decoding system configuration header\n"
+ " -s, --show [column|column,column,...]\n"
+ " show only the specified column(s)\n"
+ " -S, --Summary\n"
+ " limits output to 1-line system summary per interval\n"
+ " -T, --TCC temperature\n"
+ " sets the Thermal Control Circuit temperature in\n"
+ " degrees Celsius\n"
+ " -h, --help print this help message\n"
+ " -v, --version print version information\n"
"\n"
"For more help, run \"man turbostat\"\n");
}
outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%sCPU", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%sAPIC", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%sX2APIC", (printed++ ? delim : ""));
if (DO_BIC(BIC_Avg_MHz))
outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : ""));
if (DO_BIC(BIC_Busy))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
} else {
if (DO_BIC(BIC_Package)) {
if (p)
}
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id);
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->apic_id);
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->x2apic_id);
}
if (DO_BIC(BIC_Avg_MHz))
if (!printed || !summary_only)
print_header("\t");
- if (topo.num_cpus > 1)
- format_counters(&average.threads, &average.cores,
- &average.packages);
+ format_counters(&average.threads, &average.cores, &average.packages);
printed = 1;
int i;
struct msr_counter *mp;
+ /* we run cpuid just the 1st time, copy the results */
+ if (DO_BIC(BIC_APIC))
+ new->apic_id = old->apic_id;
+ if (DO_BIC(BIC_X2APIC))
+ new->x2apic_id = old->x2apic_id;
+
/*
* the timestamps from start of measurement interval are in "old"
* the timestamp from end of measurement interval are in "new"
int i;
struct msr_counter *mp;
+ /* copy un-changing apic_id's */
+ if (DO_BIC(BIC_APIC))
+ average.threads.apic_id = t->apic_id;
+ if (DO_BIC(BIC_X2APIC))
+ average.threads.x2apic_id = t->x2apic_id;
+
/* remember first tv_begin */
if (average.threads.tv_begin.tv_sec == 0)
average.threads.tv_begin = t->tv_begin;
return 0;
}
+void get_apic_id(struct thread_data *t)
+{
+ unsigned int eax, ebx, ecx, edx, max_level;
+
+ eax = ebx = ecx = edx = 0;
+
+ if (!genuine_intel)
+ return;
+
+ __cpuid(0, max_level, ebx, ecx, edx);
+
+ __cpuid(1, eax, ebx, ecx, edx);
+ t->apic_id = (ebx >> 24) & 0xf;
+
+ if (max_level < 0xb)
+ return;
+
+ if (!DO_BIC(BIC_X2APIC))
+ return;
+
+ ecx = 0;
+ __cpuid(0xb, eax, ebx, ecx, edx);
+ t->x2apic_id = edx;
+
+ if (debug && (t->apic_id != t->x2apic_id))
+ fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
+}
+
/*
* get_counters(...)
* migrate to cpu
struct msr_counter *mp;
int i;
-
gettimeofday(&t->tv_begin, (struct timezone *)NULL);
if (cpu_migrate(cpu)) {
return -1;
}
+ if (first_counter_read)
+ get_apic_id(t);
retry:
t->tsc = rdtsc(); /* we are running on local CPU of interest */
void set_node_data(void)
{
- char path[80];
- FILE *filep;
- int pkg, node, cpu;
-
- struct pkg_node_info {
- int count;
- int min;
- } *pni;
-
- pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
- if (!pni)
- err(1, "calloc pkg_node_count");
-
- for (pkg = 0; pkg < topo.num_packages; pkg++)
- pni[pkg].min = topo.num_cpus;
-
- for (node = 0; node <= topo.max_node_num; node++) {
- /* find the "first" cpu in the node */
- sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
- filep = fopen(path, "r");
- if (!filep)
- continue;
- fscanf(filep, "%d", &cpu);
- fclose(filep);
-
- pkg = cpus[cpu].physical_package_id;
- pni[pkg].count++;
-
- if (node < pni[pkg].min)
- pni[pkg].min = node;
- }
-
- for (pkg = 0; pkg < topo.num_packages; pkg++)
- if (pni[pkg].count > topo.nodes_per_pkg)
- topo.nodes_per_pkg = pni[0].count;
-
- for (cpu = 0; cpu < topo.num_cpus; cpu++) {
- pkg = cpus[cpu].physical_package_id;
- node = cpus[cpu].physical_node_id;
- cpus[cpu].logical_node_id = node - pni[pkg].min;
+ int pkg, node, lnode, cpu, cpux;
+ int cpu_count;
+
+ /* initialize logical_node_id */
+ for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu)
+ cpus[cpu].logical_node_id = -1;
+
+ cpu_count = 0;
+ for (pkg = 0; pkg < topo.num_packages; pkg++) {
+ lnode = 0;
+ for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) {
+ if (cpus[cpu].physical_package_id != pkg)
+ continue;
+ /* find a cpu with an unset logical_node_id */
+ if (cpus[cpu].logical_node_id != -1)
+ continue;
+ cpus[cpu].logical_node_id = lnode;
+ node = cpus[cpu].physical_node_id;
+ cpu_count++;
+ /*
+ * find all matching cpus on this pkg and set
+ * the logical_node_id
+ */
+ for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) {
+ if ((cpus[cpux].physical_package_id == pkg) &&
+ (cpus[cpux].physical_node_id == node)) {
+ cpus[cpux].logical_node_id = lnode;
+ cpu_count++;
+ }
+ }
+ lnode++;
+ if (lnode > topo.nodes_per_pkg)
+ topo.nodes_per_pkg = lnode;
+ }
+ if (cpu_count >= topo.max_cpu_num)
+ break;
}
- free(pni);
-
}
int get_physical_node_id(struct cpu_topology *thiscpu)
}
}
+
void turbostat_loop()
{
int retval;
snapshot_proc_sysfs_files();
retval = for_all_cpus(get_counters, EVEN_COUNTERS);
+ first_counter_read = 0;
if (retval < -1) {
exit(retval);
} else if (retval == -1) {
family = (fms >> 8) & 0xf;
model = (fms >> 4) & 0xf;
stepping = fms & 0xf;
- if (family == 6 || family == 0xf)
+ if (family == 0xf)
+ family += (fms >> 20) & 0xff;
+ if (family >= 6)
model += ((fms >> 16) & 0xf) << 4;
if (!quiet) {
fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
max_level, family, model, stepping, family, model, stepping);
- fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
+ fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
ecx & (1 << 0) ? "SSE3" : "-",
ecx & (1 << 3) ? "MONITOR" : "-",
ecx & (1 << 6) ? "SMX" : "-",
edx & (1 << 4) ? "TSC" : "-",
edx & (1 << 5) ? "MSR" : "-",
edx & (1 << 22) ? "ACPI-TM" : "-",
+ edx & (1 << 28) ? "HT" : "-",
edx & (1 << 29) ? "TM" : "-");
}
return;
}
-
/*
* in /dev/cpu/ return success for names that are numbers
* ie. filter out ".", "..", "microcode".
siblings = get_thread_siblings(&cpus[i]);
if (siblings > max_siblings)
max_siblings = siblings;
- if (cpus[i].thread_id != -1)
+ if (cpus[i].thread_id == 0)
topo.num_cores++;
-
- if (debug > 1)
- fprintf(outf,
- "cpu %d pkg %d node %d core %d thread %d\n",
- i, cpus[i].physical_package_id,
- cpus[i].physical_node_id,
- cpus[i].physical_core_id,
- cpus[i].thread_id);
}
topo.cores_per_node = max_core_id + 1;
topo.threads_per_core = max_siblings;
if (debug > 1)
fprintf(outf, "max_siblings %d\n", max_siblings);
+
+ if (debug < 1)
+ return;
+
+ for (i = 0; i <= topo.max_cpu_num; ++i) {
+ fprintf(outf,
+ "cpu %d pkg %d node %d lnode %d core %d thread %d\n",
+ i, cpus[i].physical_package_id,
+ cpus[i].physical_node_id,
+ cpus[i].logical_node_id,
+ cpus[i].physical_core_id,
+ cpus[i].thread_id);
+ }
+
}
void
struct core_data *c;
struct pkg_data *p;
+
+ /* Workaround for systems where physical_node_id==-1
+ * and logical_node_id==(-1 - topo.num_cpus)
+ */
+ if (node_id < 0)
+ node_id = 0;
+
t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
c = GET_CORE(core_base, core_id, node_id, pkg_id);
p = GET_PKG(pkg_base, pkg_id);
snapshot_proc_sysfs_files();
status = for_all_cpus(get_counters, EVEN_COUNTERS);
+ first_counter_read = 0;
if (status)
exit(status);
/* clear affinity side-effect of get_counters() */
}
void print_version() {
- fprintf(outf, "turbostat version 18.06.01"
+ fprintf(outf, "turbostat version 18.07.27"
" - Len Brown <lenb@kernel.org>\n");
}
break;
case 'e':
/* --enable specified counter */
- bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+ bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST);
break;
case 'd':
debug++;
int main(int argc, char **argv)
{
outf = stderr;
-
cmdline(argc, argv);
if (!quiet)
pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES;
pcap->header.length = sizeof(*pcap);
pcap->highest_capability = 1;
- pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH |
- ACPI_NFIT_CAPABILITY_MEM_FLUSH;
+ pcap->capabilities = ACPI_NFIT_CAPABILITY_MEM_FLUSH;
offset += pcap->header.length;
if (t->setup_hotplug) {
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
all: $(TEST_CUSTOM_PROGS)
-$(TEST_CUSTOM_PROGS): urandom_read
-
-urandom_read: urandom_read.c
+$(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
$(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id
# Order correspond to 'make run_tests' order
BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
ifneq ($(BTF_LLC_PROBE),)
ifneq ($(BTF_PAHOLE_PROBE),)
unsigned int numa_node;
};
+#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \
+ struct ____btf_map_##name { \
+ type_key key; \
+ type_val value; \
+ }; \
+ struct ____btf_map_##name \
+ __attribute__ ((section(".maps." #name), used)) \
+ ____btf_map_##name = { }
+
static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
(void *) BPF_FUNC_skb_load_bytes;
static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_IPIP=y
+CONFIG_IPV6=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
+CONFIG_IPV6_GRE=y
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_HMAC=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_VXLAN=y
+CONFIG_GENEVE=y
.max_entries = 4,
},
+{
+ .descr = "struct test #3 Invalid member offset",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int64 */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8),
+
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 16),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* int64 n; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0",
+ .str_sec_size = sizeof("\0A\0m\0n\0"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_test3_map",
+ .key_size = sizeof(int),
+ .value_size = 16,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid member bits_offset",
+},
+
/* Test member exceeds the size of struct.
*
* struct A {
.key_size = sizeof(int),
.value_size = sizeof(void *) * 4,
.key_type_id = 1,
- .value_type_id = 4,
+ .value_type_id = 5,
.max_entries = 4,
},
.err_str = "type != 0",
},
+{
+ .descr = "arraymap invalid btf key (a bit field)",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* 32 bit int with 32 bit offset */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 32, 32, 8),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_map_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 2,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .map_create_err = true,
+},
+
+{
+ .descr = "arraymap invalid btf key (!= 32 bits)",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* 16 bit int with 0 bit offset */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 16, 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_map_check_btf",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 2,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .map_create_err = true,
+},
+
+{
+ .descr = "arraymap invalid btf value (too small)",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_map_check_btf",
+ .key_size = sizeof(int),
+ /* btf_value_size < map->value_size */
+ .value_size = sizeof(__u64),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .map_create_err = true,
+},
+
+{
+ .descr = "arraymap invalid btf value (too big)",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_map_check_btf",
+ .key_size = sizeof(int),
+ /* btf_value_size > map->value_size */
+ .value_size = sizeof(__u16),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .map_create_err = true,
+},
+
}; /* struct btf_raw_test raw_tests[] */
static const char *get_next_str(const char *start, const char *end)
BTF_ENUM_ENC(NAME_TBD, 2),
BTF_ENUM_ENC(NAME_TBD, 3),
/* struct pprint_mapv */ /* [16] */
- BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28),
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 32),
BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */
BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */
BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */
unsigned int v6;
};
-typedef int btf_map_key;
-typedef struct ipv_counts btf_map_value;
-btf_map_key dumm_key;
-btf_map_value dummy_value;
-
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.max_entries = 4,
};
+BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
+
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
SRC_TREE=../../../../
test_run()
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
# datagram can be read on NS6 when binding to fb00::6.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
cleanup()
ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4
+ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4
-ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6
+ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6
ip netns exec ns4 ip -6 addr add fc42::1 dev lo
ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8
+ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8
ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
def bpftool_prog_list(expected=None, ns=""):
_, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+ # Remove the base progs
+ for p in base_progs:
+ if p in progs:
+ progs.remove(p)
if expected is not None:
if len(progs) != expected:
fail(True, "%d BPF programs loaded, expected %d" %
def bpftool_map_list(expected=None, ns=""):
_, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+ # Remove the base maps
+ for m in base_maps:
+ if m in maps:
+ maps.remove(m)
if expected is not None:
if len(maps) != expected:
fail(True, "%d BPF maps loaded, expected %d" %
# Check tools
ret, progs = bpftool("prog", fail=False)
skip(ret != 0, "bpftool not installed")
-# Check no BPF programs are loaded
-skip(len(progs) != 0, "BPF programs already loaded on the system")
+base_progs = progs
+_, base_maps = bpftool("map")
# Check netdevsim
ret, out = cmd("modprobe netdevsim", fail=False)
while (s->bytes_recvd < total_bytes) {
if (txmsg_cork) {
timeout.tv_sec = 0;
- timeout.tv_usec = 1000;
+ timeout.tv_usec = 300000;
} else {
timeout.tv_sec = 1;
timeout.tv_usec = 0;
int main(int argc, char **argv)
{
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
int iov_count = 1, length = 1024, rate = 1;
struct sockmap_options options = {0};
int opt, longindex, err, cg_fd = 0;
char *bpf_file = BPF_SOCKMAP_FILENAME;
int test = PING_PONG;
- if (setrlimit(RLIMIT_MEMLOCK, &r)) {
- perror("setrlimit(RLIMIT_MEMLOCK)");
- return 1;
- }
-
if (argc < 2)
return test_suite();
test_xfrm_tunnel()
{
config_device
- #tcpdump -nei veth1 ip &
- output=$(mktemp)
- cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
- setup_xfrm_tunnel
+ > /sys/kernel/debug/tracing/trace
+ setup_xfrm_tunnel
tc qdisc add dev veth1 clsact
tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
sec xfrm_get_state
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
sleep 1
- grep "reqid 1" $output
+ grep "reqid 1" /sys/kernel/debug/tracing/trace
check_err $?
- grep "spi 0x1" $output
+ grep "spi 0x1" /sys/kernel/debug/tracing/trace
check_err $?
- grep "remote ip 0xac100164" $output
+ grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
check_err $?
cleanup
if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: xfrm tunnel"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+ echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
}
attach_bpf()
ip link del ip6geneve11 2> /dev/null
ip link del erspan11 2> /dev/null
ip link del ip6erspan11 2> /dev/null
+ ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
+ ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
+ ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
+ ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
}
cleanup_exit()
check()
{
- ip link help $1 2>&1 | grep -q "^Usage:"
+ ip link help 2>&1 | grep -q "\s$1\s"
if [ $? -ne 0 ];then
echo "SKIP $1: iproute2 not support"
cleanup
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_LWT_XMIT,
},
+ {
+ "make headroom for LWT_XMIT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_2, 34),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+ /* split for s390 to succeed */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_IMM(BPF_REG_2, 42),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_LWT_XMIT,
+ },
{
"invalid access of tc_classid for LWT_IN",
.insns = {
.errstr = "BPF_XADD stores into R2 packet",
.prog_type = BPF_PROG_TYPE_XDP,
},
+ {
+ "xadd/w check whether src/dst got mangled, 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 3,
+ },
+ {
+ "xadd/w check whether src/dst got mangled, 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+ BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+ BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 3,
+ },
{
"bpf_get_stack return R0 within range",
.insns = {
}
if (fd_prog >= 0) {
+ __u8 tmp[TEST_DATA_LEN << 2];
+ __u32 size_tmp = sizeof(tmp);
+
err = bpf_prog_test_run(fd_prog, 1, test->data,
- sizeof(test->data), NULL, NULL,
+ sizeof(test->data), tmp, &size_tmp,
&retval, NULL);
if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
printf("Unexpected bpf_prog_test_run error\n");
return len;
}
-static ssize_t write_text(const char *path, char *buf, size_t len)
+static ssize_t write_text(const char *path, char *buf, ssize_t len)
{
int fd;
int cg_write(const char *cgroup, const char *control, char *buf)
{
char path[PATH_MAX];
- size_t len = strlen(buf);
+ ssize_t len = strlen(buf);
snprintf(path, sizeof(path), "%s/%s", cgroup, control);
--- /dev/null
+#!/bin/sh
+# description: Snapshot and tracing setting
+# flags: instance
+
+[ ! -f snapshot ] && exit_unsupported
+
+echo "Set tracing off"
+echo 0 > tracing_on
+
+echo "Allocate and take a snapshot"
+echo 1 > snapshot
+
+# Since trace buffer is empty, snapshot is also empty, but allocated
+grep -q "Snapshot is allocated" snapshot
+
+echo "Ensure keep tracing off"
+test `cat tracing_on` -eq 0
+
+echo "Set tracing on"
+echo 1 > tracing_on
+
+echo "Take a snapshot again"
+echo 1 > snapshot
+
+echo "Ensure keep tracing on"
+test `cat tracing_on` -eq 1
+
+exit 0
ARG2=%r1
OFFS=4
;;
+ppc64*)
+ ARG2=%r4
+ OFFS=8
+;;
+ppc*)
+ ARG2=%r4
+ OFFS=4
+;;
*)
echo "Please implement other architecture here"
exit_untested
GOODREG=%r0
BADREG=%ax
;;
+ppc*)
+ GOODREG=%r3
+ BADREG=%msr
+;;
+*)
+ echo "Please implement other architecture here"
+ exit_untested
esac
test_goodarg() # Good-args
udpgso
udpgso_bench_rx
udpgso_bench_tx
+tcp_inq
CONFIG_INET6_XFRM_MODE_TUNNEL=y
CONFIG_IPV6_VTI=y
CONFIG_DUMMY=y
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
log_test $? 2 "Attempt to add duplicate route - reject route"
- # iproute2 prepend only sets NLM_F_CREATE
- # - adds a new route; does NOT convert existing route to ECMP
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
- check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
- log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
-
# route append with same prefix adds a new route
# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
log_test $? 0 "Append nexthop to existing route - gw"
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
- check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
- log_test $? 0 "Append nexthop to existing route - dev only"
-
- # multipath route can not have a nexthop that is a reject route
- add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
- run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
- log_test $? 2 "Append nexthop to existing route - reject route"
-
- # reject route can not be converted to multipath route
- run_cmd "$IP -6 ro flush 2001:db8:104::/64"
- run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
- log_test $? 2 "Append nexthop to existing reject route - gw"
-
- run_cmd "$IP -6 ro flush 2001:db8:104::/64"
- run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
- run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
- log_test $? 2 "Append nexthop to existing reject route - dev only"
-
# insert mpath directly
add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
log_test $? 0 "Single path with multipath"
- # single path with reject
- #
- add_initial_route6 "nexthop via 2001:db8:101::2"
- run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
- check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
- log_test $? 0 "Single path with reject route"
-
# single path with single path using MULTIPATH attribute
#
add_initial_route6 "via 2001:db8:101::2"
check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
log_test $? 0 "Multipath with single path via multipath attribute"
- # multipath with reject
- add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
- run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
- check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
- log_test $? 0 "Multipath with reject route"
-
# route replace fails - invalid nexthop 1
add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
exit(1);
}
- fd = socket(AF_INET6, SOCK_STREAM, 0);
+ fd = socket(cfg_family, SOCK_STREAM, 0);
if (fd == -1) {
perror("socket");
exit(1);
echo "udp gso"
run_in_netns ${args} -S
-
- echo "udp gso zerocopy"
- run_in_netns ${args} -S -z
}
run_tcp() {
#
# Released under the terms of the GPL v2.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
. ./common_tests
if [ -e $REBOOT_FLAG ]; then
rm $REBOOT_FLAG
else
prlog "pstore_crash_test has not been executed yet. we skip further tests."
- exit 0
+ exit $ksft_skip
fi
prlog -n "Mounting pstore filesystem ... "
#!/bin/bash
#
-# Usage: configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file build-output-dir results-dir
#
# Create a .config file from the spec file. Run from the kernel source tree.
# Exits with 0 if all went well, with 1 if all went well but the config
c=$1
buildloc=$2
+resdir=$3
builddir=
-if test -n $buildloc
+if echo $buildloc | grep -q '^O='
then
- if echo $buildloc | grep -q '^O='
+ builddir=`echo $buildloc | sed -e 's/^O=//'`
+ if test ! -d $builddir
then
- builddir=`echo $buildloc | sed -e 's/^O=//'`
- if test ! -d $builddir
- then
- mkdir $builddir
- fi
- else
- echo Bad build directory: \"$buildloc\"
- exit 2
+ mkdir $builddir
fi
+else
+ echo Bad build directory: \"$buildloc\"
+ exit 2
fi
sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
grep '^grep' < $T/u.sh > $T/upd.sh
echo "cat - $c" >> $T/upd.sh
make mrproper
-make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
+make $buildloc distclean > $resdir/Make.distclean 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
mv $builddir/.config $builddir/.config.sav
sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
+yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
# verify new config matches specification.
configcheck.sh $builddir/.config $c
#
# Build a kvm-ready Linux kernel from the tree in the current directory.
#
-# Usage: kvm-build.sh config-template build-dir
+# Usage: kvm-build.sh config-template build-dir resdir
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
exit 1
fi
builddir=${2}
+resdir=${3}
T=${TMPDIR-/tmp}/test-linux.sh.$$
trap 'rm -rf $T' 0
CONFIG_VIRTIO_CONSOLE=y
___EOF___
-configinit.sh $T/config O=$builddir
+configinit.sh $T/config O=$builddir $resdir
retval=$?
if test $retval -gt 1
then
exit 2
fi
ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1
retval=$?
-if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out
then
echo Kernel build error
- egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+ egrep "Stop|Error|error:|warning:" < $resdir/Make.out
echo Run aborted.
exit 3
fi
else
print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
fi
+ echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags
fi
head -1 $resdir/log
fi
TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+ rm -f $i/console.log.*.diags
kvm-recheck-${TORTURE_SUITE}.sh $i
if test -f "$i/console.log"
then
ln -s $base_resdir/.config $resdir # for kvm-recheck.sh
# Arch-independent indicator
touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $builddir
+elif kvm-build.sh $T/Kc2 $builddir $resdir
then
# Had to build a kernel for this test.
QEMU="`identify_qemu $builddir/vmlinux`"
BOOT_IMAGE="`identify_boot_image $QEMU`"
- cp $builddir/Make*.out $resdir
cp $builddir/vmlinux $resdir
cp $builddir/.config $resdir
+ cp $builddir/Module.symvers $resdir > /dev/null || :
+ cp $builddir/System.map $resdir > /dev/null || :
if test -n "$BOOT_IMAGE"
then
cp $builddir/$BOOT_IMAGE $resdir
print "needqemurun="
jn=1
for (j = first; j < pastlast; j++) {
- builddir=KVM "/b" jn
+ builddir=KVM "/b1"
cpusr[jn] = cpus[j];
if (cfrep[cf[j]] == "") {
cfr[jn] = cf[j];
print_warning Summary: $summary
cat $T.diags >> $file.diags
fi
+for i in $file.*.diags
+do
+ if test -f "$i"
+ then
+ cat $i >> $file.diags
+ fi
+done
if ! test -s $file.diags
then
rm -f $file.diags
-rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30
+rcutree.gp_preinit_delay=12
rcutree.gp_init_delay=3
rcutree.gp_cleanup_delay=3
rcutree.kthread_prio=2
+++ /dev/null
-rcutree.rcu_fanout_exact=1
if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
then
echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
- echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+ echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30
fi
}
#error "Unsupported architecture"
#endif
+#elif defined(__s390__)
+
+#define RSEQ_INJECT_INPUT \
+ , [loop_cnt_1]"m"(loop_cnt[1]) \
+ , [loop_cnt_2]"m"(loop_cnt[2]) \
+ , [loop_cnt_3]"m"(loop_cnt[3]) \
+ , [loop_cnt_4]"m"(loop_cnt[4]) \
+ , [loop_cnt_5]"m"(loop_cnt[5]) \
+ , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG "r12"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+ "ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+ "je 333f\n\t" \
+ "222:\n\t" \
+ "ahi %%" INJECT_ASM_REG ", -1\n\t" \
+ "jnz 222b\n\t" \
+ "333:\n\t"
+
#elif defined(__ARMEL__)
#define RSEQ_INJECT_INPUT \
"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
"bne 222b\n\t" \
"333:\n\t"
+
+#elif defined(__mips__)
+
+#define RSEQ_INJECT_INPUT \
+ , [loop_cnt_1]"m"(loop_cnt[1]) \
+ , [loop_cnt_2]"m"(loop_cnt[2]) \
+ , [loop_cnt_3]"m"(loop_cnt[3]) \
+ , [loop_cnt_4]"m"(loop_cnt[4]) \
+ , [loop_cnt_5]"m"(loop_cnt[5]) \
+ , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG "$5"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+ "beqz " INJECT_ASM_REG ", 333f\n\t" \
+ "222:\n\t" \
+ "addiu " INJECT_ASM_REG ", -1\n\t" \
+ "bnez " INJECT_ASM_REG ", 222b\n\t" \
+ "333:\n\t"
+
#else
#error unsupported target
#endif
#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
abort_label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
+ ".balign 32\n\t" \
__rseq_str(table_label) ":\n\t" \
".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \
--- /dev/null
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Author: Paul Burton <paul.burton@mips.com>
+ * (C) Copyright 2018 MIPS Tech LLC
+ *
+ * Based on rseq-arm.h:
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#define RSEQ_SIG 0x53053053
+
+#define rseq_smp_mb() __asm__ __volatile__ ("sync" ::: "memory")
+#define rseq_smp_rmb() rseq_smp_mb()
+#define rseq_smp_wmb() rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p) \
+__extension__ ({ \
+ __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \
+ rseq_smp_mb(); \
+ ____p1; \
+})
+
+#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v) \
+do { \
+ rseq_smp_mb(); \
+ RSEQ_WRITE_ONCE(*p, v); \
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#if _MIPS_SZLONG == 64
+# define LONG ".dword"
+# define LONG_LA "dla"
+# define LONG_L "ld"
+# define LONG_S "sd"
+# define LONG_ADDI "daddiu"
+# define U32_U64_PAD(x) x
+#elif _MIPS_SZLONG == 32
+# define LONG ".word"
+# define LONG_LA "la"
+# define LONG_L "lw"
+# define LONG_S "sw"
+# define LONG_ADDI "addiu"
+# ifdef __BIG_ENDIAN
+# define U32_U64_PAD(x) "0x0, " x
+# else
+# define U32_U64_PAD(x) x ", 0x0"
+# endif
+#else
+# error unsupported _MIPS_SZLONG
+#endif
+
+#define __RSEQ_ASM_DEFINE_TABLE(version, flags, start_ip, \
+ post_commit_offset, abort_ip) \
+ ".pushsection __rseq_table, \"aw\"\n\t" \
+ ".balign 32\n\t" \
+ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+ ".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \
+ __RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \
+ (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \
+ RSEQ_INJECT_ASM(1) \
+ LONG_LA " $4, " __rseq_str(cs_label) "\n\t" \
+ LONG_S " $4, %[" __rseq_str(rseq_cs) "]\n\t" \
+ __rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
+ RSEQ_INJECT_ASM(2) \
+ "lw $4, %[" __rseq_str(current_cpu_id) "]\n\t" \
+ "bne $4, %[" __rseq_str(cpu_id) "], " __rseq_str(label) "\n\t"
+
+#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+ abort_label, version, flags, \
+ start_ip, post_commit_offset, abort_ip) \
+ ".balign 32\n\t" \
+ __rseq_str(table_label) ":\n\t" \
+ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+ ".word " __rseq_str(RSEQ_SIG) "\n\t" \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "b %l[" __rseq_str(abort_label) "]\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \
+ start_ip, post_commit_ip, abort_ip) \
+ __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+ abort_label, 0x0, 0x0, start_ip, \
+ (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "b %l[" __rseq_str(cmpfail_label) "]\n\t"
+
+#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "beq $4, %[expectnot], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "beq $4, %[expectnot], %l[error2]\n\t"
+#endif
+ LONG_S " $4, %[load]\n\t"
+ LONG_ADDI " $4, %[voffp]\n\t"
+ LONG_L " $4, 0($4)\n\t"
+ /* final store */
+ LONG_S " $4, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expectnot] "r" (expectnot),
+ [voffp] "Ir" (voffp),
+ [load] "m" (*load)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+ LONG_L " $4, %[v]\n\t"
+ LONG_ADDI " $4, %[count]\n\t"
+ /* final store */
+ LONG_S " $4, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(4)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [v] "m" (*v),
+ [count] "Ir" (count)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort
+#ifdef RSEQ_COMPARE_TWICE
+ , error1
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* try store */
+ LONG_S " %[newv2], %[v2]\n\t"
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* try store input */
+ [v2] "m" (*v2),
+ [newv2] "r" (newv2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* try store */
+ LONG_S " %[newv2], %[v2]\n\t"
+ RSEQ_INJECT_ASM(5)
+ "sync\n\t" /* full sync provides store-release */
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* try store input */
+ [v2] "m" (*v2),
+ [newv2] "r" (newv2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+ LONG_L " $4, %[v2]\n\t"
+ "bne $4, %[expect2], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+ LONG_L " $4, %[v2]\n\t"
+ "bne $4, %[expect2], %l[error3]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* cmp2 input */
+ [v2] "m" (*v2),
+ [expect2] "r" (expect2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2, error3
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("1st expected value comparison failed");
+error3:
+ rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ uintptr_t rseq_scratch[3];
+
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ LONG_S " %[src], %[rseq_scratch0]\n\t"
+ LONG_S " %[dst], %[rseq_scratch1]\n\t"
+ LONG_S " %[len], %[rseq_scratch2]\n\t"
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 5f\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 7f\n\t"
+#endif
+ /* try memcpy */
+ "beqz %[len], 333f\n\t" \
+ "222:\n\t" \
+ "lb $4, 0(%[src])\n\t" \
+ "sb $4, 0(%[dst])\n\t" \
+ LONG_ADDI " %[src], 1\n\t" \
+ LONG_ADDI " %[dst], 1\n\t" \
+ LONG_ADDI " %[len], -1\n\t" \
+ "bnez %[len], 222b\n\t" \
+ "333:\n\t" \
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t"
+ "b 8f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ abort, 1b, 2b, 4f)
+ RSEQ_ASM_DEFINE_CMPFAIL(5,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_DEFINE_CMPFAIL(6,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error1)
+ RSEQ_ASM_DEFINE_CMPFAIL(7,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error2)
+#endif
+ "8:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv),
+ /* try memcpy input */
+ [dst] "r" (dst),
+ [src] "r" (src),
+ [len] "r" (len),
+ [rseq_scratch0] "m" (rseq_scratch[0]),
+ [rseq_scratch1] "m" (rseq_scratch[1]),
+ [rseq_scratch2] "m" (rseq_scratch[2])
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ uintptr_t rseq_scratch[3];
+
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ LONG_S " %[src], %[rseq_scratch0]\n\t"
+ LONG_S " %[dst], %[rseq_scratch1]\n\t"
+ LONG_S " %[len], %[rseq_scratch2]\n\t"
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 5f\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 7f\n\t"
+#endif
+ /* try memcpy */
+ "beqz %[len], 333f\n\t" \
+ "222:\n\t" \
+ "lb $4, 0(%[src])\n\t" \
+ "sb $4, 0(%[dst])\n\t" \
+ LONG_ADDI " %[src], 1\n\t" \
+ LONG_ADDI " %[dst], 1\n\t" \
+ LONG_ADDI " %[len], -1\n\t" \
+ "bnez %[len], 222b\n\t" \
+ "333:\n\t" \
+ RSEQ_INJECT_ASM(5)
+ "sync\n\t" /* full sync provides store-release */
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t"
+ "b 8f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ abort, 1b, 2b, 4f)
+ RSEQ_ASM_DEFINE_CMPFAIL(5,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_DEFINE_CMPFAIL(6,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error1)
+ RSEQ_ASM_DEFINE_CMPFAIL(7,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error2)
+#endif
+ "8:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv),
+ /* try memcpy input */
+ [dst] "r" (dst),
+ [src] "r" (src),
+ [len] "r" (len),
+ [rseq_scratch0] "m" (rseq_scratch[0]),
+ [rseq_scratch1] "m" (rseq_scratch[1]),
+ [rseq_scratch2] "m" (rseq_scratch[2])
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
--- /dev/null
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#define RSEQ_SIG 0x53053053
+
+#define rseq_smp_mb() __asm__ __volatile__ ("bcr 15,0" ::: "memory")
+#define rseq_smp_rmb() rseq_smp_mb()
+#define rseq_smp_wmb() rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p) \
+__extension__ ({ \
+ __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \
+ rseq_barrier(); \
+ ____p1; \
+})
+
+#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v) \
+do { \
+ rseq_barrier(); \
+ RSEQ_WRITE_ONCE(*p, v); \
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L "lg"
+#define LONG_S "stg"
+#define LONG_LT_R "ltgr"
+#define LONG_CMP "cg"
+#define LONG_CMP_R "cgr"
+#define LONG_ADDI "aghi"
+#define LONG_ADD_R "agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
+ start_ip, post_commit_offset, abort_ip) \
+ ".pushsection __rseq_table, \"aw\"\n\t" \
+ ".balign 32\n\t" \
+ __rseq_str(label) ":\n\t" \
+ ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ ".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+ ".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
+ start_ip, post_commit_offset, abort_ip) \
+ ".pushsection __rseq_table, \"aw\"\n\t" \
+ ".balign 32\n\t" \
+ __rseq_str(label) ":\n\t" \
+ ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+ ".popsection\n\t"
+
+#define LONG_L "l"
+#define LONG_S "st"
+#define LONG_LT_R "ltr"
+#define LONG_CMP "c"
+#define LONG_CMP_R "cr"
+#define LONG_ADDI "ahi"
+#define LONG_ADD_R "ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+ __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \
+ (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \
+ RSEQ_INJECT_ASM(1) \
+ "larl %%r0, " __rseq_str(cs_label) "\n\t" \
+ LONG_S " %%r0, %[" __rseq_str(rseq_cs) "]\n\t" \
+ __rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
+ RSEQ_INJECT_ASM(2) \
+ "c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+ "jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label) \
+ ".pushsection __rseq_failure, \"ax\"\n\t" \
+ ".long " __rseq_str(RSEQ_SIG) "\n\t" \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "j %l[" __rseq_str(abort_label) "]\n\t" \
+ ".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \
+ ".pushsection __rseq_failure, \"ax\"\n\t" \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "j %l[" __rseq_str(cmpfail_label) "]\n\t" \
+ ".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[error2]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " %%r1, %[v]\n\t"
+ LONG_CMP_R " %%r1, %[expectnot]\n\t"
+ "je %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " %%r1, %[v]\n\t"
+ LONG_CMP_R " %%r1, %[expectnot]\n\t"
+ "je %l[error2]\n\t"
+#endif
+ LONG_S " %%r1, %[load]\n\t"
+ LONG_ADD_R " %%r1, %[voffp]\n\t"
+ LONG_L " %%r1, 0(%%r1)\n\t"
+ /* final store */
+ LONG_S " %%r1, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expectnot] "r" (expectnot),
+ [voffp] "r" (voffp),
+ [load] "m" (*load)
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0", "r1"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+ LONG_L " %%r0, %[v]\n\t"
+ LONG_ADD_R " %%r0, %[count]\n\t"
+ /* final store */
+ LONG_S " %%r0, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(4)
+ RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [count] "r" (count)
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0"
+ RSEQ_INJECT_CLOBBER
+ : abort
+#ifdef RSEQ_COMPARE_TWICE
+ , error1
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[error2]\n\t"
+#endif
+ /* try store */
+ LONG_S " %[newv2], %[v2]\n\t"
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* try store input */
+ [v2] "m" (*v2),
+ [newv2] "r" (newv2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+ LONG_CMP " %[expect2], %[v2]\n\t"
+ "jnz %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz %l[error2]\n\t"
+ LONG_CMP " %[expect2], %[v2]\n\t"
+ "jnz %l[error3]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* cmp2 input */
+ [v2] "m" (*v2),
+ [expect2] "r" (expect2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2, error3
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("1st expected value comparison failed");
+error3:
+ rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ uint64_t rseq_scratch[3];
+
+ RSEQ_INJECT_C(9)
+
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+ LONG_S " %[src], %[rseq_scratch0]\n\t"
+ LONG_S " %[dst], %[rseq_scratch1]\n\t"
+ LONG_S " %[len], %[rseq_scratch2]\n\t"
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz 5f\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+ LONG_CMP " %[expect], %[v]\n\t"
+ "jnz 7f\n\t"
+#endif
+ /* try memcpy */
+ LONG_LT_R " %[len], %[len]\n\t"
+ "jz 333f\n\t"
+ "222:\n\t"
+ "ic %%r0,0(%[src])\n\t"
+ "stc %%r0,0(%[dst])\n\t"
+ LONG_ADDI " %[src], 1\n\t"
+ LONG_ADDI " %[dst], 1\n\t"
+ LONG_ADDI " %[len], -1\n\t"
+ "jnz 222b\n\t"
+ "333:\n\t"
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t"
+ RSEQ_ASM_DEFINE_ABORT(4,
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ abort)
+ RSEQ_ASM_DEFINE_CMPFAIL(5,
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_DEFINE_CMPFAIL(6,
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error1)
+ RSEQ_ASM_DEFINE_CMPFAIL(7,
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error2)
+#endif
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv),
+ /* try memcpy input */
+ [dst] "r" (dst),
+ [src] "r" (src),
+ [len] "r" (len),
+ [rseq_scratch0] "m" (rseq_scratch[0]),
+ [rseq_scratch1] "m" (rseq_scratch[1]),
+ [rseq_scratch2] "m" (rseq_scratch[2])
+ RSEQ_INJECT_INPUT
+ : "memory", "cc", "r0"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ return 0;
+abort:
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+ newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
#include <rseq-arm.h>
#elif defined(__PPC__)
#include <rseq-ppc.h>
+#elif defined(__mips__)
+#include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
#else
#error unsupported target
#endif
return cpu;
}
+static inline void rseq_clear_rseq_cs(void)
+{
+#ifdef __LP64__
+ __rseq_abi.rseq_cs.ptr = 0;
+#else
+ __rseq_abi.rseq_cs.ptr.ptr32 = 0;
+#endif
+}
+
/*
- * rseq_prepare_unload() should be invoked by each thread using rseq_finish*()
- * at least once between their last rseq_finish*() and library unload of the
- * library defining the rseq critical section (struct rseq_cs). This also
- * applies to use of rseq in code generated by JIT: rseq_prepare_unload()
- * should be invoked at least once by each thread using rseq_finish*() before
- * reclaim of the memory holding the struct rseq_cs.
+ * rseq_prepare_unload() should be invoked by each thread executing a rseq
+ * critical section at least once between their last critical section and
+ * library unload of the library defining the rseq critical section
+ * (struct rseq_cs). This also applies to use of rseq in code generated by
+ * JIT: rseq_prepare_unload() should be invoked at least once by each
+ * thread executing a rseq critical section before reclaim of the memory
+ * holding the struct rseq_cs.
*/
static inline void rseq_prepare_unload(void)
{
- __rseq_abi.rseq_cs = 0;
+ rseq_clear_rseq_cs();
}
#endif /* RSEQ_H_ */
+# SPDX-License-Identifier: GPL-2.0
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/x86_64/x86/)
+
+ifneq ($(ARCH),sparc64)
+nothing:
+.PHONY: all clean run_tests install
+.SILENT:
+else
+
SUBDIRS := drivers
TEST_PROGS := run.sh
+
.PHONY: all clean
include ../lib.mk
fi \
done
-override define RUN_TESTS
- @cd $(OUTPUT); ./run.sh
-endef
-
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
done;
endef
-override define EMIT_TESTS
- echo "./run.sh"
-endef
-
override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
+endif
-
+# SPDX-License-Identifier: GPL-2.0
INCLUDEDIR := -I.
CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
# SPDX-License-Identifier: GPL-2.0
# Runs static keys kernel module tests
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_static_key_base; then
+ echo "static_key: module test_static_key_base is not found [SKIP]"
+ exit $ksft_skip
+fi
+
+if ! /sbin/modprobe -q -n test_static_keys; then
+ echo "static_key: module test_static_keys is not found [SKIP]"
+ exit $ksft_skip
+fi
+
if /sbin/modprobe -q test_static_key_base; then
if /sbin/modprobe -q test_static_keys; then
echo "static_key: ok"
--- /dev/null
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
# This performs a series tests against the proc sysctl interface.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
TEST_NAME="sysctl"
TEST_DRIVER="test_${TEST_NAME}"
TEST_DIR=$(dirname $0)
echo "$0: $DIR not present" >&2
echo "You must have the following enabled in your kernel:" >&2
cat $TEST_DIR/config >&2
- exit 1
+ exit $ksft_skip
fi
}
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
if ! which perl 2> /dev/null > /dev/null; then
echo "$0: You need perl installed"
- exit 1
+ exit $ksft_skip
fi
if ! which getconf 2> /dev/null > /dev/null; then
echo "$0: You need getconf installed"
- exit 1
+ exit $ksft_skip
fi
if ! which diff 2> /dev/null > /dev/null; then
echo "$0: You need diff installed"
- exit 1
+ exit $ksft_skip
fi
}
function load_req_mod()
{
- trap "test_modprobe" EXIT
-
if [ ! -d $DIR ]; then
+ if ! modprobe -q -n $TEST_DRIVER; then
+ echo "$0: module $TEST_DRIVER not found [SKIP]"
+ exit $ksft_skip
+ fi
modprobe $TEST_DRIVER
if [ $? -ne 0 ]; then
exit
test_reqs
allow_user_defaults
check_production_sysctl_writes_strict
+test_modprobe
load_req_mod
trap "test_finish" EXIT
"matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*use tcindex 65535.*index 1",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000)));
if (llabs(eppm - ppm) > 1000) {
+ if (tx1.offset || tx2.offset ||
+ tx1.freq != tx2.freq || tx1.tick != tx2.tick) {
+ printf(" [SKIP]\n");
+ return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n");
+ }
printf(" [FAILED]\n");
return ksft_exit_fail();
}
# SPDX-License-Identifier: GPL-2.0
# Runs copy_to/from_user infrastructure using test_user_copy kernel module
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_user_copy; then
+ echo "user: module test_user_copy is not found [SKIP]"
+ exit $ksft_skip
+fi
if /sbin/modprobe -q test_user_copy; then
/sbin/modprobe -q -r test_user_copy
echo "user_copy: ok"
#include <unistd.h>
#include <string.h>
+#include "../kselftest.h"
+
#define MAP_SIZE 1048576
struct map_list {
printf("Either the sysctl compact_unevictable_allowed is not\n"
"set to 1 or couldn't read the proc file.\n"
"Skipping the test\n");
- return 0;
+ return KSFT_SKIP;
}
lim.rlim_cur = RLIM_INFINITY;
#include <stdbool.h>
#include "mlock2.h"
+#include "../kselftest.h"
+
struct vm_boundaries {
unsigned long start;
unsigned long end;
if (mlock2_(map, 2 * page_size, 0)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(0)");
goto unmap;
if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(MLOCK_ONFAULT)");
goto unmap;
if (munlock(map, 2 * page_size)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("munlock()");
goto unmap;
if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(MLOCK_ONFAULT)");
goto unmap;
if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock(ONFAULT)\n");
goto out;
# SPDX-License-Identifier: GPL-2.0
#please run as root
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
mnt=./huge
exitcode=0
echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
if [ $? -ne 0 ]; then
echo "Please run this test as root"
- exit 1
+ exit $ksft_skip
fi
while read name size unit; do
if [ "$name" = "HugePages_Free:" ]; then
#include <setjmp.h>
#include <stdbool.h>
+#include "../kselftest.h"
+
#ifdef __NR_userfaultfd
static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
int main(void)
{
printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
- return 0;
+ return KSFT_SKIP;
}
#endif /* __NR_userfaultfd */
*/
for (int i = 0; i < NGREG; i++) {
greg_t req = requested_regs[i], res = resulting_regs[i];
+
if (i == REG_TRAPNO || i == REG_IP)
continue; /* don't care */
- if (i == REG_SP) {
- printf("\tSP: %llx -> %llx\n", (unsigned long long)req,
- (unsigned long long)res);
+ if (i == REG_SP) {
/*
- * In many circumstances, the high 32 bits of rsp
- * are zeroed. For example, we could be a real
- * 32-bit program, or we could hit any of a number
- * of poorly-documented IRET or segmented ESP
- * oddities. If this happens, it's okay.
+ * If we were using a 16-bit stack segment, then
+ * the kernel is a bit stuck: IRET only restores
+ * the low 16 bits of ESP/RSP if SS is 16-bit.
+ * The kernel uses a hack to restore bits 31:16,
+ * but that hack doesn't help with bits 63:32.
+ * On Intel CPUs, bits 63:32 end up zeroed, and, on
+ * AMD CPUs, they leak the high bits of the kernel
+ * espfix64 stack pointer. There's very little that
+ * the kernel can do about it.
+ *
+ * Similarly, if we are returning to a 32-bit context,
+ * the CPU will often lose the high 32 bits of RSP.
*/
- if (res == (req & 0xFFFFFFFF))
- continue; /* OK; not expected to work */
+
+ if (res == req)
+ continue;
+
+ if (cs_bits != 64 && ((res ^ req) & 0xFFFFFFFF) == 0) {
+ printf("[NOTE]\tSP: %llx -> %llx\n",
+ (unsigned long long)req,
+ (unsigned long long)res);
+ continue;
+ }
+
+ printf("[FAIL]\tSP mismatch: requested 0x%llx; got 0x%llx\n",
+ (unsigned long long)requested_regs[i],
+ (unsigned long long)resulting_regs[i]);
+ nerrs++;
+ continue;
}
bool ignore_reg = false;
#endif
/* Sanity check on the kernel */
- if (i == REG_CX && requested_regs[i] != resulting_regs[i]) {
+ if (i == REG_CX && req != res) {
printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
- (unsigned long long)requested_regs[i],
- (unsigned long long)resulting_regs[i]);
+ (unsigned long long)req,
+ (unsigned long long)res);
nerrs++;
continue;
}
- if (requested_regs[i] != resulting_regs[i] && !ignore_reg) {
- /*
- * SP is particularly interesting here. The
- * usual cause of failures is that we hit the
- * nasty IRET case of returning to a 16-bit SS,
- * in which case bits 16:31 of the *kernel*
- * stack pointer persist in ESP.
- */
+ if (req != res && !ignore_reg) {
printf("[FAIL]\tReg %d mismatch: requested 0x%llx; got 0x%llx\n",
- i, (unsigned long long)requested_regs[i],
- (unsigned long long)resulting_regs[i]);
+ i, (unsigned long long)req,
+ (unsigned long long)res);
nerrs++;
}
}
# SPDX-License-Identifier: GPL-2.0
TCID="zram.sh"
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
. ./zram_lib.sh
run_zram () {
else
echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
echo "$TCID : CONFIG_ZRAM is not set"
- exit 1
+ exit $ksft_skip
fi
dev_makeswap=-1
dev_mounted=-1
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
trap INT
check_prereqs()
if [ $uid -ne 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
}
/******************** Little Endian Handling ********************************/
-#define cpu_to_le16(x) htole16(x)
-#define cpu_to_le32(x) htole32(x)
+/*
+ * cpu_to_le16/32 are used when initializing structures, a context where a
+ * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way
+ * that allows them to be used when initializing structures.
+ */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define cpu_to_le16(x) (x)
+#define cpu_to_le32(x) (x)
+#else
+#define cpu_to_le16(x) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))
+#define cpu_to_le32(x) \
+ ((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >> 8) | \
+ (((x) & 0x0000ff00u) << 8) | (((x) & 0x000000ffu) << 24))
+#endif
+
#define le32_to_cpu(x) le32toh(x)
#define le16_to_cpu(x) le16toh(x)
-
/******************** Messages and Errors ***********************************/
static const char argv0[] = "ffs-test";
} while (0);
/* Weak barriers should be used. If not - it's a bug */
# define mb() abort()
-# define rmb() abort()
-# define wmb() abort()
+# define dma_rmb() abort()
+# define dma_wmb() abort()
#else
#error Please fill in barrier macros
#endif
return __kmalloc_fake;
return malloc(s);
}
+static inline void *kmalloc_array(unsigned n, size_t s, gfp_t gfp)
+{
+ return kmalloc(n * s, gfp);
+}
+
static inline void *kzalloc(size_t s, gfp_t gfp)
{
void *p = kmalloc(s, gfp);
*/
BUG_ON((unsigned long) page & 0x03);
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
sg->page_link = page_link | (unsigned long) page;
static inline struct page *sg_page(struct scatterlist *sg)
{
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
return (struct page *)((sg)->page_link & ~0x3);
**/
static inline void sg_mark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
/*
* Set termination bit, clear potential chain bit
*/
**/
static inline void sg_unmark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
sg->page_link &= ~0x02;
}
static inline struct scatterlist *sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
if (sg_is_last(sg))
return NULL;
static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
{
memset(sgl, 0, sizeof(*sgl) * nents);
-#ifdef CONFIG_DEBUG_SG
- {
- unsigned int i;
- for (i = 0; i < nents; i++)
- sgl[i].sg_magic = SG_MAGIC;
- }
-#endif
sg_mark_end(&sgl[nents - 1]);
}
config KVM_COMPAT
def_bool y
- depends on KVM && COMPAT && !S390
+ depends on KVM && COMPAT && !(S390 || ARM64)
config HAVE_KVM_IRQ_BYPASS
bool
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.pause = false;
- swake_up(kvm_arch_vcpu_wq(vcpu));
+ swake_up_one(kvm_arch_vcpu_wq(vcpu));
}
}
{
struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
- swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+ swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
(!vcpu->arch.pause)));
if (vcpu->arch.power_off || vcpu->arch.pause) {
phys_addr_t next;
assert_spin_locked(&kvm->mmu_lock);
+ WARN_ON(size & ~PAGE_MASK);
+
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
/*
smp_mb(); /* Make sure the above is visible */
wq = kvm_arch_vcpu_wq(vcpu);
- swake_up(wq);
+ swake_up_one(wq);
return PSCI_RET_SUCCESS;
}
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)info->vcpu.start);
kvm_vgic_global_state.vcpu_base = 0;
- } else if (!PAGE_ALIGNED(resource_size(&info->vcpu))) {
- pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
- (unsigned long long)resource_size(&info->vcpu),
- PAGE_SIZE);
- kvm_vgic_global_state.vcpu_base = 0;
} else {
kvm_vgic_global_state.vcpu_base = info->vcpu.start;
kvm_vgic_global_state.can_emulate_gicv2 = true;
trace_kvm_async_pf_completed(addr, gva);
if (swq_has_sleeper(&vcpu->wq))
- swake_up(&vcpu->wq);
+ swake_up_one(&vcpu->wq);
mmput(mm);
kvm_put_kvm(vcpu->kvm);
{
struct kvm_kernel_irqfd *irqfd =
container_of(work, struct kvm_kernel_irqfd, shutdown);
+ struct kvm *kvm = irqfd->kvm;
u64 cnt;
+ /* Make sure irqfd has been initalized in assign path. */
+ synchronize_srcu(&kvm->irq_srcu);
+
/*
* Synchronize with the wait-queue and unhook ourselves to prevent
* further events.
idx = srcu_read_lock(&kvm->irq_srcu);
irqfd_update(kvm, irqfd);
- srcu_read_unlock(&kvm->irq_srcu, idx);
list_add_tail(&irqfd->list, &kvm->irqfds.items);
if (events & EPOLLIN)
schedule_work(&irqfd->inject);
- /*
- * do not drop the file until the irqfd is fully initialized, otherwise
- * we might race against the EPOLLHUP
- */
- fdput(f);
#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
if (kvm_arch_has_irq_bypass()) {
irqfd->consumer.token = (void *)irqfd->eventfd;
}
#endif
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ /*
+ * do not drop the file until the irqfd is fully initialized, otherwise
+ * we might race against the EPOLLHUP
+ */
+ fdput(f);
return 0;
fail:
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
+#define KVM_COMPAT(c) .compat_ioctl = (c)
+#else
+static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg) { return -EINVAL; }
+#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl
#endif
static int hardware_enable_all(void);
static void hardware_disable_all(void);
kvm_arch_vcpu_blocking(vcpu);
for (;;) {
- prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_vcpu_check_block(vcpu) < 0)
break;
wqp = kvm_arch_vcpu_wq(vcpu);
if (swq_has_sleeper(wqp)) {
- swake_up(wqp);
+ swake_up_one(wqp);
++vcpu->stat.halt_wakeup;
return true;
}
static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vcpu_compat_ioctl,
-#endif
.mmap = kvm_vcpu_mmap,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vcpu_compat_ioctl),
};
/*
static const struct file_operations kvm_device_fops = {
.unlocked_ioctl = kvm_device_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_device_ioctl,
-#endif
.release = kvm_device_release,
+ KVM_COMPAT(kvm_device_ioctl),
};
struct kvm_device *kvm_device_from_filp(struct file *filp)
static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vm_compat_ioctl,
-#endif
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vm_compat_ioctl),
};
static int kvm_dev_ioctl_create_vm(unsigned long type)
static struct file_operations kvm_chardev_ops = {
.unlocked_ioctl = kvm_dev_ioctl,
- .compat_ioctl = kvm_dev_ioctl,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_dev_ioctl),
};
static struct miscdevice kvm_dev = {
projects / linux-2.6-microblaze.git / commitdiff
