/include/ksym/
/arch/*/include/generated/
+# Generated lkdtm tests
+/tools/testing/selftests/lkdtm/*.sh
+!/tools/testing/selftests/lkdtm/run.sh
+
# stgit generated dirs
patches-*
Documentation/process/license-rules.rst
for more details.
+
+All contributions to the Linux Kernel are subject to this COPYING file.
S: Orlando, Florida
S: USA
+N: Paul Burton
+E: paulburton@kernel.org
+W: https://pburton.com
+D: MIPS maintainer 2018-2020
+
N: Lennert Buytenhek
E: kernel@wantstofly.org
D: Original (2.4) rewrite of the ethernet bridging code
In both styles, same key words are automatically merged when parsing it
at boot time. So you can append similar trees or key-values.
+Same-key Values
+---------------
+
+It is prohibited that two or more values or arrays share a same-key.
+For example,::
+
+ foo = bar, baz
+ foo = qux # !ERROR! we can not re-define same key
+
+If you want to append the value to existing key as an array member,
+you can use ``+=`` operator. For example::
+
+ foo = bar, baz
+ foo += qux
+
+In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``.
+
+However, a sub-key and a value can not co-exist under a parent key.
+For example, following config is NOT allowed.::
+
+ foo = value1
+ foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist
+
+
Comments
--------
==============================
Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file. The Linux kernel decodes
-the last part of the initrd image in memory to get the boot configuration
-data.
+to the end of the initrd (initramfs) image file with size, checksum and
+12-byte magic word as below.
+
+[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+
+The Linux kernel decodes the last part of the initrd image in memory to
+get the boot configuration data.
Because of this "piggyback" method, there is no need to change or
update the boot loader and the kernel image itself.
dynamic table installation which will install SSDT
tables to /sys/firmware/acpi/tables/dynamic.
+ acpi_no_watchdog [HW,ACPI,WDT]
+ Ignore the ACPI-based watchdog interface (WDAT) and let
+ a native driver control the watchdog device instead.
+
acpi_rsdp= [ACPI,EFI,KEXEC]
Pass the RSDP address to the kernel, mostly used
on machines running EFI runtime service to boot the
incurs a small amount of overhead in the scheduler
but is useful for debugging and performance tuning.
+ sched_thermal_decay_shift=
+ [KNL, SMP] Set a decay shift for scheduler thermal
+ pressure signal. Thermal pressure signal follows the
+ default decay period of other scheduler pelt
+ signals(usually 32 ms but configurable). Setting
+ sched_thermal_decay_shift will left shift the decay
+ period for the thermal pressure signal by the shift
+ value.
+ i.e. with the default pelt decay period of 32 ms
+ sched_thermal_decay_shift thermal pressure decay pr
+ 1 64 ms
+ 2 128 ms
+ and so on.
+ Format: integer between 0 and 10
+ Default is 0.
+
skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
xtime_lock contention on larger systems, and/or RCU lock
contention on all systems with CONFIG_MAXSMP set.
As a single binary will need to support both 48-bit and 52-bit VA
spaces, the VMEMMAP must be sized large enough for 52-bit VAs and
-also must be sized large enought to accommodate a fixed PAGE_OFFSET.
+also must be sized large enough to accommodate a fixed PAGE_OFFSET.
Most code in the kernel should not need to consider the VA_BITS, for
code that does need to know the VA size the variables are
how the user addresses are used by the kernel:
1. User addresses not accessed by the kernel but used for address space
- management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use
- of valid tagged pointers in this context is always allowed.
+ management (e.g. ``mprotect()``, ``madvise()``). The use of valid
+ tagged pointers in this context is allowed with the exception of
+ ``brk()``, ``mmap()`` and the ``new_address`` argument to
+ ``mremap()`` as these have the potential to alias with existing
+ user addresses.
+
+ NOTE: This behaviour changed in v5.6 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for the ``brk()``,
+ ``mmap()`` and ``mremap()`` system calls.
2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
relaxation is disabled by default and the application thread needs to
Once the kernel is built and installed, a simple
.. code-block:: bash
+
modprobe example-test
...will run the tests.
- enum:
- allwinner,sun8i-h3-tcon-tv
- allwinner,sun50i-a64-tcon-tv
- - allwinner,sun50i-h6-tcon-tv
- const: allwinner,sun8i-a83t-tcon-tv
+ - items:
+ - enum:
+ - allwinner,sun50i-h6-tcon-tv
+ - const: allwinner,sun8i-r40-tcon-tv
+
reg:
maxItems: 1
maxItems: 1
clocks:
- minItems: 2
- maxItems: 3
- items:
- - description: The CSI interface clock
- - description: The CSI ISP clock
- - description: The CSI DRAM clock
+ oneOf:
+ - items:
+ - description: The CSI interface clock
+ - description: The CSI DRAM clock
+
+ - items:
+ - description: The CSI interface clock
+ - description: The CSI ISP clock
+ - description: The CSI DRAM clock
clock-names:
- minItems: 2
- maxItems: 3
- items:
- - const: bus
- - const: isp
- - const: ram
+ oneOf:
+ - items:
+ - const: bus
+ - const: ram
+
+ - items:
+ - const: bus
+ - const: isp
+ - const: ram
resets:
maxItems: 1
+ # FIXME: This should be made required eventually once every SoC will
+ # have the MBUS declared.
+ interconnects:
+ maxItems: 1
+
+ # FIXME: This should be made required eventually once every SoC will
+ # have the MBUS declared.
+ interconnect-names:
+ const: dma-mem
+
# See ./video-interfaces.txt for details
port:
type: object
interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
#iommu-cells = <1>;
+ #reset-cells = <1>;
};
external-memory-controller@7001b000 {
timing-0 {
clock-frequency = <12750000>;
- nvidia,emc-zcal-cnt-long = <0x00000042>;
- nvidia,emc-auto-cal-interval = <0x001fffff>;
- nvidia,emc-ctt-term-ctrl = <0x00000802>;
- nvidia,emc-cfg = <0x73240000>;
- nvidia,emc-cfg-2 = <0x000008c5>;
- nvidia,emc-sel-dpd-ctrl = <0x00040128>;
- nvidia,emc-bgbias-ctl0 = <0x00000008>;
nvidia,emc-auto-cal-config = <0xa1430000>;
nvidia,emc-auto-cal-config2 = <0x00000000>;
nvidia,emc-auto-cal-config3 = <0x00000000>;
- nvidia,emc-mode-reset = <0x80001221>;
+ nvidia,emc-auto-cal-interval = <0x001fffff>;
+ nvidia,emc-bgbias-ctl0 = <0x00000008>;
+ nvidia,emc-cfg = <0x73240000>;
+ nvidia,emc-cfg-2 = <0x000008c5>;
+ nvidia,emc-ctt-term-ctrl = <0x00000802>;
nvidia,emc-mode-1 = <0x80100003>;
nvidia,emc-mode-2 = <0x80200008>;
nvidia,emc-mode-4 = <0x00000000>;
+ nvidia,emc-mode-reset = <0x80001221>;
+ nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+ nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+ nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+ nvidia,emc-zcal-cnt-long = <0x00000042>;
+ nvidia,emc-zcal-interval = <0x00000000>;
nvidia,emc-configuration = <
0x00000000 /* EMC_RC */
pinctrl-1 = <&mmc1_idle>;
pinctrl-2 = <&mmc1_sleep>;
...
- interrupts-extended = <&intc 64 &gpio2 28 GPIO_ACTIVE_LOW>;
+ interrupts-extended = <&intc 64 &gpio2 28 IRQ_TYPE_LEVEL_LOW>;
};
mmc1_idle : pinmux_cirq_pin {
examples:
- |
davinci_mdio: mdio@5c030000 {
- compatible = "ti,davinci_mdio";
reg = <0x5c030000 0x1000>;
#address-cells = <1>;
#size-cells = <0>;
end, that is, write operations can only be append writes. Zonefs makes no
attempt at accepting random writes and will fail any write request that has a
start offset not corresponding to the end of the file, or to the end of the last
-write issued and still in-flight (for asynchrnous I/O operations).
+write issued and still in-flight (for asynchronous I/O operations).
Since dirty page writeback by the page cache does not guarantee a sequential
write pattern, zonefs prevents buffered writes and writeable shared mappings
zonefs relies on the sequential delivery of write I/O requests to the device
implemented by the block layer elevator. An elevator implementing the sequential
write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature)
-must be used. This type of elevator (e.g. mq-deadline) is the set by default
+must be used. This type of elevator (e.g. mq-deadline) is set by default
for zoned block devices on device initialization.
There are no restrictions on the type of I/O used for read operations in
may still happen in the case of a partial failure of a very large direct I/O
operation split into multiple BIOs/requests or asynchronous I/O operations.
If one of the write request within the set of sequential write requests
- issued to the device fails, all write requests after queued after it will
+ issued to the device fails, all write requests queued after it will
become unaligned and fail.
* Delayed write errors: similarly to regular block devices, if the device side
causing all data to be dropped after the sector that caused the error.
All I/O errors detected by zonefs are notified to the user with an error code
-return for the system call that trigered or detected the error. The recovery
+return for the system call that triggered or detected the error. The recovery
actions taken by zonefs in response to I/O errors depend on the I/O type (read
vs write) and on the reason for the error (bad sector, unaligned writes or zone
condition change).
* A zone condition change to read-only or offline also always triggers zonefs
I/O error recovery.
-Zonefs minimal I/O error recovery may change a file size and a file access
+Zonefs minimal I/O error recovery may change a file size and file access
permissions.
* File size changes:
A file size may also be reduced to reflect a delayed write error detected on
fsync(): in this case, the amount of data effectively written in the zone may
be less than originally indicated by the file inode size. After such I/O
- error, zonefs always fixes a file inode size to reflect the amount of data
+ error, zonefs always fixes the file inode size to reflect the amount of data
persistently stored in the file zone.
* Access permission changes:
permissions to read-only applies to all files. The file system is remounted
read-only.
* Access permission and file size changes due to the device transitioning zones
- to the offline condition are permanent. Remounting or reformating the device
+ to the offline condition are permanent. Remounting or reformatting the device
with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good
state.
* File access permission changes to read-only due to the device transitioning
- zones to the read-only condition are permanent. Remounting or reformating
+ zones to the read-only condition are permanent. Remounting or reformatting
the device will not re-enable file write access.
* File access permission changes implied by the remount-ro, zone-ro and
zone-offline mount options are temporary for zones in a good condition.
zonefs define the "errors=<behavior>" mount option to allow the user to specify
zonefs behavior in response to I/O errors, inode size inconsistencies or zone
-condition chages. The defined behaviors are as follow:
+condition changes. The defined behaviors are as follow:
* remount-ro (default)
* zone-ro
* zone-offline
* repair
-The I/O error actions defined for each behavior is detailed in the previous
+The I/O error actions defined for each behavior are detailed in the previous
section.
Zonefs User Space Tools
dual loop voltage regulators.
The family includes XDPE12284 and XDPE12254 devices.
The devices from this family complaint with:
+
- Intel VR13 and VR13HC rev 1.3, IMVP8 rev 1.2 and IMPVP9 rev 1.3 DC-DC
converter specification.
- Intel SVID rev 1.9. protocol.
Example::
#arch/x86/boot/Makefile
- subdir- := compressed/
+ subdir- := compressed
The above assignment instructs kbuild to descend down in the
directory compressed/ when "make clean" is executed.
in arch/$(ARCH)/include/(uapi/)/asm, Kbuild will automatically generate
a wrapper of the asm-generic one.
- The convention is to list one subdir per line and
- preferably in alphabetic order.
-
8 Kbuild Variables
==================
The stubs set one of the two matching criteria, and set the other one to
match anything.
-When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module,
-unregister fixup and free allocate memory are required.
+When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module load
+time, the module needs to unregister the fixup and free allocated memory when
+it's unloaded.
Call one of following function before unloading module::
drivers-testing
energy-model
freezing-of-tasks
- interface
opp
pci
pm_qos_interface
an involved disclosed party. The current ambassadors list:
============= ========================================================
- ARM
+ ARM Grant Likely <grant.likely@arm.com>
AMD Tom Lendacky <tom.lendacky@amd.com>
IBM
Intel Tony Luck <tony.luck@intel.com>
Qualcomm Trilok Soni <tsoni@codeaurora.org>
- Microsoft Sasha Levin <sashal@kernel.org>
+ Microsoft James Morris <jamorris@linux.microsoft.com>
VMware
Xen Andrew Cooper <andrew.cooper3@citrix.com>
- Canonical Tyler Hicks <tyhicks@canonical.com>
+ Canonical John Johansen <john.johansen@canonical.com>
Debian Ben Hutchings <ben@decadent.org.uk>
Oracle Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Red Hat Josh Poimboeuf <jpoimboe@redhat.com>
SUSE Jiri Kosina <jkosina@suse.cz>
- Amazon Peter Bowen <pzb@amzn.com>
+ Amazon
Google Kees Cook <keescook@chromium.org>
============= ========================================================
address of the associated 'lock entry', plus or minus, of what will
be called the 'lock word', from that 'lock entry'. The 'lock word'
is always a 32 bit word, unlike the other words above. The 'lock
- word' holds 3 flag bits in the upper 3 bits, and the thread id (TID)
- of the thread holding the lock in the bottom 29 bits. See further
+ word' holds 2 flag bits in the upper 2 bits, and the thread id (TID)
+ of the thread holding the lock in the bottom 30 bits. See further
below for a description of the flag bits.
The third word, called 'list_op_pending', contains transient copy of
A given futex lock structure in a user shared memory region may be held
at different times by any of the threads with access to that region. The
thread currently holding such a lock, if any, is marked with the threads
-TID in the lower 29 bits of the 'lock word'.
+TID in the lower 30 bits of the 'lock word'.
When adding or removing a lock from its list of held locks, in order for
the kernel to correctly handle lock cleanup regardless of when the task
1) set the 'list_op_pending' word to the address of the 'lock entry'
to be inserted,
2) acquire the futex lock,
- 3) add the lock entry, with its thread id (TID) in the bottom 29 bits
+ 3) add the lock entry, with its thread id (TID) in the bottom 30 bits
of the 'lock word', to the linked list starting at 'head', and
4) clear the 'list_op_pending' word.
On exit, the kernel will consider the address stored in
'list_op_pending' and the address of each 'lock word' found by walking
-the list starting at 'head'. For each such address, if the bottom 29
+the list starting at 'head'. For each such address, if the bottom 30
bits of the 'lock word' at offset 'offset' from that address equals the
exiting threads TID, then the kernel will do two things:
future kernel configuration changes) elements.
When the kernel sees a list entry whose 'lock word' doesn't have the
-current threads TID in the lower 29 bits, it does nothing with that
+current threads TID in the lower 30 bits, it does nothing with that
entry, and goes on to the next entry.
-
-Bit 29 (0x20000000) of the 'lock word' is reserved for future use.
parallel="-j$parallel"
fi
-exec "$sphinx" "$parallel" "$@"
+exec "$sphinx" $parallel "$@"
VMware
Xen Andrew Cooper <andrew.cooper3@citrix.com>
- Canonical Tyler Hicks <tyhicks@canonical.com>
+ Canonical John Johansen <john.johansen@canonical.com>
Debian Ben Hutchings <ben@decadent.org.uk>
Oracle Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Red Hat Josh Poimboeuf <jpoimboe@redhat.com>
track the secure pages by hypervisor.
4.122 KVM_S390_NORMAL_RESET
+---------------------------
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the cpu reset definition in the POP (Principles Of Operation).
4.123 KVM_S390_INITIAL_RESET
+----------------------------
-Capability: none
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: none
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the initial cpu reset definition in the POP. However, the cpu is not
put into ESA mode. This reset is a superset of the normal reset.
4.124 KVM_S390_CLEAR_RESET
+--------------------------
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the clear cpu reset definition in the POP. However, the cpu is not put
tlb
mtrr
pat
- intel_mpx
intel-iommu
intel_txt
amd-memory-encryption
C-SKY ARCHITECTURE
M: Guo Ren <guoren@kernel.org>
+L: linux-csky@vger.kernel.org
T: git https://github.com/c-sky/csky-linux.git
S: Supported
F: arch/csky/
F: Documentation/filesystems/ceph.txt
F: fs/ceph/
-CERTIFICATE HANDLING:
+CERTIFICATE HANDLING
M: David Howells <dhowells@redhat.com>
M: David Woodhouse <dwmw2@infradead.org>
L: keyrings@vger.kernel.org
F: scripts/sign-file.c
F: scripts/extract-cert.c
-CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
+CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM
L: devel@driverdev.osuosl.org
S: Obsolete
F: drivers/staging/wusbcore/
F: drivers/media/dvb-frontends/ec100*
ECRYPT FILE SYSTEM
-M: Tyler Hicks <tyhicks@canonical.com>
+M: Tyler Hicks <code@tyhicks.com>
L: ecryptfs@vger.kernel.org
W: http://ecryptfs.org
W: https://launchpad.net/ecryptfs
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs.git
-S: Supported
+S: Odd Fixes
F: Documentation/filesystems/ecryptfs.txt
F: fs/ecryptfs/
S: Supported
F: drivers/uio/uio_pci_generic.c
-GENERIC VDSO LIBRARY:
+GENERIC VDSO LIBRARY
M: Andy Lutomirski <luto@kernel.org>
M: Thomas Gleixner <tglx@linutronix.de>
M: Vincenzo Frascino <vincenzo.frascino@arm.com>
M: Rodrigo Vivi <rodrigo.vivi@intel.com>
L: intel-gfx@lists.freedesktop.org
W: https://01.org/linuxgraphics/
-B: https://01.org/linuxgraphics/documentation/how-report-bugs
+B: https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
C: irc://chat.freenode.net/intel-gfx
Q: http://patchwork.freedesktop.org/project/intel-gfx/
T: git git://anongit.freedesktop.org/drm-intel
F: security/keys/trusted.c
F: include/keys/trusted.h
-KEYS/KEYRINGS:
+KEYS/KEYRINGS
M: David Howells <dhowells@redhat.com>
M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
L: keyrings@vger.kernel.org
F: drivers/usb/image/microtek.*
MIPS
-M: Ralf Baechle <ralf@linux-mips.org>
-M: Paul Burton <paulburton@kernel.org>
+M: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
L: linux-mips@vger.kernel.org
W: http://www.linux-mips.org/
-T: git git://git.linux-mips.org/pub/scm/ralf/linux.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git
Q: http://patchwork.linux-mips.org/project/linux-mips/list/
-S: Supported
+S: Maintained
F: Documentation/devicetree/bindings/mips/
F: Documentation/mips/
F: arch/mips/
F: drivers/scsi/sun3_scsi.*
F: drivers/scsi/sun3_scsi_vme.c
-NCSI LIBRARY:
+NCSI LIBRARY
M: Samuel Mendoza-Jonas <sam@mendozajonas.com>
S: Maintained
F: net/ncsi/
L: linux-pci@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/pci/cdns,*.txt
-F: drivers/pci/controller/pcie-cadence*
+F: drivers/pci/controller/cadence/
PCI DRIVER FOR FREESCALE LAYERSCAPE
M: Minghuan Lian <minghuan.Lian@nxp.com>
S: Maintained
F: drivers/block/ps3vram.c
-PSAMPLE PACKET SAMPLING SUPPORT:
+PSAMPLE PACKET SAMPLING SUPPORT
M: Yotam Gigi <yotam.gi@gmail.com>
S: Maintained
F: net/psample
F: include/net/psample.h
F: include/uapi/linux/psample.h
+PRESSURE STALL INFORMATION (PSI)
+M: Johannes Weiner <hannes@cmpxchg.org>
+S: Maintained
+F: kernel/sched/psi.c
+F: include/linux/psi*
+
PSTORE FILESYSTEM
M: Kees Cook <keescook@chromium.org>
M: Anton Vorontsov <anton@enomsg.org>
F: include/media/drv-intf/saa7146*
SAFESETID SECURITY MODULE
-M: Micah Morton <mortonm@chromium.org>
-S: Supported
-F: security/safesetid/
-F: Documentation/admin-guide/LSM/SafeSetID.rst
+M: Micah Morton <mortonm@chromium.org>
+S: Supported
+F: security/safesetid/
+F: Documentation/admin-guide/LSM/SafeSetID.rst
SAMSUNG AUDIO (ASoC) DRIVERS
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Mika Westerberg <mika.westerberg@linux.intel.com>
M: Yehezkel Bernat <YehezkelShB@gmail.com>
L: linux-usb@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
F: Documentation/admin-guide/thunderbolt.rst
F: drivers/thunderbolt/
F: include/linux/thunderbolt.h
F: Documentation/admin-guide/ufs.rst
F: fs/ufs/
-UHID USERSPACE HID IO DRIVER:
+UHID USERSPACE HID IO DRIVER
M: David Herrmann <dh.herrmann@googlemail.com>
L: linux-input@vger.kernel.org
S: Maintained
F: drivers/usb/common/ulpi.c
F: include/linux/ulpi/
-ULTRA-WIDEBAND (UWB) SUBSYSTEM:
+ULTRA-WIDEBAND (UWB) SUBSYSTEM
L: devel@driverdev.osuosl.org
S: Obsolete
F: drivers/staging/uwb/
-UNICODE SUBSYSTEM:
+UNICODE SUBSYSTEM
M: Gabriel Krisman Bertazi <krisman@collabora.com>
L: linux-fsdevel@vger.kernel.org
S: Supported
F: fs/unicode/
-UNICORE32 ARCHITECTURE:
+UNICORE32 ARCHITECTURE
M: Guan Xuetao <gxt@pku.edu.cn>
W: http://mprc.pku.edu.cn/~guanxuetao/linux
S: Maintained
F: include/linux/usb.h
F: include/linux/usb/
-USB TYPEC PI3USB30532 MUX DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+USB TYPEC BUS FOR ALTERNATE MODES
+M: Heikki Krogerus <heikki.krogerus@linux.intel.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: drivers/usb/typec/mux/pi3usb30532.c
+F: Documentation/ABI/testing/sysfs-bus-typec
+F: Documentation/driver-api/usb/typec_bus.rst
+F: drivers/usb/typec/altmodes/
+F: include/linux/usb/typec_altmode.h
USB TYPEC CLASS
M: Heikki Krogerus <heikki.krogerus@linux.intel.com>
F: drivers/usb/typec/
F: include/linux/usb/typec.h
-USB TYPEC BUS FOR ALTERNATE MODES
-M: Heikki Krogerus <heikki.krogerus@linux.intel.com>
+USB TYPEC PI3USB30532 MUX DRIVER
+M: Hans de Goede <hdegoede@redhat.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: Documentation/ABI/testing/sysfs-bus-typec
-F: Documentation/driver-api/usb/typec_bus.rst
-F: drivers/usb/typec/altmodes/
-F: include/linux/usb/typec_altmode.h
+F: drivers/usb/typec/mux/pi3usb30532.c
USB TYPEC PORT CONTROLLER DRIVERS
M: Guenter Roeck <linux@roeck-us.net>
F: include/uapi/linux/vbox*.h
F: drivers/virt/vboxguest/
-VIRTUAL BOX SHARED FOLDER VFS DRIVER:
+VIRTUAL BOX SHARED FOLDER VFS DRIVER
M: Hans de Goede <hdegoede@redhat.com>
L: linux-fsdevel@vger.kernel.org
S: Maintained
VERSION = 5
PATCHLEVEL = 6
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
#
# If KBUILD_VERBOSE equals 0 then the above command will be hidden.
# If KBUILD_VERBOSE equals 1 then the above command is displayed.
+# If KBUILD_VERBOSE equals 2 then give the reason why each target is rebuilt.
#
# To put more focus on warnings, be less verbose as default
# Use 'make V=1' to see the full commands
%.dtb: include/config/kernel.release scripts_dtc
$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
-PHONY += dtbs dtbs_install dt_binding_check
+PHONY += dtbs dtbs_install dtbs_check
dtbs dtbs_check: include/config/kernel.release scripts_dtc
$(Q)$(MAKE) $(build)=$(dtstree)
scripts_dtc: scripts_basic
$(Q)$(MAKE) $(build)=scripts/dtc
+PHONY += dt_binding_check
dt_binding_check: scripts_dtc
$(Q)$(MAKE) $(build)=Documentation/devicetree/bindings
static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
-static inline void kvm_arm_vhe_guest_enter(void) {}
-static inline void kvm_arm_vhe_guest_exit(void) {}
-
#define KVM_BP_HARDEN_UNKNOWN -1
#define KVM_BP_HARDEN_WA_NEEDED 0
#define KVM_BP_HARDEN_NOT_REQUIRED 1
/* Enable topology flag updates */
#define arch_update_cpu_topology topology_update_cpu_topology
+/* Replace task scheduler's default thermal pressure retrieve API */
+#define arch_scale_thermal_pressure topology_get_thermal_pressure
+
#else
static inline void init_cpu_topology(void) { }
CONFIG_ARCH_ZYNQMP=y
CONFIG_ARM64_VA_BITS_48=y
CONFIG_SCHED_MC=y
+CONFIG_SCHED_SMT=y
CONFIG_NUMA=y
CONFIG_SECCOMP=y
CONFIG_KEXEC=y
isb();
}
-static inline void gic_write_dir(u32 irq)
+static __always_inline void gic_write_dir(u32 irq)
{
write_sysreg_s(irq, SYS_ICC_DIR_EL1);
isb();
return test_bit(ICACHEF_ALIASING, &__icache_flags);
}
-static inline int icache_is_vpipt(void)
+static __always_inline int icache_is_vpipt(void)
{
return test_bit(ICACHEF_VPIPT, &__icache_flags);
}
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
-static inline void __flush_icache_all(void)
+static __always_inline void __flush_icache_all(void)
{
if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
return;
return cpuid_feature_extract_signed_field_width(features, field, 4);
}
-static inline unsigned int __attribute_const__
+static __always_inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
{
return (u64)(features << (64 - width - field)) >> (64 - width);
}
-static inline unsigned int __attribute_const__
+static __always_inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field(u64 features, int field)
{
return cpuid_feature_extract_unsigned_field_width(features, field, 4);
return val == 0x1;
}
-static inline bool system_supports_fpsimd(void)
+static __always_inline bool system_supports_fpsimd(void)
{
return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
}
!cpus_have_const_cap(ARM64_HAS_PAN);
}
-static inline bool system_supports_sve(void)
+static __always_inline bool system_supports_sve(void)
{
return IS_ENABLED(CONFIG_ARM64_SVE) &&
cpus_have_const_cap(ARM64_SVE);
}
-static inline bool system_supports_cnp(void)
+static __always_inline bool system_supports_cnp(void)
{
return IS_ENABLED(CONFIG_ARM64_CNP) &&
cpus_have_const_cap(ARM64_HAS_CNP);
}
#define __raw_writel __raw_writel
-static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
{
asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
}
}
#define __raw_readl __raw_readl
-static inline u32 __raw_readl(const volatile void __iomem *addr)
+static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
{
u32 val;
asm volatile(ALTERNATIVE("ldr %w0, [%1]",
void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr);
void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr);
-static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.hcr_el2 & HCR_RW);
}
vcpu->arch.vsesr_el2 = vsesr;
}
-static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
+static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
{
return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
}
*__vcpu_elr_el1(vcpu) = v;
}
-static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
+static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
{
return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
}
-static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
+static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
{
return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT);
}
-static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
{
if (vcpu_mode_is_32bit(vcpu))
return kvm_condition_valid32(vcpu);
* coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
* AArch32 with banked registers.
*/
-static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
u8 reg_num)
{
return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
}
-static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
unsigned long val)
{
if (reg_num != 31)
return mode != PSR_MODE_EL0t;
}
-static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
+static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
{
return vcpu->arch.fault.esr_el2;
}
-static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
+static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
{
u32 esr = kvm_vcpu_get_hsr(vcpu);
return -1;
}
-static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu)
+static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu)
{
return vcpu->arch.fault.far_el2;
}
-static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
+static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
{
return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
}
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
}
-static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
}
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
}
-static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
+static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
{
return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
}
-static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
}
-static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
}
-static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
+static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
{
return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
}
/* This one is not specific to Data Abort */
-static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL);
}
-static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
+static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
{
return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
}
return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
}
-static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
+static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
{
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
}
-static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
{
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
}
-static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
{
switch (kvm_vcpu_trap_get_fault(vcpu)) {
case FSC_SEA:
}
}
-static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
+static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
{
u32 esr = kvm_vcpu_get_hsr(vcpu);
return ESR_ELx_SYS64_ISS_RT(esr);
return data; /* Leave LE untouched */
}
-static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
+static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
if (vcpu_mode_is_32bit(vcpu))
kvm_skip_instr32(vcpu, is_wide_instr);
* Skip an instruction which has been emulated at hyp while most guest sysregs
* are live.
*/
-static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
static inline void kvm_clr_pmu_events(u32 clr) {}
#endif
-static inline void kvm_arm_vhe_guest_enter(void)
-{
- local_daif_mask();
-
- /*
- * Having IRQs masked via PMR when entering the guest means the GIC
- * will not signal the CPU of interrupts of lower priority, and the
- * only way to get out will be via guest exceptions.
- * Naturally, we want to avoid this.
- *
- * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
- * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
- */
- pmr_sync();
-}
-
-static inline void kvm_arm_vhe_guest_exit(void)
-{
- /*
- * local_daif_restore() takes care to properly restore PSTATE.DAIF
- * and the GIC PMR if the host is using IRQ priorities.
- */
- local_daif_restore(DAIF_PROCCTX_NOIRQ);
-
- /*
- * When we exit from the guest we change a number of CPU configuration
- * parameters, such as traps. Make sure these changes take effect
- * before running the host or additional guests.
- */
- isb();
-}
-
#define KVM_BP_HARDEN_UNKNOWN -1
#define KVM_BP_HARDEN_WA_NEEDED 0
#define KVM_BP_HARDEN_NOT_REQUIRED 1
#define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1)
#define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1)
+/*
+ * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
+ * static inline can allow the compiler to out-of-line this. KVM always wants
+ * the macro version as its always inlined.
+ */
+#define __kvm_swab32(x) ___constant_swab32(x)
+
int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
__le32 *origptr, __le32 *updptr, int nr_inst);
void kvm_compute_layout(void);
-static inline unsigned long __kern_hyp_va(unsigned long v)
+static __always_inline unsigned long __kern_hyp_va(unsigned long v)
{
asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
"ror %0, %0, #1\n"
extern void *__kvm_bp_vect_base;
extern int __kvm_harden_el2_vector_slot;
+/* This is only called on a VHE system */
static inline void *kvm_get_hyp_vector(void)
{
struct bp_hardening_data *data = arm64_get_bp_hardening_data();
#ifdef CONFIG_ARM64_LSE_ATOMICS
-#define __LSE_PREAMBLE ".arch armv8-a+lse\n"
+#define __LSE_PREAMBLE ".arch_extension lse\n"
#include <linux/compiler_types.h>
#include <linux/export.h>
((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
#define untagged_addr(addr) ({ \
- u64 __addr = (__force u64)addr; \
+ u64 __addr = (__force u64)(addr); \
__addr &= __untagged_addr(__addr); \
(__force __typeof__(addr))__addr; \
})
/* Enable topology flag updates */
#define arch_update_cpu_topology topology_update_cpu_topology
+/* Replace task scheduler's default thermal pressure retrieve API */
+#define arch_scale_thermal_pressure topology_get_thermal_pressure
+
#include <asm-generic/topology.h>
#endif /* _ASM_ARM_TOPOLOGY_H */
return read_sysreg(CurrentEL) == CurrentEL_EL2;
}
-static inline bool has_vhe(void)
+static __always_inline bool has_vhe(void)
{
if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN))
return true;
}
/* Switch to the guest for VHE systems running in EL2 */
-int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
return exit_code;
}
-NOKPROBE_SYMBOL(kvm_vcpu_run_vhe);
+NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
+
+int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ local_daif_mask();
+
+ /*
+ * Having IRQs masked via PMR when entering the guest means the GIC
+ * will not signal the CPU of interrupts of lower priority, and the
+ * only way to get out will be via guest exceptions.
+ * Naturally, we want to avoid this.
+ *
+ * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
+ * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
+ */
+ pmr_sync();
+
+ ret = __kvm_vcpu_run_vhe(vcpu);
+
+ /*
+ * local_daif_restore() takes care to properly restore PSTATE.DAIF
+ * and the GIC PMR if the host is using IRQ priorities.
+ */
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+ /*
+ * When we exit from the guest we change a number of CPU configuration
+ * parameters, such as traps. Make sure these changes take effect
+ * before running the host or additional guests.
+ */
+ isb();
+
+ return ret;
+}
/* Switch to the guest for legacy non-VHE systems */
int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
u32 data = vcpu_get_reg(vcpu, rd);
if (__is_be(vcpu)) {
/* guest pre-swabbed data, undo this for writel() */
- data = swab32(data);
+ data = __kvm_swab32(data);
}
writel_relaxed(data, addr);
} else {
u32 data = readl_relaxed(addr);
if (__is_be(vcpu)) {
/* guest expects swabbed data */
- data = swab32(data);
+ data = __kvm_swab32(data);
}
vcpu_set_reg(vcpu, rd, data);
}
select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2
select COMMON_CLK
select CLKSRC_MMIO
- select CLKSRC_OF
select CSKY_MPINTC if CPU_CK860
select CSKY_MP_TIMER if CPU_CK860
select CSKY_APB_INTC
select GX6605S_TIMER if CPU_CK610
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_COPY_THREAD_TLS
select HAVE_DYNAMIC_FTRACE
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_PERF_EVENTS
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
+ select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select MAY_HAVE_SPARSE_IRQ
select MODULES_USE_ELF_RELA if MODULES
select TIMER_OF
select USB_ARCH_HAS_EHCI
select USB_ARCH_HAS_OHCI
+ select GENERIC_PCI_IOMAP
+ select HAVE_PCI
+ select PCI_DOMAINS_GENERIC if PCI
+ select PCI_SYSCALL if PCI
+ select PCI_MSI if PCI
config CPU_HAS_CACHEV2
bool
config CPU_HAS_LDSTEX
bool
help
- For SMP, CPU needs "ldex&stex" instrcutions to atomic operations.
+ For SMP, CPU needs "ldex&stex" instructions for atomic operations.
config CPU_NEED_TLBSYNC
bool
bool "stop"
endchoice
+menuconfig HAVE_TCM
+ bool "Tightly-Coupled/Sram Memory"
+ select GENERIC_ALLOCATOR
+ help
+ The implementation are not only used by TCM (Tightly-Coupled Meory)
+ but also used by sram on SOC bus. It follow existed linux tcm
+ software interface, so that old tcm application codes could be
+ re-used directly.
+
+if HAVE_TCM
+config ITCM_RAM_BASE
+ hex "ITCM ram base"
+ default 0xffffffff
+
+config ITCM_NR_PAGES
+ int "Page count of ITCM size: NR*4KB"
+ range 1 256
+ default 32
+
+config HAVE_DTCM
+ bool "DTCM Support"
+
+config DTCM_RAM_BASE
+ hex "DTCM ram base"
+ depends on HAVE_DTCM
+ default 0xffffffff
+
+config DTCM_NR_PAGES
+ int "Page count of DTCM size: NR*4KB"
+ depends on HAVE_DTCM
+ range 1 256
+ default 32
+endif
+
config CPU_HAS_VDSP
bool "CPU has VDSP coprocessor"
depends on CPU_HAS_FPU && CPU_HAS_FPUV2
bool "CPU has FPU coprocessor"
depends on CPU_CK807 || CPU_CK810 || CPU_CK860
+config CPU_HAS_ICACHE_INS
+ bool "CPU has Icache invalidate instructions"
+ depends on CPU_HAS_CACHEV2
+
config CPU_HAS_TEE
bool "CPU has Trusted Execution Environment"
depends on CPU_CK810
Say N if you want to disable CPU hotplug.
endmenu
+source "arch/csky/Kconfig.platforms"
+
source "kernel/Kconfig.hz"
--- /dev/null
+menu "Platform drivers selection"
+
+config ARCH_CSKY_DW_APB_ICTL
+ bool "Select dw-apb interrupt controller"
+ select DW_APB_ICTL
+ default y
+ help
+ This enables support for snps dw-apb-ictl
+endmenu
#define flush_icache_page(vma, page) do {} while (0);
#define flush_icache_range(start, end) cache_wbinv_range(start, end)
-
-#define flush_icache_user_range(vma,page,addr,len) \
- flush_dcache_page(page)
+#define flush_icache_mm_range(mm, start, end) cache_wbinv_range(start, end)
+#define flush_icache_deferred(mm) do {} while (0);
#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
do { \
#define LSAVE_A4 40
#define LSAVE_A5 44
+#define usp ss1
+
.macro USPTOKSP
- mtcr sp, ss1
+ mtcr sp, usp
mfcr sp, ss0
.endm
.macro KSPTOUSP
mtcr sp, ss0
- mfcr sp, ss1
+ mfcr sp, usp
.endm
.macro SAVE_ALL epc_inc
add lr, r13
stw lr, (sp, 8)
+ mov lr, sp
+ addi lr, 32
+ addi lr, 32
+ addi lr, 16
+ bt 2f
mfcr lr, ss1
+2:
stw lr, (sp, 16)
stw a0, (sp, 20)
ldw a0, (sp, 12)
mtcr a0, epsr
btsti a0, 31
+ bt 1f
ldw a0, (sp, 16)
mtcr a0, ss1
-
+1:
ldw a0, (sp, 24)
ldw a1, (sp, 28)
ldw a2, (sp, 32)
addi sp, 32
addi sp, 8
- bt 1f
+ bt 2f
KSPTOUSP
-1:
+2:
rte
.endm
#include <linux/mm.h>
#include <asm/cache.h>
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+ pte_t *pte)
{
- unsigned long start;
+ unsigned long addr;
+ struct page *page;
- start = (unsigned long) kmap_atomic(page);
+ page = pfn_to_page(pte_pfn(*pte));
+ if (page == ZERO_PAGE(0))
+ return;
- cache_wbinv_range(start, start + PAGE_SIZE);
+ if (test_and_set_bit(PG_dcache_clean, &page->flags))
+ return;
- kunmap_atomic((void *)start);
-}
+ addr = (unsigned long) kmap_atomic(page);
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
- unsigned long vaddr, int len)
-{
- unsigned long kaddr;
+ dcache_wb_range(addr, addr + PAGE_SIZE);
- kaddr = (unsigned long) kmap_atomic(page) + (vaddr & ~PAGE_MASK);
+ if (vma->vm_flags & VM_EXEC)
+ icache_inv_range(addr, addr + PAGE_SIZE);
+
+ kunmap_atomic((void *) addr);
+}
- cache_wbinv_range(kaddr, kaddr + len);
+void flush_icache_deferred(struct mm_struct *mm)
+{
+ unsigned int cpu = smp_processor_id();
+ cpumask_t *mask = &mm->context.icache_stale_mask;
- kunmap_atomic((void *)kaddr);
+ if (cpumask_test_cpu(cpu, mask)) {
+ cpumask_clear_cpu(cpu, mask);
+ /*
+ * Ensure the remote hart's writes are visible to this hart.
+ * This pairs with a barrier in flush_icache_mm.
+ */
+ smp_mb();
+ local_icache_inv_all(NULL);
+ }
}
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
- pte_t *pte)
+void flush_icache_mm_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
{
- unsigned long addr, pfn;
- struct page *page;
+ unsigned int cpu;
+ cpumask_t others, *mask;
- pfn = pte_pfn(*pte);
- if (unlikely(!pfn_valid(pfn)))
- return;
+ preempt_disable();
- page = pfn_to_page(pfn);
- if (page == ZERO_PAGE(0))
+#ifdef CONFIG_CPU_HAS_ICACHE_INS
+ if (mm == current->mm) {
+ icache_inv_range(start, end);
+ preempt_enable();
return;
+ }
+#endif
- addr = (unsigned long) kmap_atomic(page);
+ /* Mark every hart's icache as needing a flush for this MM. */
+ mask = &mm->context.icache_stale_mask;
+ cpumask_setall(mask);
- cache_wbinv_range(addr, addr + PAGE_SIZE);
+ /* Flush this hart's I$ now, and mark it as flushed. */
+ cpu = smp_processor_id();
+ cpumask_clear_cpu(cpu, mask);
+ local_icache_inv_all(NULL);
- kunmap_atomic((void *) addr);
+ /*
+ * Flush the I$ of other harts concurrently executing, and mark them as
+ * flushed.
+ */
+ cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+
+ if (mm != current->active_mm || !cpumask_empty(&others)) {
+ on_each_cpu_mask(&others, local_icache_inv_all, NULL, 1);
+ cpumask_clear(mask);
+ }
+
+ preempt_enable();
}
#define flush_cache_all() do { } while (0)
#define flush_cache_mm(mm) do { } while (0)
#define flush_cache_dup_mm(mm) do { } while (0)
+#define flush_cache_range(vma, start, end) do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn) do { } while (0)
-#define flush_cache_range(vma, start, end) \
- do { \
- if (vma->vm_flags & VM_EXEC) \
- icache_inv_all(); \
- } while (0)
+#define PG_dcache_clean PG_arch_1
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+static inline void flush_dcache_page(struct page *page)
+{
+ if (test_bit(PG_dcache_clean, &page->flags))
+ clear_bit(PG_dcache_clean, &page->flags);
+}
-#define flush_cache_page(vma, vmaddr, pfn) do { } while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page) do { } while (0)
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
+#define flush_icache_page(vma, page) do { } while (0)
#define flush_icache_range(start, end) cache_wbinv_range(start, end)
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
- unsigned long vaddr, int len);
+void flush_icache_mm_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end);
+void flush_icache_deferred(struct mm_struct *mm);
#define flush_cache_vmap(start, end) do { } while (0)
#define flush_cache_vunmap(start, end) do { } while (0)
#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
do { \
memcpy(dst, src, len); \
- cache_wbinv_range((unsigned long)dst, (unsigned long)dst + len); \
+ if (vma->vm_flags & VM_EXEC) { \
+ dcache_wb_range((unsigned long)dst, \
+ (unsigned long)dst + len); \
+ flush_icache_mm_range(current->mm, \
+ (unsigned long)dst, \
+ (unsigned long)dst + len); \
+ } \
} while (0)
#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
memcpy(dst, src, len)
mfcr lr, epsr
stw lr, (sp, 12)
+ btsti lr, 31
+ bf 1f
+ addi lr, sp, 152
+ br 2f
+1:
mfcr lr, usp
+2:
stw lr, (sp, 16)
stw a0, (sp, 20)
mtcr a0, epc
ldw a0, (sp, 12)
mtcr a0, epsr
+ btsti a0, 31
ldw a0, (sp, 16)
mtcr a0, usp
+ mtcr a0, ss0
#ifdef CONFIG_CPU_HAS_HILO
ldw a0, (sp, 140)
addi sp, 40
ldm r16-r30, (sp)
addi sp, 72
+ bf 1f
+ mfcr sp, ss0
+1:
rte
.endm
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_CPU_CK807=y
-CONFIG_CPU_HAS_FPU=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_TTY_PRINTK=y
# CONFIG_VGA_CONSOLE is not set
-CONFIG_CSKY_MPTIMER=y
-CONFIG_GX6605S_TIMER=y
CONFIG_PM_DEVFREQ=y
CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
CONFIG_DEVFREQ_GOV_PERFORMANCE=y
CONFIG_ROMFS_FS=y
CONFIG_NFS_FS=y
CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
generic-y += mm-arch-hooks.h
generic-y += mmiowb.h
generic-y += module.h
-generic-y += pci.h
generic-y += percpu.h
generic-y += preempt.h
generic-y += qrwlock.h
void icache_inv_range(unsigned long start, unsigned long end);
void icache_inv_all(void);
+void local_icache_inv_all(void *priv);
void dcache_wb_range(unsigned long start, unsigned long end);
void dcache_wbinv_all(void);
#ifndef __ASM_CSKY_CACHEFLUSH_H
#define __ASM_CSKY_CACHEFLUSH_H
+#include <linux/mm.h>
#include <abi/cacheflush.h>
#endif /* __ASM_CSKY_CACHEFLUSH_H */
#define __ASM_CSKY_FIXMAP_H
#include <asm/page.h>
+#include <asm/memory.h>
#ifdef CONFIG_HIGHMEM
#include <linux/threads.h>
#include <asm/kmap_types.h>
#endif
enum fixed_addresses {
+#ifdef CONFIG_HAVE_TCM
+ FIX_TCM = TCM_NR_PAGES,
+#endif
#ifdef CONFIG_HIGHMEM
FIX_KMAP_BEGIN,
FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
__end_of_fixed_addresses
};
-#define FIXADDR_TOP 0xffffc000
#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
#include <asm-generic/fixmap.h>
+extern void fixrange_init(unsigned long start, unsigned long end,
+ pgd_t *pgd_base);
+extern void __init fixaddr_init(void);
+
#endif /* __ASM_CSKY_FIXMAP_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_MEMORY_H
+#define __ASM_CSKY_MEMORY_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+#include <linux/sizes.h>
+
+#define FIXADDR_TOP _AC(0xffffc000, UL)
+#define PKMAP_BASE _AC(0xff800000, UL)
+#define VMALLOC_START _AC(0xc0008000, UL)
+#define VMALLOC_END (PKMAP_BASE - (PAGE_SIZE * 2))
+
+#ifdef CONFIG_HAVE_TCM
+#ifdef CONFIG_HAVE_DTCM
+#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES + CONFIG_DTCM_NR_PAGES)
+#else
+#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES)
+#endif
+#define FIXADDR_TCM _AC(FIXADDR_TOP - (TCM_NR_PAGES * PAGE_SIZE), UL)
+#endif
+
+#endif
typedef struct {
atomic64_t asid;
void *vdso;
+ cpumask_t icache_stale_mask;
} mm_context_t;
#endif /* __ASM_CSKY_MMU_H */
TLBMISS_HANDLER_SETUP_PGD(next->pgd);
write_mmu_entryhi(next->context.asid.counter);
+
+ flush_icache_deferred(next);
}
#endif /* __ASM_CSKY_MMU_CONTEXT_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_PCI_H
+#define __ASM_CSKY_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO 0
+#define PCIBIOS_MIN_MEM 0
+
+/* C-SKY shim does not initialize PCI bus */
+#define pcibios_assign_all_busses() 1
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+ /* no legacy IRQ on csky */
+ return -ENODEV;
+}
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+ /* always show the domain in /proc */
+ return 1;
+}
+#endif /* CONFIG_PCI */
+
+#endif /* __ASM_CSKY_PCI_H */
#define __ASM_CSKY_PGTABLE_H
#include <asm/fixmap.h>
+#include <asm/memory.h>
#include <asm/addrspace.h>
#include <abi/pgtable-bits.h>
#include <asm-generic/pgtable-nopmd.h>
#define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE)
#define FIRST_USER_ADDRESS 0UL
-#define PKMAP_BASE (0xff800000)
-
-#define VMALLOC_START (0xc0008000)
-#define VMALLOC_END (PKMAP_BASE - 2*PAGE_SIZE)
-
/*
* C-SKY is two-level paging structure:
*/
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+ unsigned long canary;
+
+ /* Try to get a semi random initial value. */
+ get_random_bytes(&canary, sizeof(canary));
+ canary ^= LINUX_VERSION_CODE;
+ canary &= CANARY_MASK;
+
+ current->stack_canary = canary;
+ __stack_chk_guard = current->stack_canary;
+}
+
+#endif /* __ASM_SH_STACKPROTECTOR_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_TCM_H
+#define __ASM_CSKY_TCM_H
+
+#ifndef CONFIG_HAVE_TCM
+#error "You should not be including tcm.h unless you have a TCM!"
+#endif
+
+#include <linux/compiler.h>
+
+/* Tag variables with this */
+#define __tcmdata __section(.tcm.data)
+/* Tag constants with this */
+#define __tcmconst __section(.tcm.rodata)
+/* Tag functions inside TCM called from outside TCM with this */
+#define __tcmfunc __section(.tcm.text) noinline
+/* Tag function inside TCM called from inside TCM with this */
+#define __tcmlocalfunc __section(.tcm.text)
+
+void *tcm_alloc(size_t len);
+void tcm_free(void *addr, size_t len);
+
+#endif
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_NEW_STAT
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
#define __ARCH_WANT_SET_GET_RLIMIT
#define __ARCH_WANT_TIME32_SYSCALLS
#include <asm-generic/unistd.h>
mfcr a3, epc
addi a3, TRAP0_SIZE
- subi sp, 8
+ subi sp, 16
stw a3, (sp, 0)
mfcr a3, epsr
stw a3, (sp, 4)
+ mfcr a3, usp
+ stw a3, (sp, 8)
psrset ee
#ifdef CONFIG_CPU_HAS_LDSTEX
mtcr a3, epc
ldw a3, (sp, 4)
mtcr a3, epsr
- addi sp, 8
+ ldw a3, (sp, 8)
+ mtcr a3, usp
+ addi sp, 16
KSPTOUSP
rte
END(csky_cmpxchg)
struct cpuinfo_csky cpu_data[NR_CPUS];
+#ifdef CONFIG_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
asmlinkage void ret_from_fork(void);
asmlinkage void ret_from_kernel_thread(void);
return sw->r15;
}
-int copy_thread(unsigned long clone_flags,
+int copy_thread_tls(unsigned long clone_flags,
unsigned long usp,
unsigned long kthread_arg,
- struct task_struct *p)
+ struct task_struct *p,
+ unsigned long tls)
{
struct switch_stack *childstack;
struct pt_regs *childregs = task_pt_regs(p);
childregs->usp = usp;
if (clone_flags & CLONE_SETTLS)
task_thread_info(p)->tp_value = childregs->tls
- = childregs->regs[0];
+ = tls;
childregs->a0 = 0;
childstack->r15 = (unsigned long) ret_from_fork;
signed long size;
memblock_reserve(__pa(_stext), _end - _stext);
-#ifdef CONFIG_BLK_DEV_INITRD
- memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
-#endif
early_init_fdt_reserve_self();
early_init_fdt_scan_reserved_mem();
sparse_init();
+ fixaddr_init();
+
#ifdef CONFIG_HIGHMEM
kmap_init();
#endif
int rc;
if (ipi_irq == 0)
- panic("%s IRQ mapping failed\n", __func__);
+ return;
rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt",
&ipi_dummy_dev);
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
-#include <linux/clk-provider.h>
#include <linux/clocksource.h>
+#include <linux/of_clk.h>
void __init time_init(void)
{
#include <asm/vmlinux.lds.h>
#include <asm/page.h>
+#include <asm/memory.h>
OUTPUT_ARCH(csky)
ENTRY(_start)
RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
_edata = .;
+#ifdef CONFIG_HAVE_TCM
+ .tcm_start : {
+ . = ALIGN(PAGE_SIZE);
+ __tcm_start = .;
+ }
+
+ .text_data_tcm FIXADDR_TCM : AT(__tcm_start)
+ {
+ . = ALIGN(4);
+ __stcm_text_data = .;
+ *(.tcm.text)
+ *(.tcm.rodata)
+#ifndef CONFIG_HAVE_DTCM
+ *(.tcm.data)
+#endif
+ . = ALIGN(4);
+ __etcm_text_data = .;
+ }
+
+ . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_data_tcm);
+
+#ifdef CONFIG_HAVE_DTCM
+ #define ITCM_SIZE CONFIG_ITCM_NR_PAGES * PAGE_SIZE
+
+ .dtcm_start : {
+ __dtcm_start = .;
+ }
+
+ .data_tcm FIXADDR_TCM + ITCM_SIZE : AT(__dtcm_start)
+ {
+ . = ALIGN(4);
+ __stcm_data = .;
+ *(.tcm.data)
+ . = ALIGN(4);
+ __etcm_data = .;
+ }
+
+ . = ADDR(.dtcm_start) + SIZEOF(.data_tcm);
+
+ .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_tcm)) {
+#else
+ .tcm_end : AT(ADDR(.tcm_start) + SIZEOF(.text_data_tcm)) {
+#endif
+ . = ALIGN(PAGE_SIZE);
+ __tcm_end = .;
+ }
+#endif
+
EXCEPTION_TABLE(L1_CACHE_BYTES)
BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES)
VBR_BASE
# SPDX-License-Identifier: GPL-2.0-only
ifeq ($(CONFIG_CPU_HAS_CACHEV2),y)
obj-y += cachev2.o
+CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE)
else
obj-y += cachev1.o
+CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE)
endif
obj-y += dma-mapping.o
obj-y += tlb.o
obj-y += asid.o
obj-y += context.o
+obj-$(CONFIG_HAVE_TCM) += tcm.o
cache_op_all(INS_CACHE|CACHE_INV, 0);
}
+void local_icache_inv_all(void *priv)
+{
+ cache_op_all(INS_CACHE|CACHE_INV, 0);
+}
+
void dcache_wb_range(unsigned long start, unsigned long end)
{
cache_op_range(start, end, DATA_CACHE|CACHE_CLR, 0);
#include <linux/spinlock.h>
#include <linux/smp.h>
+#include <linux/mm.h>
#include <asm/cache.h>
#include <asm/barrier.h>
-inline void dcache_wb_line(unsigned long start)
+#define INS_CACHE (1 << 0)
+#define CACHE_INV (1 << 4)
+
+void local_icache_inv_all(void *priv)
{
- asm volatile("dcache.cval1 %0\n"::"r"(start):"memory");
+ mtcr("cr17", INS_CACHE|CACHE_INV);
sync_is();
}
+void icache_inv_all(void)
+{
+ on_each_cpu(local_icache_inv_all, NULL, 1);
+}
+
+#ifdef CONFIG_CPU_HAS_ICACHE_INS
void icache_inv_range(unsigned long start, unsigned long end)
{
unsigned long i = start & ~(L1_CACHE_BYTES - 1);
asm volatile("icache.iva %0\n"::"r"(i):"memory");
sync_is();
}
-
-void icache_inv_all(void)
+#else
+void icache_inv_range(unsigned long start, unsigned long end)
{
- asm volatile("icache.ialls\n":::"memory");
- sync_is();
+ icache_inv_all();
}
+#endif
-void dcache_wb_range(unsigned long start, unsigned long end)
+inline void dcache_wb_line(unsigned long start)
{
- unsigned long i = start & ~(L1_CACHE_BYTES - 1);
-
- for (; i < end; i += L1_CACHE_BYTES)
- asm volatile("dcache.cval1 %0\n"::"r"(i):"memory");
+ asm volatile("dcache.cval1 %0\n"::"r"(start):"memory");
sync_is();
}
-void dcache_inv_range(unsigned long start, unsigned long end)
+void dcache_wb_range(unsigned long start, unsigned long end)
{
unsigned long i = start & ~(L1_CACHE_BYTES - 1);
for (; i < end; i += L1_CACHE_BYTES)
- asm volatile("dcache.civa %0\n"::"r"(i):"memory");
+ asm volatile("dcache.cval1 %0\n"::"r"(i):"memory");
sync_is();
}
void cache_wbinv_range(unsigned long start, unsigned long end)
{
- unsigned long i = start & ~(L1_CACHE_BYTES - 1);
-
- for (; i < end; i += L1_CACHE_BYTES)
- asm volatile("dcache.cval1 %0\n"::"r"(i):"memory");
- sync_is();
-
- i = start & ~(L1_CACHE_BYTES - 1);
- for (; i < end; i += L1_CACHE_BYTES)
- asm volatile("icache.iva %0\n"::"r"(i):"memory");
- sync_is();
+ dcache_wb_range(start, end);
+ icache_inv_range(start, end);
}
EXPORT_SYMBOL(cache_wbinv_range);
return pte_page(*pte);
}
-static void __init fixrange_init(unsigned long start, unsigned long end,
- pgd_t *pgd_base)
+static void __init kmap_pages_init(void)
{
-#ifdef CONFIG_HIGHMEM
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
- int i, j, k;
unsigned long vaddr;
-
- vaddr = start;
- i = __pgd_offset(vaddr);
- j = __pud_offset(vaddr);
- k = __pmd_offset(vaddr);
- pgd = pgd_base + i;
-
- for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
- pud = (pud_t *)pgd;
- for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) {
- pmd = (pmd_t *)pud;
- for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) {
- if (pmd_none(*pmd)) {
- pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
- if (!pte)
- panic("%s: Failed to allocate %lu bytes align=%lx\n",
- __func__, PAGE_SIZE,
- PAGE_SIZE);
-
- set_pmd(pmd, __pmd(__pa(pte)));
- BUG_ON(pte != pte_offset_kernel(pmd, 0));
- }
- vaddr += PMD_SIZE;
- }
- k = 0;
- }
- j = 0;
- }
-#endif
-}
-
-void __init fixaddr_kmap_pages_init(void)
-{
- unsigned long vaddr;
- pgd_t *pgd_base;
-#ifdef CONFIG_HIGHMEM
pgd_t *pgd;
pmd_t *pmd;
pud_t *pud;
pte_t *pte;
-#endif
- pgd_base = swapper_pg_dir;
-
- /*
- * Fixed mappings:
- */
- vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
- fixrange_init(vaddr, 0, pgd_base);
-
-#ifdef CONFIG_HIGHMEM
- /*
- * Permanent kmaps:
- */
+
vaddr = PKMAP_BASE;
- fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
+ fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir);
pgd = swapper_pg_dir + __pgd_offset(vaddr);
pud = (pud_t *)pgd;
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pkmap_page_table = pte;
-#endif
}
void __init kmap_init(void)
{
unsigned long vaddr;
- fixaddr_kmap_pages_init();
+ kmap_pages_init();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN);
#include <linux/swap.h>
#include <linux/proc_fs.h>
#include <linux/pfn.h>
+#include <linux/initrd.h>
#include <asm/setup.h>
#include <asm/cachectl.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
+EXPORT_SYMBOL(invalid_pte_table);
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
__page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+ unsigned long size;
+
+ if (initrd_start >= initrd_end) {
+ pr_err("initrd not found or empty");
+ goto disable;
+ }
+
+ if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+ pr_err("initrd extends beyond end of memory");
+ goto disable;
+ }
+
+ size = initrd_end - initrd_start;
+
+ if (memblock_is_region_reserved(__pa(initrd_start), size)) {
+ pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region",
+ __pa(initrd_start), size);
+ goto disable;
+ }
+
+ memblock_reserve(__pa(initrd_start), size);
+
+ pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
+ (void *)(initrd_start), size);
+
+ initrd_below_start_ok = 1;
+
+ return;
+
+disable:
+ initrd_start = initrd_end = 0;
+
+ pr_err(" - disabling initrd\n");
+}
+#endif
+
void __init mem_init(void)
{
#ifdef CONFIG_HIGHMEM
#endif
high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
+#ifdef CONFIG_BLK_DEV_INITRD
+ setup_initrd();
+#endif
+
memblock_free_all();
#ifdef CONFIG_HIGHMEM
/* Setup page mask to 4k */
write_mmu_pagemask(0);
}
+
+void __init fixrange_init(unsigned long start, unsigned long end,
+ pgd_t *pgd_base)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ int i, j, k;
+ unsigned long vaddr;
+
+ vaddr = start;
+ i = __pgd_offset(vaddr);
+ j = __pud_offset(vaddr);
+ k = __pmd_offset(vaddr);
+ pgd = pgd_base + i;
+
+ for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
+ pud = (pud_t *)pgd;
+ for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) {
+ pmd = (pmd_t *)pud;
+ for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) {
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+ if (!pte)
+ panic("%s: Failed to allocate %lu bytes align=%lx\n",
+ __func__, PAGE_SIZE,
+ PAGE_SIZE);
+
+ set_pmd(pmd, __pmd(__pa(pte)));
+ BUG_ON(pte != pte_offset_kernel(pmd, 0));
+ }
+ vaddr += PMD_SIZE;
+ }
+ k = 0;
+ }
+ j = 0;
+ }
+}
+
+void __init fixaddr_init(void)
+{
+ unsigned long vaddr;
+
+ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+ fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir);
+}
#include <linux/syscalls.h>
#include <asm/page.h>
-#include <asm/cache.h>
+#include <asm/cacheflush.h>
#include <asm/cachectl.h>
SYSCALL_DEFINE3(cacheflush,
{
switch (cache) {
case ICACHE:
- icache_inv_range((unsigned long)addr,
- (unsigned long)addr + bytes);
- break;
+ case BCACHE:
+ flush_icache_mm_range(current->mm,
+ (unsigned long)addr,
+ (unsigned long)addr + bytes);
case DCACHE:
dcache_wb_range((unsigned long)addr,
(unsigned long)addr + bytes);
break;
- case BCACHE:
- cache_wbinv_range((unsigned long)addr,
- (unsigned long)addr + bytes);
- break;
default:
return -EINVAL;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/highmem.h>
+#include <linux/genalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+
+#if (CONFIG_ITCM_RAM_BASE == 0xffffffff)
+#error "You should define ITCM_RAM_BASE"
+#endif
+
+#ifdef CONFIG_HAVE_DTCM
+#if (CONFIG_DTCM_RAM_BASE == 0xffffffff)
+#error "You should define DTCM_RAM_BASE"
+#endif
+
+#if (CONFIG_DTCM_RAM_BASE == CONFIG_ITCM_RAM_BASE)
+#error "You should define correct DTCM_RAM_BASE"
+#endif
+#endif
+
+extern char __tcm_start, __tcm_end, __dtcm_start;
+
+static struct gen_pool *tcm_pool;
+
+static void __init tcm_mapping_init(void)
+{
+ pte_t *tcm_pte;
+ unsigned long vaddr, paddr;
+ int i;
+
+ paddr = CONFIG_ITCM_RAM_BASE;
+
+ if (pfn_valid(PFN_DOWN(CONFIG_ITCM_RAM_BASE)))
+ goto panic;
+
+#ifndef CONFIG_HAVE_DTCM
+ for (i = 0; i < TCM_NR_PAGES; i++) {
+#else
+ for (i = 0; i < CONFIG_ITCM_NR_PAGES; i++) {
+#endif
+ vaddr = __fix_to_virt(FIX_TCM - i);
+
+ tcm_pte =
+ pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr);
+
+ set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL));
+
+ flush_tlb_one(vaddr);
+
+ paddr = paddr + PAGE_SIZE;
+ }
+
+#ifdef CONFIG_HAVE_DTCM
+ if (pfn_valid(PFN_DOWN(CONFIG_DTCM_RAM_BASE)))
+ goto panic;
+
+ paddr = CONFIG_DTCM_RAM_BASE;
+
+ for (i = 0; i < CONFIG_DTCM_NR_PAGES; i++) {
+ vaddr = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES - i);
+
+ tcm_pte =
+ pte_offset_kernel((pmd_t *) pgd_offset_k(vaddr), vaddr);
+
+ set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL));
+
+ flush_tlb_one(vaddr);
+
+ paddr = paddr + PAGE_SIZE;
+ }
+#endif
+
+#ifndef CONFIG_HAVE_DTCM
+ memcpy((void *)__fix_to_virt(FIX_TCM),
+ &__tcm_start, &__tcm_end - &__tcm_start);
+
+ pr_info("%s: mapping tcm va:0x%08lx to pa:0x%08x\n",
+ __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE);
+
+ pr_info("%s: __tcm_start va:0x%08lx size:%d\n",
+ __func__, (unsigned long)&__tcm_start, &__tcm_end - &__tcm_start);
+#else
+ memcpy((void *)__fix_to_virt(FIX_TCM),
+ &__tcm_start, &__dtcm_start - &__tcm_start);
+
+ pr_info("%s: mapping itcm va:0x%08lx to pa:0x%08x\n",
+ __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE);
+
+ pr_info("%s: __itcm_start va:0x%08lx size:%d\n",
+ __func__, (unsigned long)&__tcm_start, &__dtcm_start - &__tcm_start);
+
+ memcpy((void *)__fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES),
+ &__dtcm_start, &__tcm_end - &__dtcm_start);
+
+ pr_info("%s: mapping dtcm va:0x%08lx to pa:0x%08x\n",
+ __func__, __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES),
+ CONFIG_DTCM_RAM_BASE);
+
+ pr_info("%s: __dtcm_start va:0x%08lx size:%d\n",
+ __func__, (unsigned long)&__dtcm_start, &__tcm_end - &__dtcm_start);
+
+#endif
+ return;
+panic:
+ panic("TCM init error");
+}
+
+void *tcm_alloc(size_t len)
+{
+ unsigned long vaddr;
+
+ if (!tcm_pool)
+ return NULL;
+
+ vaddr = gen_pool_alloc(tcm_pool, len);
+ if (!vaddr)
+ return NULL;
+
+ return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+void tcm_free(void *addr, size_t len)
+{
+ gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+static int __init tcm_setup_pool(void)
+{
+#ifndef CONFIG_HAVE_DTCM
+ u32 pool_size = (u32) (TCM_NR_PAGES * PAGE_SIZE)
+ - (u32) (&__tcm_end - &__tcm_start);
+
+ u32 tcm_pool_start = __fix_to_virt(FIX_TCM)
+ + (u32) (&__tcm_end - &__tcm_start);
+#else
+ u32 pool_size = (u32) (CONFIG_DTCM_NR_PAGES * PAGE_SIZE)
+ - (u32) (&__tcm_end - &__dtcm_start);
+
+ u32 tcm_pool_start = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES)
+ + (u32) (&__tcm_end - &__dtcm_start);
+#endif
+ int ret;
+
+ tcm_pool = gen_pool_create(2, -1);
+
+ ret = gen_pool_add(tcm_pool, tcm_pool_start, pool_size, -1);
+ if (ret) {
+ pr_err("%s: gen_pool add failed!\n", __func__);
+ return ret;
+ }
+
+ pr_info("%s: Added %d bytes @ 0x%08x to memory pool\n",
+ __func__, pool_size, tcm_pool_start);
+
+ return 0;
+}
+
+static int __init tcm_init(void)
+{
+ tcm_mapping_init();
+
+ tcm_setup_pool();
+
+ return 0;
+}
+arch_initcall(tcm_init);
// SPDX-License-Identifier: GPL-2.0
#include <dt-bindings/clock/jz4740-cgu.h>
+#include <dt-bindings/clock/ingenic,tcu.h>
/ {
#address-cells = <1>;
#clock-cells = <1>;
};
- watchdog: watchdog@10002000 {
- compatible = "ingenic,jz4740-watchdog";
- reg = <0x10002000 0x10>;
-
- clocks = <&cgu JZ4740_CLK_RTC>;
- clock-names = "rtc";
- };
-
tcu: timer@10002000 {
compatible = "ingenic,jz4740-tcu", "simple-mfd";
reg = <0x10002000 0x1000>;
interrupt-parent = <&intc>;
interrupts = <23 22 21>;
+
+ watchdog: watchdog@0 {
+ compatible = "ingenic,jz4740-watchdog";
+ reg = <0x0 0xc>;
+
+ clocks = <&tcu TCU_CLK_WDT>;
+ clock-names = "wdt";
+ };
};
rtc_dev: rtc@10003000 {
// SPDX-License-Identifier: GPL-2.0
#include <dt-bindings/clock/jz4780-cgu.h>
+#include <dt-bindings/clock/ingenic,tcu.h>
#include <dt-bindings/dma/jz4780-dma.h>
/ {
interrupt-parent = <&intc>;
interrupts = <27 26 25>;
+
+ watchdog: watchdog@0 {
+ compatible = "ingenic,jz4780-watchdog";
+ reg = <0x0 0xc>;
+
+ clocks = <&tcu TCU_CLK_WDT>;
+ clock-names = "wdt";
+ };
};
rtc_dev: rtc@10003000 {
status = "disabled";
};
- watchdog: watchdog@10002000 {
- compatible = "ingenic,jz4780-watchdog";
- reg = <0x10002000 0x10>;
-
- clocks = <&cgu JZ4780_CLK_RTCLK>;
- clock-names = "rtc";
- };
-
nemc: nemc@13410000 {
compatible = "ingenic,jz4780-nemc";
reg = <0x13410000 0x10000>;
// SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/ingenic,tcu.h>
#include <dt-bindings/clock/x1000-cgu.h>
#include <dt-bindings/dma/x1000-dma.h>
compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog";
reg = <0x0 0x10>;
- clocks = <&cgu X1000_CLK_RTCLK>;
+ clocks = <&tcu TCU_CLK_WDT>;
clock-names = "wdt";
};
};
i2c0: i2c-controller@10050000 {
compatible = "ingenic,x1000-i2c";
reg = <0x10050000 0x1000>;
-
#address-cells = <1>;
#size-cells = <0>;
i2c1: i2c-controller@10051000 {
compatible = "ingenic,x1000-i2c";
reg = <0x10051000 0x1000>;
-
#address-cells = <1>;
#size-cells = <0>;
i2c2: i2c-controller@10052000 {
compatible = "ingenic,x1000-i2c";
reg = <0x10052000 0x1000>;
-
#address-cells = <1>;
#size-cells = <0>;
* effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use
* optimized memory barrier primitives."). Here we specify that the affected
* sync instructions should be emitted twice.
+ * Note that this expression is evaluated by the assembler (not the compiler),
+ * and that the assembler evaluates '==' as 0 or -1, not 0 or 1.
*/
#ifdef CONFIG_CPU_CAVIUM_OCTEON
-# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb))
+# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb))
#else
# define __SYNC_rpt(type) 1
#endif
{
list_del(&v->list);
if (v->load_addr)
- release_progmem(v);
+ release_progmem(v->load_addr);
kfree(v);
}
cflags-vdso := $(ccflags-vdso) \
$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
$(call cc-option, -fno-asynchronous-unwind-tables) \
$(call cc-option, -fno-stack-protector)
CFLAGS_REMOVE_vgettimeofday.o = -pg
+DISABLE_VDSO := n
+
#
# For the pre-R6 code in arch/mips/vdso/vdso.h for locating
# the base address of VDSO, the linker will emit a R_MIPS_PC32
ifndef CONFIG_CPU_MIPSR6
ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
$(warning MIPS VDSO requires binutils >= 2.25)
- obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y))
- ccflags-vdso += -DDISABLE_MIPS_VDSO
+ DISABLE_VDSO := y
endif
endif
+#
+# GCC (at least up to version 9.2) appears to emit function calls that make use
+# of the GOT when targeting microMIPS, which we can't use in the VDSO due to
+# the lack of relocations. As such, we disable the VDSO for microMIPS builds.
+#
+ifdef CONFIG_CPU_MICROMIPS
+ DISABLE_VDSO := y
+endif
+
+ifeq ($(DISABLE_VDSO),y)
+ obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y))
+ ccflags-vdso += -DDISABLE_MIPS_VDSO
+endif
+
# VDSO linker flags.
VDSO_LDFLAGS := \
-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
UBSAN_SANITIZE := n
KCOV_INSTRUMENT := n
+# Check that we don't have PIC 'jalr t9' calls left
+quiet_cmd_vdso_mips_check = VDSOCHK $@
+ cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \
+ then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \
+ rm -f $@; /bin/false); fi
+
#
# Shared build commands.
#
quiet_cmd_vdsold_and_vdso_check = LD $@
- cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
+ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check); $(cmd_vdso_mips_check)
quiet_cmd_vdsold = VDSO $@
cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \
/*
* Some number of bits at the level of the page table that points to
* a hugepte are used to encode the size. This masks those bits.
+ * On 8xx, HW assistance requires 4k alignment for the hugepte.
*/
+#ifdef CONFIG_PPC_8xx
+#define HUGEPD_SHIFT_MASK 0xfff
+#else
#define HUGEPD_SHIFT_MASK 0x3f
+#endif
#ifndef __ASSEMBLY__
unsigned long srr1;
unsigned long dar;
unsigned long dsisr;
+#ifdef CONFIG_PPC_BOOK3S_32
+ unsigned long r0, r3, r4, r5, r6, r8, r9, r11;
+ unsigned long lr, ctr;
+#endif
#endif
/* Debug Registers */
struct debug_reg debug;
OFFSET(SRR1, thread_struct, srr1);
OFFSET(DAR, thread_struct, dar);
OFFSET(DSISR, thread_struct, dsisr);
+#ifdef CONFIG_PPC_BOOK3S_32
+ OFFSET(THR0, thread_struct, r0);
+ OFFSET(THR3, thread_struct, r3);
+ OFFSET(THR4, thread_struct, r4);
+ OFFSET(THR5, thread_struct, r5);
+ OFFSET(THR6, thread_struct, r6);
+ OFFSET(THR8, thread_struct, r8);
+ OFFSET(THR9, thread_struct, r9);
+ OFFSET(THR11, thread_struct, r11);
+ OFFSET(THLR, thread_struct, lr);
+ OFFSET(THCTR, thread_struct, ctr);
+#endif
#endif
#ifdef CONFIG_SPE
OFFSET(THREAD_EVR0, thread_struct, evr[0]);
eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
eeh_handle_normal_event(pe);
} else {
+ eeh_for_each_pe(pe, tmp_pe)
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
+ edev->mode &= ~EEH_DEV_NO_HANDLER;
+
+ /* Notify all devices to be down */
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
+ eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+ eeh_pe_report(
+ "error_detected(permanent failure)", pe,
+ eeh_report_failure, NULL);
+
pci_lock_rescan_remove();
list_for_each_entry(hose, &hose_list, list_node) {
phb_pe = eeh_phb_pe_get(hose);
(phb_pe->state & EEH_PE_RECOVERING))
continue;
- eeh_for_each_pe(pe, tmp_pe)
- eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
- edev->mode &= ~EEH_DEV_NO_HANDLER;
-
- /* Notify all devices to be down */
- eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
- eeh_set_channel_state(pe, pci_channel_io_perm_failure);
- eeh_pe_report(
- "error_detected(permanent failure)", pe,
- eeh_report_failure, NULL);
bus = eeh_pe_bus_get(phb_pe);
if (!bus) {
pr_err("%s: Cannot find PCI bus for "
1: lis r3,exc_exit_restart_end@ha
addi r3,r3,exc_exit_restart_end@l
cmplw r12,r3
-#if CONFIG_PPC_BOOK3S_601
+#ifdef CONFIG_PPC_BOOK3S_601
bge 2b
#else
bge 3f
lis r4,exc_exit_restart@ha
addi r4,r4,exc_exit_restart@l
cmplw r12,r4
-#if CONFIG_PPC_BOOK3S_601
+#ifdef CONFIG_PPC_BOOK3S_601
blt 2b
#else
blt 3f
mtspr SPRN_SRR0,r8
mtspr SPRN_SRR1,r9
RFI
-1: tophys(r9,r1)
+1: tophys_novmstack r9, r1
+#ifdef CONFIG_VMAP_STACK
+ li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */
+ mtmsr r0
+ isync
+#endif
lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */
lwz r9,8(r9) /* original msr value */
addi r1,r1,INT_FRAME_SIZE
li r0,0
- tophys(r7, r2)
+ tophys_novmstack r7, r2
stw r0, THREAD + RTAS_SP(r7)
mtspr SPRN_SRR0,r8
mtspr SPRN_SRR1,r9
7: EXCEPTION_PROLOG_2
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_CHRP
- bne cr1,1f
+#ifdef CONFIG_VMAP_STACK
+ mfspr r4, SPRN_SPRG_THREAD
+ tovirt(r4, r4)
+ lwz r4, RTAS_SP(r4)
+ cmpwi cr1, r4, 0
#endif
- EXC_XFER_STD(0x200, machine_check_exception)
-#ifdef CONFIG_PPC_CHRP
-1: b machine_check_in_rtas
+ beq cr1, machine_check_tramp
+ b machine_check_in_rtas
+#else
+ b machine_check_tramp
#endif
/* Data access exception. */
. = 0x300
DO_KVM 0x300
DataAccess:
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mfspr r10, SPRN_SPRG_THREAD
+BEGIN_MMU_FTR_SECTION
+ stw r11, THR11(r10)
+ mfspr r10, SPRN_DSISR
+ mfcr r11
+#ifdef CONFIG_PPC_KUAP
+ andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+#else
+ andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
+#endif
+ mfspr r10, SPRN_SPRG_THREAD
+ beq hash_page_dsi
+.Lhash_page_dsi_cont:
+ mtcr r11
+ lwz r11, THR11(r10)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r11, SPRN_DAR
+ stw r11, DAR(r10)
+ mfspr r11, SPRN_DSISR
+ stw r11, DSISR(r10)
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+ andi. r11, r11, MSR_PR
+
+ EXCEPTION_PROLOG_1
+ b handle_page_fault_tramp_1
+#else /* CONFIG_VMAP_STACK */
EXCEPTION_PROLOG handle_dar_dsisr=1
get_and_save_dar_dsisr_on_stack r4, r5, r11
BEGIN_MMU_FTR_SECTION
FTR_SECTION_ELSE
b handle_page_fault_tramp_2
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+#endif /* CONFIG_VMAP_STACK */
/* Instruction access exception. */
. = 0x400
DO_KVM 0x400
InstructionAccess:
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r10, SPRN_SPRG_THREAD
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+BEGIN_MMU_FTR_SECTION
+ andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */
+ bne hash_page_isi
+.Lhash_page_isi_cont:
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+ andi. r11, r11, MSR_PR
+
+ EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2
+#else /* CONFIG_VMAP_STACK */
EXCEPTION_PROLOG
andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */
beq 1f /* if so, try to put a PTE */
BEGIN_MMU_FTR_SECTION
bl hash_page
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif /* CONFIG_VMAP_STACK */
1: mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
stw r4, _DAR(r11)
EXCEPTION_PROLOG handle_dar_dsisr=1
save_dar_dsisr_on_stack r4, r5, r11
addi r3,r1,STACK_FRAME_OVERHEAD
- EXC_XFER_STD(0x600, alignment_exception)
+ b alignment_exception_tramp
/* Program check exception */
EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
. = 0x3000
+machine_check_tramp:
+ EXC_XFER_STD(0x200, machine_check_exception)
+
+alignment_exception_tramp:
+ EXC_XFER_STD(0x600, alignment_exception)
+
handle_page_fault_tramp_1:
+#ifdef CONFIG_VMAP_STACK
+ EXCEPTION_PROLOG_2 handle_dar_dsisr=1
+#endif
lwz r4, _DAR(r11)
lwz r5, _DSISR(r11)
/* fall through */
handle_page_fault_tramp_2:
EXC_XFER_LITE(0x300, handle_page_fault)
+#ifdef CONFIG_VMAP_STACK
+.macro save_regs_thread thread
+ stw r0, THR0(\thread)
+ stw r3, THR3(\thread)
+ stw r4, THR4(\thread)
+ stw r5, THR5(\thread)
+ stw r6, THR6(\thread)
+ stw r8, THR8(\thread)
+ stw r9, THR9(\thread)
+ mflr r0
+ stw r0, THLR(\thread)
+ mfctr r0
+ stw r0, THCTR(\thread)
+.endm
+
+.macro restore_regs_thread thread
+ lwz r0, THLR(\thread)
+ mtlr r0
+ lwz r0, THCTR(\thread)
+ mtctr r0
+ lwz r0, THR0(\thread)
+ lwz r3, THR3(\thread)
+ lwz r4, THR4(\thread)
+ lwz r5, THR5(\thread)
+ lwz r6, THR6(\thread)
+ lwz r8, THR8(\thread)
+ lwz r9, THR9(\thread)
+.endm
+
+hash_page_dsi:
+ save_regs_thread r10
+ mfdsisr r3
+ mfdar r4
+ mfsrr0 r5
+ mfsrr1 r9
+ rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ b .Lhash_page_dsi_cont
+
+hash_page_isi:
+ mr r11, r10
+ mfspr r10, SPRN_SPRG_THREAD
+ save_regs_thread r10
+ li r3, 0
+ lwz r4, SRR0(r10)
+ lwz r9, SRR1(r10)
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ mr r10, r11
+ b .Lhash_page_isi_cont
+
+ .globl fast_hash_page_return
+fast_hash_page_return:
+ andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ bne 1f
+
+ /* DSI */
+ mtcr r11
+ lwz r11, THR11(r10)
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ SYNC
+ RFI
+
+1: /* ISI */
+ mtcr r11
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ SYNC
+ RFI
+
stack_overflow:
vmap_stack_overflow_exception
+#endif
AltiVecUnavailable:
EXCEPTION_PROLOG
.endm
.macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0
+#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S)
+BEGIN_MMU_FTR_SECTION
+ mtcr r10
+FTR_SECTION_ELSE
+ stw r10, _CCR(r11)
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+#else
stw r10,_CCR(r11) /* save registers */
+#endif
+ mfspr r10, SPRN_SPRG_SCRATCH0
stw r12,GPR12(r11)
stw r9,GPR9(r11)
- mfspr r10,SPRN_SPRG_SCRATCH0
stw r10,GPR10(r11)
+#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S)
+BEGIN_MMU_FTR_SECTION
+ mfcr r10
+ stw r10, _CCR(r11)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
mfspr r12,SPRN_SPRG_SCRATCH1
stw r12,GPR11(r11)
mflr r10
stw r10, _DSISR(r11)
.endif
lwz r9, SRR1(r12)
+#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S)
+BEGIN_MMU_FTR_SECTION
+ andi. r10, r9, MSR_PR
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
lwz r12, SRR0(r12)
#else
mfspr r12,SPRN_SRR0
* set. All other Linux PTE bits control the behavior
* of the MMU.
*/
- rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */
+ rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */
rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */
ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
mfspr r9,SPRN_HID0
andis. r9,r9,HID0_NAP@h
beq 1f
+#ifdef CONFIG_VMAP_STACK
+ addis r9, r11, nap_save_msscr0@ha
+#else
addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha
+#endif
lwz r9,nap_save_msscr0@l(r9)
mtspr SPRN_MSSCR0, r9
sync
1:
END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
BEGIN_FTR_SECTION
+#ifdef CONFIG_VMAP_STACK
+ addis r9, r11, nap_save_hid1@ha
+#else
addis r9,r11,(nap_save_hid1-KERNELBASE)@ha
+#endif
lwz r9,nap_save_hid1@l(r9)
mtspr SPRN_HID1, r9
END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
* normal/non-checkpointed stack pointer.
*/
+ unsigned long ret = tsk->thread.regs->gpr[1];
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BUG_ON(tsk != current);
if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) {
+ preempt_disable();
tm_reclaim_current(TM_CAUSE_SIGNAL);
if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr))
- return tsk->thread.ckpt_regs.gpr[1];
+ ret = tsk->thread.ckpt_regs.gpr[1];
+
+ /*
+ * If we treclaim, we must clear the current thread's TM bits
+ * before re-enabling preemption. Otherwise we might be
+ * preempted and have the live MSR[TS] changed behind our back
+ * (tm_recheckpoint_new_task() would recheckpoint). Besides, we
+ * enter the signal handler in non-transactional state.
+ */
+ tsk->thread.regs->msr &= ~MSR_TS_MASK;
+ preempt_enable();
}
#endif
- return tsk->thread.regs->gpr[1];
+ return ret;
}
*/
static int save_tm_user_regs(struct pt_regs *regs,
struct mcontext __user *frame,
- struct mcontext __user *tm_frame, int sigret)
+ struct mcontext __user *tm_frame, int sigret,
+ unsigned long msr)
{
- unsigned long msr = regs->msr;
-
WARN_ON(tm_suspend_disabled);
- /* Remove TM bits from thread's MSR. The MSR in the sigcontext
- * just indicates to userland that we were doing a transaction, but we
- * don't want to return in transactional state. This also ensures
- * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
- */
- regs->msr &= ~MSR_TS_MASK;
-
/* Save both sets of general registers */
if (save_general_regs(¤t->thread.ckpt_regs, frame)
|| save_general_regs(regs, tm_frame))
int sigret;
unsigned long tramp;
struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+#endif
BUG_ON(tsk != current);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tm_frame = &rt_sf->uc_transact.uc_mcontext;
- if (MSR_TM_ACTIVE(regs->msr)) {
+ if (MSR_TM_ACTIVE(msr)) {
if (__put_user((unsigned long)&rt_sf->uc_transact,
&rt_sf->uc.uc_link) ||
__put_user((unsigned long)tm_frame,
&rt_sf->uc_transact.uc_regs))
goto badframe;
- if (save_tm_user_regs(regs, frame, tm_frame, sigret))
+ if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr))
goto badframe;
}
else
int sigret;
unsigned long tramp;
struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+#endif
BUG_ON(tsk != current);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tm_mctx = &frame->mctx_transact;
- if (MSR_TM_ACTIVE(regs->msr)) {
+ if (MSR_TM_ACTIVE(msr)) {
if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
- sigret))
+ sigret, msr))
goto badframe;
}
else
static long setup_tm_sigcontexts(struct sigcontext __user *sc,
struct sigcontext __user *tm_sc,
struct task_struct *tsk,
- int signr, sigset_t *set, unsigned long handler)
+ int signr, sigset_t *set, unsigned long handler,
+ unsigned long msr)
{
/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
* process never used altivec yet (MSR_VEC is zero in pt_regs of
elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
#endif
struct pt_regs *regs = tsk->thread.regs;
- unsigned long msr = tsk->thread.regs->msr;
long err = 0;
BUG_ON(tsk != current);
- BUG_ON(!MSR_TM_ACTIVE(regs->msr));
+ BUG_ON(!MSR_TM_ACTIVE(msr));
WARN_ON(tm_suspend_disabled);
*/
msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX);
- /* Remove TM bits from thread's MSR. The MSR in the sigcontext
- * just indicates to userland that we were doing a transaction, but we
- * don't want to return in transactional state. This also ensures
- * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
- */
- regs->msr &= ~MSR_TS_MASK;
-
#ifdef CONFIG_ALTIVEC
err |= __put_user(v_regs, &sc->v_regs);
err |= __put_user(tm_v_regs, &tm_sc->v_regs);
unsigned long newsp = 0;
long err = 0;
struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+#endif
BUG_ON(tsk != current);
err |= __put_user(0, &frame->uc.uc_flags);
err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- if (MSR_TM_ACTIVE(regs->msr)) {
+ if (MSR_TM_ACTIVE(msr)) {
/* The ucontext_t passed to userland points to the second
* ucontext_t (for transactional state) with its uc_link ptr.
*/
err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext,
&frame->uc_transact.uc_mcontext,
tsk, ksig->sig, NULL,
- (unsigned long)ksig->ka.sa.sa_handler);
+ (unsigned long)ksig->ka.sa.sa_handler,
+ msr);
} else
#endif
{
#include <asm/feature-fixups.h>
#include <asm/code-patching-asm.h>
-#ifdef CONFIG_VMAP_STACK
-#define ADDR_OFFSET 0
-#else
-#define ADDR_OFFSET PAGE_OFFSET
-#endif
-
#ifdef CONFIG_SMP
.section .bss
.align 2
.text
_GLOBAL(hash_page)
#ifdef CONFIG_SMP
- lis r8, (mmu_hash_lock - ADDR_OFFSET)@h
- ori r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l
+ lis r8, (mmu_hash_lock - PAGE_OFFSET)@h
+ ori r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l
lis r0,0x0fff
b 10f
11: lwz r6,0(r8)
cmplw 0,r4,r0
ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */
-#ifdef CONFIG_VMAP_STACK
- tovirt(r5, r5)
-#endif
blt+ 112f /* assume user more likely */
- lis r5, (swapper_pg_dir - ADDR_OFFSET)@ha /* if kernel address, use */
- addi r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l /* kernel page table */
+ lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ addi r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */
112:
#ifndef CONFIG_PTE_64BIT
lwzx r8,r8,r5 /* Get L1 entry */
rlwinm. r8,r8,0,0,20 /* extract pt base address */
#endif
-#ifdef CONFIG_VMAP_STACK
- tovirt(r8, r8)
-#endif
#ifdef CONFIG_SMP
beq- hash_page_out /* return if no mapping */
#else
bne- retry /* retry if someone got there first */
mfsrin r3,r4 /* get segment reg for segment */
+#ifndef CONFIG_VMAP_STACK
mfctr r0
stw r0,_CTR(r11)
+#endif
bl create_hpte /* add the hash table entry */
#ifdef CONFIG_SMP
eieio
- lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha
+ lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha
li r0,0
- stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8)
+ stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
#endif
+#ifdef CONFIG_VMAP_STACK
+ b fast_hash_page_return
+#else
/* Return from the exception */
lwz r5,_CTR(r11)
mtctr r5
lwz r0,GPR0(r11)
lwz r8,GPR8(r11)
b fast_exception_return
+#endif
#ifdef CONFIG_SMP
hash_page_out:
eieio
- lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha
+ lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha
li r0,0
- stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8)
+ stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
blr
#endif /* CONFIG_SMP */
patch_site 1f, patch__hash_page_A1
patch_site 2f, patch__hash_page_A2
/* Get the address of the primary PTE group in the hash table (r3) */
-0: lis r0, (Hash_base - ADDR_OFFSET)@h /* base address of hash table */
+0: lis r0, (Hash_base - PAGE_OFFSET)@h /* base address of hash table */
1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */
2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
xor r3,r3,r0 /* make primary hash */
beq+ 10f /* no PTE: go look for an empty slot */
tlbie r4
- lis r4, (htab_hash_searches - ADDR_OFFSET)@ha
- lwz r6, (htab_hash_searches - ADDR_OFFSET)@l(r4)
+ lis r4, (htab_hash_searches - PAGE_OFFSET)@ha
+ lwz r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
addi r6,r6,1 /* count how many searches we do */
- stw r6, (htab_hash_searches - ADDR_OFFSET)@l(r4)
+ stw r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
mtctr r0
beq+ found_empty
/* update counter of times that the primary PTEG is full */
- lis r4, (primary_pteg_full - ADDR_OFFSET)@ha
- lwz r6, (primary_pteg_full - ADDR_OFFSET)@l(r4)
+ lis r4, (primary_pteg_full - PAGE_OFFSET)@ha
+ lwz r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
addi r6,r6,1
- stw r6, (primary_pteg_full - ADDR_OFFSET)@l(r4)
+ stw r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
patch_site 0f, patch__hash_page_C
/* Search the secondary PTEG for an empty slot */
* lockup here but that shouldn't happen
*/
-1: lis r4, (next_slot - ADDR_OFFSET)@ha /* get next evict slot */
- lwz r6, (next_slot - ADDR_OFFSET)@l(r4)
+1: lis r4, (next_slot - PAGE_OFFSET)@ha /* get next evict slot */
+ lwz r6, (next_slot - PAGE_OFFSET)@l(r4)
addi r6,r6,HPTE_SIZE /* search for candidate */
andi. r6,r6,7*HPTE_SIZE
stw r6,next_slot@l(r4)
void __init MMU_init_hw_patch(void)
{
unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
- unsigned int hash;
+ unsigned int hash = (unsigned int)Hash - PAGE_OFFSET;
if (ppc_md.progress)
ppc_md.progress("hash:patch", 0x345);
/*
* Patch up the instructions in hashtable.S:create_hpte
*/
- if (IS_ENABLED(CONFIG_VMAP_STACK))
- hash = (unsigned int)Hash;
- else
- hash = (unsigned int)Hash - PAGE_OFFSET;
-
modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16);
modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6);
modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6);
/*
* Patch up the instructions in hashtable.S:flush_hash_page
*/
- modify_instruction_site(&patch__flush_hash_A0, 0xffff,
- ((unsigned int)Hash - PAGE_OFFSET) >> 16);
+ modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16);
modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6);
modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6);
modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask);
if (pshift >= pdshift) {
cachep = PGT_CACHE(PTE_T_ORDER);
num_hugepd = 1 << (pshift - pdshift);
+ new = NULL;
} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
- cachep = PGT_CACHE(PTE_INDEX_SIZE);
+ cachep = NULL;
num_hugepd = 1;
+ new = pte_alloc_one(mm);
} else {
cachep = PGT_CACHE(pdshift - pshift);
num_hugepd = 1;
+ new = NULL;
}
- if (!cachep) {
+ if (!cachep && !new) {
WARN_ONCE(1, "No page table cache created for hugetlb tables");
return -ENOMEM;
}
- new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+ if (cachep)
+ new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
BUG_ON(pshift > HUGEPD_SHIFT_MASK);
BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
if (i < num_hugepd) {
for (i = i - 1 ; i >= 0; i--, hpdp--)
*hpdp = __hugepd(0);
- kmem_cache_free(cachep, new);
+ if (cachep)
+ kmem_cache_free(cachep, new);
+ else
+ pte_free(mm, new);
} else {
kmemleak_ignore(new);
}
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
else if (IS_ENABLED(CONFIG_PPC_8xx))
- pgtable_free_tlb(tlb, hugepte,
- get_hugepd_cache_index(PTE_INDEX_SIZE));
+ pgtable_free_tlb(tlb, hugepte, 0);
else
pgtable_free_tlb(tlb, hugepte,
get_hugepd_cache_index(pdshift - shift));
* if we have pdshift and shift value same, we don't
* use pgt cache for hugepd.
*/
- if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
- pgtable_cache_add(PTE_INDEX_SIZE);
- else if (pdshift > shift)
- pgtable_cache_add(pdshift - shift);
- else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx))
+ if (pdshift > shift) {
+ if (!IS_ENABLED(CONFIG_PPC_8xx))
+ pgtable_cache_add(pdshift - shift);
+ } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) ||
+ IS_ENABLED(CONFIG_PPC_8xx)) {
pgtable_cache_add(PTE_T_ORDER);
+ }
configured = true;
}
static void __init kasan_early_hash_table(void)
{
- unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash :
- __pa(early_hash);
+ unsigned int hash = __pa(early_hash);
modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16);
modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16);
int c;
c = skipbl();
+ if (c == '\n') {
+ *s = 0;
+ return;
+ }
+
do {
if( size > 1 ){
*s++ = c;
Image
Image.gz
+loader
+loader.lds
#define EXC_LOAD_PAGE_FAULT 13
#define EXC_STORE_PAGE_FAULT 15
+/* PMP configuration */
+#define PMP_R 0x01
+#define PMP_W 0x02
+#define PMP_X 0x04
+#define PMP_A 0x18
+#define PMP_A_TOR 0x08
+#define PMP_A_NA4 0x10
+#define PMP_A_NAPOT 0x18
+#define PMP_L 0x80
+
/* symbolic CSR names: */
#define CSR_CYCLE 0xc00
#define CSR_TIME 0xc01
#define CSR_MCAUSE 0x342
#define CSR_MTVAL 0x343
#define CSR_MIP 0x344
+#define CSR_PMPCFG0 0x3a0
+#define CSR_PMPADDR0 0x3b0
#define CSR_MHARTID 0xf14
#ifdef CONFIG_RISCV_M_MODE
/* Reset all registers except ra, a0, a1 */
call reset_regs
+ /* Setup a PMP to permit access to all of memory. */
+ li a0, -1
+ csrw CSR_PMPADDR0, a0
+ li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
+ csrw CSR_PMPCFG0, a0
+
/*
* The hartid in a0 is expected later on, and we have no firmware
* to hand it to us.
csr_write(CSR_SCRATCH, 0);
/* Set the exception vector address */
csr_write(CSR_TVEC, &handle_exception);
- /* Enable all interrupts */
- csr_write(CSR_IE, -1);
+ /* Enable interrupts */
+ csr_write(CSR_IE, IE_SIE | IE_EIE);
}
for (i = 0; i < PTRS_PER_PTE; ++i)
set_pte(kasan_early_shadow_pte + i,
mk_pte(virt_to_page(kasan_early_shadow_page),
- PAGE_KERNEL));
+ PAGE_KERNEL));
for (i = 0; i < PTRS_PER_PMD; ++i)
set_pmd(kasan_early_shadow_pmd + i,
- pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)),
- __pgprot(_PAGE_TABLE)));
+ pfn_pmd(PFN_DOWN
+ (__pa((uintptr_t) kasan_early_shadow_pte)),
+ __pgprot(_PAGE_TABLE)));
for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
i += PGDIR_SIZE, ++pgd)
set_pgd(pgd,
- pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))),
- __pgprot(_PAGE_TABLE)));
+ pfn_pgd(PFN_DOWN
+ (__pa(((uintptr_t) kasan_early_shadow_pmd))),
+ __pgprot(_PAGE_TABLE)));
/* init for swapper_pg_dir */
pgd = pgd_offset_k(KASAN_SHADOW_START);
for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
i += PGDIR_SIZE, ++pgd)
set_pgd(pgd,
- pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))),
- __pgprot(_PAGE_TABLE)));
+ pfn_pgd(PFN_DOWN
+ (__pa(((uintptr_t) kasan_early_shadow_pmd))),
+ __pgprot(_PAGE_TABLE)));
flush_tlb_all();
}
static void __init populate(void *start, void *end)
{
- unsigned long i;
+ unsigned long i, offset;
unsigned long vaddr = (unsigned long)start & PAGE_MASK;
unsigned long vend = PAGE_ALIGN((unsigned long)end);
unsigned long n_pages = (vend - vaddr) / PAGE_SIZE;
+ unsigned long n_ptes =
+ ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE;
unsigned long n_pmds =
- (n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 :
- n_pages / PTRS_PER_PTE;
+ ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD;
+
+ pte_t *pte =
+ memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+ pmd_t *pmd =
+ memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
pgd_t *pgd = pgd_offset_k(vaddr);
- pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE);
- pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE);
for (i = 0; i < n_pages; i++) {
phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
-
- set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
+ set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
}
- for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD)
- set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))),
+ for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE)
+ set_pmd(&pmd[i],
+ pfn_pmd(PFN_DOWN(__pa(&pte[offset])),
__pgprot(_PAGE_TABLE)));
- for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE)
- set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))),
+ for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD)
+ set_pgd(&pgd[i],
+ pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
__pgprot(_PAGE_TABLE)));
flush_tlb_all();
unsigned long i;
kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
- (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+ (void *)kasan_mem_to_shadow((void *)
+ VMALLOC_END));
for_each_memblock(memory, reg) {
void *start = (void *)__va(reg->base);
if (start >= end)
break;
- populate(kasan_mem_to_shadow(start),
- kasan_mem_to_shadow(end));
+ populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
};
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(&kasan_early_shadow_pte[i],
mk_pte(virt_to_page(kasan_early_shadow_page),
- __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED)));
+ __pgprot(_PAGE_PRESENT | _PAGE_READ |
+ _PAGE_ACCESSED)));
memset(kasan_early_shadow_page, 0, PAGE_SIZE);
init_task.kasan_depth = 0;
#KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
KBUILD_IMAGE := $(boot)/bzImage
-install: vmlinux
+install:
$(Q)$(MAKE) $(build)=$(boot) $@
bzImage: vmlinux
$(obj)/startup.a: $(OBJECTS) FORCE
$(call if_changed,ar)
-install: $(CONFIGURE) $(obj)/bzImage
+install:
sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
System.map "$(INSTALL_PATH)"
*(unsigned long *) prng.parm_block ^= seed;
for (i = 0; i < 16; i++) {
cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
- (char *) entropy, (char *) entropy,
+ (u8 *) entropy, (u8 *) entropy,
sizeof(entropy));
memcpy(prng.parm_block, entropy, sizeof(entropy));
}
CONFIG_CRASH_DUMP=y
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
+CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
CONFIG_CMM=m
CONFIG_APPLDATA_BASE=y
CONFIG_KVM=m
# CONFIG_NET_VENDOR_EMULEX is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_GOOGLE is not set
-# CONFIG_NET_VENDOR_HP 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_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_XXHASH=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
CONFIG_GDB_SCRIPTS=y
CONFIG_FRAME_WARN=1024
CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_PAGEALLOC=y
CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
CONFIG_DEBUG_PER_CPU_MAPS=y
CONFIG_DEBUG_SHIRQ=y
+CONFIG_PANIC_ON_OOPS=y
CONFIG_DETECT_HUNG_TASK=y
CONFIG_WQ_WATCHDOG=y
-CONFIG_PANIC_ON_OOPS=y
CONFIG_DEBUG_TIMEKEEPING=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCK_STAT=y
CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_DEBUG_CREDENTIALS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=300
+CONFIG_LATENCYTOP=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_STACK_TRACER=y
+CONFIG_IRQSOFF_TRACER=y
+CONFIG_PREEMPT_TRACER=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_HIST_TRIGGERS=y
+CONFIG_S390_PTDUMP=y
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAIL_FUTEX=y
CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
-CONFIG_LATENCYTOP=y
-CONFIG_IRQSOFF_TRACER=y
-CONFIG_PREEMPT_TRACER=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-CONFIG_HIST_TRIGGERS=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
CONFIG_TEST_SORT=y
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_S390_PTDUMP=y
CONFIG_CRASH_DUMP=y
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
+CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
CONFIG_CMM=m
CONFIG_APPLDATA_BASE=y
CONFIG_KVM=m
# CONFIG_NET_VENDOR_EMULEX is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
# CONFIG_NET_VENDOR_GOOGLE is not set
-# CONFIG_NET_VENDOR_HP 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_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_XXHASH=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_PANIC_ON_OOPS=y
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_STACK_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
-CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
+CONFIG_S390_PTDUMP=y
CONFIG_LKDTM=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_S390_PTDUMP=y
static inline void storage_key_init_range(unsigned long start, unsigned long end)
{
- if (PAGE_DEFAULT_KEY)
+ if (PAGE_DEFAULT_KEY != 0)
__storage_key_init_range(start, end);
}
void cpu_detect_mhz_feature(void);
extern const struct seq_operations cpuinfo_op;
-extern int sysctl_ieee_emulation_warnings;
extern void execve_tail(void);
extern void __bpon(void);
* @scount: SBAL count
* @sflags: whole SBAL flags
* @length: length
- * @addr: address
+ * @addr: absolute data address
*/
struct qdio_buffer_element {
u8 eflags;
u8 scount;
u8 sflags;
u32 length;
- void *addr;
+ u64 addr;
} __attribute__ ((packed, aligned(16)));
/**
* @sbal: absolute SBAL address
*/
struct sl_element {
- unsigned long sbal;
+ u64 sbal;
} __attribute__ ((packed));
/**
#define __PAGE_OFFSET __PAGE_OFFSET_BASE
#include "../../mm/ident_map.c"
-/* Used by pgtable.h asm code to force instruction serialization. */
-unsigned long __force_order;
-
/* Used to track our page table allocation area. */
struct alloc_pgt_data {
unsigned char *pgt_buf;
void io_bitmap_share(struct task_struct *tsk);
void io_bitmap_exit(void);
-void tss_update_io_bitmap(void);
+void native_tss_update_io_bitmap(void);
+
+#ifdef CONFIG_PARAVIRT_XXL
+#include <asm/paravirt.h>
+#else
+#define tss_update_io_bitmap native_tss_update_io_bitmap
+#endif
+
#else
static inline void io_bitmap_share(struct task_struct *tsk) { }
static inline void io_bitmap_exit(void) { }
#define X86EMUL_SMM_MASK (1 << 6)
#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7)
+/*
+ * fastop functions are declared as taking a never-defined fastop parameter,
+ * so they can't be called from C directly.
+ */
+struct fastop;
+
+typedef void (*fastop_t)(struct fastop *);
+
struct x86_emulate_ctxt {
const struct x86_emulate_ops *ops;
struct operand src;
struct operand src2;
struct operand dst;
- int (*execute)(struct x86_emulate_ctxt *ctxt);
+ union {
+ int (*execute)(struct x86_emulate_ctxt *ctxt);
+ fastop_t fop;
+ };
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
/*
* The following six fields are cleared together,
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+ void (*update_emulated_instruction)(struct kvm_vcpu *vcpu);
void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
void (*patch_hypercall)(struct kvm_vcpu *vcpu,
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
- void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+ int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
#define MSR_K7_HWCR 0xc0010015
#define MSR_K7_HWCR_SMMLOCK_BIT 0
#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT 30
+#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
}
+#ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_update_io_bitmap(void)
+{
+ PVOP_VCALL0(cpu.update_io_bitmap);
+}
+#endif
+
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
void (*load_sp0)(unsigned long sp0);
+#ifdef CONFIG_X86_IOPL_IOPERM
+ void (*update_io_bitmap)(void);
+#endif
+
void (*wbinvd)(void);
/* cpuid emulation, mostly so that caps bits can be disabled */
}
#endif /* CONFIG_SCHED_MC_PRIO */
+#ifdef CONFIG_SMP
+#include <asm/cpufeature.h>
+
+DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key);
+
+#define arch_scale_freq_invariant() static_branch_likely(&arch_scale_freq_key)
+
+DECLARE_PER_CPU(unsigned long, arch_freq_scale);
+
+static inline long arch_scale_freq_capacity(int cpu)
+{
+ return per_cpu(arch_freq_scale, cpu);
+}
+#define arch_scale_freq_capacity arch_scale_freq_capacity
+
+extern void arch_scale_freq_tick(void);
+#define arch_scale_freq_tick arch_scale_freq_tick
+
+extern void arch_set_max_freq_ratio(bool turbo_disabled);
+#else
+static inline void arch_set_max_freq_ratio(bool turbo_disabled)
+{
+}
+#endif
+
#endif /* _ASM_X86_TOPOLOGY_H */
#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA)
#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING)
-#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000
+#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
#define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING)
#define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING)
#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */
#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */
+#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
#endif /* _ASM_X86_VMXFEATURES_H */
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
static const int amd_erratum_383[];
static const int amd_erratum_400[];
+static const int amd_erratum_1054[];
static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
/*
/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
if (!cpu_has(c, X86_FEATURE_XENPV))
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+ /*
+ * Turn on the Instructions Retired free counter on machines not
+ * susceptible to erratum #1054 "Instructions Retired Performance
+ * Counter May Be Inaccurate".
+ */
+ if (cpu_has(c, X86_FEATURE_IRPERF) &&
+ !cpu_has_amd_erratum(c, amd_erratum_1054))
+ msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
}
#ifdef CONFIG_X86_32
static const int amd_erratum_383[] =
AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+ AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
{
* cpuid bit to be set. We need to ensure that we
* update that bit in this CPU's "cpu_info".
*/
- get_cpu_cap(c);
+ set_cpu_cap(c, X86_FEATURE_OSPKE);
}
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
.store = store,
};
+static void threshold_block_release(struct kobject *kobj);
+
static struct kobj_type threshold_ktype = {
.sysfs_ops = &threshold_ops,
.default_attrs = default_attrs,
+ .release = threshold_block_release,
};
static const char *get_name(unsigned int bank, struct threshold_block *b)
return buf_mcatype;
}
-static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
- unsigned int block, u32 address)
+static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb,
+ unsigned int bank, unsigned int block,
+ u32 address)
{
struct threshold_block *b = NULL;
u32 low, high;
INIT_LIST_HEAD(&b->miscj);
- if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
- list_add(&b->miscj,
- &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
- } else {
- per_cpu(threshold_banks, cpu)[bank]->blocks = b;
- }
+ if (tb->blocks)
+ list_add(&b->miscj, &tb->blocks->miscj);
+ else
+ tb->blocks = b;
- err = kobject_init_and_add(&b->kobj, &threshold_ktype,
- per_cpu(threshold_banks, cpu)[bank]->kobj,
- get_name(bank, b));
+ err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
if (err)
goto out_free;
recurse:
if (!address)
return 0;
- err = allocate_threshold_blocks(cpu, bank, block, address);
+ err = allocate_threshold_blocks(cpu, tb, bank, block, address);
if (err)
goto out_free;
goto out_free;
}
- per_cpu(threshold_banks, cpu)[bank] = b;
-
if (is_shared_bank(bank)) {
refcount_set(&b->cpus, 1);
}
}
- err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
- if (!err)
- goto out;
+ err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+ if (err)
+ goto out_free;
+
+ per_cpu(threshold_banks, cpu)[bank] = b;
+
+ return 0;
out_free:
kfree(b);
return err;
}
-static void deallocate_threshold_block(unsigned int cpu,
- unsigned int bank)
+static void threshold_block_release(struct kobject *kobj)
+{
+ kfree(to_block(kobj));
+}
+
+static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
{
struct threshold_block *pos = NULL;
struct threshold_block *tmp = NULL;
return;
list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
- kobject_put(&pos->kobj);
list_del(&pos->miscj);
- kfree(pos);
+ kobject_put(&pos->kobj);
}
- kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
- per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
+ kobject_put(&head->blocks->kobj);
}
static void __threshold_remove_blocks(struct threshold_bank *b)
static enum efi_secureboot_mode get_sb_mode(void)
{
- efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
- efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
efi_status_t status;
unsigned long size;
}
/* Get variable contents into buffer */
- status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+ status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
NULL, &size, &secboot);
if (status == EFI_NOT_FOUND) {
pr_info("ima: secureboot mode disabled\n");
}
size = sizeof(setupmode);
- status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+ status = efi.get_variable(L"SetupMode", &efi_variable_guid,
NULL, &size, &setupmode);
if (status != EFI_SUCCESS) /* ignore unknown SetupMode */
}
}
+static bool pv_tlb_flush_supported(void)
+{
+ return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
+
#ifdef CONFIG_SMP
+
+static bool pv_ipi_supported(void)
+{
+ return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+}
+
+static bool pv_sched_yield_supported(void)
+{
+ return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
#define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG)
static void __send_ipi_mask(const struct cpumask *mask, int vector)
static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
{
unsigned int this_cpu = smp_processor_id();
- struct cpumask new_mask;
+ struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
const struct cpumask *local_mask;
- cpumask_copy(&new_mask, mask);
- cpumask_clear_cpu(this_cpu, &new_mask);
- local_mask = &new_mask;
+ cpumask_copy(new_mask, mask);
+ cpumask_clear_cpu(this_cpu, new_mask);
+ local_mask = new_mask;
__send_ipi_mask(local_mask, vector);
}
update_intr_gate(X86_TRAP_PF, async_page_fault);
}
-static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
static void kvm_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
u8 state;
int cpu;
struct kvm_steal_time *src;
- struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+ struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
cpumask_copy(flushmask, cpumask);
/*
pv_ops.time.steal_clock = kvm_steal_clock;
}
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
- kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ if (pv_tlb_flush_supported()) {
pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
pv_ops.mmu.tlb_remove_table = tlb_remove_table;
+ pr_info("KVM setup pv remote TLB flush\n");
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
#ifdef CONFIG_SMP
smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
- if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
- !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
- kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ if (pv_sched_yield_supported()) {
smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
pr_info("KVM setup pv sched yield\n");
}
static void __init kvm_apic_init(void)
{
#if defined(CONFIG_SMP)
- if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI))
+ if (pv_ipi_supported())
kvm_setup_pv_ipi();
#endif
}
}
arch_initcall(activate_jump_labels);
-static __init int kvm_setup_pv_tlb_flush(void)
+static __init int kvm_alloc_cpumask(void)
{
int cpu;
+ bool alloc = false;
if (!kvm_para_available() || nopv)
return 0;
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
- kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ if (pv_tlb_flush_supported())
+ alloc = true;
+
+#if defined(CONFIG_SMP)
+ if (pv_ipi_supported())
+ alloc = true;
+#endif
+
+ if (alloc)
for_each_possible_cpu(cpu) {
- zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+ zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
}
- pr_info("KVM setup pv remote TLB flush\n");
- }
return 0;
}
-arch_initcall(kvm_setup_pv_tlb_flush);
+arch_initcall(kvm_alloc_cpumask);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
#include <asm/timer.h>
#include <asm/special_insns.h>
#include <asm/tlb.h>
+#include <asm/io_bitmap.h>
/*
* nop stub, which must not clobber anything *including the stack* to
.cpu.iret = native_iret,
.cpu.swapgs = native_swapgs,
+#ifdef CONFIG_X86_IOPL_IOPERM
+ .cpu.update_io_bitmap = native_tss_update_io_bitmap,
+#endif
+
.cpu.start_context_switch = paravirt_nop,
.cpu.end_context_switch = paravirt_nop,
/**
* tss_update_io_bitmap - Update I/O bitmap before exiting to usermode
*/
-void tss_update_io_bitmap(void)
+void native_tss_update_io_bitmap(void)
{
struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
struct thread_struct *t = ¤t->thread;
*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}
+static void init_freq_invariance(void);
+
/*
* Report back to the Boot Processor during boot time or to the caller processor
* during CPU online.
*/
set_cpu_sibling_map(raw_smp_processor_id());
+ init_freq_invariance();
+
/*
* Get our bogomips.
* Update loops_per_jiffy in cpu_data. Previous call to
set_sched_topology(x86_topology);
set_cpu_sibling_map(0);
-
+ init_freq_invariance();
smp_sanity_check();
switch (apic_intr_mode) {
}
#endif
+
+/*
+ * APERF/MPERF frequency ratio computation.
+ *
+ * The scheduler wants to do frequency invariant accounting and needs a <1
+ * ratio to account for the 'current' frequency, corresponding to
+ * freq_curr / freq_max.
+ *
+ * Since the frequency freq_curr on x86 is controlled by micro-controller and
+ * our P-state setting is little more than a request/hint, we need to observe
+ * the effective frequency 'BusyMHz', i.e. the average frequency over a time
+ * interval after discarding idle time. This is given by:
+ *
+ * BusyMHz = delta_APERF / delta_MPERF * freq_base
+ *
+ * where freq_base is the max non-turbo P-state.
+ *
+ * The freq_max term has to be set to a somewhat arbitrary value, because we
+ * can't know which turbo states will be available at a given point in time:
+ * it all depends on the thermal headroom of the entire package. We set it to
+ * the turbo level with 4 cores active.
+ *
+ * Benchmarks show that's a good compromise between the 1C turbo ratio
+ * (freq_curr/freq_max would rarely reach 1) and something close to freq_base,
+ * which would ignore the entire turbo range (a conspicuous part, making
+ * freq_curr/freq_max always maxed out).
+ *
+ * An exception to the heuristic above is the Atom uarch, where we choose the
+ * highest turbo level for freq_max since Atom's are generally oriented towards
+ * power efficiency.
+ *
+ * Setting freq_max to anything less than the 1C turbo ratio makes the ratio
+ * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
+ */
+
+DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key);
+
+static DEFINE_PER_CPU(u64, arch_prev_aperf);
+static DEFINE_PER_CPU(u64, arch_prev_mperf);
+static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE;
+static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE;
+
+void arch_set_max_freq_ratio(bool turbo_disabled)
+{
+ arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE :
+ arch_turbo_freq_ratio;
+}
+
+static bool turbo_disabled(void)
+{
+ u64 misc_en;
+ int err;
+
+ err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+ if (err)
+ return false;
+
+ return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
+}
+
+static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+ int err;
+
+ err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */
+ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */
+
+ return true;
+}
+
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+
+#define ICPU(model) \
+ {X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0}
+
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_XEON_PHI_KNL),
+ ICPU(INTEL_FAM6_XEON_PHI_KNM),
+ {}
+};
+
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_SKYLAKE_X),
+ {}
+};
+
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_D),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS),
+ {}
+};
+
+static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+ int num_delta_fratio)
+{
+ int fratio, delta_fratio, found;
+ int err, i;
+ u64 msr;
+
+ if (!x86_match_cpu(has_knl_turbo_ratio_limits))
+ return false;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+ if (err)
+ return false;
+
+ fratio = (msr >> 8) & 0xFF;
+ i = 16;
+ found = 0;
+ do {
+ if (found >= num_delta_fratio) {
+ *turbo_freq = fratio;
+ return true;
+ }
+
+ delta_fratio = (msr >> (i + 5)) & 0x7;
+
+ if (delta_fratio) {
+ found += 1;
+ fratio -= delta_fratio;
+ }
+
+ i += 8;
+ } while (i < 64);
+
+ return true;
+}
+
+static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+{
+ u64 ratios, counts;
+ u32 group_size;
+ int err, i;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+ if (err)
+ return false;
+
+ for (i = 0; i < 64; i += 8) {
+ group_size = (counts >> i) & 0xFF;
+ if (group_size >= size) {
+ *turbo_freq = (ratios >> i) & 0xFF;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+ int err;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+ *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */
+
+ return true;
+}
+
+static bool intel_set_max_freq_ratio(void)
+{
+ u64 base_freq, turbo_freq;
+
+ if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
+ goto out;
+
+ if (x86_match_cpu(has_glm_turbo_ratio_limits) &&
+ skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+ goto out;
+
+ if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+ goto out;
+
+ if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
+ skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4))
+ goto out;
+
+ if (core_set_max_freq_ratio(&base_freq, &turbo_freq))
+ goto out;
+
+ return false;
+
+out:
+ arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
+ base_freq);
+ arch_set_max_freq_ratio(turbo_disabled());
+ return true;
+}
+
+static void init_counter_refs(void *arg)
+{
+ u64 aperf, mperf;
+
+ rdmsrl(MSR_IA32_APERF, aperf);
+ rdmsrl(MSR_IA32_MPERF, mperf);
+
+ this_cpu_write(arch_prev_aperf, aperf);
+ this_cpu_write(arch_prev_mperf, mperf);
+}
+
+static void init_freq_invariance(void)
+{
+ bool ret = false;
+
+ if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF))
+ return;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ ret = intel_set_max_freq_ratio();
+
+ if (ret) {
+ on_each_cpu(init_counter_refs, NULL, 1);
+ static_branch_enable(&arch_scale_freq_key);
+ } else {
+ pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
+ }
+}
+
+DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+
+void arch_scale_freq_tick(void)
+{
+ u64 freq_scale;
+ u64 aperf, mperf;
+ u64 acnt, mcnt;
+
+ if (!arch_scale_freq_invariant())
+ return;
+
+ rdmsrl(MSR_IA32_APERF, aperf);
+ rdmsrl(MSR_IA32_MPERF, mperf);
+
+ acnt = aperf - this_cpu_read(arch_prev_aperf);
+ mcnt = mperf - this_cpu_read(arch_prev_mperf);
+ if (!mcnt)
+ return;
+
+ this_cpu_write(arch_prev_aperf, aperf);
+ this_cpu_write(arch_prev_mperf, mperf);
+
+ acnt <<= 2*SCHED_CAPACITY_SHIFT;
+ mcnt *= arch_max_freq_ratio;
+
+ freq_scale = div64_u64(acnt, mcnt);
+
+ if (freq_scale > SCHED_CAPACITY_SCALE)
+ freq_scale = SCHED_CAPACITY_SCALE;
+
+ this_cpu_write(arch_freq_scale, freq_scale);
+}
If unsure, say N.
+config KVM_WERROR
+ bool "Compile KVM with -Werror"
+ # KASAN may cause the build to fail due to larger frames
+ default y if X86_64 && !KASAN
+ # We use the dependency on !COMPILE_TEST to not be enabled
+ # blindly in allmodconfig or allyesconfig configurations
+ depends on (X86_64 && !KASAN) || !COMPILE_TEST
+ depends on EXPERT
+ help
+ Add -Werror to the build flags for (and only for) i915.ko.
+
+ If in doubt, say "N".
+
config KVM_INTEL
tristate "KVM for Intel (and compatible) processors support"
depends on KVM && IA32_FEAT_CTL
# SPDX-License-Identifier: GPL-2.0
ccflags-y += -Iarch/x86/kvm
+ccflags-$(CONFIG_KVM_WERROR) += -Werror
KVM := ../../../virt/kvm
#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
#define FASTOP_SIZE 8
-/*
- * fastop functions have a special calling convention:
- *
- * dst: rax (in/out)
- * src: rdx (in/out)
- * src2: rcx (in)
- * flags: rflags (in/out)
- * ex: rsi (in:fastop pointer, out:zero if exception)
- *
- * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
- * different operand sizes can be reached by calculation, rather than a jump
- * table (which would be bigger than the code).
- *
- * fastop functions are declared as taking a never-defined fastop parameter,
- * so they can't be called from C directly.
- */
-
-struct fastop;
-
struct opcode {
u64 flags : 56;
u64 intercept : 8;
#define ON64(x)
#endif
-typedef void (*fastop_t)(struct fastop *);
-
+/*
+ * fastop functions have a special calling convention:
+ *
+ * dst: rax (in/out)
+ * src: rdx (in/out)
+ * src2: rcx (in)
+ * flags: rflags (in/out)
+ * ex: rsi (in:fastop pointer, out:zero if exception)
+ *
+ * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
+ * different operand sizes can be reached by calculation, rather than a jump
+ * table (which would be bigger than the code).
+ */
static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
#define __FOP_FUNC(name) \
if (ctxt->execute) {
if (ctxt->d & Fastop)
- rc = fastop(ctxt, (fastop_t)ctxt->execute);
+ rc = fastop(ctxt, ctxt->fop);
else
rc = ctxt->execute(ctxt);
if (rc != X86EMUL_CONTINUE)
kvm_set_msi_irq(vcpu->kvm, entry, &irq);
- if (irq.level &&
+ if (irq.trig_mode &&
kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
irq.dest_id, irq.dest_mode))
__set_bit(irq.vector, ioapic_handled_vectors);
static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
{
u8 val;
- if (pv_eoi_get_user(vcpu, &val) < 0)
+ if (pv_eoi_get_user(vcpu, &val) < 0) {
printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
(unsigned long long)vcpu->arch.pv_eoi.msr_val);
+ return false;
+ }
return val & 0x1;
}
apic->regs + APIC_TMR);
}
- if (vcpu->arch.apicv_active)
- kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
- else {
+ if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
kvm_lapic_set_irr(vector, apic);
-
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
}
/* These depend on page entry type, so compute them now. */
__field(bool, r)
__field(bool, x)
- __field(u8, u)
+ __field(signed char, u)
),
TP_fast_assign(
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+#ifdef MODULE
static const struct x86_cpu_id svm_cpu_id[] = {
X86_FEATURE_MATCH(X86_FEATURE_SVM),
{}
};
MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
+#endif
#define IOPM_ALLOC_ORDER 2
#define MSRPM_ALLOC_ORDER 1
static int svm_cpu_init(int cpu)
{
struct svm_cpu_data *sd;
- int r;
sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
if (!sd)
return -ENOMEM;
sd->cpu = cpu;
- r = -ENOMEM;
sd->save_area = alloc_page(GFP_KERNEL);
if (!sd->save_area)
- goto err_1;
+ goto free_cpu_data;
if (svm_sev_enabled()) {
- r = -ENOMEM;
sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
sizeof(void *),
GFP_KERNEL);
if (!sd->sev_vmcbs)
- goto err_1;
+ goto free_save_area;
}
per_cpu(svm_data, cpu) = sd;
return 0;
-err_1:
+free_save_area:
+ __free_page(sd->save_area);
+free_cpu_data:
kfree(sd);
- return r;
+ return -ENOMEM;
}
kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
}
+static void svm_hardware_teardown(void)
+{
+ int cpu;
+
+ if (svm_sev_enabled()) {
+ bitmap_free(sev_asid_bitmap);
+ bitmap_free(sev_reclaim_asid_bitmap);
+
+ sev_flush_asids();
+ }
+
+ for_each_possible_cpu(cpu)
+ svm_cpu_uninit(cpu);
+
+ __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
+ iopm_base = 0;
+}
+
static __init int svm_hardware_setup(void)
{
int cpu;
return 0;
err:
- __free_pages(iopm_pages, IOPM_ALLOC_ORDER);
- iopm_base = 0;
+ svm_hardware_teardown();
return r;
}
-static __exit void svm_hardware_unsetup(void)
-{
- int cpu;
-
- if (svm_sev_enabled()) {
- bitmap_free(sev_asid_bitmap);
- bitmap_free(sev_reclaim_asid_bitmap);
-
- sev_flush_asids();
- }
-
- for_each_possible_cpu(cpu)
- svm_cpu_uninit(cpu);
-
- __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
- iopm_base = 0;
-}
-
static void init_seg(struct vmcb_seg *seg)
{
seg->selector = 0;
static int avic_init_vcpu(struct vcpu_svm *svm)
{
int ret;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
- if (!kvm_vcpu_apicv_active(&svm->vcpu))
+ if (!avic || !irqchip_in_kernel(vcpu->kvm))
return 0;
ret = avic_init_backing_page(&svm->vcpu);
struct vmcb *vmcb = svm->vmcb;
bool activated = kvm_vcpu_apicv_active(vcpu);
+ if (!avic)
+ return;
+
if (activated) {
/**
* During AVIC temporary deactivation, guest could update
return;
}
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
{
+ if (!vcpu->arch.apicv_active)
+ return -1;
+
kvm_lapic_set_irr(vec, vcpu->arch.apic);
smp_mb__after_atomic();
put_cpu();
} else
kvm_vcpu_wake_up(vcpu);
+
+ return 0;
}
static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
- .hardware_unsetup = svm_hardware_unsetup,
+ .hardware_unsetup = svm_hardware_teardown,
.check_processor_compatibility = svm_check_processor_compat,
.hardware_enable = svm_hardware_enable,
.hardware_disable = svm_hardware_disable,
.run = svm_vcpu_run,
.handle_exit = handle_exit,
.skip_emulated_instruction = skip_emulated_instruction,
+ .update_emulated_instruction = NULL,
.set_interrupt_shadow = svm_set_interrupt_shadow,
.get_interrupt_shadow = svm_get_interrupt_shadow,
.patch_hypercall = svm_patch_hypercall,
extern bool __read_mostly enable_unrestricted_guest;
extern bool __read_mostly enable_ept_ad_bits;
extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
extern int __read_mostly pt_mode;
#define PT_MODE_SYSTEM 0
* or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume.
*
* Returns:
- * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
- * NVMX_ENTRY_VMFAIL: Consistency check VMFail
- * NVMX_ENTRY_VMEXIT: Consistency check VMExit
- * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
+ * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode
+ * NVMX_VMENTRY_VMFAIL: Consistency check VMFail
+ * NVMX_VMENTRY_VMEXIT: Consistency check VMExit
+ * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error
*/
enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
bool from_vmentry)
unsigned long exit_qual;
bool block_nested_events =
vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
+ bool mtf_pending = vmx->nested.mtf_pending;
struct kvm_lapic *apic = vcpu->arch.apic;
+ /*
+ * Clear the MTF state. If a higher priority VM-exit is delivered first,
+ * this state is discarded.
+ */
+ vmx->nested.mtf_pending = false;
+
if (lapic_in_kernel(vcpu) &&
test_bit(KVM_APIC_INIT, &apic->pending_events)) {
if (block_nested_events)
return 0;
}
+ /*
+ * Process any exceptions that are not debug traps before MTF.
+ */
+ if (vcpu->arch.exception.pending &&
+ !vmx_pending_dbg_trap(vcpu) &&
+ nested_vmx_check_exception(vcpu, &exit_qual)) {
+ if (block_nested_events)
+ return -EBUSY;
+ nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ return 0;
+ }
+
+ if (mtf_pending) {
+ if (block_nested_events)
+ return -EBUSY;
+ nested_vmx_update_pending_dbg(vcpu);
+ nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0);
+ return 0;
+ }
+
if (vcpu->arch.exception.pending &&
- nested_vmx_check_exception(vcpu, &exit_qual)) {
+ nested_vmx_check_exception(vcpu, &exit_qual)) {
if (block_nested_events)
return -EBUSY;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
return 1;
}
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+ int size)
{
- unsigned long exit_qualification;
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
gpa_t bitmap, last_bitmap;
- unsigned int port;
- int size;
u8 b;
- if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
- return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
- exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
- port = exit_qualification >> 16;
- size = (exit_qualification & 7) + 1;
-
last_bitmap = (gpa_t)-1;
b = -1;
return false;
}
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ unsigned long exit_qualification;
+ unsigned short port;
+ int size;
+
+ if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+ return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+ port = exit_qualification >> 16;
+ size = (exit_qualification & 7) + 1;
+
+ return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
/*
- * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
+ * Return 1 if we should exit from L2 to L1 to handle an MSR access,
* rather than handle it ourselves in L0. I.e., check whether L1 expressed
* disinterest in the current event (read or write a specific MSR) by using an
* MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
if (vmx->nested.nested_run_pending)
kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+
+ if (vmx->nested.mtf_pending)
+ kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING;
}
}
vmx->nested.nested_run_pending =
!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+ vmx->nested.mtf_pending =
+ !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
+
ret = -EINVAL;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
* bit in the high half is on if the corresponding bit in the control field
* may be on. See also vmx_control_verify().
*/
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
- bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
{
/*
* Note that as a general rule, the high half of the MSRs (bits in
PIN_BASED_EXT_INTR_MASK |
PIN_BASED_NMI_EXITING |
PIN_BASED_VIRTUAL_NMIS |
- (apicv ? PIN_BASED_POSTED_INTR : 0);
+ (enable_apicv ? PIN_BASED_POSTED_INTR : 0);
msrs->pinbased_ctls_high |=
PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
PIN_BASED_VMX_PREEMPTION_TIMER;
};
void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
- bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
void nested_vmx_hardware_unsetup(void);
__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
void nested_vmx_set_vmcs_shadowing_bitmap(void);
int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+ int size);
static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
{
return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
}
+static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
+}
+
static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
{
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+#ifdef MODULE
static const struct x86_cpu_id vmx_cpu_id[] = {
X86_FEATURE_MATCH(X86_FEATURE_VMX),
{}
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+#endif
bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
static bool __read_mostly fasteoi = 1;
module_param(fasteoi, bool, S_IRUGO);
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
module_param(enable_apicv, bool, S_IRUGO);
/*
vmx->guest_msrs[i].mask);
}
+
+ if (vmx->nested.need_vmcs12_to_shadow_sync)
+ nested_sync_vmcs12_to_shadow(vcpu);
+
if (vmx->guest_state_loaded)
return;
return 1;
}
+
+/*
+ * Recognizes a pending MTF VM-exit and records the nested state for later
+ * delivery.
+ */
+static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!is_guest_mode(vcpu))
+ return;
+
+ /*
+ * Per the SDM, MTF takes priority over debug-trap exceptions besides
+ * T-bit traps. As instruction emulation is completed (i.e. at the
+ * instruction boundary), any #DB exception pending delivery must be a
+ * debug-trap. Record the pending MTF state to be delivered in
+ * vmx_check_nested_events().
+ */
+ if (nested_cpu_has_mtf(vmcs12) &&
+ (!vcpu->arch.exception.pending ||
+ vcpu->arch.exception.nr == DB_VECTOR))
+ vmx->nested.mtf_pending = true;
+ else
+ vmx->nested.mtf_pending = false;
+}
+
+static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+ vmx_update_emulated_instruction(vcpu);
+ return skip_emulated_instruction(vcpu);
+}
+
static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
{
/*
* 2. If target vcpu isn't running(root mode), kick it to pick up the
* interrupt from PIR in next vmentry.
*/
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int r;
r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
if (!r)
- return;
+ return 0;
+
+ if (!vcpu->arch.apicv_active)
+ return -1;
if (pi_test_and_set_pir(vector, &vmx->pi_desc))
- return;
+ return 0;
/* If a previous notification has sent the IPI, nothing to do. */
if (pi_test_and_set_on(&vmx->pi_desc))
- return;
+ return 0;
if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
kvm_vcpu_kick(vcpu);
+
+ return 0;
}
/*
vmcs_write32(PLE_WINDOW, vmx->ple_window);
}
- if (vmx->nested.need_vmcs12_to_shadow_sync)
- nested_sync_vmcs12_to_shadow(vcpu);
+ /*
+ * We did this in prepare_switch_to_guest, because it needs to
+ * be within srcu_read_lock.
+ */
+ WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync);
if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
if (nested)
nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
- vmx_capability.ept,
- kvm_vcpu_apicv_active(vcpu));
+ vmx_capability.ept);
else
memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
return -EIO;
if (nested)
- nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
- enable_apicv);
+ nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
smp_processor_id());
to_vmx(vcpu)->req_immediate_exit = true;
}
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+ struct x86_instruction_info *info)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ unsigned short port;
+ bool intercept;
+ int size;
+
+ if (info->intercept == x86_intercept_in ||
+ info->intercept == x86_intercept_ins) {
+ port = info->src_val;
+ size = info->dst_bytes;
+ } else {
+ port = info->dst_val;
+ size = info->src_bytes;
+ }
+
+ /*
+ * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+ * VM-exits depend on the 'unconditional IO exiting' VM-execution
+ * control.
+ *
+ * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+ */
+ if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+ intercept = nested_cpu_has(vmcs12,
+ CPU_BASED_UNCOND_IO_EXITING);
+ else
+ intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+ /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */
+ return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
static int vmx_check_intercept(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+ switch (info->intercept) {
/*
* RDPID causes #UD if disabled through secondary execution controls.
* Because it is marked as EmulateOnUD, we need to intercept it here.
*/
- if (info->intercept == x86_intercept_rdtscp &&
- !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
- ctxt->exception.vector = UD_VECTOR;
- ctxt->exception.error_code_valid = false;
- return X86EMUL_PROPAGATE_FAULT;
- }
+ case x86_intercept_rdtscp:
+ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+ ctxt->exception.vector = UD_VECTOR;
+ ctxt->exception.error_code_valid = false;
+ return X86EMUL_PROPAGATE_FAULT;
+ }
+ break;
+
+ case x86_intercept_in:
+ case x86_intercept_ins:
+ case x86_intercept_out:
+ case x86_intercept_outs:
+ return vmx_check_intercept_io(vcpu, info);
+
+ case x86_intercept_lgdt:
+ case x86_intercept_lidt:
+ case x86_intercept_lldt:
+ case x86_intercept_ltr:
+ case x86_intercept_sgdt:
+ case x86_intercept_sidt:
+ case x86_intercept_sldt:
+ case x86_intercept_str:
+ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+ return X86EMUL_CONTINUE;
+
+ /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */
+ break;
/* TODO: check more intercepts... */
- return X86EMUL_CONTINUE;
+ default:
+ break;
+ }
+
+ return X86EMUL_UNHANDLEABLE;
}
#ifdef CONFIG_X86_64
if (nested) {
nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
- vmx_capability.ept, enable_apicv);
+ vmx_capability.ept);
r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
if (r)
.run = vmx_vcpu_run,
.handle_exit = vmx_handle_exit,
- .skip_emulated_instruction = skip_emulated_instruction,
+ .skip_emulated_instruction = vmx_skip_emulated_instruction,
+ .update_emulated_instruction = vmx_update_emulated_instruction,
.set_interrupt_shadow = vmx_set_interrupt_shadow,
.get_interrupt_shadow = vmx_get_interrupt_shadow,
.patch_hypercall = vmx_patch_hypercall,
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
+ /* Pending MTF VM-exit into L1. */
+ bool mtf_pending;
+
struct loaded_vmcs vmcs02;
/*
kvm_rip_write(vcpu, ctxt->eip);
if (r && ctxt->tf)
r = kvm_vcpu_do_singlestep(vcpu);
+ if (kvm_x86_ops->update_emulated_instruction)
+ kvm_x86_ops->update_emulated_instruction(vcpu);
__kvm_set_rflags(vcpu, ctxt->eflags);
}
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
#ifdef CONFIG_CPU_FREQ
- struct cpufreq_policy policy;
+ struct cpufreq_policy *policy;
int cpu;
- memset(&policy, 0, sizeof(policy));
cpu = get_cpu();
- cpufreq_get_policy(&policy, cpu);
- if (policy.cpuinfo.max_freq)
- max_tsc_khz = policy.cpuinfo.max_freq;
+ policy = cpufreq_cpu_get(cpu);
+ if (policy && policy->cpuinfo.max_freq)
+ max_tsc_khz = policy->cpuinfo.max_freq;
put_cpu();
+ cpufreq_cpu_put(policy);
#endif
cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
if (!ops->cpu_has_kvm_support()) {
- printk(KERN_ERR "kvm: no hardware support\n");
+ pr_err_ratelimited("kvm: no hardware support\n");
r = -EOPNOTSUPP;
goto out;
}
if (ops->disabled_by_bios()) {
- printk(KERN_ERR "kvm: disabled by bios\n");
+ pr_err_ratelimited("kvm: disabled by bios\n");
r = -EOPNOTSUPP;
goto out;
}
{
const struct ptdump_range ptdump_ranges[] = {
#ifdef CONFIG_X86_64
-
-#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1))
-#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \
- normalize_addr_shift)
-
{0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
- {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
+ {GUARD_HOLE_END_ADDR, ~0UL},
#else
{0, ~0UL},
#endif
static inline phys_addr_t
virt_to_phys_or_null_size(void *va, unsigned long size)
{
- bool bad_size;
+ phys_addr_t pa;
if (!va)
return 0;
if (virt_addr_valid(va))
return virt_to_phys(va);
- /*
- * A fully aligned variable on the stack is guaranteed not to
- * cross a page bounary. Try to catch strings on the stack by
- * checking that 'size' is a power of two.
- */
- bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+ pa = slow_virt_to_phys(va);
- WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+ /* check if the object crosses a page boundary */
+ if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK))
+ return 0;
- return slow_virt_to_phys(va);
+ return pa;
}
#define virt_to_phys_or_null(addr) \
static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
- 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;
+ return EFI_UNSUPPORTED;
}
static efi_status_t efi_thunk_set_time(efi_time_t *tm)
{
- 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;
+ return EFI_UNSUPPORTED;
}
static efi_status_t
efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
efi_time_t *tm)
{
- 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);
- phys_tm = virt_to_phys_or_null(tm);
-
- 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;
+ return EFI_UNSUPPORTED;
}
static efi_status_t
efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
{
- 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;
+ return EFI_UNSUPPORTED;
}
static unsigned long efi_name_size(efi_char16_t *name)
efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 *attr, unsigned long *data_size, void *data)
{
+ u8 buf[24] __aligned(8);
+ efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
efi_status_t status;
u32 phys_name, phys_vendor, phys_attr;
u32 phys_data_size, phys_data;
spin_lock_irqsave(&efi_runtime_lock, flags);
+ *vnd = *vendor;
+
phys_data_size = virt_to_phys_or_null(data_size);
- phys_vendor = virt_to_phys_or_null(vendor);
+ phys_vendor = virt_to_phys_or_null(vnd);
phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
phys_attr = virt_to_phys_or_null(attr);
phys_data = virt_to_phys_or_null_size(data, *data_size);
- status = efi_thunk(get_variable, phys_name, phys_vendor,
- phys_attr, phys_data_size, phys_data);
+ if (!phys_name || (data && !phys_data))
+ status = EFI_INVALID_PARAMETER;
+ else
+ status = efi_thunk(get_variable, phys_name, phys_vendor,
+ phys_attr, phys_data_size, phys_data);
spin_unlock_irqrestore(&efi_runtime_lock, flags);
efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 attr, unsigned long data_size, void *data)
{
+ u8 buf[24] __aligned(8);
+ efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
u32 phys_name, phys_vendor, phys_data;
efi_status_t status;
unsigned long flags;
spin_lock_irqsave(&efi_runtime_lock, flags);
+ *vnd = *vendor;
+
phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
- phys_vendor = virt_to_phys_or_null(vendor);
+ phys_vendor = virt_to_phys_or_null(vnd);
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);
+ if (!phys_name || !phys_data)
+ status = EFI_INVALID_PARAMETER;
+ else
+ status = efi_thunk(set_variable, phys_name, phys_vendor,
+ attr, data_size, phys_data);
spin_unlock_irqrestore(&efi_runtime_lock, flags);
u32 attr, unsigned long data_size,
void *data)
{
+ u8 buf[24] __aligned(8);
+ efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
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;
+ *vnd = *vendor;
+
phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
- phys_vendor = virt_to_phys_or_null(vendor);
+ phys_vendor = virt_to_phys_or_null(vnd);
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);
+ if (!phys_name || !phys_data)
+ status = EFI_INVALID_PARAMETER;
+ else
+ status = efi_thunk(set_variable, phys_name, phys_vendor,
+ attr, data_size, phys_data);
spin_unlock_irqrestore(&efi_runtime_lock, flags);
efi_char16_t *name,
efi_guid_t *vendor)
{
+ u8 buf[24] __aligned(8);
+ efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
efi_status_t status;
u32 phys_name_size, phys_name, phys_vendor;
unsigned long flags;
spin_lock_irqsave(&efi_runtime_lock, flags);
+ *vnd = *vendor;
+
phys_name_size = virt_to_phys_or_null(name_size);
- phys_vendor = virt_to_phys_or_null(vendor);
+ phys_vendor = virt_to_phys_or_null(vnd);
phys_name = virt_to_phys_or_null_size(name, *name_size);
- status = efi_thunk(get_next_variable, phys_name_size,
- phys_name, phys_vendor);
+ if (!phys_name)
+ status = EFI_INVALID_PARAMETER;
+ else
+ status = efi_thunk(get_next_variable, phys_name_size,
+ phys_name, phys_vendor);
spin_unlock_irqrestore(&efi_runtime_lock, flags);
+ *vendor = *vnd;
return status;
}
static efi_status_t
efi_thunk_get_next_high_mono_count(u32 *count)
{
- 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;
+ return EFI_UNSUPPORTED;
}
static void
#include <asm/mwait.h>
#include <asm/pci_x86.h>
#include <asm/cpu.h>
+#ifdef CONFIG_X86_IOPL_IOPERM
+#include <asm/io_bitmap.h>
+#endif
#ifdef CONFIG_ACPI
#include <linux/acpi.h>
this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
+#ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_update_io_bitmap(void)
+{
+ struct physdev_set_iobitmap iobitmap;
+ struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+
+ native_tss_update_io_bitmap();
+
+ iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) +
+ tss->x86_tss.io_bitmap_base;
+ if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID)
+ iobitmap.nr_ports = 0;
+ else
+ iobitmap.nr_ports = IO_BITMAP_BITS;
+
+ HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+#endif
+
static void xen_io_delay(void)
{
}
static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
int ret;
+#ifdef CONFIG_X86_64
+ unsigned int which;
+ u64 base;
+#endif
ret = 0;
switch (msr) {
#ifdef CONFIG_X86_64
- unsigned which;
- u64 base;
-
case MSR_FS_BASE: which = SEGBASE_FS; goto set;
case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set;
case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set;
.write_idt_entry = xen_write_idt_entry,
.load_sp0 = xen_load_sp0,
+#ifdef CONFIG_X86_IOPL_IOPERM
+ .update_io_bitmap = xen_update_io_bitmap,
+#endif
.io_delay = xen_io_delay,
/* Xen takes care of %gs when switching to usermode for us */
*/
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
- blk_mq_request_bypass_insert(rq, false);
+ blk_mq_request_bypass_insert(rq, false, false);
return;
}
bool has_sched,
struct request *rq)
{
- /* dispatch flush rq directly */
- if (rq->rq_flags & RQF_FLUSH_SEQ) {
- spin_lock(&hctx->lock);
- list_add(&rq->queuelist, &hctx->dispatch);
- spin_unlock(&hctx->lock);
+ /*
+ * dispatch flush and passthrough rq directly
+ *
+ * passthrough request has to be added to hctx->dispatch directly.
+ * For some reason, device may be in one situation which can't
+ * handle FS request, so STS_RESOURCE is always returned and the
+ * FS request will be added to hctx->dispatch. However passthrough
+ * request may be required at that time for fixing the problem. If
+ * passthrough request is added to scheduler queue, there isn't any
+ * chance to dispatch it given we prioritize requests in hctx->dispatch.
+ */
+ if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
return true;
- }
if (has_sched)
rq->rq_flags |= RQF_SORTED;
WARN_ON(e && (rq->tag != -1));
- if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
+ if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
+ blk_mq_request_bypass_insert(rq, at_head, false);
goto run;
+ }
if (e && e->type->ops.insert_requests) {
LIST_HEAD(list);
return tag + tag_offset;
}
-void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
- struct blk_mq_ctx *ctx, unsigned int tag)
+void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
+ unsigned int tag)
{
if (!blk_mq_tag_is_reserved(tags, tag)) {
const int real_tag = tag - tags->nr_reserved_tags;
extern void blk_mq_free_tags(struct blk_mq_tags *tags);
extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
- struct blk_mq_ctx *ctx, unsigned int tag);
+extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
+ unsigned int tag);
extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
struct blk_mq_tags **tags,
unsigned int depth, bool can_grow);
blk_pm_mark_last_busy(rq);
rq->mq_hctx = NULL;
if (rq->tag != -1)
- blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+ blk_mq_put_tag(hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
- blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+ blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
* merge.
*/
if (rq->rq_flags & RQF_DONTPREP)
- blk_mq_request_bypass_insert(rq, false);
+ blk_mq_request_bypass_insert(rq, false, false);
else
blk_mq_sched_insert_request(rq, true, false, false);
}
q->mq_ops->commit_rqs(hctx);
spin_lock(&hctx->lock);
- list_splice_init(list, &hctx->dispatch);
+ list_splice_tail_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
/*
* Should only be used carefully, when the caller knows we want to
* bypass a potential IO scheduler on the target device.
*/
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+ bool run_queue)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
spin_lock(&hctx->lock);
- list_add_tail(&rq->queuelist, &hctx->dispatch);
+ if (at_head)
+ list_add(&rq->queuelist, &hctx->dispatch);
+ else
+ list_add_tail(&rq->queuelist, &hctx->dispatch);
spin_unlock(&hctx->lock);
if (run_queue)
if (bypass_insert)
return BLK_STS_RESOURCE;
- blk_mq_request_bypass_insert(rq, run_queue);
+ blk_mq_request_bypass_insert(rq, false, run_queue);
return BLK_STS_OK;
}
ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
- blk_mq_request_bypass_insert(rq, true);
+ blk_mq_request_bypass_insert(rq, false, true);
else if (ret != BLK_STS_OK)
blk_mq_end_request(rq, ret);
if (ret != BLK_STS_OK) {
if (ret == BLK_STS_RESOURCE ||
ret == BLK_STS_DEV_RESOURCE) {
- blk_mq_request_bypass_insert(rq,
+ blk_mq_request_bypass_insert(rq, false,
list_empty(list));
break;
}
}
static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
unsigned long ret = 0;
}
static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
- struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
struct hrtimer_sleeper hs;
if (q->poll_nsec > 0)
nsecs = q->poll_nsec;
else
- nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+ nsecs = blk_mq_poll_nsecs(q, rq);
if (!nsecs)
return false;
return false;
}
- return blk_mq_poll_hybrid_sleep(q, hctx, rq);
+ return blk_mq_poll_hybrid_sleep(q, rq);
}
/**
*/
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+ bool run_queue);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
- blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
+ blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
rq->tag = -1;
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
[HASH_ALGO_TGR_128] = "tgr128",
[HASH_ALGO_TGR_160] = "tgr160",
[HASH_ALGO_TGR_192] = "tgr192",
- [HASH_ALGO_SM3_256] = "sm3-256",
+ [HASH_ALGO_SM3_256] = "sm3",
[HASH_ALGO_STREEBOG_256] = "streebog256",
[HASH_ALGO_STREEBOG_512] = "streebog512",
};
}
#endif
+static bool acpi_no_watchdog;
+
static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
{
const struct acpi_table_wdat *wdat = NULL;
acpi_status status;
- if (acpi_disabled)
+ if (acpi_disabled || acpi_no_watchdog)
return NULL;
status = acpi_get_table(ACPI_SIG_WDAT, 0,
}
EXPORT_SYMBOL_GPL(acpi_has_watchdog);
+/* ACPI watchdog can be disabled on boot command line */
+static int __init disable_acpi_watchdog(char *str)
+{
+ acpi_no_watchdog = true;
+ return 1;
+}
+__setup("acpi_no_watchdog", disable_acpi_watchdog);
+
void __init acpi_watchdog_init(void)
{
const struct acpi_wdat_entry *entries;
gas = &entries[i].register_region;
res.start = gas->address;
+ res.end = res.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1;
if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
res.flags = IORESOURCE_MEM;
- res.end = res.start + ALIGN(gas->access_width, 4) - 1;
} else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
res.flags = IORESOURCE_IO;
- res.end = res.start + gas->access_width - 1;
} else {
pr_warn("Unsupported address space: %u\n",
gas->space_id);
handler) (acpi_gbl_fixed_event_handlers[event].context));
}
+/*******************************************************************************
+ *
+ * FUNCTION: acpi_any_fixed_event_status_set
+ *
+ * PARAMETERS: None
+ *
+ * RETURN: TRUE or FALSE
+ *
+ * DESCRIPTION: Checks the PM status register for active fixed events
+ *
+ ******************************************************************************/
+
+u32 acpi_any_fixed_event_status_set(void)
+{
+ acpi_status status;
+ u32 in_status;
+ u32 in_enable;
+ u32 i;
+
+ status = acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &in_enable);
+ if (ACPI_FAILURE(status)) {
+ return (FALSE);
+ }
+
+ status = acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &in_status);
+ if (ACPI_FAILURE(status)) {
+ return (FALSE);
+ }
+
+ /*
+ * Check for all possible Fixed Events and dispatch those that are active
+ */
+ for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) {
+
+ /* Both the status and enable bits must be on for this event */
+
+ if ((in_status & acpi_gbl_fixed_event_info[i].status_bit_mask) &&
+ (in_enable & acpi_gbl_fixed_event_info[i].enable_bit_mask)) {
+ return (TRUE);
+ }
+ }
+
+ return (FALSE);
+}
+
#endif /* !ACPI_REDUCED_HARDWARE */
if (irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
return true;
+ /*
+ * If the status bit of any enabled fixed event is set, the
+ * wakeup is regarded as valid.
+ */
+ if (acpi_any_fixed_event_status_set())
+ return true;
+
/*
* If there are no EC events to process and at least one of the
* other enabled GPEs is active, the wakeup is regarded as a
/* selects the fdc and drive, and enables the fdc's input/dma. */
static void set_fdc(int drive)
{
+ unsigned int new_fdc = fdc;
+
if (drive >= 0 && drive < N_DRIVE) {
- fdc = FDC(drive);
+ new_fdc = FDC(drive);
current_drive = drive;
}
- if (fdc != 1 && fdc != 0) {
+ if (new_fdc >= N_FDC) {
pr_info("bad fdc value\n");
return;
}
+ fdc = new_fdc;
set_dor(fdc, ~0, 8);
#if N_FDC > 1
set_dor(1 - fdc, ~8, 0);
#include <linux/fault-inject.h>
struct nullb_cmd {
- struct list_head list;
- struct llist_node ll_list;
- struct __call_single_data csd;
struct request *rq;
struct bio *bio;
unsigned int tag;
for (i = 0; i < nq->queue_depth; i++) {
cmd = &nq->cmds[i];
- INIT_LIST_HEAD(&cmd->list);
- cmd->ll_list.next = NULL;
cmd->tag = -1U;
}
.release = pcd_block_release,
.ioctl = pcd_block_ioctl,
#ifdef CONFIG_COMPAT
- .ioctl = blkdev_compat_ptr_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
#endif
.check_events = pcd_block_check_events,
};
.check_events = gdrom_bdops_check_events,
.ioctl = gdrom_bdops_ioctl,
#ifdef CONFIG_COMPAT
- .ioctl = blkdev_compat_ptr_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
#endif
};
tpm-$(CONFIG_OF) += eventlog/of.o
obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
obj-$(CONFIG_TCG_TIS) += tpm_tis.o
-obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o
-tpm_tis_spi_mod-y := tpm_tis_spi.o
-tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
+obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
+tpm_tis_spi-y := tpm_tis_spi_main.o
+tpm_tis_spi-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o
return 0;
}
+ bank->crypto_id = HASH_ALGO__LAST;
+
return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size);
}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 Infineon Technologies AG
- * Copyright (C) 2016 STMicroelectronics SAS
- *
- * Authors:
- * Peter Huewe <peter.huewe@infineon.com>
- * Christophe Ricard <christophe-h.ricard@st.com>
- *
- * Maintained by: <tpmdd-devel@lists.sourceforge.net>
- *
- * Device driver for TCG/TCPA TPM (trusted platform module).
- * Specifications at www.trustedcomputinggroup.org
- *
- * This device driver implements the TPM interface as defined in
- * the TCG TPM Interface Spec version 1.3, revision 27 via _raw/native
- * SPI access_.
- *
- * It is based on the original tpm_tis device driver from Leendert van
- * Dorn and Kyleen Hall and Jarko Sakkinnen.
- */
-
-#include <linux/acpi.h>
-#include <linux/completion.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-#include <linux/of_device.h>
-#include <linux/spi/spi.h>
-#include <linux/tpm.h>
-
-#include "tpm.h"
-#include "tpm_tis_core.h"
-#include "tpm_tis_spi.h"
-
-#define MAX_SPI_FRAMESIZE 64
-
-/*
- * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short,
- * keep trying to read from the device until MISO goes high indicating the
- * wait state has ended.
- *
- * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
- */
-static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy,
- struct spi_transfer *spi_xfer)
-{
- struct spi_message m;
- int ret, i;
-
- if ((phy->iobuf[3] & 0x01) == 0) {
- // handle SPI wait states
- phy->iobuf[0] = 0;
-
- for (i = 0; i < TPM_RETRY; i++) {
- spi_xfer->len = 1;
- spi_message_init(&m);
- spi_message_add_tail(spi_xfer, &m);
- ret = spi_sync_locked(phy->spi_device, &m);
- if (ret < 0)
- return ret;
- if (phy->iobuf[0] & 0x01)
- break;
- }
-
- if (i == TPM_RETRY)
- return -ETIMEDOUT;
- }
-
- return 0;
-}
-
-int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
- u8 *in, const u8 *out)
-{
- struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
- int ret = 0;
- struct spi_message m;
- struct spi_transfer spi_xfer;
- u8 transfer_len;
-
- spi_bus_lock(phy->spi_device->master);
-
- while (len) {
- transfer_len = min_t(u16, len, MAX_SPI_FRAMESIZE);
-
- phy->iobuf[0] = (in ? 0x80 : 0) | (transfer_len - 1);
- phy->iobuf[1] = 0xd4;
- phy->iobuf[2] = addr >> 8;
- phy->iobuf[3] = addr;
-
- memset(&spi_xfer, 0, sizeof(spi_xfer));
- spi_xfer.tx_buf = phy->iobuf;
- spi_xfer.rx_buf = phy->iobuf;
- spi_xfer.len = 4;
- spi_xfer.cs_change = 1;
-
- spi_message_init(&m);
- spi_message_add_tail(&spi_xfer, &m);
- ret = spi_sync_locked(phy->spi_device, &m);
- if (ret < 0)
- goto exit;
-
- ret = phy->flow_control(phy, &spi_xfer);
- if (ret < 0)
- goto exit;
-
- spi_xfer.cs_change = 0;
- spi_xfer.len = transfer_len;
- spi_xfer.delay_usecs = 5;
-
- if (in) {
- spi_xfer.tx_buf = NULL;
- } else if (out) {
- spi_xfer.rx_buf = NULL;
- memcpy(phy->iobuf, out, transfer_len);
- out += transfer_len;
- }
-
- spi_message_init(&m);
- spi_message_add_tail(&spi_xfer, &m);
- reinit_completion(&phy->ready);
- ret = spi_sync_locked(phy->spi_device, &m);
- if (ret < 0)
- goto exit;
-
- if (in) {
- memcpy(in, phy->iobuf, transfer_len);
- in += transfer_len;
- }
-
- len -= transfer_len;
- }
-
-exit:
- spi_bus_unlock(phy->spi_device->master);
- return ret;
-}
-
-static int tpm_tis_spi_read_bytes(struct tpm_tis_data *data, u32 addr,
- u16 len, u8 *result)
-{
- return tpm_tis_spi_transfer(data, addr, len, result, NULL);
-}
-
-static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
- u16 len, const u8 *value)
-{
- return tpm_tis_spi_transfer(data, addr, len, NULL, value);
-}
-
-int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
-{
- __le16 result_le;
- int rc;
-
- rc = data->phy_ops->read_bytes(data, addr, sizeof(u16),
- (u8 *)&result_le);
- if (!rc)
- *result = le16_to_cpu(result_le);
-
- return rc;
-}
-
-int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
-{
- __le32 result_le;
- int rc;
-
- rc = data->phy_ops->read_bytes(data, addr, sizeof(u32),
- (u8 *)&result_le);
- if (!rc)
- *result = le32_to_cpu(result_le);
-
- return rc;
-}
-
-int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
-{
- __le32 value_le;
- int rc;
-
- value_le = cpu_to_le32(value);
- rc = data->phy_ops->write_bytes(data, addr, sizeof(u32),
- (u8 *)&value_le);
-
- return rc;
-}
-
-int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
- int irq, const struct tpm_tis_phy_ops *phy_ops)
-{
- phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
- if (!phy->iobuf)
- return -ENOMEM;
-
- phy->spi_device = spi;
-
- return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL);
-}
-
-static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
- .read_bytes = tpm_tis_spi_read_bytes,
- .write_bytes = tpm_tis_spi_write_bytes,
- .read16 = tpm_tis_spi_read16,
- .read32 = tpm_tis_spi_read32,
- .write32 = tpm_tis_spi_write32,
-};
-
-static int tpm_tis_spi_probe(struct spi_device *dev)
-{
- struct tpm_tis_spi_phy *phy;
- int irq;
-
- phy = devm_kzalloc(&dev->dev, sizeof(struct tpm_tis_spi_phy),
- GFP_KERNEL);
- if (!phy)
- return -ENOMEM;
-
- phy->flow_control = tpm_tis_spi_flow_control;
-
- /* If the SPI device has an IRQ then use that */
- if (dev->irq > 0)
- irq = dev->irq;
- else
- irq = -1;
-
- init_completion(&phy->ready);
- return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops);
-}
-
-typedef int (*tpm_tis_spi_probe_func)(struct spi_device *);
-
-static int tpm_tis_spi_driver_probe(struct spi_device *spi)
-{
- const struct spi_device_id *spi_dev_id = spi_get_device_id(spi);
- tpm_tis_spi_probe_func probe_func;
-
- probe_func = of_device_get_match_data(&spi->dev);
- if (!probe_func && spi_dev_id)
- probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data;
- if (!probe_func)
- return -ENODEV;
-
- return probe_func(spi);
-}
-
-static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume);
-
-static int tpm_tis_spi_remove(struct spi_device *dev)
-{
- struct tpm_chip *chip = spi_get_drvdata(dev);
-
- tpm_chip_unregister(chip);
- tpm_tis_remove(chip);
- return 0;
-}
-
-static const struct spi_device_id tpm_tis_spi_id[] = {
- { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
- { "cr50", (unsigned long)cr50_spi_probe },
- {}
-};
-MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id);
-
-static const struct of_device_id of_tis_spi_match[] = {
- { .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe },
- { .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe },
- { .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe },
- { .compatible = "google,cr50", .data = cr50_spi_probe },
- {}
-};
-MODULE_DEVICE_TABLE(of, of_tis_spi_match);
-
-static const struct acpi_device_id acpi_tis_spi_match[] = {
- {"SMO0768", 0},
- {}
-};
-MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match);
-
-static struct spi_driver tpm_tis_spi_driver = {
- .driver = {
- .name = "tpm_tis_spi",
- .pm = &tpm_tis_pm,
- .of_match_table = of_match_ptr(of_tis_spi_match),
- .acpi_match_table = ACPI_PTR(acpi_tis_spi_match),
- },
- .probe = tpm_tis_spi_driver_probe,
- .remove = tpm_tis_spi_remove,
- .id_table = tpm_tis_spi_id,
-};
-module_spi_driver(tpm_tis_spi_driver);
-
-MODULE_DESCRIPTION("TPM Driver for native SPI access");
-MODULE_LICENSE("GPL");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 Infineon Technologies AG
+ * Copyright (C) 2016 STMicroelectronics SAS
+ *
+ * Authors:
+ * Peter Huewe <peter.huewe@infineon.com>
+ * Christophe Ricard <christophe-h.ricard@st.com>
+ *
+ * Maintained by: <tpmdd-devel@lists.sourceforge.net>
+ *
+ * Device driver for TCG/TCPA TPM (trusted platform module).
+ * Specifications at www.trustedcomputinggroup.org
+ *
+ * This device driver implements the TPM interface as defined in
+ * the TCG TPM Interface Spec version 1.3, revision 27 via _raw/native
+ * SPI access_.
+ *
+ * It is based on the original tpm_tis device driver from Leendert van
+ * Dorn and Kyleen Hall and Jarko Sakkinnen.
+ */
+
+#include <linux/acpi.h>
+#include <linux/completion.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/tpm.h>
+
+#include "tpm.h"
+#include "tpm_tis_core.h"
+#include "tpm_tis_spi.h"
+
+#define MAX_SPI_FRAMESIZE 64
+
+/*
+ * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short,
+ * keep trying to read from the device until MISO goes high indicating the
+ * wait state has ended.
+ *
+ * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
+ */
+static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy,
+ struct spi_transfer *spi_xfer)
+{
+ struct spi_message m;
+ int ret, i;
+
+ if ((phy->iobuf[3] & 0x01) == 0) {
+ // handle SPI wait states
+ phy->iobuf[0] = 0;
+
+ for (i = 0; i < TPM_RETRY; i++) {
+ spi_xfer->len = 1;
+ spi_message_init(&m);
+ spi_message_add_tail(spi_xfer, &m);
+ ret = spi_sync_locked(phy->spi_device, &m);
+ if (ret < 0)
+ return ret;
+ if (phy->iobuf[0] & 0x01)
+ break;
+ }
+
+ if (i == TPM_RETRY)
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+ u8 *in, const u8 *out)
+{
+ struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+ int ret = 0;
+ struct spi_message m;
+ struct spi_transfer spi_xfer;
+ u8 transfer_len;
+
+ spi_bus_lock(phy->spi_device->master);
+
+ while (len) {
+ transfer_len = min_t(u16, len, MAX_SPI_FRAMESIZE);
+
+ phy->iobuf[0] = (in ? 0x80 : 0) | (transfer_len - 1);
+ phy->iobuf[1] = 0xd4;
+ phy->iobuf[2] = addr >> 8;
+ phy->iobuf[3] = addr;
+
+ memset(&spi_xfer, 0, sizeof(spi_xfer));
+ spi_xfer.tx_buf = phy->iobuf;
+ spi_xfer.rx_buf = phy->iobuf;
+ spi_xfer.len = 4;
+ spi_xfer.cs_change = 1;
+
+ spi_message_init(&m);
+ spi_message_add_tail(&spi_xfer, &m);
+ ret = spi_sync_locked(phy->spi_device, &m);
+ if (ret < 0)
+ goto exit;
+
+ ret = phy->flow_control(phy, &spi_xfer);
+ if (ret < 0)
+ goto exit;
+
+ spi_xfer.cs_change = 0;
+ spi_xfer.len = transfer_len;
+ spi_xfer.delay_usecs = 5;
+
+ if (in) {
+ spi_xfer.tx_buf = NULL;
+ } else if (out) {
+ spi_xfer.rx_buf = NULL;
+ memcpy(phy->iobuf, out, transfer_len);
+ out += transfer_len;
+ }
+
+ spi_message_init(&m);
+ spi_message_add_tail(&spi_xfer, &m);
+ reinit_completion(&phy->ready);
+ ret = spi_sync_locked(phy->spi_device, &m);
+ if (ret < 0)
+ goto exit;
+
+ if (in) {
+ memcpy(in, phy->iobuf, transfer_len);
+ in += transfer_len;
+ }
+
+ len -= transfer_len;
+ }
+
+exit:
+ spi_bus_unlock(phy->spi_device->master);
+ return ret;
+}
+
+static int tpm_tis_spi_read_bytes(struct tpm_tis_data *data, u32 addr,
+ u16 len, u8 *result)
+{
+ return tpm_tis_spi_transfer(data, addr, len, result, NULL);
+}
+
+static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
+ u16 len, const u8 *value)
+{
+ return tpm_tis_spi_transfer(data, addr, len, NULL, value);
+}
+
+int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
+{
+ __le16 result_le;
+ int rc;
+
+ rc = data->phy_ops->read_bytes(data, addr, sizeof(u16),
+ (u8 *)&result_le);
+ if (!rc)
+ *result = le16_to_cpu(result_le);
+
+ return rc;
+}
+
+int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
+{
+ __le32 result_le;
+ int rc;
+
+ rc = data->phy_ops->read_bytes(data, addr, sizeof(u32),
+ (u8 *)&result_le);
+ if (!rc)
+ *result = le32_to_cpu(result_le);
+
+ return rc;
+}
+
+int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
+{
+ __le32 value_le;
+ int rc;
+
+ value_le = cpu_to_le32(value);
+ rc = data->phy_ops->write_bytes(data, addr, sizeof(u32),
+ (u8 *)&value_le);
+
+ return rc;
+}
+
+int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
+ int irq, const struct tpm_tis_phy_ops *phy_ops)
+{
+ phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
+ if (!phy->iobuf)
+ return -ENOMEM;
+
+ phy->spi_device = spi;
+
+ return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL);
+}
+
+static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
+ .read_bytes = tpm_tis_spi_read_bytes,
+ .write_bytes = tpm_tis_spi_write_bytes,
+ .read16 = tpm_tis_spi_read16,
+ .read32 = tpm_tis_spi_read32,
+ .write32 = tpm_tis_spi_write32,
+};
+
+static int tpm_tis_spi_probe(struct spi_device *dev)
+{
+ struct tpm_tis_spi_phy *phy;
+ int irq;
+
+ phy = devm_kzalloc(&dev->dev, sizeof(struct tpm_tis_spi_phy),
+ GFP_KERNEL);
+ if (!phy)
+ return -ENOMEM;
+
+ phy->flow_control = tpm_tis_spi_flow_control;
+
+ /* If the SPI device has an IRQ then use that */
+ if (dev->irq > 0)
+ irq = dev->irq;
+ else
+ irq = -1;
+
+ init_completion(&phy->ready);
+ return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops);
+}
+
+typedef int (*tpm_tis_spi_probe_func)(struct spi_device *);
+
+static int tpm_tis_spi_driver_probe(struct spi_device *spi)
+{
+ const struct spi_device_id *spi_dev_id = spi_get_device_id(spi);
+ tpm_tis_spi_probe_func probe_func;
+
+ probe_func = of_device_get_match_data(&spi->dev);
+ if (!probe_func && spi_dev_id)
+ probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data;
+ if (!probe_func)
+ return -ENODEV;
+
+ return probe_func(spi);
+}
+
+static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume);
+
+static int tpm_tis_spi_remove(struct spi_device *dev)
+{
+ struct tpm_chip *chip = spi_get_drvdata(dev);
+
+ tpm_chip_unregister(chip);
+ tpm_tis_remove(chip);
+ return 0;
+}
+
+static const struct spi_device_id tpm_tis_spi_id[] = {
+ { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+ { "cr50", (unsigned long)cr50_spi_probe },
+ {}
+};
+MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id);
+
+static const struct of_device_id of_tis_spi_match[] = {
+ { .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe },
+ { .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe },
+ { .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe },
+ { .compatible = "google,cr50", .data = cr50_spi_probe },
+ {}
+};
+MODULE_DEVICE_TABLE(of, of_tis_spi_match);
+
+static const struct acpi_device_id acpi_tis_spi_match[] = {
+ {"SMO0768", 0},
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match);
+
+static struct spi_driver tpm_tis_spi_driver = {
+ .driver = {
+ .name = "tpm_tis_spi",
+ .pm = &tpm_tis_pm,
+ .of_match_table = of_match_ptr(of_tis_spi_match),
+ .acpi_match_table = ACPI_PTR(acpi_tis_spi_match),
+ },
+ .probe = tpm_tis_spi_driver_probe,
+ .remove = tpm_tis_spi_remove,
+ .id_table = tpm_tis_spi_id,
+};
+module_spi_driver(tpm_tis_spi_driver);
+
+MODULE_DESCRIPTION("TPM Driver for native SPI access");
+MODULE_LICENSE("GPL");
pol = policy->last_policy;
} else if (def_gov) {
pol = cpufreq_parse_policy(def_gov->name);
- } else {
- return -ENODATA;
+ /*
+ * In case the default governor is neiter "performance"
+ * nor "powersave", fall back to the initial policy
+ * value set by the driver.
+ */
+ if (pol == CPUFREQ_POLICY_UNKNOWN)
+ pol = policy->policy;
}
+ if (pol != CPUFREQ_POLICY_PERFORMANCE &&
+ pol != CPUFREQ_POLICY_POWERSAVE)
+ return -ENODATA;
}
return cpufreq_set_policy(policy, gov, pol);
*/
if (global.turbo_disabled_mf != global.turbo_disabled) {
global.turbo_disabled_mf = global.turbo_disabled;
+ arch_set_max_freq_ratio(global.turbo_disabled);
for_each_possible_cpu(cpu)
intel_pstate_update_max_freq(cpu);
} else {
{
struct devfreq *devfreq;
struct devfreq_governor *governor;
- static atomic_t devfreq_no = ATOMIC_INIT(-1);
int err = 0;
if (!dev || !profile || !governor_name) {
devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
atomic_set(&devfreq->suspend_count, 0);
- dev_set_name(&devfreq->dev, "devfreq%d",
- atomic_inc_return(&devfreq_no));
+ dev_set_name(&devfreq->dev, "%s", dev_name(dev));
err = device_register(&devfreq->dev);
if (err) {
mutex_unlock(&devfreq->lock);
seed = early_memremap(efi.rng_seed, sizeof(*seed));
if (seed != NULL) {
- size = seed->size;
+ size = READ_ONCE(seed->size);
early_memunmap(seed, sizeof(*seed));
} else {
pr_err("Could not map UEFI random seed!\n");
sizeof(*seed) + size);
if (seed != NULL) {
pr_notice("seeding entropy pool\n");
- add_bootloader_randomness(seed->bits, seed->size);
+ add_bootloader_randomness(seed->bits, size);
early_memunmap(seed, sizeof(*seed) + size);
} else {
pr_err("Could not map UEFI random seed!\n");
config FSI_MASTER_ASPEED
tristate "FSI ASPEED master"
+ depends on HAS_IOMEM
help
This option enables a FSI master that is present behind an OPB bridge
in the AST2600.
static struct drm_driver kms_driver = {
.driver_features =
- DRIVER_USE_AGP | DRIVER_ATOMIC |
+ DRIVER_ATOMIC |
DRIVER_GEM |
DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ |
DRIVER_SYNCOBJ_TIMELINE,
uint32_t srbm_soft_reset;
bool prt_warning;
uint64_t stolen_size;
+ uint32_t sdpif_register;
/* apertures */
u64 shared_aperture_start;
u64 shared_aperture_end;
return 0;
}
+static int psp_dtm_unload(struct psp_context *psp)
+{
+ int ret;
+ struct psp_gfx_cmd_resp *cmd;
+
+ /*
+ * TODO: bypass the unloading in sriov for now
+ */
+ if (amdgpu_sriov_vf(psp->adev))
+ return 0;
+
+ cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+ if (!cmd)
+ return -ENOMEM;
+
+ psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id);
+
+ ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+ kfree(cmd);
+
+ return ret;
+}
+
int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
{
/*
if (!psp->dtm_context.dtm_initialized)
return 0;
- ret = psp_hdcp_unload(psp);
+ ret = psp_dtm_unload(psp);
if (ret)
return ret;
{
uint64_t clock;
+ amdgpu_gfx_off_ctrl(adev, false);
mutex_lock(&adev->gfx.gpu_clock_mutex);
WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
mutex_unlock(&adev->gfx.gpu_clock_mutex);
+ amdgpu_gfx_off_ctrl(adev, true);
return clock;
}
return false;
}
+static bool is_raven_kicker(struct amdgpu_device *adev)
+{
+ if (adev->pm.fw_version >= 0x41e2b)
+ return true;
+ else
+ return false;
+}
+
static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
{
if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
break;
case CHIP_RAVEN:
if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) &&
- ((adev->gfx.rlc_fw_version != 106 &&
+ ((!is_raven_kicker(adev) &&
adev->gfx.rlc_fw_version < 531) ||
- (adev->gfx.rlc_fw_version == 53815) ||
(adev->gfx.rlc_feature_version < 1) ||
!adev->gfx.rlc.is_rlc_v2_1))
adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
{
uint64_t clock;
+ amdgpu_gfx_off_ctrl(adev, false);
mutex_lock(&adev->gfx.gpu_clock_mutex);
if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
uint32_t tmp, lsb, msb, i = 0;
((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
}
mutex_unlock(&adev->gfx.gpu_clock_mutex);
+ amdgpu_gfx_off_ctrl(adev, true);
return clock;
}
}
}
+/**
+ * gmc_v9_0_restore_registers - restores regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This restores register values, saved at suspend.
+ */
+static void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
+{
+ if (adev->asic_type == CHIP_RAVEN)
+ WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
+}
+
/**
* gmc_v9_0_gart_enable - gart enable
*
return r;
}
+/**
+ * gmc_v9_0_save_registers - saves regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This saves potential register values that should be
+ * restored upon resume
+ */
+static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
+{
+ if (adev->asic_type == CHIP_RAVEN)
+ adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
+}
+
/**
* gmc_v9_0_gart_disable - gart disable
*
static int gmc_v9_0_suspend(void *handle)
{
+ int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- return gmc_v9_0_hw_fini(adev);
+ r = gmc_v9_0_hw_fini(adev);
+ if (r)
+ return r;
+
+ gmc_v9_0_save_registers(adev);
+
+ return 0;
}
static int gmc_v9_0_resume(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ gmc_v9_0_restore_registers(adev);
r = gmc_v9_0_hw_init(adev);
if (r)
return r;
static u32 soc15_get_xclk(struct amdgpu_device *adev)
{
- return adev->clock.spll.reference_freq;
+ u32 reference_clock = adev->clock.spll.reference_freq;
+
+ if (adev->asic_type == CHIP_RAVEN)
+ return reference_clock / 4;
+
+ return reference_clock;
}
mutex_lock(&aconnector->hpd_lock);
#ifdef CONFIG_DRM_AMD_DC_HDCP
- if (adev->asic_type >= CHIP_RAVEN)
+ if (adev->dm.hdcp_workqueue)
hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index);
#endif
if (aconnector->fake_enable)
}
}
#ifdef CONFIG_DRM_AMD_DC_HDCP
- if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ)
- hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index);
+ if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) {
+ if (adev->dm.hdcp_workqueue)
+ hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index);
+ }
#endif
if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) ||
(dc_link->type == dc_connection_mst_branch))
drm_connector_attach_vrr_capable_property(
&aconnector->base);
#ifdef CONFIG_DRM_AMD_DC_HDCP
- if (adev->asic_type >= CHIP_RAVEN)
+ if (adev->dm.hdcp_workqueue)
drm_connector_attach_content_protection_property(&aconnector->base, true);
#endif
}
enum mod_hdcp_status status;
if (is_dp_hdcp(hdcp))
- status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) &&
- HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ?
+ status = (hdcp->auth.msg.hdcp2.rxcaps_dp[0] == HDCP_2_2_RX_CAPS_VERSION_VAL) &&
+ HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[2]) ?
MOD_HDCP_STATUS_SUCCESS :
MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
else
#define mmCRTC4_CRTC_DRR_CONTROL 0x0f3e
#define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX 2
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0 0x395d
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX 2
// addressBlock: dce_dc_fmt4_dispdec
// base address: 0x2000
if (ret)
return ret;
+ bitmap_zero(feature->enabled, feature->feature_num);
+ bitmap_zero(feature->supported, feature->feature_num);
+
if (en) {
ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
if (ret)
feature->feature_num);
bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
feature->feature_num);
- } else {
- bitmap_zero(feature->enabled, feature->feature_num);
- bitmap_zero(feature->supported, feature->feature_num);
}
return ret;
struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks;
int ret = 0;
- max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
+ if (!smu->smu_table.max_sustainable_clocks)
+ max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
GFP_KERNEL);
+ else
+ max_sustainable_clocks = smu->smu_table.max_sustainable_clocks;
+
smu->smu_table.max_sustainable_clocks = (void *)max_sustainable_clocks;
max_sustainable_clocks->uclock = smu->smu_table.boot_values.uclk / 100;
static int tc_aux_wait_busy(struct tc_data *tc)
{
- return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000);
+ return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000);
}
static int tc_aux_write_data(struct tc_data *tc, const void *data,
if (ret)
goto err;
- ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+ ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000);
if (ret == -ETIMEDOUT) {
dev_err(tc->dev, "Timeout waiting for PHY to become ready");
return ret;
int ret;
ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE,
- LT_LOOPDONE, 1, 1000);
+ LT_LOOPDONE, 500, 100000);
if (ret) {
dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n");
return ret;
dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl);
- ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+ ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000);
if (ret) {
dev_err(dev, "timeout waiting for phy become ready");
return ret;
dvi->connector_type,
dvi->ddc);
if (ret) {
- dev_err(dvi->dev, "drm_connector_init() failed: %d\n", ret);
+ dev_err(dvi->dev, "drm_connector_init_with_ddc() failed: %d\n",
+ ret);
return ret;
}
* depending on the hardware this may require the framebuffer
* to be in a specific tiling format.
*/
- if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 ||
+ if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 &&
+ (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) ||
!plane->rotation_property)
return false;
if (rotation && freestanding)
return -EINVAL;
+ if (!(rotation & DRM_MODE_ROTATE_MASK))
+ rotation |= DRM_MODE_ROTATE_0;
+
+ /* Make sure there is exactly one rotation defined */
+ if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK))
+ return -EINVAL;
+
mode->rotation_reflection = rotation;
return 0;
help
This option enables capturing the GPU state when a hang is detected.
This information is vital for triaging hangs and assists in debugging.
- Please report any hang to
- https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
- for triaging.
+ Please report any hang for triaging according to:
+ https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
If in doubt, say "Y".
$(shell cd $(srctree)/$(src) && find * -name '*.h')))
quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
- cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@
+ cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@
$(obj)/%.hdrtest: $(src)/%.h FORCE
$(call if_changed_dep,hdrtest)
void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
struct intel_crtc_state *crtc_state)
{
- if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
+ if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000)
+ crtc_state->min_voltage_level = 3;
+ else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
crtc_state->min_voltage_level = 1;
else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
crtc_state->min_voltage_level = 2;
u32 base;
if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
- base = obj->phys_handle->busaddr;
+ base = sg_dma_address(obj->mm.pages->sgl);
else
base = intel_plane_ggtt_offset(plane_state);
* have readout for pipe gamma enable.
*/
crtc_state->uapi.color_mgmt_changed = true;
+
+ /*
+ * FIXME hack to force full modeset when DSC is being
+ * used.
+ *
+ * As long as we do not have full state readout and
+ * config comparison of crtc_state->dsc, we have no way
+ * to ensure reliable fastset. Remove once we have
+ * readout for DSC.
+ */
+ if (crtc_state->dsc.compression_enable) {
+ ret = drm_atomic_add_affected_connectors(state,
+ &crtc->base);
+ if (ret)
+ goto out;
+ crtc_state->uapi.mode_changed = true;
+ drm_dbg_kms(dev, "Force full modeset for DSC\n");
+ }
}
}
if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
return -ENODEV;
+ /*
+ * If the cancel fails, we then need to reset, cleanly!
+ *
+ * If the per-engine reset fails, all hope is lost! We resort
+ * to a full GPU reset in that unlikely case, but realistically
+ * if the engine could not reset, the full reset does not fare
+ * much better. The damage has been done.
+ *
+ * However, if we cannot reset an engine by itself, we cannot
+ * cleanup a hanging persistent context without causing
+ * colateral damage, and we should not pretend we can by
+ * exposing the interface.
+ */
+ if (!intel_has_reset_engine(&ctx->i915->gt))
+ return -ENODEV;
+
i915_gem_context_clear_persistence(ctx);
}
void *gvt_info;
};
-
- /** for phys allocated objects */
- struct drm_dma_handle *phys_handle;
};
static inline struct drm_i915_gem_object *
static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
{
struct address_space *mapping = obj->base.filp->f_mapping;
- struct drm_dma_handle *phys;
- struct sg_table *st;
struct scatterlist *sg;
- char *vaddr;
+ struct sg_table *st;
+ dma_addr_t dma;
+ void *vaddr;
+ void *dst;
int i;
- int err;
if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
return -EINVAL;
- /* Always aligning to the object size, allows a single allocation
+ /*
+ * Always aligning to the object size, allows a single allocation
* to handle all possible callers, and given typical object sizes,
* the alignment of the buddy allocation will naturally match.
*/
- phys = drm_pci_alloc(obj->base.dev,
- roundup_pow_of_two(obj->base.size),
- roundup_pow_of_two(obj->base.size));
- if (!phys)
+ vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size),
+ &dma, GFP_KERNEL);
+ if (!vaddr)
return -ENOMEM;
- vaddr = phys->vaddr;
+ st = kmalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ goto err_pci;
+
+ if (sg_alloc_table(st, 1, GFP_KERNEL))
+ goto err_st;
+
+ sg = st->sgl;
+ sg->offset = 0;
+ sg->length = obj->base.size;
+
+ sg_assign_page(sg, (struct page *)vaddr);
+ sg_dma_address(sg) = dma;
+ sg_dma_len(sg) = obj->base.size;
+
+ dst = vaddr;
for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
struct page *page;
- char *src;
+ void *src;
page = shmem_read_mapping_page(mapping, i);
- if (IS_ERR(page)) {
- err = PTR_ERR(page);
- goto err_phys;
- }
+ if (IS_ERR(page))
+ goto err_st;
src = kmap_atomic(page);
- memcpy(vaddr, src, PAGE_SIZE);
- drm_clflush_virt_range(vaddr, PAGE_SIZE);
+ memcpy(dst, src, PAGE_SIZE);
+ drm_clflush_virt_range(dst, PAGE_SIZE);
kunmap_atomic(src);
put_page(page);
- vaddr += PAGE_SIZE;
+ dst += PAGE_SIZE;
}
intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
- st = kmalloc(sizeof(*st), GFP_KERNEL);
- if (!st) {
- err = -ENOMEM;
- goto err_phys;
- }
-
- if (sg_alloc_table(st, 1, GFP_KERNEL)) {
- kfree(st);
- err = -ENOMEM;
- goto err_phys;
- }
-
- sg = st->sgl;
- sg->offset = 0;
- sg->length = obj->base.size;
-
- sg_dma_address(sg) = phys->busaddr;
- sg_dma_len(sg) = obj->base.size;
-
- obj->phys_handle = phys;
-
__i915_gem_object_set_pages(obj, st, sg->length);
return 0;
-err_phys:
- drm_pci_free(obj->base.dev, phys);
-
- return err;
+err_st:
+ kfree(st);
+err_pci:
+ dma_free_coherent(&obj->base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size),
+ vaddr, dma);
+ return -ENOMEM;
}
static void
i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
struct sg_table *pages)
{
+ dma_addr_t dma = sg_dma_address(pages->sgl);
+ void *vaddr = sg_page(pages->sgl);
+
__i915_gem_object_release_shmem(obj, pages, false);
if (obj->mm.dirty) {
struct address_space *mapping = obj->base.filp->f_mapping;
- char *vaddr = obj->phys_handle->vaddr;
+ void *src = vaddr;
int i;
for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
continue;
dst = kmap_atomic(page);
- drm_clflush_virt_range(vaddr, PAGE_SIZE);
- memcpy(dst, vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(src, PAGE_SIZE);
+ memcpy(dst, src, PAGE_SIZE);
kunmap_atomic(dst);
set_page_dirty(page);
if (obj->mm.madv == I915_MADV_WILLNEED)
mark_page_accessed(page);
put_page(page);
- vaddr += PAGE_SIZE;
+
+ src += PAGE_SIZE;
}
obj->mm.dirty = false;
}
sg_free_table(pages);
kfree(pages);
- drm_pci_free(obj->base.dev, obj->phys_handle);
+ dma_free_coherent(&obj->base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size),
+ vaddr, dma);
}
static void phys_release(struct drm_i915_gem_object *obj)
with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
freed = i915_gem_shrink(i915, -1UL, NULL,
I915_SHRINK_BOUND |
- I915_SHRINK_UNBOUND |
- I915_SHRINK_ACTIVE);
+ I915_SHRINK_UNBOUND);
}
return freed;
freed_pages = 0;
with_intel_runtime_pm(&i915->runtime_pm, wakeref)
freed_pages += i915_gem_shrink(i915, -1UL, NULL,
- I915_SHRINK_ACTIVE |
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_WRITEBACK);
struct intel_engine_cs *engine =
container_of(b, struct intel_engine_cs, breadcrumbs);
+ if (unlikely(intel_engine_is_virtual(engine)))
+ engine = intel_virtual_engine_get_sibling(engine, 0);
+
intel_engine_add_retire(engine, tl);
}
void intel_engine_add_retire(struct intel_engine_cs *engine,
struct intel_timeline *tl)
{
+ /* We don't deal well with the engine disappearing beneath us */
+ GEM_BUG_ON(intel_engine_is_virtual(engine));
+
if (add_retire(engine, tl))
schedule_work(&engine->retire_work);
}
bool close);
static void
__execlists_update_reg_state(const struct intel_context *ce,
- const struct intel_engine_cs *engine);
+ const struct intel_engine_cs *engine,
+ u32 head);
static void mark_eio(struct i915_request *rq)
{
head = rq->tail;
else
head = active_request(ce->timeline, rq)->head;
- ce->ring->head = intel_ring_wrap(ce->ring, head);
- intel_ring_update_space(ce->ring);
+ head = intel_ring_wrap(ce->ring, head);
/* Scrub the context image to prevent replaying the previous batch */
restore_default_state(ce, engine);
- __execlists_update_reg_state(ce, engine);
+ __execlists_update_reg_state(ce, engine, head);
/* We've switched away, so this should be a no-op, but intent matters */
ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
{
struct intel_context *ce = rq->context;
u64 desc = ce->lrc_desc;
- u32 tail;
+ u32 tail, prev;
/*
* WaIdleLiteRestore:bdw,skl
* subsequent resubmissions (for lite restore). Should that fail us,
* and we try and submit the same tail again, force the context
* reload.
+ *
+ * If we need to return to a preempted context, we need to skip the
+ * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+ * HW has a tendency to ignore us rewinding the TAIL to the end of
+ * an earlier request.
*/
tail = intel_ring_set_tail(rq->ring, rq->tail);
- if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+ prev = ce->lrc_reg_state[CTX_RING_TAIL];
+ if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
desc |= CTX_DESC_FORCE_RESTORE;
ce->lrc_reg_state[CTX_RING_TAIL] = tail;
rq->tail = rq->wa_tail;
return *last;
}
+#define for_each_waiter(p__, rq__) \
+ list_for_each_entry_lockless(p__, \
+ &(rq__)->sched.waiters_list, \
+ wait_link)
+
static void defer_request(struct i915_request *rq, struct list_head * const pl)
{
LIST_HEAD(list);
GEM_BUG_ON(i915_request_is_active(rq));
list_move_tail(&rq->sched.link, pl);
- list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+ for_each_waiter(p, rq) {
struct i915_request *w =
container_of(p->waiter, typeof(*w), sched);
*/
__unwind_incomplete_requests(engine);
- /*
- * If we need to return to the preempted context, we
- * need to skip the lite-restore and force it to
- * reload the RING_TAIL. Otherwise, the HW has a
- * tendency to ignore us rewinding the TAIL to the
- * end of an earlier request.
- */
- last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
last = NULL;
} else if (need_timeslice(engine, last) &&
timer_expired(&engine->execlists.timer)) {
static void
__execlists_update_reg_state(const struct intel_context *ce,
- const struct intel_engine_cs *engine)
+ const struct intel_engine_cs *engine,
+ u32 head)
{
struct intel_ring *ring = ce->ring;
u32 *regs = ce->lrc_reg_state;
- GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+ GEM_BUG_ON(!intel_ring_offset_valid(ring, head));
GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
- regs[CTX_RING_HEAD] = ring->head;
+ regs[CTX_RING_HEAD] = head;
regs[CTX_RING_TAIL] = ring->tail;
/* RPCS */
ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
- __execlists_update_reg_state(ce, engine);
+ __execlists_update_reg_state(ce, engine, ce->ring->tail);
return 0;
}
/* Scrub away the garbage */
execlists_init_reg_state(ce->lrc_reg_state,
ce, ce->engine, ce->ring, true);
- __execlists_update_reg_state(ce, ce->engine);
+ __execlists_update_reg_state(ce, ce->engine, ce->ring->tail);
ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
}
struct intel_engine_execlists * const execlists = &engine->execlists;
struct intel_context *ce;
struct i915_request *rq;
+ u32 head;
mb(); /* paranoia: read the CSB pointers from after the reset */
clflush(execlists->csb_write);
if (i915_request_completed(rq)) {
/* Idle context; tidy up the ring so we can restart afresh */
- ce->ring->head = intel_ring_wrap(ce->ring, rq->tail);
+ head = intel_ring_wrap(ce->ring, rq->tail);
goto out_replay;
}
/* Context has requests still in-flight; it should not be idle! */
GEM_BUG_ON(i915_active_is_idle(&ce->active));
rq = active_request(ce->timeline, rq);
- ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
- GEM_BUG_ON(ce->ring->head == ce->ring->tail);
+ head = intel_ring_wrap(ce->ring, rq->head);
+ GEM_BUG_ON(head == ce->ring->tail);
/*
* If this request hasn't started yet, e.g. it is waiting on a
out_replay:
ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
- ce->ring->head, ce->ring->tail);
- intel_ring_update_space(ce->ring);
+ head, ce->ring->tail);
__execlists_reset_reg_state(ce, engine);
- __execlists_update_reg_state(ce, engine);
+ __execlists_update_reg_state(ce, engine, head);
ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
unwind:
restore_default_state(ce, engine);
/* Rerun the request; its payload has been neutered (if guilty). */
- ce->ring->head = head;
- intel_ring_update_space(ce->ring);
-
- __execlists_update_reg_state(ce, engine);
+ __execlists_update_reg_state(ce, engine, head);
}
bool
kref_init(&ring->ref);
ring->size = size;
+ ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
/*
* Workaround an erratum on the i830 which causes a hang if
return pos & (ring->size - 1);
}
+static inline int intel_ring_direction(const struct intel_ring *ring,
+ u32 next, u32 prev)
+{
+ typecheck(typeof(ring->size), next);
+ typecheck(typeof(ring->size), prev);
+ return (next - prev) << ring->wrap;
+}
+
static inline bool
intel_ring_offset_valid(const struct intel_ring *ring,
unsigned int pos)
*/
atomic_t pin_count;
- u32 head;
- u32 tail;
- u32 emit;
+ u32 head; /* updated during retire, loosely tracks RING_HEAD */
+ u32 tail; /* updated on submission, used for RING_TAIL */
+ u32 emit; /* updated during request construction */
u32 space;
u32 size;
+ u32 wrap;
u32 effective_size;
};
}
GEM_BUG_ON(!ce[1]->ring->size);
intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
- __execlists_update_reg_state(ce[1], engine);
+ __execlists_update_reg_state(ce[1], engine, ce[1]->ring->head);
rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
if (IS_ERR(rq[0])) {
dmabuf_obj = container_of(pos,
struct intel_vgpu_dmabuf_obj, list);
if (dmabuf_obj == obj) {
+ list_del(pos);
intel_gvt_hypervisor_put_vfio_device(vgpu);
idr_remove(&vgpu->object_idr,
dmabuf_obj->dmabuf_id);
kfree(dmabuf_obj->info);
kfree(dmabuf_obj);
- list_del(pos);
break;
}
}
intel_vgpu_reset_mmio(vgpu, dmlr);
populate_pvinfo_page(vgpu);
- intel_vgpu_reset_display(vgpu);
if (dmlr) {
+ intel_vgpu_reset_display(vgpu);
intel_vgpu_reset_cfg_space(vgpu);
/* only reset the failsafe mode when dmlr reset */
vgpu->failsafe = false;
struct drm_i915_gem_pwrite *args,
struct drm_file *file)
{
- void *vaddr = obj->phys_handle->vaddr + args->offset;
+ void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
char __user *user_data = u64_to_user_ptr(args->data_ptr);
/*
ret = i915_gem_gtt_pwrite_fast(obj, args);
if (ret == -EFAULT || ret == -ENOSPC) {
- if (obj->phys_handle)
- ret = i915_gem_phys_pwrite(obj, args, file);
- else
+ if (i915_gem_object_has_struct_page(obj))
ret = i915_gem_shmem_pwrite(obj, args);
+ else
+ ret = i915_gem_phys_pwrite(obj, args, file);
}
i915_gem_object_unpin_pages(obj);
if (!xchg(&warned, true) &&
ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
- pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+ pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n");
+ pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n");
pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n");
pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n",
.has_rc6 = 1, \
.has_rc6p = 1, \
.has_rps = true, \
- .ppgtt_type = INTEL_PPGTT_FULL, \
+ .ppgtt_type = INTEL_PPGTT_ALIASING, \
.ppgtt_size = 31, \
IVB_PIPE_OFFSETS, \
IVB_CURSOR_OFFSETS, \
.has_rps = true,
.display.has_gmch = 1,
.display.has_hotplug = 1,
- .ppgtt_type = INTEL_PPGTT_FULL,
+ .ppgtt_type = INTEL_PPGTT_ALIASING,
.ppgtt_size = 31,
.has_snoop = true,
.has_coherent_ggtt = false,
return sprintf(buf, "config=0x%lx\n", eattr->val);
}
-static struct attribute_group i915_pmu_events_attr_group = {
- .name = "events",
- /* Patch in attrs at runtime. */
-};
-
static ssize_t
i915_pmu_get_attr_cpumask(struct device *dev,
struct device_attribute *attr,
.attrs = i915_cpumask_attrs,
};
-static const struct attribute_group *i915_pmu_attr_groups[] = {
- &i915_pmu_format_attr_group,
- &i915_pmu_events_attr_group,
- &i915_pmu_cpumask_attr_group,
- NULL
-};
-
#define __event(__config, __name, __unit) \
{ \
.config = (__config), \
static void free_event_attributes(struct i915_pmu *pmu)
{
- struct attribute **attr_iter = i915_pmu_events_attr_group.attrs;
+ struct attribute **attr_iter = pmu->events_attr_group.attrs;
for (; *attr_iter; attr_iter++)
kfree((*attr_iter)->name);
- kfree(i915_pmu_events_attr_group.attrs);
+ kfree(pmu->events_attr_group.attrs);
kfree(pmu->i915_attr);
kfree(pmu->pmu_attr);
- i915_pmu_events_attr_group.attrs = NULL;
+ pmu->events_attr_group.attrs = NULL;
pmu->i915_attr = NULL;
pmu->pmu_attr = NULL;
}
static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
{
- struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+ struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
GEM_BUG_ON(!pmu->base.event_init);
static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
{
- struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+ struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
unsigned int target;
GEM_BUG_ON(!pmu->base.event_init);
return 0;
}
-static enum cpuhp_state cpuhp_slot = CPUHP_INVALID;
-
static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
{
enum cpuhp_state slot;
return ret;
slot = ret;
- ret = cpuhp_state_add_instance(slot, &pmu->node);
+ ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node);
if (ret) {
cpuhp_remove_multi_state(slot);
return ret;
}
- cpuhp_slot = slot;
+ pmu->cpuhp.slot = slot;
return 0;
}
static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu)
{
- WARN_ON(cpuhp_slot == CPUHP_INVALID);
- WARN_ON(cpuhp_state_remove_instance(cpuhp_slot, &pmu->node));
- cpuhp_remove_multi_state(cpuhp_slot);
+ WARN_ON(pmu->cpuhp.slot == CPUHP_INVALID);
+ WARN_ON(cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node));
+ cpuhp_remove_multi_state(pmu->cpuhp.slot);
+ pmu->cpuhp.slot = CPUHP_INVALID;
}
static bool is_igp(struct drm_i915_private *i915)
void i915_pmu_register(struct drm_i915_private *i915)
{
struct i915_pmu *pmu = &i915->pmu;
+ const struct attribute_group *attr_groups[] = {
+ &i915_pmu_format_attr_group,
+ &pmu->events_attr_group,
+ &i915_pmu_cpumask_attr_group,
+ NULL
+ };
+
int ret = -ENOMEM;
if (INTEL_GEN(i915) <= 2) {
spin_lock_init(&pmu->lock);
hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
pmu->timer.function = i915_sample;
+ pmu->cpuhp.slot = CPUHP_INVALID;
if (!is_igp(i915)) {
pmu->name = kasprintf(GFP_KERNEL,
if (!pmu->name)
goto err;
- i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
- if (!i915_pmu_events_attr_group.attrs)
+ pmu->events_attr_group.name = "events";
+ pmu->events_attr_group.attrs = create_event_attributes(pmu);
+ if (!pmu->events_attr_group.attrs)
goto err_name;
- pmu->base.attr_groups = i915_pmu_attr_groups;
+ pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups),
+ GFP_KERNEL);
+ if (!pmu->base.attr_groups)
+ goto err_attr;
+
pmu->base.task_ctx_nr = perf_invalid_context;
pmu->base.event_init = i915_pmu_event_init;
pmu->base.add = i915_pmu_event_add;
ret = perf_pmu_register(&pmu->base, pmu->name, -1);
if (ret)
- goto err_attr;
+ goto err_groups;
ret = i915_pmu_register_cpuhp_state(pmu);
if (ret)
err_unreg:
perf_pmu_unregister(&pmu->base);
+err_groups:
+ kfree(pmu->base.attr_groups);
err_attr:
pmu->base.event_init = NULL;
free_event_attributes(pmu);
perf_pmu_unregister(&pmu->base);
pmu->base.event_init = NULL;
+ kfree(pmu->base.attr_groups);
if (!is_igp(i915))
kfree(pmu->name);
free_event_attributes(pmu);
struct i915_pmu {
/**
- * @node: List node for CPU hotplug handling.
+ * @cpuhp: Struct used for CPU hotplug handling.
*/
- struct hlist_node node;
+ struct {
+ struct hlist_node node;
+ enum cpuhp_state slot;
+ } cpuhp;
/**
* @base: PMU base.
*/
* @sleep_last: Last time GT parked for RC6 estimation.
*/
ktime_t sleep_last;
+ /**
+ * @events_attr_group: Device events attribute group.
+ */
+ struct attribute_group events_attr_group;
/**
* @i915_attr: Memory block holding device attributes.
*/
i915_sw_fence_init(&rq->submit, submit_notify);
i915_sw_fence_init(&rq->semaphore, semaphore_notify);
+ dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
+
rq->file_priv = NULL;
rq->capture_list = NULL;
}
}
- ret = intel_timeline_get_seqno(tl, rq, &seqno);
- if (ret)
- goto err_free;
-
rq->i915 = ce->engine->i915;
rq->context = ce;
rq->engine = ce->engine;
rq->ring = ce->ring;
rq->execution_mask = ce->engine->mask;
+ kref_init(&rq->fence.refcount);
+ rq->fence.flags = 0;
+ rq->fence.error = 0;
+ INIT_LIST_HEAD(&rq->fence.cb_list);
+
+ ret = intel_timeline_get_seqno(tl, rq, &seqno);
+ if (ret)
+ goto err_free;
+
+ rq->fence.context = tl->fence_context;
+ rq->fence.seqno = seqno;
+
RCU_INIT_POINTER(rq->timeline, tl);
RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
rq->hwsp_seqno = tl->hwsp_seqno;
rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
- dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
- tl->fence_context, seqno);
-
/* We bump the ref for the fence chain */
i915_sw_fence_reinit(&i915_request_get(rq)->submit);
i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
if (!node_signaled(signal)) {
INIT_LIST_HEAD(&dep->dfs_link);
- list_add(&dep->wait_link, &signal->waiters_list);
- list_add(&dep->signal_link, &node->signalers_list);
dep->signaler = signal;
dep->waiter = node;
dep->flags = flags;
!node_started(signal))
node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
+ /* All set, now publish. Beware the lockless walkers. */
+ list_add(&dep->signal_link, &node->signalers_list);
+ list_add_rcu(&dep->wait_link, &signal->waiters_list);
+
/*
* As we do not allow WAIT to preempt inflight requests,
* once we have executed a request, along with triggering
#include "i915_drv.h"
#include "i915_utils.h"
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
- "providing the dmesg log by booting with drm.debug=0xf"
+#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs"
+#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details."
void
__i915_printk(struct drm_i915_private *dev_priv, const char *level,
return true;
}
+#define GBIF_CLIENT_HALT_MASK BIT(0)
+#define GBIF_ARB_HALT_MASK BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+ struct msm_gpu *gpu = &adreno_gpu->base;
+
+ if (!a6xx_has_gbif(adreno_gpu)) {
+ gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+ spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+ 0xf) == 0xf);
+ gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+ return;
+ }
+
+ /* Halt new client requests on GBIF */
+ gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+ spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+ (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+ /* Halt all AXI requests on GBIF */
+ gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+ spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+ (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+ /* The GBIF halt needs to be explicitly cleared */
+ gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
/* Gracefully try to shut down the GMU and by extension the GPU */
static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
{
struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
- struct msm_gpu *gpu = &adreno_gpu->base;
u32 val;
/*
return;
}
- /* Clear the VBIF pipe before shutting down */
- gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
- spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf)
- == 0xf);
- gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+ a6xx_bus_clear_pending_transactions(adreno_gpu);
/* tell the GMU we want to slumber */
a6xx_gmu_notify_slumber(gmu);
struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
int ret;
- /*
- * During a previous slumber, GBIF halt is asserted to ensure
- * no further transaction can go through GPU before GPU
- * headswitch is turned off.
- *
- * This halt is deasserted once headswitch goes off but
- * incase headswitch doesn't goes off clear GBIF halt
- * here to ensure GPU wake-up doesn't fail because of
- * halted GPU transactions.
- */
- gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-
/* Make sure the GMU keeps the GPU on while we set it up */
a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
/* Select CP0 to always count cycles */
gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
- gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
- gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
- gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
- gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+ if (adreno_is_a630(adreno_gpu)) {
+ gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
+ gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
+ gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
+ gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+ }
/* Enable fault detection */
gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,
REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
};
-#define GBIF_CLIENT_HALT_MASK BIT(0)
-#define GBIF_ARB_HALT_MASK BIT(1)
-
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
-{
- struct msm_gpu *gpu = &adreno_gpu->base;
-
- if(!a6xx_has_gbif(adreno_gpu)){
- gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
- spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
- 0xf) == 0xf);
- gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
- return;
- }
-
- /* Halt new client requests on GBIF */
- gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
- spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
- (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
-
- /* Halt all AXI requests on GBIF */
- gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
- spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
- (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
-
- /*
- * GMU needs DDR access in slumber path. Deassert GBIF halt now
- * to allow for GMU to access system memory.
- */
- gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-}
-
static int a6xx_pm_resume(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
devfreq_suspend_device(gpu->devfreq.devfreq);
- /*
- * Make sure the GMU is idle before continuing (because some transitions
- * may use VBIF
- */
- a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
-
- /* Clear the VBIF pipe before shutting down */
- /* FIXME: This accesses the GPU - do we need to make sure it is on? */
- a6xx_bus_clear_pending_transactions(adreno_gpu);
-
return a6xx_gmu_stop(a6xx_gpu);
}
#include "a6xx_gmu.h"
#include "a6xx_gmu.xml.h"
+#include "a6xx_gpu.h"
#define HFI_MSG_ID(val) [val] = #val
NULL, 0);
}
-static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
{
- struct a6xx_hfi_msg_bw_table msg = { 0 };
+ /* Send a single "off" entry since the 618 GMU doesn't do bus scaling */
+ msg->bw_level_num = 1;
+
+ msg->ddr_cmds_num = 3;
+ msg->ddr_wait_bitmask = 0x01;
+
+ msg->ddr_cmds_addrs[0] = 0x50000;
+ msg->ddr_cmds_addrs[1] = 0x5003c;
+ msg->ddr_cmds_addrs[2] = 0x5000c;
+
+ msg->ddr_cmds_data[0][0] = 0x40000000;
+ msg->ddr_cmds_data[0][1] = 0x40000000;
+ msg->ddr_cmds_data[0][2] = 0x40000000;
/*
- * The sdm845 GMU doesn't do bus frequency scaling on its own but it
- * does need at least one entry in the list because it might be accessed
- * when the GMU is shutting down. Send a single "off" entry.
+ * These are the CX (CNOC) votes - these are used by the GMU but the
+ * votes are known and fixed for the target
*/
+ msg->cnoc_cmds_num = 1;
+ msg->cnoc_wait_bitmask = 0x01;
+
+ msg->cnoc_cmds_addrs[0] = 0x5007c;
+ msg->cnoc_cmds_data[0][0] = 0x40000000;
+ msg->cnoc_cmds_data[1][0] = 0x60000001;
+}
- msg.bw_level_num = 1;
+static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+ /* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
+ msg->bw_level_num = 1;
- msg.ddr_cmds_num = 3;
- msg.ddr_wait_bitmask = 0x07;
+ msg->ddr_cmds_num = 3;
+ msg->ddr_wait_bitmask = 0x07;
- msg.ddr_cmds_addrs[0] = 0x50000;
- msg.ddr_cmds_addrs[1] = 0x5005c;
- msg.ddr_cmds_addrs[2] = 0x5000c;
+ msg->ddr_cmds_addrs[0] = 0x50000;
+ msg->ddr_cmds_addrs[1] = 0x5005c;
+ msg->ddr_cmds_addrs[2] = 0x5000c;
- msg.ddr_cmds_data[0][0] = 0x40000000;
- msg.ddr_cmds_data[0][1] = 0x40000000;
- msg.ddr_cmds_data[0][2] = 0x40000000;
+ msg->ddr_cmds_data[0][0] = 0x40000000;
+ msg->ddr_cmds_data[0][1] = 0x40000000;
+ msg->ddr_cmds_data[0][2] = 0x40000000;
/*
* These are the CX (CNOC) votes. This is used but the values for the
* sdm845 GMU are known and fixed so we can hard code them.
*/
- msg.cnoc_cmds_num = 3;
- msg.cnoc_wait_bitmask = 0x05;
+ msg->cnoc_cmds_num = 3;
+ msg->cnoc_wait_bitmask = 0x05;
- msg.cnoc_cmds_addrs[0] = 0x50034;
- msg.cnoc_cmds_addrs[1] = 0x5007c;
- msg.cnoc_cmds_addrs[2] = 0x5004c;
+ msg->cnoc_cmds_addrs[0] = 0x50034;
+ msg->cnoc_cmds_addrs[1] = 0x5007c;
+ msg->cnoc_cmds_addrs[2] = 0x5004c;
- msg.cnoc_cmds_data[0][0] = 0x40000000;
- msg.cnoc_cmds_data[0][1] = 0x00000000;
- msg.cnoc_cmds_data[0][2] = 0x40000000;
+ msg->cnoc_cmds_data[0][0] = 0x40000000;
+ msg->cnoc_cmds_data[0][1] = 0x00000000;
+ msg->cnoc_cmds_data[0][2] = 0x40000000;
+
+ msg->cnoc_cmds_data[1][0] = 0x60000001;
+ msg->cnoc_cmds_data[1][1] = 0x20000001;
+ msg->cnoc_cmds_data[1][2] = 0x60000001;
+}
+
+
+static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+{
+ struct a6xx_hfi_msg_bw_table msg = { 0 };
+ struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+ struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
- msg.cnoc_cmds_data[1][0] = 0x60000001;
- msg.cnoc_cmds_data[1][1] = 0x20000001;
- msg.cnoc_cmds_data[1][2] = 0x60000001;
+ if (adreno_is_a618(adreno_gpu))
+ a618_build_bw_table(&msg);
+ else
+ a6xx_build_bw_table(&msg);
return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg),
NULL, 0);
INTERLEAVED_RGB_FMT(RGB565,
0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
- C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+ C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
false, 2, 0,
DPU_FETCH_LINEAR, 1),
INTERLEAVED_RGB_FMT(BGR565,
0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
- C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+ C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
false, 2, 0,
DPU_FETCH_LINEAR, 1),
#define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
+#define HW_REV 0x0
#define HW_INTR_STATUS 0x0010
/* Max BW defined in KBps */
struct irq_domain *domain;
};
+struct dpu_hw_cfg {
+ u32 val;
+ u32 offset;
+};
+
+struct dpu_mdss_hw_init_handler {
+ u32 hw_rev;
+ u32 hw_reg_count;
+ struct dpu_hw_cfg* hw_cfg;
+};
+
struct dpu_mdss {
struct msm_mdss base;
void __iomem *mmio;
u32 num_paths;
};
+static struct dpu_hw_cfg hw_cfg[] = {
+ {
+ /* UBWC global settings */
+ .val = 0x1E,
+ .offset = 0x144,
+ }
+};
+
+static struct dpu_mdss_hw_init_handler cfg_handler[] = {
+ { .hw_rev = DPU_HW_VER_620,
+ .hw_reg_count = ARRAY_SIZE(hw_cfg),
+ .hw_cfg = hw_cfg
+ },
+};
+
+static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev)
+{
+ int i;
+ u32 count = 0;
+ struct dpu_hw_cfg *hw_cfg = NULL;
+
+ for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+ if (cfg_handler[i].hw_rev == hw_rev) {
+ hw_cfg = cfg_handler[i].hw_cfg;
+ count = cfg_handler[i].hw_reg_count;
+ break;
+ }
+ }
+
+ for (i = 0; i < count; i++ ) {
+ writel_relaxed(hw_cfg->val,
+ dpu_mdss->mmio + hw_cfg->offset);
+ hw_cfg++;
+ }
+
+ return;
+}
+
static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev,
struct dpu_mdss *dpu_mdss)
{
struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
struct dss_module_power *mp = &dpu_mdss->mp;
int ret;
+ u32 mdss_rev;
dpu_mdss_icc_request_bw(mdss);
ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
- if (ret)
+ if (ret) {
DPU_ERROR("clock enable failed, ret:%d\n", ret);
+ return ret;
+ }
+
+ mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV);
+ dpu_mdss_hw_init(dpu_mdss, mdss_rev);
return ret;
}
ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
msecs_to_jiffies(50));
if (ret == 0)
- dev_warn(dev->dev, "pp done time out, lm=%d\n",
- mdp5_cstate->pipeline.mixer->lm);
+ dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+ mdp5_cstate->pipeline.mixer->lm);
}
static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
return num;
}
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
{
int id = dsi_mgr_connector_get_id(connector);
struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
struct mipi_dsi_host *host = msm_dsi->host;
struct drm_panel *panel = msm_dsi->panel;
+ struct msm_dsi_pll *src_pll;
bool is_dual_dsi = IS_DUAL_DSI();
int ret;
id, ret);
}
+ /* Save PLL status if it is a clock source */
+ src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+ msm_dsi_pll_save_state(src_pll);
+
ret = msm_dsi_host_power_off(host);
if (ret)
pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
if (!phy || !phy->cfg->ops.disable)
return;
- /* Save PLL status if it is a clock source */
- if (phy->usecase != MSM_DSI_PHY_SLAVE)
- msm_dsi_pll_save_state(phy->pll);
-
phy->cfg->ops.disable(phy);
dsi_phy_regulator_disable(phy);
if (pll_10nm->slave)
dsi_pll_enable_pll_bias(pll_10nm->slave);
+ rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+ if (rc) {
+ pr_err("vco_set_rate failed, rc=%d\n", rc);
+ return rc;
+ }
+
/* Start PLL */
pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
0x01);
asyw->clr.ntfy = armw->ntfy.handle != 0;
asyw->clr.sema = armw->sema.handle != 0;
asyw->clr.xlut = armw->xlut.handle != 0;
+ if (asyw->clr.xlut && asyw->visible)
+ asyw->set.xlut = asyw->xlut.handle != 0;
asyw->clr.csc = armw->csc.valid;
if (wndw->func->image_clr)
asyw->clr.image = armw->image.handle[0] != 0;
static const struct nvkm_device_chip
nv167_chipset = {
.name = "TU117",
+ .acr = tu102_acr_new,
.bar = tu102_bar_new,
.bios = nvkm_bios_new,
.bus = gf100_bus_new,
.disp = tu102_disp_new,
.dma = gv100_dma_new,
.fifo = tu102_fifo_new,
+ .gr = tu102_gr_new,
.nvdec[0] = gm107_nvdec_new,
.nvenc[0] = gm107_nvenc_new,
.sec2 = tu102_sec2_new,
static const struct nvkm_device_chip
nv168_chipset = {
.name = "TU116",
+ .acr = tu102_acr_new,
.bar = tu102_bar_new,
.bios = nvkm_bios_new,
.bus = gf100_bus_new,
.disp = tu102_disp_new,
.dma = gv100_dma_new,
.fifo = tu102_fifo_new,
+ .gr = tu102_gr_new,
.nvdec[0] = gm107_nvdec_new,
.nvenc[0] = gm107_nvenc_new,
.sec2 = tu102_sec2_new,
MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin");
MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_method_init.bin");
+
static const struct gf100_gr_fwif
tu102_gr_fwif[] = {
{ 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin");
MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_unload.bin");
+
static const struct nvkm_acr_hsf_fwif
tu102_acr_unload_fwif[] = {
{ 0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 },
MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin");
MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin");
MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_asb.bin");
static const struct nvkm_acr_hsf_fwif
tu102_acr_asb_fwif[] = {
MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin");
MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_ahesasc.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_ahesasc.bin");
+
static const struct nvkm_acr_hsf_fwif
tu102_acr_ahesasc_fwif[] = {
{ 0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 },
MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin");
}
if (job->bos) {
- struct panfrost_gem_object *bo;
-
- for (i = 0; i < job->bo_count; i++) {
- bo = to_panfrost_bo(job->bos[i]);
+ for (i = 0; i < job->bo_count; i++)
drm_gem_object_put_unlocked(job->bos[i]);
- }
kvfree(job->bos);
}
as = mmu->as;
if (as >= 0) {
int en = atomic_inc_return(&mmu->as_count);
- WARN_ON(en >= NUM_JOB_SLOTS);
+
+ /*
+ * AS can be retained by active jobs or a perfcnt context,
+ * hence the '+ 1' here.
+ */
+ WARN_ON(en >= (NUM_JOB_SLOTS + 1));
list_move(&mmu->list, &pfdev->as_lru_list);
goto out;
struct panfrost_file_priv *user = file_priv->driver_priv;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
struct drm_gem_shmem_object *bo;
- u32 cfg;
+ u32 cfg, as;
int ret;
if (user == perfcnt->user)
perfcnt->user = user;
- /*
- * Always use address space 0 for now.
- * FIXME: this needs to be updated when we start using different
- * address space.
- */
- cfg = GPU_PERFCNT_CFG_AS(0) |
+ as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
+ cfg = GPU_PERFCNT_CFG_AS(as) |
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
/*
drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
perfcnt->buf = NULL;
panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+ panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
panfrost_gem_mapping_put(perfcnt->mapping);
perfcnt->mapping = NULL;
pm_runtime_mark_last_busy(pfdev->dev);
#include <linux/vga_switcheroo.h>
#include <linux/mmu_notifier.h>
+#include <drm/drm_agpsupport.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_drv.h>
#include <drm/drm_fb_helper.h>
const struct pci_device_id *ent)
{
unsigned long flags = 0;
+ struct drm_device *dev;
int ret;
if (!ent)
if (ret)
return ret;
- return drm_get_pci_dev(pdev, ent, &kms_driver);
+ dev = drm_dev_alloc(&kms_driver, &pdev->dev);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
+
+ ret = pci_enable_device(pdev);
+ if (ret)
+ goto err_free;
+
+ dev->pdev = pdev;
+#ifdef __alpha__
+ dev->hose = pdev->sysdata;
+#endif
+
+ pci_set_drvdata(pdev, dev);
+
+ if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP))
+ dev->agp = drm_agp_init(dev);
+ if (dev->agp) {
+ dev->agp->agp_mtrr = arch_phys_wc_add(
+ dev->agp->agp_info.aper_base,
+ dev->agp->agp_info.aper_size *
+ 1024 * 1024);
+ }
+
+ ret = drm_dev_register(dev, ent->driver_data);
+ if (ret)
+ goto err_agp;
+
+ return 0;
+
+err_agp:
+ if (dev->agp)
+ arch_phys_wc_del(dev->agp->agp_mtrr);
+ kfree(dev->agp);
+ pci_disable_device(pdev);
+err_free:
+ drm_dev_put(dev);
+ return ret;
}
static void
static struct drm_driver kms_driver = {
.driver_features =
- DRIVER_USE_AGP | DRIVER_GEM | DRIVER_RENDER,
+ DRIVER_GEM | DRIVER_RENDER,
.load = radeon_driver_load_kms,
.open = radeon_driver_open_kms,
.postclose = radeon_driver_postclose_kms,
#include <linux/uaccess.h>
#include <linux/vga_switcheroo.h>
+#include <drm/drm_agpsupport.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_file.h>
#include <drm/drm_ioctl.h>
radeon_modeset_fini(rdev);
radeon_device_fini(rdev);
+ if (dev->agp)
+ arch_phys_wc_del(dev->agp->agp_mtrr);
+ kfree(dev->agp);
+ dev->agp = NULL;
+
done_free:
kfree(rdev);
dev->dev_private = NULL;
cmdline_test(drm_cmdline_test_rotate_90)
cmdline_test(drm_cmdline_test_rotate_180)
cmdline_test(drm_cmdline_test_rotate_270)
+cmdline_test(drm_cmdline_test_rotate_multiple)
cmdline_test(drm_cmdline_test_rotate_invalid_val)
cmdline_test(drm_cmdline_test_rotate_truncated)
cmdline_test(drm_cmdline_test_hmirror)
return 0;
}
+static int drm_cmdline_test_rotate_multiple(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90",
+ &no_connector,
+ &mode));
+
+ return 0;
+}
+
static int drm_cmdline_test_rotate_invalid_val(void *ignored)
{
struct drm_cmdline_mode mode = { };
FAIL_ON(!mode.specified);
FAIL_ON(mode.xres != 720);
FAIL_ON(mode.yres != 480);
- FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X);
+ FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X));
FAIL_ON(mode.refresh_specified);
FAIL_ON(!mode.specified);
FAIL_ON(mode.xres != 720);
FAIL_ON(mode.yres != 480);
- FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y);
+ FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y));
FAIL_ON(mode.refresh_specified);
if (data->has_sp) {
input2 = input_allocate_device();
if (!input2) {
- input_free_device(input2);
+ ret = -ENOMEM;
goto exit;
}
unsigned long **bit, int *max)
{
if (usage->hid == (HID_UP_CUSTOM | 0x0003) ||
- usage->hid == (HID_UP_MSVENDOR | 0x0003)) {
+ usage->hid == (HID_UP_MSVENDOR | 0x0003) ||
+ usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) {
/* The fn key on Apple USB keyboards */
set_bit(EV_REP, hi->input->evbit);
hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN);
struct bigben_device {
struct hid_device *hid;
struct hid_report *report;
+ bool removed;
u8 led_state; /* LED1 = 1 .. LED4 = 8 */
u8 right_motor_on; /* right motor off/on 0/1 */
u8 left_motor_force; /* left motor force 0-255 */
struct bigben_device, worker);
struct hid_field *report_field = bigben->report->field[0];
+ if (bigben->removed)
+ return;
+
if (bigben->work_led) {
bigben->work_led = false;
report_field->value[0] = 0x01; /* 1 = led message */
static int hid_bigben_play_effect(struct input_dev *dev, void *data,
struct ff_effect *effect)
{
- struct bigben_device *bigben = data;
+ struct hid_device *hid = input_get_drvdata(dev);
+ struct bigben_device *bigben = hid_get_drvdata(hid);
u8 right_motor_on;
u8 left_motor_force;
+ if (!bigben) {
+ hid_err(hid, "no device data\n");
+ return 0;
+ }
+
if (effect->type != FF_RUMBLE)
return 0;
{
struct bigben_device *bigben = hid_get_drvdata(hid);
+ bigben->removed = true;
cancel_work_sync(&bigben->worker);
- hid_hw_close(hid);
hid_hw_stop(hid);
}
return -ENOMEM;
hid_set_drvdata(hid, bigben);
bigben->hid = hid;
+ bigben->removed = false;
error = hid_parse(hid);
if (error) {
INIT_WORK(&bigben->worker, bigben_worker);
- error = input_ff_create_memless(hidinput->input, bigben,
+ error = input_ff_create_memless(hidinput->input, NULL,
hid_bigben_play_effect);
if (error)
- return error;
+ goto error_hw_stop;
name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1;
sizeof(struct led_classdev) + name_sz,
GFP_KERNEL
);
- if (!led)
- return -ENOMEM;
+ if (!led) {
+ error = -ENOMEM;
+ goto error_hw_stop;
+ }
name = (void *)(&led[1]);
snprintf(name, name_sz,
"%s:red:bigben%d",
bigben->leds[n] = led;
error = devm_led_classdev_register(&hid->dev, led);
if (error)
- return error;
+ goto error_hw_stop;
}
/* initial state: LED1 is on, no rumble effect */
hid_info(hid, "LED and force feedback support for BigBen gamepad\n");
return 0;
+
+error_hw_stop:
+ hid_hw_stop(hid);
+ return error;
}
static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc,
rsize = ((report->size - 1) >> 3) + 1;
- if (rsize > HID_MAX_BUFFER_SIZE)
+ if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE)
+ rsize = HID_MAX_BUFFER_SIZE - 1;
+ else if (rsize > HID_MAX_BUFFER_SIZE)
rsize = HID_MAX_BUFFER_SIZE;
if (csize < rsize) {
{ HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) },
{ HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) },
/* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */
- { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS,
- USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_SYNAPTICS,
+ USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) },
{ }
};
MODULE_DEVICE_TABLE(hid, ite_devices);
{
int status;
- long charge_sts = (long)data[2];
+ long flags = (long) data[2];
- *level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
- switch (data[2] & 0xe0) {
- case 0x00:
- status = POWER_SUPPLY_STATUS_CHARGING;
- break;
- case 0x20:
- status = POWER_SUPPLY_STATUS_FULL;
- *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
- break;
- case 0x40:
+ if (flags & 0x80)
+ switch (flags & 0x07) {
+ case 0:
+ status = POWER_SUPPLY_STATUS_CHARGING;
+ break;
+ case 1:
+ status = POWER_SUPPLY_STATUS_FULL;
+ *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL;
+ break;
+ case 2:
+ status = POWER_SUPPLY_STATUS_NOT_CHARGING;
+ break;
+ default:
+ status = POWER_SUPPLY_STATUS_UNKNOWN;
+ break;
+ }
+ else
status = POWER_SUPPLY_STATUS_DISCHARGING;
- break;
- case 0xe0:
- status = POWER_SUPPLY_STATUS_NOT_CHARGING;
- break;
- default:
- status = POWER_SUPPLY_STATUS_UNKNOWN;
- }
*charge_type = POWER_SUPPLY_CHARGE_TYPE_STANDARD;
- if (test_bit(3, &charge_sts)) {
+ if (test_bit(3, &flags)) {
*charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST;
}
- if (test_bit(4, &charge_sts)) {
+ if (test_bit(4, &flags)) {
*charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE;
}
-
- if (test_bit(5, &charge_sts)) {
+ if (test_bit(5, &flags)) {
*level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL;
}
},
.driver_data = (void *)&sipodev_desc
},
+ {
+ .ident = "Trekstor SURFBOOK E11B",
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"),
+ },
+ .driver_data = (void *)&sipodev_desc
+ },
{
.ident = "Direkt-Tek DTLAPY116-2",
.matches = {
hiddev->exist = 0;
if (hiddev->open) {
- mutex_unlock(&hiddev->existancelock);
hid_hw_close(hiddev->hid);
wake_up_interruptible(&hiddev->wait);
+ mutex_unlock(&hiddev->existancelock);
} else {
mutex_unlock(&hiddev->existancelock);
kfree(hiddev);
struct acpi_device *acpi_dev = to_acpi_device(dev);
struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
acpi_string val;
+ int ret;
+ mutex_lock(&resource->lock);
switch (attr->index) {
case 0:
val = resource->model_number;
val = "";
break;
}
-
- return sprintf(buf, "%s\n", val);
+ ret = sprintf(buf, "%s\n", val);
+ mutex_unlock(&resource->lock);
+ return ret;
}
static ssize_t show_val(struct device *dev,
resource = acpi_driver_data(device);
- mutex_lock(&resource->lock);
switch (event) {
case METER_NOTIFY_CONFIG:
+ mutex_lock(&resource->lock);
free_capabilities(resource);
res = read_capabilities(resource);
+ mutex_unlock(&resource->lock);
if (res)
break;
break;
case METER_NOTIFY_TRIP:
sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME);
- update_meter(resource);
break;
case METER_NOTIFY_CAP:
sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME);
- update_cap(resource);
break;
case METER_NOTIFY_INTERVAL:
sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME);
- update_avg_interval(resource);
break;
case METER_NOTIFY_CAPPING:
sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME);
WARN(1, "Unexpected event %d\n", event);
break;
}
- mutex_unlock(&resource->lock);
acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS,
dev_name(&device->dev), event, 0);
resource = acpi_driver_data(device);
hwmon_device_unregister(resource->hwmon_dev);
- free_capabilities(resource);
remove_attrs(resource);
+ free_capabilities(resource);
kfree(resource);
return 0;
/* channel 0.., name 1.. */
if (!(data->have_temp & (1 << channel)))
return 0;
- if (attr == hwmon_temp_input || attr == hwmon_temp_label)
+ if (attr == hwmon_temp_input)
return 0444;
+ if (attr == hwmon_temp_label) {
+ if (data->temp_label)
+ return 0444;
+ return 0;
+ }
if (channel == 2 && data->temp3_val_only)
return 0;
if (attr == hwmon_temp_max) {
/* SCL Low Time */
writel(t_low, idev->base + ALTR_I2C_SCL_LOW);
/* SDA Hold Time, 300ns */
- writel(div_u64(300 * clk_mhz, 1000), idev->base + ALTR_I2C_SDA_HOLD);
+ writel(3 * clk_mhz / 10, idev->base + ALTR_I2C_SDA_HOLD);
/* Mask all master interrupt bits */
altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false);
#define X1000_I2C_DC_STOP BIT(9)
-static const char * const jz4780_i2c_abrt_src[] = {
- "ABRT_7B_ADDR_NOACK",
- "ABRT_10ADDR1_NOACK",
- "ABRT_10ADDR2_NOACK",
- "ABRT_XDATA_NOACK",
- "ABRT_GCALL_NOACK",
- "ABRT_GCALL_READ",
- "ABRT_HS_ACKD",
- "SBYTE_ACKDET",
- "ABRT_HS_NORSTRT",
- "SBYTE_NORSTRT",
- "ABRT_10B_RD_NORSTRT",
- "ABRT_MASTER_DIS",
- "ARB_LOST",
- "SLVFLUSH_TXFIFO",
- "SLV_ARBLOST",
- "SLVRD_INTX",
-};
-
#define JZ4780_I2C_INTST_IGC BIT(11)
#define JZ4780_I2C_INTST_ISTT BIT(10)
#define JZ4780_I2C_INTST_ISTP BIT(9)
static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src)
{
- int i;
-
- dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src);
- dev_err(&i2c->adap.dev, "device addr=%x\n",
- jz4780_i2c_readw(i2c, JZ4780_I2C_TAR));
- dev_err(&i2c->adap.dev, "send cmd count:%d %d\n",
- i2c->cmd, i2c->cmd_buf[i2c->cmd]);
- dev_err(&i2c->adap.dev, "receive data count:%d %d\n",
- i2c->cmd, i2c->data_buf[i2c->cmd]);
-
- for (i = 0; i < 16; i++) {
- if (src & BIT(i))
- dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n",
- i, jz4780_i2c_abrt_src[i]);
- }
+ dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n",
+ src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]);
}
static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c,
.release = ide_gd_release,
.ioctl = ide_gd_ioctl,
#ifdef CONFIG_COMPAT
- .ioctl = ide_gd_compat_ioctl,
+ .compat_ioctl = ide_gd_compat_ioctl,
#endif
.getgeo = ide_gd_getgeo,
.check_events = ide_gd_check_events,
}
}
+static void
+isert_wait4cmds(struct iscsi_conn *conn)
+{
+ isert_info("iscsi_conn %p\n", conn);
+
+ if (conn->sess) {
+ target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+ target_wait_for_sess_cmds(conn->sess->se_sess);
+ }
+}
+
/**
* isert_put_unsol_pending_cmds() - Drop commands waiting for
* unsolicitate dataout
ib_drain_qp(isert_conn->qp);
isert_put_unsol_pending_cmds(conn);
+ isert_wait4cmds(conn);
isert_wait4logout(isert_conn);
queue_work(isert_release_wq, &isert_conn->release_work);
obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu-mod.o
-arm-smmu-mod-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
struct acpi_table_header *ivrs_base;
acpi_status status;
int i, remap_cache_sz, ret = 0;
+ u32 pci_id;
if (!amd_iommu_detected)
return -ENODEV;
if (ret)
goto out;
+ /* Disable IOMMU if there's Stoney Ridge graphics */
+ for (i = 0; i < 32; i++) {
+ pci_id = read_pci_config(0, i, 0, 0);
+ if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+ pr_info("Disable IOMMU on Stoney Ridge\n");
+ amd_iommu_disabled = true;
+ break;
+ }
+ }
+
/* Disable any previously enabled IOMMUs */
if (!is_kdump_kernel() || amd_iommu_disabled)
disable_iommus();
ret = early_amd_iommu_init();
init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
- pr_info("AMD IOMMU disabled on kernel command-line\n");
+ pr_info("AMD IOMMU disabled\n");
init_state = IOMMU_CMDLINE_DISABLED;
ret = -EINVAL;
}
return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
}
+static bool attach_deferred(struct device *dev)
+{
+ return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+}
+
/**
* is_downstream_to_pci_bridge - test if a device belongs to the PCI
* sub-hierarchy of a candidate PCI-PCI bridge
{
struct device_domain_info *info;
- if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
- dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+ if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
return NULL;
if (dev_is_pci(dev))
return NULL;
}
-static struct dmar_domain *deferred_attach_domain(struct device *dev)
+static void do_deferred_attach(struct device *dev)
{
- if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
- struct iommu_domain *domain;
-
- dev->archdata.iommu = NULL;
- domain = iommu_get_domain_for_dev(dev);
- if (domain)
- intel_iommu_attach_device(domain, dev);
- }
+ struct iommu_domain *domain;
- return find_domain(dev);
+ dev->archdata.iommu = NULL;
+ domain = iommu_get_domain_for_dev(dev);
+ if (domain)
+ intel_iommu_attach_device(domain, dev);
}
static inline struct device_domain_info *
struct device_domain_info *info;
info = dev->archdata.iommu;
- if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
+ if (info)
return (info->domain == si_domain);
return 0;
if (iommu_dummy(dev))
return false;
+ if (unlikely(attach_deferred(dev)))
+ do_deferred_attach(dev);
+
ret = identity_mapping(dev);
if (ret) {
u64 dma_mask = *dev->dma_mask;
BUG_ON(dir == DMA_NONE);
- domain = deferred_attach_domain(dev);
+ domain = find_domain(dev);
if (!domain)
return DMA_MAPPING_ERROR;
if (!iommu_need_mapping(dev))
return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
- domain = deferred_attach_domain(dev);
+ domain = find_domain(dev);
if (!domain)
return 0;
int prot = 0;
int ret;
- domain = deferred_attach_domain(dev);
+ if (unlikely(attach_deferred(dev)))
+ do_deferred_attach(dev);
+
+ domain = find_domain(dev);
+
if (WARN_ON(dir == DMA_NONE || !domain))
return DMA_MAPPING_ERROR;
static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
struct device *dev)
{
- return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+ return attach_deferred(dev);
}
static int
{
struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
- if (WARN_ON(qcom_domain->iommu)) /* forgot to detach? */
- return;
-
iommu_put_dma_cookie(domain);
- /* NOTE: unmap can be called after client device is powered off,
- * for example, with GPUs or anything involving dma-buf. So we
- * cannot rely on the device_link. Make sure the IOMMU is on to
- * avoid unclocked accesses in the TLB inv path:
- */
- pm_runtime_get_sync(qcom_domain->iommu->dev);
-
- free_io_pgtable_ops(qcom_domain->pgtbl_ops);
-
- pm_runtime_put_sync(qcom_domain->iommu->dev);
+ if (qcom_domain->iommu) {
+ /*
+ * NOTE: unmap can be called after client device is powered
+ * off, for example, with GPUs or anything involving dma-buf.
+ * So we cannot rely on the device_link. Make sure the IOMMU
+ * is on to avoid unclocked accesses in the TLB inv path:
+ */
+ pm_runtime_get_sync(qcom_domain->iommu->dev);
+ free_io_pgtable_ops(qcom_domain->pgtbl_ops);
+ pm_runtime_put_sync(qcom_domain->iommu->dev);
+ }
kfree(qcom_domain);
}
struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
unsigned i;
- if (!qcom_domain->iommu)
+ if (WARN_ON(!qcom_domain->iommu))
return;
pm_runtime_get_sync(qcom_iommu->dev);
ctx->domain = NULL;
}
pm_runtime_put_sync(qcom_iommu->dev);
-
- qcom_domain->iommu = NULL;
}
static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
/* i2c probing and setup */
/************************************************************************/
-static int
-do_attach( struct i2c_adapter *adapter )
+static void do_attach(struct i2c_adapter *adapter)
{
+ struct i2c_board_info info = { };
+ struct device_node *np;
+
/* scan 0x48-0x4f (DS1775) and 0x2c-2x2f (ADM1030) */
static const unsigned short scan_ds1775[] = {
0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
I2C_CLIENT_END
};
- if( strncmp(adapter->name, "uni-n", 5) )
- return 0;
-
- if( !x.running ) {
- struct i2c_board_info info;
+ if (x.running || strncmp(adapter->name, "uni-n", 5))
+ return;
- memset(&info, 0, sizeof(struct i2c_board_info));
- strlcpy(info.type, "therm_ds1775", I2C_NAME_SIZE);
+ np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775");
+ if (np) {
+ of_node_put(np);
+ } else {
+ strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE);
i2c_new_probed_device(adapter, &info, scan_ds1775, NULL);
+ }
- strlcpy(info.type, "therm_adm1030", I2C_NAME_SIZE);
+ np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030");
+ if (np) {
+ of_node_put(np);
+ } else {
+ strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE);
i2c_new_probed_device(adapter, &info, scan_adm1030, NULL);
-
- if( x.thermostat && x.fan ) {
- x.running = 1;
- x.poll_task = kthread_run(control_loop, NULL, "g4fand");
- }
}
- return 0;
}
static int
enum chip { ds1775, adm1030 };
static const struct i2c_device_id therm_windtunnel_id[] = {
- { "therm_ds1775", ds1775 },
- { "therm_adm1030", adm1030 },
+ { "MAC,ds1775", ds1775 },
+ { "MAC,adm1030", adm1030 },
{ }
};
MODULE_DEVICE_TABLE(i2c, therm_windtunnel_id);
do_probe(struct i2c_client *cl, const struct i2c_device_id *id)
{
struct i2c_adapter *adapter = cl->adapter;
+ int ret = 0;
if( !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA
| I2C_FUNC_SMBUS_WRITE_BYTE) )
switch (id->driver_data) {
case adm1030:
- return attach_fan( cl );
+ ret = attach_fan(cl);
+ break;
case ds1775:
- return attach_thermostat(cl);
+ ret = attach_thermostat(cl);
+ break;
}
- return 0;
+
+ if (!x.running && x.thermostat && x.fan) {
+ x.running = 1;
+ x.poll_task = kthread_run(control_loop, NULL, "g4fand");
+ }
+
+ return ret;
}
static struct i2c_driver g4fan_driver = {
goto out;
}
- hdev->asic_funcs->halt_coresight(hdev);
+ if (!hdev->hard_reset_pending)
+ hdev->asic_funcs->halt_coresight(hdev);
+
hdev->in_debug = 0;
goto out;
if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
dev_info(hdev->dev,
"H/W state is dirty, must reset before initializing\n");
+ hdev->asic_funcs->halt_engines(hdev, true);
hdev->asic_funcs->hw_fini(hdev, true);
}
*/
static void goya_disable_external_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return;
+
WREG32(mmDMA_QM_0_GLBL_CFG0, 0);
WREG32(mmDMA_QM_1_GLBL_CFG0, 0);
WREG32(mmDMA_QM_2_GLBL_CFG0, 0);
{
int rc, retval = 0;
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return retval;
+
rc = goya_stop_queue(hdev,
mmDMA_QM_0_GLBL_CFG1,
mmDMA_QM_0_CP_STS,
*/
static void goya_disable_internal_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ goto disable_tpc;
+
WREG32(mmMME_QM_GLBL_CFG0, 0);
WREG32(mmMME_CMDQ_GLBL_CFG0, 0);
+disable_tpc:
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return;
+
WREG32(mmTPC0_QM_GLBL_CFG0, 0);
WREG32(mmTPC0_CMDQ_GLBL_CFG0, 0);
*/
static int goya_stop_internal_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
int rc, retval = 0;
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ goto stop_tpc;
+
/*
* Each queue (QMAN) is a separate H/W logic. That means that each
* QMAN can be stopped independently and failure to stop one does NOT
retval = -EIO;
}
+stop_tpc:
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return retval;
+
rc = goya_stop_queue(hdev,
mmTPC0_QM_GLBL_CFG1,
mmTPC0_QM_CP_STS,
static void goya_dma_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return;
+
WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
WREG32(mmDMA_QM_1_GLBL_CFG1, 1 << DMA_QM_1_GLBL_CFG1_DMA_STOP_SHIFT);
WREG32(mmDMA_QM_2_GLBL_CFG1, 1 << DMA_QM_2_GLBL_CFG1_DMA_STOP_SHIFT);
static void goya_tpc_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return;
+
WREG32(mmTPC0_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT);
WREG32(mmTPC1_CFG_TPC_STALL, 1 << TPC1_CFG_TPC_STALL_V_SHIFT);
WREG32(mmTPC2_CFG_TPC_STALL, 1 << TPC2_CFG_TPC_STALL_V_SHIFT);
static void goya_mme_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ return;
+
WREG32(mmMME_STALL, 0xFFFFFFFF);
}
rc = goya_send_job_on_qman0(hdev, job);
- hl_cb_put(job->patched_cb);
-
hl_debugfs_remove_job(hdev, job);
kfree(job);
cb->cs_cnt--;
}
}
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int cur = 0, max = 0;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev_rcu(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ if (max <= cur)
+ max = cur;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return max;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return max;
+}
+#endif
+
static void bond_get_stats(struct net_device *bond_dev,
struct rtnl_link_stats64 *stats)
{
struct rtnl_link_stats64 temp;
struct list_head *iter;
struct slave *slave;
+ int nest_level = 0;
- spin_lock(&bond->stats_lock);
- memcpy(stats, &bond->bond_stats, sizeof(*stats));
rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+ nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+ spin_lock_nested(&bond->stats_lock, nest_level);
+ memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
bond_for_each_slave_rcu(bond, slave, iter) {
const struct rtnl_link_stats64 *new =
dev_get_stats(slave->dev, &temp);
/* save off the slave stats for the next run */
memcpy(&slave->slave_stats, new, sizeof(*new));
}
- rcu_read_unlock();
memcpy(&bond->bond_stats, stats, sizeof(*stats));
spin_unlock(&bond->stats_lock);
+ rcu_read_unlock();
}
static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
case BOND_RELEASE_OLD:
case SIOCBONDRELEASE:
res = bond_release(bond_dev, slave_dev);
+ if (!res)
+ netdev_update_lockdep_key(slave_dev);
break;
case BOND_SETHWADDR_OLD:
case SIOCBONDSETHWADDR:
case '-':
slave_dbg(bond->dev, dev, "Releasing interface\n");
ret = bond_release(bond->dev, dev);
+ if (!ret)
+ netdev_update_lockdep_key(dev);
break;
default:
b53_get_vlan_entry(dev, vid, vl);
+ if (vid == 0 && vid == b53_default_pvid(dev))
+ untagged = true;
+
vl->members |= BIT(port);
if (untagged && !dsa_is_cpu_port(ds, port))
vl->untag |= BIT(port);
/* Force link status for IMP port */
reg = core_readl(priv, offset);
reg |= (MII_SW_OR | LINK_STS);
- if (priv->type == BCM7278_DEVICE_ID)
- reg |= GMII_SPEED_UP_2G;
+ reg &= ~GMII_SPEED_UP_2G;
core_writel(priv, reg, offset);
/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
switch (direction) {
case MV88E6XXX_EGRESS_DIR_INGRESS:
dest_port_chip = &chip->ingress_dest_port;
- reg &= MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK;
+ reg &= ~MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK;
reg |= port <<
__bf_shf(MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK);
break;
case MV88E6XXX_EGRESS_DIR_EGRESS:
dest_port_chip = &chip->egress_dest_port;
- reg &= MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK;
+ reg &= ~MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK;
reg |= port <<
__bf_shf(MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK);
break;
if (flags & ~AQ_PRIV_FLAGS_MASK)
return -EOPNOTSUPP;
+ if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) {
+ netdev_info(ndev, "Can't enable more than one loopback simultaneously\n");
+ return -EINVAL;
+ }
+
cfg->priv_flags = flags;
if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
}
if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
- (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+ (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK,
aq_nic->active_vlans))) {
netdev_err(aq_nic->ndev,
"ethtool: unknown vlan-id specified");
void (*enable_ptp)(struct aq_hw_s *self, int enable);
+ void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj);
+
int (*set_eee_rate)(struct aq_hw_s *self, u32 speed);
int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate,
dx_buff->len,
DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
+ if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+ ret = 0;
goto exit;
+ }
first = dx_buff;
dx_buff->len_pkt = skb->len;
if (likely(frags)) {
err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
ring, frags);
- if (err >= 0) {
- ++ring->stats.tx.packets;
- ring->stats.tx.bytes += skb->len;
- }
} else {
err = NETDEV_TX_BUSY;
}
netif_device_detach(nic->ndev);
netif_tx_stop_all_queues(nic->ndev);
- aq_nic_stop(nic);
+ if (netif_running(nic->ndev))
+ aq_nic_stop(nic);
if (deep) {
aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
{
struct pci_dev *pdev = to_pci_dev(dev);
struct aq_nic_s *nic;
- int ret;
+ int ret = 0;
nic = pci_get_drvdata(pdev);
goto err_exit;
}
- ret = aq_nic_start(nic);
- if (ret)
- goto err_exit;
+ if (netif_running(nic->ndev)) {
+ ret = aq_nic_start(nic);
+ if (ret)
+ goto err_exit;
+ }
netif_device_attach(nic->ndev);
netif_tx_start_all_queues(nic->ndev);
}
}
- if (unlikely(buff->is_eop))
- dev_kfree_skb_any(buff->skb);
+ if (unlikely(buff->is_eop)) {
+ ++self->stats.rx.packets;
+ self->stats.tx.bytes += buff->skb->len;
+ dev_kfree_skb_any(buff->skb);
+ }
buff->pa = 0U;
buff->eop_index = 0xffffU;
self->sw_head = aq_ring_next_dx(self, self->sw_head);
err = 0;
goto err_exit;
}
- if (buff->is_error || buff->is_cso_err) {
+ if (buff->is_error ||
+ (buff->is_lro && buff->is_cso_err)) {
buff_ = buff;
do {
next_ = buff_->next,
u32 is_cleaned:1;
u32 is_error:1;
u32 is_vlan:1;
- u32 rsvd3:4;
+ u32 is_lro:1;
+ u32 rsvd3:3;
u16 eop_index;
u16 rsvd4;
};
}
}
+ buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+ rxd_wb->status);
if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
buff->len = rxd_wb->pkt_len %
AQ_CFG_RX_FRAME_MAX;
rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
- if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
- rxd_wb->status) {
+ if (buff->is_lro) {
/* LRO */
buff->next = rxd_wb->next_desc_ptr;
++ring->stats.rx.lro_packets;
{
struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
unsigned int i = 0U;
+ u32 vlan_promisc;
+ u32 l2_promisc;
- hw_atl_rpfl2promiscuous_mode_en_set(self,
- IS_FILTER_ENABLED(IFF_PROMISC));
+ l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) ||
+ !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET));
+ vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc;
- hw_atl_rpf_vlan_prom_mode_en_set(self,
- IS_FILTER_ENABLED(IFF_PROMISC) ||
- cfg->is_vlan_force_promisc);
+ hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc);
+
+ hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc);
hw_atl_rpfl2multicast_flr_en_set(self,
IS_FILTER_ENABLED(IFF_ALLMULTI) &&
{
self->ptp_clk_offset += delta;
+ self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset);
+
return 0;
}
fwreq.ptp_gpio_ctrl.index = index;
fwreq.ptp_gpio_ctrl.period = period;
/* Apply time offset */
- fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset;
+ fwreq.ptp_gpio_ctrl.start = start;
size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl);
return self->aq_fw_ops->send_fw_request(self, &fwreq, size);
#define HW_ATL_MIF_ADDR 0x0208U
#define HW_ATL_MIF_VAL 0x020CU
+#define HW_ATL_MPI_RPC_ADDR 0x0334U
#define HW_ATL_RPC_CONTROL_ADR 0x0338U
#define HW_ATL_RPC_STATE_ADR 0x033CU
};
static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
-
static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
enum hal_atl_utils_fw_state_e state);
-
static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self);
int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
{
self, self->mbox_addr,
self->mbox_addr != 0U,
1000U, 10000U);
+ err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self,
+ self->rpc_addr,
+ self->rpc_addr != 0U,
+ 1000U, 100000U);
return err;
}
self, fw.val,
sw.tid == fw.tid,
1000U, 100000U);
+ if (err < 0)
+ goto err_exit;
+
+ err = aq_hw_err_from_flags(self);
+ if (err < 0)
+ goto err_exit;
if (fw.len == 0xFFFFU) {
err = hw_atl_utils_fw_rpc_call(self, sw.len);
return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
}
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self)
+{
+ return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR);
+}
+
const struct aq_fw_ops aq_fw_1x_ops = {
.init = hw_atl_utils_mpi_create,
.deinit = hw_atl_fw1x_deinit,
#define HW_ATL_FW3X_EXT_CONTROL_ADDR 0x378
#define HW_ATL_FW3X_EXT_STATE_ADDR 0x37c
+#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR 0x50a0
+#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR 0x50a4
+
#define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE)
#define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE)
#define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY)
aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts);
}
+static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj)
+{
+ aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR,
+ (adj >> 0) & 0xffffffff);
+ aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR,
+ (adj >> 32) & 0xffffffff);
+}
+
static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode)
{
if (self->fw_ver_actual < HW_ATL_FW_VER_LED)
.enable_ptp = aq_fw3x_enable_ptp,
.led_control = aq_fw2x_led_control,
.set_phyloopback = aq_fw2x_set_phyloopback,
+ .adjust_ptp = aq_fw3x_adjust_ptp,
};
}
}
if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event))
- netdev_info(bp->dev, "Receive PF driver unload event!");
+ netdev_info(bp->dev, "Receive PF driver unload event!\n");
}
#else
u32 dw;
if (!pos) {
- netdev_info(bp->dev, "Unable do read adapter's DSN");
+ netdev_info(bp->dev, "Unable do read adapter's DSN\n");
return -EOPNOTSUPP;
}
if (version_printed++ == 0)
pr_info("%s", version);
+ /* Clear any pending DMA transactions from crash kernel
+ * while loading driver in capture kernel.
+ */
+ if (is_kdump_kernel()) {
+ pci_clear_master(pdev);
+ pcie_flr(pdev);
+ }
+
max_irqs = bnxt_get_max_irq(pdev);
dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
if (!dev)
dev_close(dev);
bnxt_ulp_shutdown(bp);
+ bnxt_clear_int_mode(bp);
+ pci_disable_device(pdev);
if (system_state == SYSTEM_POWER_OFF) {
- bnxt_clear_int_mode(bp);
- pci_disable_device(pdev);
pci_wake_from_d3(pdev, bp->wol);
pci_set_power_state(pdev, PCI_D3hot);
}
rc = devlink_params_register(bp->dl, bnxt_dl_params,
ARRAY_SIZE(bnxt_dl_params));
if (rc) {
- netdev_warn(bp->dev, "devlink_params_register failed. rc=%d",
+ netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n",
rc);
return rc;
}
rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params,
ARRAY_SIZE(bnxt_dl_port_params));
if (rc) {
- netdev_err(bp->dev, "devlink_port_params_register failed");
+ netdev_err(bp->dev, "devlink_port_params_register failed\n");
devlink_params_unregister(bp->dl, bnxt_dl_params,
ARRAY_SIZE(bnxt_dl_params));
return rc;
else
dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl));
if (!dl) {
- netdev_warn(bp->dev, "devlink_alloc failed");
+ netdev_warn(bp->dev, "devlink_alloc failed\n");
return -ENOMEM;
}
rc = devlink_register(dl, &bp->pdev->dev);
if (rc) {
- netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
+ netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc);
goto err_dl_free;
}
sizeof(bp->dsn));
rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id);
if (rc) {
- netdev_err(bp->dev, "devlink_port_register failed");
+ netdev_err(bp->dev, "devlink_port_register failed\n");
goto err_dl_unreg;
}
}
if (fw->size > item_len) {
- netdev_err(dev, "PKG insufficient update area in nvram: %lu",
+ netdev_err(dev, "PKG insufficient update area in nvram: %lu\n",
(unsigned long)fw->size);
rc = -EFBIG;
} else {
kfree(coredump.data);
*dump_len += sizeof(struct bnxt_coredump_record);
if (rc == -ENOBUFS)
- netdev_err(bp->dev, "Firmware returned large coredump buffer");
+ netdev_err(bp->dev, "Firmware returned large coredump buffer\n");
return rc;
}
/* check if dev belongs to the same switch */
if (!netdev_port_same_parent_id(pf_bp->dev, dev)) {
- netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
+ netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch\n",
dev->ifindex);
return BNXT_FID_INVALID;
}
struct net_device *dev = act->dev;
if (!dev) {
- netdev_info(bp->dev, "no dev in mirred action");
+ netdev_info(bp->dev, "no dev in mirred action\n");
return -EINVAL;
}
const struct ip_tunnel_key *tun_key = &tun_info->key;
if (ip_tunnel_info_af(tun_info) != AF_INET) {
- netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
+ netdev_info(bp->dev, "only IPv4 tunnel-encap is supported\n");
return -EOPNOTSUPP;
}
int i, rc;
if (!flow_action_has_entries(flow_action)) {
- netdev_info(bp->dev, "no actions");
+ netdev_info(bp->dev, "no actions\n");
return -EINVAL;
}
/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
(dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
- netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x",
+ netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n",
dissector->used_keys);
return -EOPNOTSUPP;
}
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (rc)
- netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
return rc;
}
resp = bnxt_get_hwrm_resp_addr(bp, &req);
*decap_filter_handle = resp->decap_filter_id;
} else {
- netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
}
mutex_unlock(&bp->hwrm_cmd_lock);
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (rc)
- netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
return rc;
}
resp = bnxt_get_hwrm_resp_addr(bp, &req);
*encap_record_handle = resp->encap_record_id;
} else {
- netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
}
mutex_unlock(&bp->hwrm_cmd_lock);
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (rc)
- netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
return rc;
}
tc_info->l2_ht_params);
if (rc)
netdev_err(bp->dev,
- "Error: %s: rhashtable_remove_fast: %d",
+ "Error: %s: rhashtable_remove_fast: %d\n",
__func__, rc);
kfree_rcu(l2_node, rcu);
}
if (rc) {
kfree_rcu(l2_node, rcu);
netdev_err(bp->dev,
- "Error: %s: rhashtable_insert_fast: %d",
+ "Error: %s: rhashtable_insert_fast: %d\n",
__func__, rc);
return NULL;
}
if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) &&
(flow->l4_key.ip_proto != IPPROTO_TCP &&
flow->l4_key.ip_proto != IPPROTO_UDP)) {
- netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports",
+ netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports\n",
flow->l4_key.ip_proto);
return false;
}
rc = rhashtable_remove_fast(tunnel_table, &tunnel_node->node,
*ht_params);
if (rc) {
- netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+ netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc);
rc = -1;
}
kfree_rcu(tunnel_node, rcu);
tunnel_node->refcount++;
return tunnel_node;
err:
- netdev_info(bp->dev, "error rc=%d", rc);
+ netdev_info(bp->dev, "error rc=%d\n", rc);
return NULL;
}
&decap_l2_node->node,
tc_info->decap_l2_ht_params);
if (rc)
- netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+ netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc);
kfree_rcu(decap_l2_node, rcu);
}
}
rt = ip_route_output_key(dev_net(real_dst_dev), &flow);
if (IS_ERR(rt)) {
- netdev_info(bp->dev, "no route to %pI4b", &flow.daddr);
+ netdev_info(bp->dev, "no route to %pI4b\n", &flow.daddr);
return -EOPNOTSUPP;
}
if (vlan->real_dev != real_dst_dev) {
netdev_info(bp->dev,
- "dst_dev(%s) doesn't use PF-if(%s)",
+ "dst_dev(%s) doesn't use PF-if(%s)\n",
netdev_name(dst_dev),
netdev_name(real_dst_dev));
rc = -EOPNOTSUPP;
#endif
} else if (dst_dev != real_dst_dev) {
netdev_info(bp->dev,
- "dst_dev(%s) for %pI4b is not PF-if(%s)",
+ "dst_dev(%s) for %pI4b is not PF-if(%s)\n",
netdev_name(dst_dev), &flow.daddr,
netdev_name(real_dst_dev));
rc = -EOPNOTSUPP;
nbr = dst_neigh_lookup(&rt->dst, &flow.daddr);
if (!nbr) {
- netdev_info(bp->dev, "can't lookup neighbor for %pI4b",
+ netdev_info(bp->dev, "can't lookup neighbor for %pI4b\n",
&flow.daddr);
rc = -EOPNOTSUPP;
goto put_rt;
rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node,
tc_info->flow_ht_params);
if (rc)
- netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d",
+ netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d\n",
__func__, rc);
kfree_rcu(flow_node, rcu);
free_node:
kfree_rcu(new_node, rcu);
done:
- netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d",
+ netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d\n",
__func__, tc_flow_cmd->cookie, rc);
return rc;
}
le64_to_cpu(resp_bytes[i]);
}
} else {
- netdev_info(bp->dev, "error rc=%d", rc);
+ netdev_info(bp->dev, "error rc=%d\n", rc);
}
mutex_unlock(&bp->hwrm_cmd_lock);
bp);
if (rc)
netdev_info(bp->dev,
- "Failed to register indirect blk: dev: %s",
+ "Failed to register indirect blk: dev: %s\n",
netdev->name);
break;
case NETDEV_UNREGISTER:
netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x",
*tx_cfa_action, *rx_cfa_code);
} else {
- netdev_info(bp->dev, "%s error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc);
}
mutex_unlock(&bp->hwrm_cmd_lock);
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (rc)
- netdev_info(bp->dev, "%s error rc=%d", __func__, rc);
+ netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc);
return rc;
}
return 0;
err:
- netdev_info(bp->dev, "%s error=%d", __func__, rc);
+ netdev_info(bp->dev, "%s error=%d\n", __func__, rc);
kfree(cfa_code_map);
__bnxt_vf_reps_destroy(bp);
return rc;
mutex_lock(&bp->sriov_lock);
if (bp->eswitch_mode == mode) {
- netdev_info(bp->dev, "already in %s eswitch mode",
+ netdev_info(bp->dev, "already in %s eswitch mode\n",
mode == DEVLINK_ESWITCH_MODE_LEGACY ?
"legacy" : "switchdev");
rc = -EINVAL;
}
if (pci_num_vf(bp->pdev) == 0) {
- netdev_info(bp->dev, "Enable VFs before setting switchdev mode");
+ netdev_info(bp->dev, "Enable VFs before setting switchdev mode\n");
rc = -EPERM;
goto done;
}
#define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2
#endif
#if defined(__BIG_ENDIAN)
- u16 reserverd3;
+ u16 reserved3;
u8 da0;
u8 da1;
#elif defined(__LITTLE_ENDIAN)
u8 da1;
u8 da0;
- u16 reserverd3;
+ u16 reserved3;
#endif
#if defined(__BIG_ENDIAN)
u8 da2;
*/
if (priv->ext_phy) {
reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
+ reg &= ~ID_MODE_DIS;
reg |= id_mode_dis;
if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
reg |= RGMII_MODE_EN_V123;
#define MACB_CAPS_GEM_HAS_PTP 0x00000040
#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100
+#define MACB_CAPS_MACB_IS_EMAC 0x08000000
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
/* Clear all the bits we might set later */
- ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) |
- GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+ ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE));
+
+ if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
+ if (state->interface == PHY_INTERFACE_MODE_RMII)
+ ctrl |= MACB_BIT(RM9200_RMII);
+ } else {
+ ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+
+ /* We do not support MLO_PAUSE_RX yet */
+ if (state->pause & MLO_PAUSE_TX)
+ ctrl |= MACB_BIT(PAE);
+
+ if (state->interface == PHY_INTERFACE_MODE_SGMII)
+ ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
+ }
if (state->speed == SPEED_1000)
ctrl |= GEM_BIT(GBE);
if (state->duplex)
ctrl |= MACB_BIT(FD);
- /* We do not support MLO_PAUSE_RX yet */
- if (state->pause & MLO_PAUSE_TX)
- ctrl |= MACB_BIT(PAE);
-
- if (state->interface == PHY_INTERFACE_MODE_SGMII)
- ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
-
/* Apply the new configuration, if any */
if (old_ctrl ^ ctrl)
macb_or_gem_writel(bp, NCFGR, ctrl);
unsigned int q;
u32 ctrl;
- for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
- queue_writel(queue, IDR,
- bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+ if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+ queue_writel(queue, IDR,
+ bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
/* Disable Rx and Tx */
ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE));
struct macb_queue *queue;
unsigned int q;
- macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
+ if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
+ macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
- /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
- * cleared the pipeline and control registers.
- */
- bp->macbgem_ops.mog_init_rings(bp);
- macb_init_buffers(bp);
+ /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
+ * cleared the pipeline and control registers.
+ */
+ bp->macbgem_ops.mog_init_rings(bp);
+ macb_init_buffers(bp);
- for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
- queue_writel(queue, IER,
- bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+ queue_writel(queue, IER,
+ bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+ }
/* Enable Rx and Tx */
macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
u32 ctl;
int ret;
+ ret = pm_runtime_get_sync(&lp->pdev->dev);
+ if (ret < 0)
+ return ret;
+
/* Clear internal statistics */
ctl = macb_readl(lp, NCR);
macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
q->rx_buffers, q->rx_buffers_dma);
q->rx_buffers = NULL;
- return 0;
+ return pm_runtime_put(&lp->pdev->dev);
}
/* Transmit packet */
struct net_device *dev = platform_get_drvdata(pdev);
struct macb *bp = netdev_priv(dev);
int err;
- u32 reg;
bp->queues[0].bp = bp;
macb_writel(bp, NCR, 0);
- reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG);
- if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
- reg |= MACB_BIT(RM9200_RMII);
-
- macb_writel(bp, NCFGR, reg);
+ macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG));
return 0;
}
};
static const struct macb_config emac_config = {
- .caps = MACB_CAPS_NEEDS_RSTONUBR,
+ .caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC,
.clk_init = at91ether_clk_init,
.init = at91ether_init,
};
lmac = &bgx->lmac[lmacid];
cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
- if (enable)
+ if (enable) {
cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
- else
+
+ /* enable TX FIFO Underflow interrupt */
+ bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S,
+ GMI_TXX_INT_UNDFLW);
+ } else {
cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+
+ /* Disable TX FIFO Underflow interrupt */
+ bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C,
+ GMI_TXX_INT_UNDFLW);
+ }
bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
if (bgx->is_rgx)
return bgx_init_of_phy(bgx);
}
+static irqreturn_t bgx_intr_handler(int irq, void *data)
+{
+ struct bgx *bgx = (struct bgx *)data;
+ u64 status, val;
+ int lmac;
+
+ for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+ status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT);
+ if (status & GMI_TXX_INT_UNDFLW) {
+ pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n",
+ bgx->bgx_id, lmac);
+ val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG);
+ val &= ~CMR_EN;
+ bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+ val |= CMR_EN;
+ bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+ }
+ /* clear interrupts */
+ bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void bgx_register_intr(struct pci_dev *pdev)
+{
+ struct bgx *bgx = pci_get_drvdata(pdev);
+ int ret;
+
+ ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET,
+ BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES);
+ if (ret < 0) {
+ pci_err(pdev, "Req for #%d msix vectors failed\n",
+ BGX_LMAC_VEC_OFFSET);
+ return;
+ }
+ ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL,
+ bgx, "BGX%d", bgx->bgx_id);
+ if (ret)
+ pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+}
+
static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
int err;
pci_set_drvdata(pdev, bgx);
- err = pci_enable_device(pdev);
+ err = pcim_enable_device(pdev);
if (err) {
dev_err(dev, "Failed to enable PCI device\n");
pci_set_drvdata(pdev, NULL);
bgx_init_hw(bgx);
+ bgx_register_intr(pdev);
+
/* Enable all LMACs */
for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
err = bgx_lmac_enable(bgx, lmac);
err_enable:
bgx_vnic[bgx->bgx_id] = NULL;
+ pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
err_release_regions:
pci_release_regions(pdev);
err_disable_device:
for (lmac = 0; lmac < bgx->lmac_count; lmac++)
bgx_lmac_disable(bgx, lmac);
+ pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+
bgx_vnic[bgx->bgx_id] = NULL;
pci_release_regions(pdev);
pci_disable_device(pdev);
#define BGX_GMP_GMI_TXX_BURST 0x38228
#define BGX_GMP_GMI_TXX_MIN_PKT 0x38240
#define BGX_GMP_GMI_TXX_SGMII_CTL 0x38300
+#define BGX_GMP_GMI_TXX_INT 0x38500
+#define BGX_GMP_GMI_TXX_INT_W1S 0x38508
+#define BGX_GMP_GMI_TXX_INT_ENA_W1C 0x38510
+#define BGX_GMP_GMI_TXX_INT_ENA_W1S 0x38518
+#define GMI_TXX_INT_PTP_LOST BIT_ULL(4)
+#define GMI_TXX_INT_LATE_COL BIT_ULL(3)
+#define GMI_TXX_INT_XSDEF BIT_ULL(2)
+#define GMI_TXX_INT_XSCOL BIT_ULL(1)
+#define GMI_TXX_INT_UNDFLW BIT_ULL(0)
#define BGX_MSIX_VEC_0_29_ADDR 0x400000 /* +(0..29) << 4 */
#define BGX_MSIX_VEC_0_29_CTL 0x400008
mac_addr = of_get_mac_address(np);
if (!IS_ERR(mac_addr))
ether_addr_copy(pdata->dev_addr, mac_addr);
+ else if (PTR_ERR(mac_addr) == -EPROBE_DEFER)
+ return ERR_CAST(mac_addr);
return pdata;
}
}
hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+ hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif);
hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT;
hw_ioctxt.cmdq_depth = 0;
u8 lro_en;
u8 rsvd3;
+ u8 ppf_idx;
u8 rsvd4;
- u8 rsvd5;
u16 rq_depth;
u16 rx_buf_sz_idx;
#define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx)
#define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx)
#define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx)
+#define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx)
#define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type)
#define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF)
struct hinic_wq *wq;
+ struct cpumask affinity_mask;
u32 irq;
u16 msix_entry;
if (!num_cpus)
num_cpus = num_online_cpus();
- nic_dev->num_qps = min_t(u16, nic_dev->max_qps, num_cpus);
+ nic_dev->num_qps = hinic_hwdev_num_qps(hwdev);
+ nic_dev->num_qps = min_t(u16, nic_dev->num_qps, num_cpus);
nic_dev->rss_limit = nic_dev->num_qps;
nic_dev->num_rss = nic_dev->num_qps;
struct hinic_hwdev *hwdev = nic_dev->hwdev;
struct hinic_rq *rq = rxq->rq;
struct hinic_qp *qp;
- struct cpumask mask;
int err;
rx_add_napi(rxq);
}
qp = container_of(rq, struct hinic_qp, rq);
- cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask);
- return irq_set_affinity_hint(rq->irq, &mask);
+ cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask);
+ return irq_set_affinity_hint(rq->irq, &rq->affinity_mask);
}
static void rx_free_irq(struct hinic_rxq *rxq)
else
return -EINVAL;
- /* Tell the OS link is going down, the link will go back up when fw
- * says it is ready asynchronously
- */
- ice_print_link_msg(vsi, false);
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
-
/* Set the FC mode and only restart AN if link is up */
status = ice_set_fc(pi, &aq_failures, link_up);
return -EINVAL;
}
- /* hardware only supports an ITR granularity of 2us */
- if (coalesce_usecs % 2 != 0) {
- netdev_info(vsi->netdev, "Invalid value, %s-usecs must be even\n",
- c_type_str);
- return -EINVAL;
- }
-
if (use_adaptive_coalesce) {
rc->itr_setting |= ICE_ITR_DYNAMIC;
} else {
- /* store user facing value how it was set */
+ /* save the user set usecs */
rc->itr_setting = coalesce_usecs;
- /* set to static and convert to value HW understands */
- rc->target_itr =
- ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting));
+ /* device ITR granularity is in 2 usec increments */
+ rc->target_itr = ITR_REG_ALIGN(rc->itr_setting);
}
return 0;
return 0;
}
+/**
+ * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs
+ * @netdev: netdev used for print
+ * @itr_setting: previous user setting
+ * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled
+ * @coalesce_usecs: requested value of [tx|rx]-usecs
+ * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs
+ */
+static void
+ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting,
+ u32 use_adaptive_coalesce, u32 coalesce_usecs,
+ const char *c_type_str)
+{
+ if (use_adaptive_coalesce)
+ return;
+
+ itr_setting = ITR_TO_REG(itr_setting);
+
+ if (itr_setting != coalesce_usecs && (coalesce_usecs % 2))
+ netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n",
+ c_type_str, coalesce_usecs, c_type_str,
+ ITR_REG_ALIGN(coalesce_usecs));
+}
+
/**
* __ice_set_coalesce - set ITR/INTRL values for the device
* @netdev: pointer to the netdev associated with this query
return -EINVAL;
if (q_num < 0) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[0];
int v_idx;
+ if (q_vector) {
+ ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting,
+ ec->use_adaptive_rx_coalesce,
+ ec->rx_coalesce_usecs, "rx");
+
+ ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting,
+ ec->use_adaptive_tx_coalesce,
+ ec->tx_coalesce_usecs, "tx");
+ }
+
ice_for_each_q_vector(vsi, v_idx) {
/* In some cases if DCB is configured the num_[rx|tx]q
* can be less than vsi->num_q_vectors. This check
#define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */
#define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S)
#define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */
-#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~ICE_ITR_MASK)
+#define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK)
#define ICE_ITR_ADAPTIVE_MIN_INC 0x0002
#define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002
NULL, 0);
}
+/**
+ * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset
+ * @vf: The VF being resseting
+ *
+ * The max poll time is about ~800ms, which is about the maximum time it takes
+ * for a VF to be reset and/or a VF driver to be removed.
+ */
+static void ice_wait_on_vf_reset(struct ice_vf *vf)
+{
+ int i;
+
+ for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) {
+ if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
+ break;
+ msleep(ICE_MAX_VF_RESET_SLEEP_MS);
+ }
+}
+
+/**
+ * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried
+ * @vf: VF to check if it's ready to be configured/queried
+ *
+ * The purpose of this function is to make sure the VF is not in reset, not
+ * disabled, and initialized so it can be configured and/or queried by a host
+ * administrator.
+ */
+static int ice_check_vf_ready_for_cfg(struct ice_vf *vf)
+{
+ struct ice_pf *pf;
+
+ ice_wait_on_vf_reset(vf);
+
+ if (ice_is_vf_disabled(vf))
+ return -EINVAL;
+
+ pf = vf->pf;
+ if (ice_check_vf_init(pf, vf))
+ return -EBUSY;
+
+ return 0;
+}
+
/**
* ice_set_vf_spoofchk
* @netdev: network interface device structure
enum ice_status status;
struct device *dev;
struct ice_vf *vf;
- int ret = 0;
+ int ret;
dev = ice_pf_to_dev(pf);
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
vf = &pf->vf[vf_id];
-
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
vf_vsi = pf->vsi[vf->lan_vsi_idx];
if (!vf_vsi) {
struct ice_vsi *vsi;
struct device *dev;
struct ice_vf *vf;
- int ret = 0;
+ int ret;
dev = ice_pf_to_dev(pf);
if (ice_validate_vf_id(pf, vf_id))
vf = &pf->vf[vf_id];
vsi = pf->vsi[vf->lan_vsi_idx];
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
+
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
if (le16_to_cpu(vsi->info.pvid) == vlanprio) {
/* duplicate request, so just return success */
dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio);
- return ret;
+ return 0;
}
/* If PVID, then remove all filters on the old VLAN */
if (vlan_id || qos) {
ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
if (ret)
- goto error_set_pvid;
+ return ret;
} else {
ice_vsi_manage_pvid(vsi, 0, false);
vsi->info.pvid = 0;
/* add new VLAN filter for each MAC */
ret = ice_vsi_add_vlan(vsi, vlan_id);
if (ret)
- goto error_set_pvid;
+ return ret;
}
/* The Port VLAN needs to be saved across resets the same as the
*/
vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
-error_set_pvid:
- return ret;
+ return 0;
}
/**
return 0;
}
-/**
- * ice_wait_on_vf_reset
- * @vf: The VF being resseting
- *
- * Poll to make sure a given VF is ready after reset
- */
-static void ice_wait_on_vf_reset(struct ice_vf *vf)
-{
- int i;
-
- for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) {
- if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
- break;
- msleep(20);
- }
-}
-
/**
* ice_set_vf_mac
* @netdev: network interface device structure
{
struct ice_pf *pf = ice_netdev_to_pf(netdev);
struct ice_vf *vf;
- int ret = 0;
+ int ret;
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
- vf = &pf->vf[vf_id];
- /* Don't set MAC on disabled VF */
- if (ice_is_vf_disabled(vf))
- return -EINVAL;
-
- /* In case VF is in reset mode, wait until it is completed. Depending
- * on factors like queue disabling routine, this could take ~250ms
- */
- ice_wait_on_vf_reset(vf);
-
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
-
if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) {
netdev_err(netdev, "%pM not a valid unicast address\n", mac);
return -EINVAL;
}
+ vf = &pf->vf[vf_id];
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
+
/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
* flow will use the updated dflt_lan_addr and add a MAC filter
* using ice_add_mac. Also set pf_set_mac to indicate that the PF has
vf_id, mac);
ice_vc_reset_vf(vf);
- return ret;
+ return 0;
}
/**
{
struct ice_pf *pf = ice_netdev_to_pf(netdev);
struct ice_vf *vf;
+ int ret;
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
vf = &pf->vf[vf_id];
- /* Don't set Trusted Mode on disabled VF */
- if (ice_is_vf_disabled(vf))
- return -EINVAL;
-
- /* In case VF is in reset mode, wait until it is completed. Depending
- * on factors like queue disabling routine, this could take ~250ms
- */
- ice_wait_on_vf_reset(vf);
-
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
/* Check if already trusted */
if (trusted == vf->trusted)
{
struct ice_pf *pf = ice_netdev_to_pf(netdev);
struct ice_vf *vf;
+ int ret;
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
vf = &pf->vf[vf_id];
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
switch (link_state) {
case IFLA_VF_LINK_STATE_AUTO:
struct ice_eth_stats *stats;
struct ice_vsi *vsi;
struct ice_vf *vf;
+ int ret;
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
vf = &pf->vf[vf_id];
-
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
+ ret = ice_check_vf_ready_for_cfg(vf);
+ if (ret)
+ return ret;
vsi = pf->vsi[vf->lan_vsi_idx];
if (!vsi)
#define ICE_MAX_POLICY_INTR_PER_VF 33
#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1)
#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1)
-#define ICE_MAX_VF_RESET_WAIT 15
+#define ICE_MAX_VF_RESET_TRIES 40
+#define ICE_MAX_VF_RESET_SLEEP_MS 20
#define ice_for_each_vf(pf, i) \
for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++)
netdev_err(priv->netdev, err_str);
if (!reporter)
- return err_ctx->recover(&err_ctx->ctx);
+ return err_ctx->recover(err_ctx->ctx);
return devlink_health_report(reporter, err_str, err_ctx);
}
}
}
+static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
+{
+ if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ mlx5_wq_ll_reset(&rq->mpwqe.wq);
+ else
+ mlx5_wq_cyc_reset(&rq->wqe.wq);
+}
+
/* SW parser related functions */
struct mlx5e_swp_spec {
if (!in)
return -ENOMEM;
+ if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY)
+ mlx5e_rqwq_reset(rq);
+
rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
MLX5_SET(modify_rq_in, in, rq_state, curr_state);
static void mlx5e_nic_disable(struct mlx5e_priv *priv)
{
- struct net_device *netdev = priv->netdev;
struct mlx5_core_dev *mdev = priv->mdev;
#ifdef CONFIG_MLX5_CORE_EN_DCB
mlx5e_monitor_counter_cleanup(priv);
mlx5e_disable_async_events(priv);
- mlx5_lag_remove(mdev, netdev);
+ mlx5_lag_remove(mdev);
}
int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
{
- struct net_device *netdev = priv->netdev;
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
#endif
mlx5_notifier_unregister(mdev, &priv->events_nb);
cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
- mlx5_lag_remove(mdev, netdev);
+ mlx5_lag_remove(mdev);
}
static MLX5E_DEFINE_STATS_GRP(sw_rep, 0);
static int esw_legacy_enable(struct mlx5_eswitch *esw)
{
- int ret;
+ struct mlx5_vport *vport;
+ int ret, i;
ret = esw_create_legacy_table(esw);
if (ret)
return ret;
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+ vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+
ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
if (ret)
esw_destroy_legacy_table(esw);
int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
{
- int err = 0;
-
if (!esw)
return -EOPNOTSUPP;
if (!ESW_ALLOWED(esw))
return -EPERM;
- mutex_lock(&esw->state_lock);
- if (esw->mode != MLX5_ESWITCH_LEGACY) {
- err = -EOPNOTSUPP;
- goto out;
- }
+ if (esw->mode != MLX5_ESWITCH_LEGACY)
+ return -EOPNOTSUPP;
*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
-
-out:
- mutex_unlock(&esw->state_lock);
- return err;
+ return 0;
}
int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
return -EINVAL;
}
- mlx5_eswitch_disable(esw, true);
+ mlx5_eswitch_disable(esw, false);
mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
if (err) {
{
int err, err1;
- mlx5_eswitch_disable(esw, true);
+ mlx5_eswitch_disable(esw, false);
err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024,
1 * 1024 * 1024,
64 * 1024,
- 4 * 1024, };
+ 128 };
struct mlx5_esw_chains_priv {
struct rhashtable chains_ht;
struct mlx5_lag *ldev;
int changed = 0;
- if (!net_eq(dev_net(ndev), &init_net))
- return NOTIFY_DONE;
-
if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE))
return NOTIFY_DONE;
if (!ldev->nb.notifier_call) {
ldev->nb.notifier_call = mlx5_lag_netdev_event;
- if (register_netdevice_notifier_dev_net(netdev, &ldev->nb,
- &ldev->nn)) {
+ if (register_netdevice_notifier_net(&init_net, &ldev->nb)) {
ldev->nb.notifier_call = NULL;
mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
}
}
/* Must be called with intf_mutex held */
-void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev)
+void mlx5_lag_remove(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
int i;
if (i == MLX5_MAX_PORTS) {
if (ldev->nb.notifier_call)
- unregister_netdevice_notifier_dev_net(netdev, &ldev->nb,
- &ldev->nn);
+ unregister_netdevice_notifier_net(&init_net, &ldev->nb);
mlx5_lag_mp_cleanup(ldev);
cancel_delayed_work_sync(&ldev->bond_work);
mlx5_lag_dev_free(ldev);
struct workqueue_struct *wq;
struct delayed_work bond_work;
struct notifier_block nb;
- struct netdev_net_notifier nn;
struct lag_mp lag_mp;
};
u8 feature_group, u8 access_reg_group);
void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
-void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev);
+void mlx5_lag_remove(struct mlx5_core_dev *dev);
int mlx5_irq_table_init(struct mlx5_core_dev *dev);
void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
struct mlx5dr_cmd_vport_cap *vport_cap;
struct mlx5dr_domain *dmn = sb->dmn;
struct mlx5dr_cmd_caps *caps;
+ u8 *bit_mask = sb->bit_mask;
u8 *tag = hw_ste->tag;
+ bool source_gvmi_set;
DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
if (!vport_cap)
return -EINVAL;
- if (vport_cap->vport_gvmi)
+ source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi);
+ if (vport_cap->vport_gvmi && source_gvmi_set)
MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi);
misc->source_eswitch_owner_vhca_id = 0;
struct mlx5_flow_table *next_ft)
{
struct mlx5dr_table *tbl;
+ u32 flags;
int err;
if (mlx5_dr_is_fw_table(ft->flags))
return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
log_size,
next_ft);
+ flags = ft->flags;
+ /* turn off encap/decap if not supported for sw-str by fw */
+ if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported))
+ flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
+ MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
- tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
- ft->level, ft->flags);
+ tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags);
if (!tbl) {
mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
return -EINVAL;
print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
}
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq)
+{
+ wq->wqe_ctr = 0;
+ wq->cur_sz = 0;
+ mlx5_wq_cyc_update_db_record(wq);
+}
+
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)
return err;
}
+static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq)
+{
+ struct mlx5_wqe_srq_next_seg *next_seg;
+ int i;
+
+ for (i = 0; i < wq->fbc.sz_m1; i++) {
+ next_seg = mlx5_wq_ll_get_wqe(wq, i);
+ next_seg->next_wqe_index = cpu_to_be16(i + 1);
+ }
+ next_seg = mlx5_wq_ll_get_wqe(wq, i);
+ wq->tail_next = &next_seg->next_wqe_index;
+}
+
int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *wqc, struct mlx5_wq_ll *wq,
struct mlx5_wq_ctrl *wq_ctrl)
u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride);
u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz);
struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
- struct mlx5_wqe_srq_next_seg *next_seg;
int err;
- int i;
err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
if (err) {
mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc);
- for (i = 0; i < fbc->sz_m1; i++) {
- next_seg = mlx5_wq_ll_get_wqe(wq, i);
- next_seg->next_wqe_index = cpu_to_be16(i + 1);
- }
- next_seg = mlx5_wq_ll_get_wqe(wq, i);
- wq->tail_next = &next_seg->next_wqe_index;
-
+ mlx5_wq_ll_init_list(wq);
wq_ctrl->mdev = mdev;
return 0;
return err;
}
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq)
+{
+ wq->head = 0;
+ wq->wqe_ctr = 0;
+ wq->cur_sz = 0;
+ mlx5_wq_ll_init_list(wq);
+ mlx5_wq_ll_update_db_record(wq);
+}
+
void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
{
mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);
void *wqc, struct mlx5_wq_cyc *wq,
struct mlx5_wq_ctrl *wq_ctrl);
void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq);
int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *qpc, struct mlx5_wq_qp *wq,
int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *wqc, struct mlx5_wq_ll *wq,
struct mlx5_wq_ctrl *wq_ctrl);
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq);
void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
#define MLXSW_PCI_SW_RESET 0xF0010
#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0)
#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000
-#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100
+#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200
#define MLXSW_PCI_FW_READY 0xA1844
#define MLXSW_PCI_FW_READY_MASK 0xFFFF
#define MLXSW_PCI_FW_READY_MAGIC 0x5E
* chip is busy transferring packet data (RX/TX FIFO accesses).
*/
-/**
- * ks_rdreg8 - read 8 bit register from device
- * @ks : The chip information
- * @offset: The register address
- *
- * Read a 8bit register from the chip, returning the result
- */
-static u8 ks_rdreg8(struct ks_net *ks, int offset)
-{
- u16 data;
- u8 shift_bit = offset & 0x03;
- u8 shift_data = (offset & 1) << 3;
- ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit);
- iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
- data = ioread16(ks->hw_addr);
- return (u8)(data >> shift_data);
-}
-
/**
* ks_rdreg16 - read 16 bit register from device
* @ks : The chip information
static u16 ks_rdreg16(struct ks_net *ks, int offset)
{
- ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+ ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
return ioread16(ks->hw_addr);
}
-/**
- * ks_wrreg8 - write 8bit register value to chip
- * @ks: The chip information
- * @offset: The register address
- * @value: The value to write
- *
- */
-static void ks_wrreg8(struct ks_net *ks, int offset, u8 value)
-{
- u8 shift_bit = (offset & 0x03);
- u16 value_write = (u16)(value << ((offset & 1) << 3));
- ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit);
- iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
- iowrite16(value_write, ks->hw_addr);
-}
-
/**
* ks_wrreg16 - write 16bit register value to chip
* @ks: The chip information
static void ks_wrreg16(struct ks_net *ks, int offset, u16 value)
{
- ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+ ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
iowrite16(value, ks->hw_addr);
}
{
len >>= 1;
while (len--)
- *wptr++ = (u16)ioread16(ks->hw_addr);
+ *wptr++ = be16_to_cpu(ioread16(ks->hw_addr));
}
/**
{
len >>= 1;
while (len--)
- iowrite16(*wptr++, ks->hw_addr);
+ iowrite16(cpu_to_be16(*wptr++), ks->hw_addr);
}
static void ks_disable_int(struct ks_net *ks)
u16 reg_data = 0;
/* Regardless of bus width, 8 bit read should always work.*/
- reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF;
- reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8;
+ reg_data = ks_rdreg16(ks, KS_CCR);
/* addr/data bus are multiplexed */
ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
/* 1. set sudo DMA mode */
ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
- ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+ ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
/* 2. read prepend data */
/**
ks_inblk(ks, buf, ALIGN(len, 4));
/* 4. reset sudo DMA Mode */
- ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+ ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
}
/**
{
struct net_device *netdev = pw;
struct ks_net *ks = netdev_priv(netdev);
+ unsigned long flags;
u16 status;
+ spin_lock_irqsave(&ks->statelock, flags);
/*this should be the first in IRQ handler */
ks_save_cmd_reg(ks);
status = ks_rdreg16(ks, KS_ISR);
if (unlikely(!status)) {
ks_restore_cmd_reg(ks);
+ spin_unlock_irqrestore(&ks->statelock, flags);
return IRQ_NONE;
}
ks->netdev->stats.rx_over_errors++;
/* this should be the last in IRQ handler*/
ks_restore_cmd_reg(ks);
+ spin_unlock_irqrestore(&ks->statelock, flags);
return IRQ_HANDLED;
}
/* shutdown RX/TX QMU */
ks_disable_qmu(ks);
+ ks_disable_int(ks);
/* set powermode to soft power down to save power */
ks_set_powermode(ks, PMECR_PM_SOFTDOWN);
ks->txh.txw[1] = cpu_to_le16(len);
/* 1. set sudo-DMA mode */
- ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+ ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
/* 2. write status/lenth info */
ks_outblk(ks, ks->txh.txw, 4);
/* 3. write pkt data */
ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4));
/* 4. reset sudo-DMA mode */
- ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+ ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
/* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */
ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
/* 6. wait until TXQCR_METFE is auto-cleared */
{
netdev_tx_t retv = NETDEV_TX_OK;
struct ks_net *ks = netdev_priv(netdev);
+ unsigned long flags;
- disable_irq(netdev->irq);
- ks_disable_int(ks);
- spin_lock(&ks->statelock);
+ spin_lock_irqsave(&ks->statelock, flags);
/* Extra space are required:
* 4 byte for alignment, 4 for status/length, 4 for CRC
dev_kfree_skb(skb);
} else
retv = NETDEV_TX_BUSY;
- spin_unlock(&ks->statelock);
- ks_enable_int(ks);
- enable_irq(netdev->irq);
+ spin_unlock_irqrestore(&ks->statelock, flags);
return retv;
}
if (err != 4)
break;
+ /* At this point the IFH was read correctly, so it is safe to
+ * presume that there is no error. The err needs to be reset
+ * otherwise a frame could come in CPU queue between the while
+ * condition and the check for error later on. And in that case
+ * the new frame is just removed and not processed.
+ */
+ err = 0;
+
ocelot_parse_ifh(ifh, &info);
ocelot_port = ocelot->ports[info.port];
{
struct ionic_dev *idev = &ionic->idev;
unsigned long hb_time;
- u32 fw_status;
+ u8 fw_status;
u32 hb;
/* wait a little more than one second before testing again */
if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period)))
return 0;
- /* firmware is useful only if fw_status is non-zero */
- fw_status = ioread32(&idev->dev_info_regs->fw_status);
- if (!fw_status)
+ /* firmware is useful only if the running bit is set and
+ * fw_status != 0xff (bad PCI read)
+ */
+ fw_status = ioread8(&idev->dev_info_regs->fw_status);
+ if (fw_status == 0xff ||
+ !(fw_status & IONIC_FW_STS_F_RUNNING))
return -ENXIO;
/* early FW has no heartbeat, else FW will return non-zero */
u8 version;
u8 asic_type;
u8 asic_rev;
+#define IONIC_FW_STS_F_RUNNING 0x1
u8 fw_status;
u32 fw_heartbeat;
char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN];
struct list_head entry;
struct list_head rdma_event_list;
struct workqueue_struct *rdma_wq;
+ struct kref refcnt;
+ struct completion event_comp;
bool exp_recovery;
};
static int qede_rdma_create_wq(struct qede_dev *edev)
{
INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+ kref_init(&edev->rdma_info.refcnt);
+ init_completion(&edev->rdma_info.event_comp);
+
edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
if (!edev->rdma_info.rdma_wq) {
DP_NOTICE(edev, "qedr: Could not create workqueue\n");
}
}
+static void qede_rdma_complete_event(struct kref *ref)
+{
+ struct qede_rdma_dev *rdma_dev =
+ container_of(ref, struct qede_rdma_dev, refcnt);
+
+ /* no more events will be added after this */
+ complete(&rdma_dev->event_comp);
+}
+
static void qede_rdma_destroy_wq(struct qede_dev *edev)
{
+ /* Avoid race with add_event flow, make sure it finishes before
+ * we start accessing the list and cleaning up the work
+ */
+ kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+ wait_for_completion(&edev->rdma_info.event_comp);
+
qede_rdma_cleanup_event(edev);
destroy_workqueue(edev->rdma_info.rdma_wq);
}
if (!edev->rdma_info.qedr_dev)
return;
+ /* We don't want the cleanup flow to start while we're allocating and
+ * scheduling the work
+ */
+ if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+ return; /* already being destroyed */
+
event_node = qede_rdma_get_free_event_node(edev);
if (!event_node)
- return;
+ goto out;
event_node->event = event;
event_node->ptr = edev;
INIT_WORK(&event_node->work, qede_rdma_handle_event);
queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+ kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
}
void qede_rdma_dev_event_open(struct qede_dev *edev)
#include "rmnet_vnd.h"
#include "rmnet_private.h"
-/* Locking scheme -
- * The shared resource which needs to be protected is realdev->rx_handler_data.
- * For the writer path, this is using rtnl_lock(). The writer paths are
- * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These
- * paths are already called with rtnl_lock() acquired in. There is also an
- * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For
- * dereference here, we will need to use rtnl_dereference(). Dev list writing
- * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link().
- * For the reader path, the real_dev->rx_handler_data is called in the TX / RX
- * path. We only need rcu_read_lock() for these scenarios. In these cases,
- * the rcu_read_lock() is held in __dev_queue_xmit() and
- * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl()
- * to get the relevant information. For dev list reading, we again acquire
- * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu().
- * We also use unregister_netdevice_many() to free all rmnet devices in
- * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in
- * same context.
- */
-
/* Local Definitions and Declarations */
static const struct nla_policy rmnet_policy[IFLA_RMNET_MAX + 1] = {
return rtnl_dereference(real_dev->rx_handler_data);
}
-static int rmnet_unregister_real_device(struct net_device *real_dev,
- struct rmnet_port *port)
+static int rmnet_unregister_real_device(struct net_device *real_dev)
{
+ struct rmnet_port *port = rmnet_get_port_rtnl(real_dev);
+
if (port->nr_rmnet_devs)
return -EINVAL;
kfree(port);
- /* release reference on real_dev */
- dev_put(real_dev);
-
netdev_dbg(real_dev, "Removed from rmnet\n");
return 0;
}
return -EBUSY;
}
- /* hold on to real dev for MAP data */
- dev_hold(real_dev);
-
for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++)
INIT_HLIST_HEAD(&port->muxed_ep[entry]);
return 0;
}
-static void rmnet_unregister_bridge(struct net_device *dev,
- struct rmnet_port *port)
+static void rmnet_unregister_bridge(struct rmnet_port *port)
{
- struct rmnet_port *bridge_port;
- struct net_device *bridge_dev;
+ struct net_device *bridge_dev, *real_dev, *rmnet_dev;
+ struct rmnet_port *real_port;
if (port->rmnet_mode != RMNET_EPMODE_BRIDGE)
return;
- /* bridge slave handling */
+ rmnet_dev = port->rmnet_dev;
if (!port->nr_rmnet_devs) {
- bridge_dev = port->bridge_ep;
+ /* bridge device */
+ real_dev = port->bridge_ep;
+ bridge_dev = port->dev;
- bridge_port = rmnet_get_port_rtnl(bridge_dev);
- bridge_port->bridge_ep = NULL;
- bridge_port->rmnet_mode = RMNET_EPMODE_VND;
+ real_port = rmnet_get_port_rtnl(real_dev);
+ real_port->bridge_ep = NULL;
+ real_port->rmnet_mode = RMNET_EPMODE_VND;
} else {
+ /* real device */
bridge_dev = port->bridge_ep;
- bridge_port = rmnet_get_port_rtnl(bridge_dev);
- rmnet_unregister_real_device(bridge_dev, bridge_port);
+ port->bridge_ep = NULL;
+ port->rmnet_mode = RMNET_EPMODE_VND;
}
+
+ netdev_upper_dev_unlink(bridge_dev, rmnet_dev);
+ rmnet_unregister_real_device(bridge_dev);
}
static int rmnet_newlink(struct net *src_net, struct net_device *dev,
int err = 0;
u16 mux_id;
+ if (!tb[IFLA_LINK]) {
+ NL_SET_ERR_MSG_MOD(extack, "link not specified");
+ return -EINVAL;
+ }
+
real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
if (!real_dev || !dev)
return -ENODEV;
if (err)
goto err1;
+ err = netdev_upper_dev_link(real_dev, dev, extack);
+ if (err < 0)
+ goto err2;
+
port->rmnet_mode = mode;
+ port->rmnet_dev = dev;
hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]);
return 0;
+err2:
+ unregister_netdevice(dev);
+ rmnet_vnd_dellink(mux_id, port, ep);
err1:
- rmnet_unregister_real_device(real_dev, port);
+ rmnet_unregister_real_device(real_dev);
err0:
kfree(ep);
return err;
static void rmnet_dellink(struct net_device *dev, struct list_head *head)
{
struct rmnet_priv *priv = netdev_priv(dev);
- struct net_device *real_dev;
+ struct net_device *real_dev, *bridge_dev;
+ struct rmnet_port *real_port, *bridge_port;
struct rmnet_endpoint *ep;
- struct rmnet_port *port;
- u8 mux_id;
+ u8 mux_id = priv->mux_id;
real_dev = priv->real_dev;
- if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
+ if (!rmnet_is_real_dev_registered(real_dev))
return;
- port = rmnet_get_port_rtnl(real_dev);
-
- mux_id = rmnet_vnd_get_mux(dev);
+ real_port = rmnet_get_port_rtnl(real_dev);
+ bridge_dev = real_port->bridge_ep;
+ if (bridge_dev) {
+ bridge_port = rmnet_get_port_rtnl(bridge_dev);
+ rmnet_unregister_bridge(bridge_port);
+ }
- ep = rmnet_get_endpoint(port, mux_id);
+ ep = rmnet_get_endpoint(real_port, mux_id);
if (ep) {
hlist_del_init_rcu(&ep->hlnode);
- rmnet_unregister_bridge(dev, port);
- rmnet_vnd_dellink(mux_id, port, ep);
+ rmnet_vnd_dellink(mux_id, real_port, ep);
kfree(ep);
}
- rmnet_unregister_real_device(real_dev, port);
+ netdev_upper_dev_unlink(real_dev, dev);
+ rmnet_unregister_real_device(real_dev);
unregister_netdevice_queue(dev, head);
}
-static void rmnet_force_unassociate_device(struct net_device *dev)
+static void rmnet_force_unassociate_device(struct net_device *real_dev)
{
- struct net_device *real_dev = dev;
struct hlist_node *tmp_ep;
struct rmnet_endpoint *ep;
struct rmnet_port *port;
unsigned long bkt_ep;
LIST_HEAD(list);
- if (!rmnet_is_real_dev_registered(real_dev))
- return;
-
- ASSERT_RTNL();
-
- port = rmnet_get_port_rtnl(dev);
-
- rcu_read_lock();
- rmnet_unregister_bridge(dev, port);
-
- hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) {
- unregister_netdevice_queue(ep->egress_dev, &list);
- rmnet_vnd_dellink(ep->mux_id, port, ep);
+ port = rmnet_get_port_rtnl(real_dev);
- hlist_del_init_rcu(&ep->hlnode);
- kfree(ep);
+ if (port->nr_rmnet_devs) {
+ /* real device */
+ rmnet_unregister_bridge(port);
+ hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) {
+ unregister_netdevice_queue(ep->egress_dev, &list);
+ netdev_upper_dev_unlink(real_dev, ep->egress_dev);
+ rmnet_vnd_dellink(ep->mux_id, port, ep);
+ hlist_del_init_rcu(&ep->hlnode);
+ kfree(ep);
+ }
+ rmnet_unregister_real_device(real_dev);
+ unregister_netdevice_many(&list);
+ } else {
+ rmnet_unregister_bridge(port);
}
-
- rcu_read_unlock();
- unregister_netdevice_many(&list);
-
- rmnet_unregister_real_device(real_dev, port);
}
static int rmnet_config_notify_cb(struct notifier_block *nb,
unsigned long event, void *data)
{
- struct net_device *dev = netdev_notifier_info_to_dev(data);
+ struct net_device *real_dev = netdev_notifier_info_to_dev(data);
- if (!dev)
+ if (!rmnet_is_real_dev_registered(real_dev))
return NOTIFY_DONE;
switch (event) {
case NETDEV_UNREGISTER:
- netdev_dbg(dev, "Kernel unregister\n");
- rmnet_force_unassociate_device(dev);
+ netdev_dbg(real_dev, "Kernel unregister\n");
+ rmnet_force_unassociate_device(real_dev);
break;
default:
if (!dev)
return -ENODEV;
- real_dev = __dev_get_by_index(dev_net(dev),
- nla_get_u32(tb[IFLA_LINK]));
-
- if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
+ real_dev = priv->real_dev;
+ if (!rmnet_is_real_dev_registered(real_dev))
return -ENODEV;
port = rmnet_get_port_rtnl(real_dev);
if (data[IFLA_RMNET_MUX_ID]) {
mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]);
+ if (rmnet_get_endpoint(port, mux_id)) {
+ NL_SET_ERR_MSG_MOD(extack, "MUX ID already exists");
+ return -EINVAL;
+ }
ep = rmnet_get_endpoint(port, priv->mux_id);
if (!ep)
return -ENODEV;
.fill_info = rmnet_fill_info,
};
-/* Needs either rcu_read_lock() or rtnl lock */
-struct rmnet_port *rmnet_get_port(struct net_device *real_dev)
+struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev)
{
if (rmnet_is_real_dev_registered(real_dev))
- return rcu_dereference_rtnl(real_dev->rx_handler_data);
+ return rcu_dereference_bh(real_dev->rx_handler_data);
else
return NULL;
}
struct rmnet_port *port, *slave_port;
int err;
- port = rmnet_get_port(real_dev);
+ port = rmnet_get_port_rtnl(real_dev);
/* If there is more than one rmnet dev attached, its probably being
* used for muxing. Skip the briding in that case
if (port->nr_rmnet_devs > 1)
return -EINVAL;
+ if (port->rmnet_mode != RMNET_EPMODE_VND)
+ return -EINVAL;
+
if (rmnet_is_real_dev_registered(slave_dev))
return -EBUSY;
if (err)
return -EBUSY;
- slave_port = rmnet_get_port(slave_dev);
+ err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL,
+ extack);
+ if (err) {
+ rmnet_unregister_real_device(slave_dev);
+ return err;
+ }
+
+ slave_port = rmnet_get_port_rtnl(slave_dev);
slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE;
slave_port->bridge_ep = real_dev;
+ slave_port->rmnet_dev = rmnet_dev;
port->rmnet_mode = RMNET_EPMODE_BRIDGE;
port->bridge_ep = slave_dev;
int rmnet_del_bridge(struct net_device *rmnet_dev,
struct net_device *slave_dev)
{
- struct rmnet_priv *priv = netdev_priv(rmnet_dev);
- struct net_device *real_dev = priv->real_dev;
- struct rmnet_port *port, *slave_port;
+ struct rmnet_port *port = rmnet_get_port_rtnl(slave_dev);
- port = rmnet_get_port(real_dev);
- port->rmnet_mode = RMNET_EPMODE_VND;
- port->bridge_ep = NULL;
-
- slave_port = rmnet_get_port(slave_dev);
- rmnet_unregister_real_device(slave_dev, slave_port);
+ rmnet_unregister_bridge(port);
netdev_dbg(slave_dev, "removed from rmnet as slave\n");
return 0;
static void __exit rmnet_exit(void)
{
- unregister_netdevice_notifier(&rmnet_dev_notifier);
rtnl_link_unregister(&rmnet_link_ops);
+ unregister_netdevice_notifier(&rmnet_dev_notifier);
}
module_init(rmnet_init)
u8 rmnet_mode;
struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP];
struct net_device *bridge_ep;
+ struct net_device *rmnet_dev;
};
extern struct rtnl_link_ops rmnet_link_ops;
struct rmnet_priv_stats stats;
};
-struct rmnet_port *rmnet_get_port(struct net_device *real_dev);
+struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev);
struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id);
int rmnet_add_bridge(struct net_device *rmnet_dev,
struct net_device *slave_dev,
static void
rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev)
{
+ if (skb_mac_header_was_set(skb))
+ skb_push(skb, skb->mac_len);
+
if (bridge_dev) {
skb->dev = bridge_dev;
dev_queue_xmit(skb);
return RX_HANDLER_PASS;
dev = skb->dev;
- port = rmnet_get_port(dev);
+ port = rmnet_get_port_rcu(dev);
switch (port->rmnet_mode) {
case RMNET_EPMODE_VND:
skb->dev = priv->real_dev;
mux_id = priv->mux_id;
- port = rmnet_get_port(skb->dev);
+ port = rmnet_get_port_rcu(skb->dev);
if (!port)
goto drop;
return 0;
}
-u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev)
-{
- struct rmnet_priv *priv;
-
- priv = netdev_priv(rmnet_dev);
- return priv->mux_id;
-}
-
int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable)
{
netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable);
struct rmnet_endpoint *ep);
void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev);
void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev);
-u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev);
void rmnet_vnd_setup(struct net_device *dev);
#endif /* _RMNET_VND_H_ */
u32 nic_major, u32 nic_minor,
s32 correction)
{
+ u32 sync_timestamp;
ktime_t kt = { 0 };
+ s16 delta;
if (!(nic_major & 0x80000000)) {
WARN_ON_ONCE(nic_major >> 16);
- /* Use the top bits from the latest sync event. */
- nic_major &= 0xffff;
- nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000);
+
+ /* Medford provides 48 bits of timestamp, so we must get the top
+ * 16 bits from the timesync event state.
+ *
+ * We only have the lower 16 bits of the time now, but we do
+ * have a full resolution timestamp at some point in past. As
+ * long as the difference between the (real) now and the sync
+ * is less than 2^15, then we can reconstruct the difference
+ * between those two numbers using only the lower 16 bits of
+ * each.
+ *
+ * Put another way
+ *
+ * a - b = ((a mod k) - b) mod k
+ *
+ * when -k/2 < (a-b) < k/2. In our case k is 2^16. We know
+ * (a mod k) and b, so can calculate the delta, a - b.
+ *
+ */
+ sync_timestamp = last_sync_timestamp_major(efx);
+
+ /* Because delta is s16 this does an implicit mask down to
+ * 16 bits which is what we need, assuming
+ * MEDFORD_TX_SECS_EVENT_BITS is 16. delta is signed so that
+ * we can deal with the (unlikely) case of sync timestamps
+ * arriving from the future.
+ */
+ delta = nic_major - sync_timestamp;
+
+ /* Recover the fully specified time now, by applying the offset
+ * to the (fully specified) sync time.
+ */
+ nic_major = sync_timestamp + delta;
kt = ptp->nic_to_kernel_time(nic_major, nic_minor,
correction);
{
struct stmmac_priv *priv = netdev_priv(dev);
+ rtnl_lock();
+
/* Create per netdev entries */
priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev,
&stmmac_dma_cap_fops);
- register_netdevice_notifier(&stmmac_notifier);
+ rtnl_unlock();
}
static void stmmac_exit_fs(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
- unregister_netdevice_notifier(&stmmac_notifier);
debugfs_remove_recursive(priv->dbgfs_dir);
}
#endif /* CONFIG_DEBUG_FS */
netdev_info(priv->dev, "%s: removing driver", __func__);
-#ifdef CONFIG_DEBUG_FS
- stmmac_exit_fs(ndev);
-#endif
stmmac_stop_all_dma(priv);
stmmac_mac_set(priv, priv->ioaddr, false);
netif_carrier_off(ndev);
unregister_netdev(ndev);
+#ifdef CONFIG_DEBUG_FS
+ stmmac_exit_fs(ndev);
+#endif
phylink_destroy(priv->phylink);
if (priv->plat->stmmac_rst)
reset_control_assert(priv->plat->stmmac_rst);
/* Create debugfs main directory if it doesn't exist yet */
if (!stmmac_fs_dir)
stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+ register_netdevice_notifier(&stmmac_notifier);
#endif
return 0;
static void __exit stmmac_exit(void)
{
#ifdef CONFIG_DEBUG_FS
+ unregister_netdevice_notifier(&stmmac_notifier);
debugfs_remove_recursive(stmmac_fs_dir);
#endif
}
int tx_bd_next;
int tx_bd_tail;
int rx_bd_ci;
+ int rx_bd_tail;
/* DMA channel control setup */
u32 tx_chnl_ctrl;
u32 rx_chnl_ctrl;
+ u8 coalesce_count_rx;
+
+ struct delayed_work restart_work;
};
/* Wrappers for temac_ior()/temac_iow() function pointers above */
#include <linux/ip.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/workqueue.h>
#include <linux/dma-mapping.h>
#include <linux/processor.h>
#include <linux/platform_data/xilinx-ll-temac.h>
skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
XTE_MAX_JUMBO_FRAME_SIZE,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(ndev->dev.parent, skb_dma_addr))
+ goto out;
lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr);
lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
lp->tx_bd_next = 0;
lp->tx_bd_tail = 0;
lp->rx_bd_ci = 0;
+ lp->rx_bd_tail = RX_BD_NUM - 1;
/* Enable RX DMA transfers */
wmb();
lp->dma_out(lp, RX_CURDESC_PTR, lp->rx_bd_p);
lp->dma_out(lp, RX_TAILDESC_PTR,
- lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+ lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * lp->rx_bd_tail));
/* Prepare for TX DMA transfer */
lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
stat = be32_to_cpu(cur_p->app0);
}
+ /* Matches barrier in temac_start_xmit */
+ smp_mb();
+
netif_wake_queue(ndev);
}
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
if (temac_check_tx_bd_space(lp, num_frag + 1)) {
- if (!netif_queue_stopped(ndev))
- netif_stop_queue(ndev);
- return NETDEV_TX_BUSY;
+ if (netif_queue_stopped(ndev))
+ return NETDEV_TX_BUSY;
+
+ netif_stop_queue(ndev);
+
+ /* Matches barrier in temac_start_xmit_done */
+ smp_mb();
+
+ /* Space might have just been freed - check again */
+ if (temac_check_tx_bd_space(lp, num_frag))
+ return NETDEV_TX_BUSY;
+
+ netif_wake_queue(ndev);
}
cur_p->app0 = 0;
skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
skb_headlen(skb), DMA_TO_DEVICE);
cur_p->len = cpu_to_be32(skb_headlen(skb));
+ if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, skb_dma_addr))) {
+ dev_kfree_skb_any(skb);
+ ndev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
+ }
cur_p->phys = cpu_to_be32(skb_dma_addr);
ptr_to_txbd((void *)skb, cur_p);
for (ii = 0; ii < num_frag; ii++) {
- lp->tx_bd_tail++;
- if (lp->tx_bd_tail >= TX_BD_NUM)
+ if (++lp->tx_bd_tail >= TX_BD_NUM)
lp->tx_bd_tail = 0;
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
skb_frag_address(frag),
skb_frag_size(frag),
DMA_TO_DEVICE);
+ if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) {
+ if (--lp->tx_bd_tail < 0)
+ lp->tx_bd_tail = TX_BD_NUM - 1;
+ cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
+ while (--ii >= 0) {
+ --frag;
+ dma_unmap_single(ndev->dev.parent,
+ be32_to_cpu(cur_p->phys),
+ skb_frag_size(frag),
+ DMA_TO_DEVICE);
+ if (--lp->tx_bd_tail < 0)
+ lp->tx_bd_tail = TX_BD_NUM - 1;
+ cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
+ }
+ dma_unmap_single(ndev->dev.parent,
+ be32_to_cpu(cur_p->phys),
+ skb_headlen(skb), DMA_TO_DEVICE);
+ dev_kfree_skb_any(skb);
+ ndev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
+ }
cur_p->phys = cpu_to_be32(skb_dma_addr);
cur_p->len = cpu_to_be32(skb_frag_size(frag));
cur_p->app0 = 0;
return NETDEV_TX_OK;
}
+static int ll_temac_recv_buffers_available(struct temac_local *lp)
+{
+ int available;
+
+ if (!lp->rx_skb[lp->rx_bd_ci])
+ return 0;
+ available = 1 + lp->rx_bd_tail - lp->rx_bd_ci;
+ if (available <= 0)
+ available += RX_BD_NUM;
+ return available;
+}
static void ll_temac_recv(struct net_device *ndev)
{
struct temac_local *lp = netdev_priv(ndev);
- struct sk_buff *skb, *new_skb;
- unsigned int bdstat;
- struct cdmac_bd *cur_p;
- dma_addr_t tail_p, skb_dma_addr;
- int length;
unsigned long flags;
+ int rx_bd;
+ bool update_tail = false;
spin_lock_irqsave(&lp->rx_lock, flags);
- tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
- cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
-
- bdstat = be32_to_cpu(cur_p->app0);
- while ((bdstat & STS_CTRL_APP0_CMPLT)) {
+ /* Process all received buffers, passing them on network
+ * stack. After this, the buffer descriptors will be in an
+ * un-allocated stage, where no skb is allocated for it, and
+ * they are therefore not available for TEMAC/DMA.
+ */
+ do {
+ struct cdmac_bd *bd = &lp->rx_bd_v[lp->rx_bd_ci];
+ struct sk_buff *skb = lp->rx_skb[lp->rx_bd_ci];
+ unsigned int bdstat = be32_to_cpu(bd->app0);
+ int length;
+
+ /* While this should not normally happen, we can end
+ * here when GFP_ATOMIC allocations fail, and we
+ * therefore have un-allocated buffers.
+ */
+ if (!skb)
+ break;
- skb = lp->rx_skb[lp->rx_bd_ci];
- length = be32_to_cpu(cur_p->app4) & 0x3FFF;
+ /* Loop over all completed buffer descriptors */
+ if (!(bdstat & STS_CTRL_APP0_CMPLT))
+ break;
- dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
+ dma_unmap_single(ndev->dev.parent, be32_to_cpu(bd->phys),
XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE);
+ /* The buffer is not valid for DMA anymore */
+ bd->phys = 0;
+ bd->len = 0;
+ length = be32_to_cpu(bd->app4) & 0x3FFF;
skb_put(skb, length);
skb->protocol = eth_type_trans(skb, ndev);
skb_checksum_none_assert(skb);
* (back) for proper IP checksum byte order
* (be16).
*/
- skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF);
+ skb->csum = htons(be32_to_cpu(bd->app3) & 0xFFFF);
skb->ip_summed = CHECKSUM_COMPLETE;
}
if (!skb_defer_rx_timestamp(skb))
netif_rx(skb);
+ /* The skb buffer is now owned by network stack above */
+ lp->rx_skb[lp->rx_bd_ci] = NULL;
ndev->stats.rx_packets++;
ndev->stats.rx_bytes += length;
- new_skb = netdev_alloc_skb_ip_align(ndev,
- XTE_MAX_JUMBO_FRAME_SIZE);
- if (!new_skb) {
- spin_unlock_irqrestore(&lp->rx_lock, flags);
- return;
+ rx_bd = lp->rx_bd_ci;
+ if (++lp->rx_bd_ci >= RX_BD_NUM)
+ lp->rx_bd_ci = 0;
+ } while (rx_bd != lp->rx_bd_tail);
+
+ /* DMA operations will halt when the last buffer descriptor is
+ * processed (ie. the one pointed to by RX_TAILDESC_PTR).
+ * When that happens, no more interrupt events will be
+ * generated. No IRQ_COAL or IRQ_DLY, and not even an
+ * IRQ_ERR. To avoid stalling, we schedule a delayed work
+ * when there is a potential risk of that happening. The work
+ * will call this function, and thus re-schedule itself until
+ * enough buffers are available again.
+ */
+ if (ll_temac_recv_buffers_available(lp) < lp->coalesce_count_rx)
+ schedule_delayed_work(&lp->restart_work, HZ / 1000);
+
+ /* Allocate new buffers for those buffer descriptors that were
+ * passed to network stack. Note that GFP_ATOMIC allocations
+ * can fail (e.g. when a larger burst of GFP_ATOMIC
+ * allocations occurs), so while we try to allocate all
+ * buffers in the same interrupt where they were processed, we
+ * continue with what we could get in case of allocation
+ * failure. Allocation of remaining buffers will be retried
+ * in following calls.
+ */
+ while (1) {
+ struct sk_buff *skb;
+ struct cdmac_bd *bd;
+ dma_addr_t skb_dma_addr;
+
+ rx_bd = lp->rx_bd_tail + 1;
+ if (rx_bd >= RX_BD_NUM)
+ rx_bd = 0;
+ bd = &lp->rx_bd_v[rx_bd];
+
+ if (bd->phys)
+ break; /* All skb's allocated */
+
+ skb = netdev_alloc_skb_ip_align(ndev, XTE_MAX_JUMBO_FRAME_SIZE);
+ if (!skb) {
+ dev_warn(&ndev->dev, "skb alloc failed\n");
+ break;
}
- cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
- skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data,
+ skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
XTE_MAX_JUMBO_FRAME_SIZE,
DMA_FROM_DEVICE);
- cur_p->phys = cpu_to_be32(skb_dma_addr);
- cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
- lp->rx_skb[lp->rx_bd_ci] = new_skb;
+ if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent,
+ skb_dma_addr))) {
+ dev_kfree_skb_any(skb);
+ break;
+ }
- lp->rx_bd_ci++;
- if (lp->rx_bd_ci >= RX_BD_NUM)
- lp->rx_bd_ci = 0;
+ bd->phys = cpu_to_be32(skb_dma_addr);
+ bd->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
+ bd->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
+ lp->rx_skb[rx_bd] = skb;
- cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
- bdstat = be32_to_cpu(cur_p->app0);
+ lp->rx_bd_tail = rx_bd;
+ update_tail = true;
+ }
+
+ /* Move tail pointer when buffers have been allocated */
+ if (update_tail) {
+ lp->dma_out(lp, RX_TAILDESC_PTR,
+ lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_tail);
}
- lp->dma_out(lp, RX_TAILDESC_PTR, tail_p);
spin_unlock_irqrestore(&lp->rx_lock, flags);
}
+/* Function scheduled to ensure a restart in case of DMA halt
+ * condition caused by running out of buffer descriptors.
+ */
+static void ll_temac_restart_work_func(struct work_struct *work)
+{
+ struct temac_local *lp = container_of(work, struct temac_local,
+ restart_work.work);
+ struct net_device *ndev = lp->ndev;
+
+ ll_temac_recv(ndev);
+}
+
static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev)
{
struct net_device *ndev = _ndev;
dev_dbg(&ndev->dev, "temac_close()\n");
+ cancel_delayed_work_sync(&lp->restart_work);
+
free_irq(lp->tx_irq, ndev);
free_irq(lp->rx_irq, ndev);
lp->dev = &pdev->dev;
lp->options = XTE_OPTION_DEFAULTS;
spin_lock_init(&lp->rx_lock);
+ INIT_DELAYED_WORK(&lp->restart_work, ll_temac_restart_work_func);
/* Setup mutex for synchronization of indirect register access */
if (pdata) {
*/
lp->tx_chnl_ctrl = 0x10220000;
lp->rx_chnl_ctrl = 0xff070000;
+ lp->coalesce_count_rx = 0x07;
/* Finished with the DMA node; drop the reference */
of_node_put(dma_np);
(pdata->tx_irq_count << 16);
else
lp->tx_chnl_ctrl = 0x10220000;
- if (pdata->rx_irq_timeout || pdata->rx_irq_count)
+ if (pdata->rx_irq_timeout || pdata->rx_irq_count) {
lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) |
(pdata->rx_irq_count << 16);
- else
+ lp->coalesce_count_rx = pdata->rx_irq_count;
+ } else {
lp->rx_chnl_ctrl = 0xff070000;
+ lp->coalesce_count_rx = 0x07;
+ }
}
/* Error handle returned DMA RX and TX interrupts */
init_waitqueue_head(&net_device->wait_drain);
net_device->destroy = false;
- net_device->tx_disable = false;
+ net_device->tx_disable = true;
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
}
/* In any case device is now ready */
+ nvdev->tx_disable = false;
netif_device_attach(ndev);
/* Note: enable and attach happen when sub-channels setup */
else
net->max_mtu = ETH_DATA_LEN;
+ nvdev->tx_disable = false;
+
ret = register_netdevice(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
struct device_node *np = phydev->mdio.dev.of_node;
int ret;
- /* Aneg firsly. */
+ /* Aneg firstly. */
ret = genphy_config_aneg(phydev);
/* Then we can set up the delay. */
{
int ret;
- /* Aneg firsly. */
+ /* Aneg firstly. */
if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX)
ret = genphy_c37_config_aneg(phydev);
else
}
}
+ if (!(status & MII_M1011_PHY_STATUS_RESOLVED))
+ return 0;
+
if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
phydev->duplex = DUPLEX_FULL;
else
linkmode_zero(phydev->lp_advertising);
phydev->pause = 0;
phydev->asym_pause = 0;
+ phydev->speed = SPEED_UNKNOWN;
+ phydev->duplex = DUPLEX_UNKNOWN;
if (phydev->autoneg == AUTONEG_ENABLE)
err = marvell_read_status_page_an(phydev, fiber, status);
return 0;
}
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+ /* restore the mii clock configuration */
+ iproc_mdio_config_clk(priv->base);
+
+ return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+ .resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
static const struct of_device_id iproc_mdio_of_match[] = {
{ .compatible = "brcm,iproc-mdio", },
{ /* sentinel */ },
.driver = {
.name = "iproc-mdio",
.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+ .pm = &iproc_mdio_pm_ops,
+#endif
},
.probe = iproc_mdio_probe,
.remove = iproc_mdio_remove,
BIT(VSC8531_FORCE_LED_OFF) | \
BIT(VSC8531_FORCE_LED_ON))
-#define MSCC_VSC8584_REVB_INT8051_FW "mscc_vsc8584_revb_int8051_fb48.bin"
+#define MSCC_VSC8584_REVB_INT8051_FW "microchip/mscc_vsc8584_revb_int8051_fb48.bin"
#define MSCC_VSC8584_REVB_INT8051_FW_START_ADDR 0xe800
#define MSCC_VSC8584_REVB_INT8051_FW_CRC 0xfb48
-#define MSCC_VSC8574_REVB_INT8051_FW "mscc_vsc8574_revb_int8051_29e8.bin"
+#define MSCC_VSC8574_REVB_INT8051_FW "microchip/mscc_vsc8574_revb_int8051_29e8.bin"
#define MSCC_VSC8574_REVB_INT8051_FW_START_ADDR 0x4000
#define MSCC_VSC8574_REVB_INT8051_FW_CRC 0x29e8
*/
int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart)
{
- int ret = 0;
+ int ret;
if (!restart) {
/* Configure and restart aneg if it wasn't set before */
}
if (restart)
- ret = genphy_c45_restart_aneg(phydev);
+ return genphy_c45_restart_aneg(phydev);
- return ret;
+ return 0;
}
EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg);
* MDIO bus driver and clock gated at this point.
*/
if (!netdev)
- return !phydev->suspended;
+ goto out;
if (netdev->wol_enabled)
return false;
if (device_may_wakeup(&netdev->dev))
return false;
- return true;
+out:
+ return !phydev->suspended;
}
static int mdio_bus_phy_suspend(struct device *dev)
*/
int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart)
{
- int ret = 0;
+ int ret;
if (!restart) {
/* Advertisement hasn't changed, but maybe aneg was never on to
}
if (restart)
- ret = genphy_restart_aneg(phydev);
+ return genphy_restart_aneg(phydev);
- return ret;
+ return 0;
}
EXPORT_SYMBOL(genphy_check_and_restart_aneg);
tty->disc_data = NULL;
clear_bit(SLF_INUSE, &sl->flags);
sl_free_netdev(sl->dev);
+ /* do not call free_netdev before rtnl_unlock */
+ rtnl_unlock();
free_netdev(sl->dev);
+ return err;
err_exit:
rtnl_unlock();
netdev_dbg(net, "mode: raw IP\n");
} else if (!net->header_ops) { /* don't bother if already set */
ether_setup(net);
+ /* Restoring min/max mtu values set originally by usbnet */
+ net->min_mtu = 0;
+ net->max_mtu = ETH_MAX_MTU;
clear_bit(EVENT_NO_IP_ALIGN, &dev->flags);
netdev_dbg(net, "mode: Ethernet\n");
}
enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
NETIF_F_SG | NETIF_F_GSO |
NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
+ const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
+ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
dev->netdev_ops = &netdev_ops;
dev->hard_header_len = 0;
dev->features |= WG_NETDEV_FEATURES;
dev->hw_features |= WG_NETDEV_FEATURES;
dev->hw_enc_features |= WG_NETDEV_FEATURES;
- dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
- sizeof(struct udphdr) -
- max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+ dev->mtu = ETH_DATA_LEN - overhead;
+ dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
SET_NETDEV_DEVTYPE(dev, &device_type);
under_load = skb_queue_len(&wg->incoming_handshakes) >=
MAX_QUEUED_INCOMING_HANDSHAKES / 8;
- if (under_load)
+ if (under_load) {
last_under_load = ktime_get_coarse_boottime_ns();
- else if (last_under_load)
+ } else if (last_under_load) {
under_load = !wg_birthdate_has_expired(last_under_load, 1);
+ if (!under_load)
+ last_under_load = 0;
+ }
mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
under_load);
if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
static unsigned int calculate_skb_padding(struct sk_buff *skb)
{
+ unsigned int padded_size, last_unit = skb->len;
+
+ if (unlikely(!PACKET_CB(skb)->mtu))
+ return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit;
+
/* We do this modulo business with the MTU, just in case the networking
* layer gives us a packet that's bigger than the MTU. In that case, we
* wouldn't want the final subtraction to overflow in the case of the
- * padded_size being clamped.
+ * padded_size being clamped. Fortunately, that's very rarely the case,
+ * so we optimize for that not happening.
*/
- unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
- unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
+ if (unlikely(last_unit > PACKET_CB(skb)->mtu))
+ last_unit %= PACKET_CB(skb)->mtu;
- if (padded_size > PACKET_CB(skb)->mtu)
- padded_size = PACKET_CB(skb)->mtu;
+ padded_size = min(PACKET_CB(skb)->mtu,
+ ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE));
return padded_size - last_unit;
}
wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
mutex_unlock(&wg->socket_update_lock);
synchronize_rcu();
- synchronize_net();
sock_free(old4);
sock_free(old6);
}
out:
gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+ usleep_range(10000, 15000);
}
static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
struct nfc_target *target)
{
- pr_debug("supported protocol %d\b", target->supported_protocols);
+ pr_debug("supported protocol %d\n", target->supported_protocols);
if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK |
NFC_PROTO_ISO14443_B_MASK)) {
return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen, u32 *result)
{
+ union nvme_result res = { 0 };
struct nvme_command c;
- union nvme_result res;
int ret;
memset(&c, 0, sizeof(c));
}
INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+ kfree(ctrl->ana_log_buf);
ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
if (!ctrl->ana_log_buf) {
error = -ENOMEM;
spin_lock(&nvmeq->cq_poll_lock);
found = nvme_process_cq(nvmeq, &start, &end, -1);
+ nvme_complete_cqes(nvmeq, start, end);
spin_unlock(&nvmeq->cq_poll_lock);
- nvme_complete_cqes(nvmeq, start, end);
return found;
}
(dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") ||
dmi_match(DMI_BOARD_NAME, "PRIME Z370-A")))
return NVME_QUIRK_NO_APST;
+ } else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 ||
+ pdev->device == 0xa808 || pdev->device == 0xa809)) ||
+ (pdev->vendor == 0x1e0f && pdev->device == 0x0001)) {
+ /*
+ * Forcing to use host managed nvme power settings for
+ * lowest idle power with quick resume latency on
+ * Samsung and Toshiba SSDs based on suspend behavior
+ * on Coffee Lake board for LENOVO C640
+ */
+ if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) &&
+ dmi_match(DMI_BOARD_NAME, "LNVNB161216"))
+ return NVME_QUIRK_SIMPLE_SUSPEND;
}
return 0;
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
- { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
+ .driver_data = NVME_QUIRK_SINGLE_VECTOR },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
* outbound memory @ 3GB). So instead it will start at the 1x
* multiple of its size
*/
- if (!*rc_bar2_size || *rc_bar2_offset % *rc_bar2_size ||
+ if (!*rc_bar2_size || (*rc_bar2_offset & (*rc_bar2_size - 1)) ||
(*rc_bar2_offset < SZ_4G && *rc_bar2_offset > SZ_2G)) {
dev_err(dev, "Invalid rc_bar2_offset/size: size 0x%llx, off 0x%llx\n",
*rc_bar2_size, *rc_bar2_offset);
#include <linux/platform_data/wilco-ec.h>
#include <linux/string.h>
-#include <linux/unaligned/le_memmove.h>
+#include <asm/unaligned.h>
/* Operation code; what the EC should do with the property */
enum ec_property_op {
cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset)
{
struct ccwdev_iter *iter;
+ loff_t p = *offset;
- if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
+ (*offset)++;
+ if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
return NULL;
iter = it;
if (iter->devno == __MAX_SUBCHANNEL) {
return NULL;
} else
iter->devno++;
- (*offset)++;
return iter;
}
struct channel_path *chp;
struct device *device;
- device = container_of(kobj, struct device, kobj);
+ device = kobj_to_dev(kobj);
chp = to_channelpath(device);
if (chp->cmg == -1)
return 0;
struct device *device;
unsigned int size;
- device = container_of(kobj, struct device, kobj);
+ device = kobj_to_dev(kobj);
chp = to_channelpath(device);
css = to_css(chp->dev.parent);
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/io.h>
#include <asm/qdio.h>
#include "cio.h"
/* fill in sl */
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++)
- q->sl->element[j].sbal = (unsigned long)q->sbal[j];
+ q->sl->element[j].sbal = virt_to_phys(q->sbal[j]);
}
static void setup_queues(struct qdio_irq *irq_ptr,
/* empty pin tag */
*p++ = 0x04;
*p++ = 0;
- /* encrytped key value tag and bytes */
+ /* encrypted key value tag and bytes */
p += asn1tag_write(p, 0x04, enckey, enckeysize);
/* reply cprb and payload */
/* Step 1: generate AES 256 bit random kek key */
rc = ep11_genaeskey(card, domain, 256,
- 0x00006c00, /* EN/DECRYTP, WRAP/UNWRAP */
+ 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */
kek, &keklen);
if (rc) {
DEBUG_ERR(
qeth_tx_complete_buf(buf, error, budget);
for (i = 0; i < queue->max_elements; ++i) {
- if (buf->buffer->element[i].addr && buf->is_header[i])
- kmem_cache_free(qeth_core_header_cache,
- buf->buffer->element[i].addr);
+ void *data = phys_to_virt(buf->buffer->element[i].addr);
+
+ if (data && buf->is_header[i])
+ kmem_cache_free(qeth_core_header_cache, data);
buf->is_header[i] = 0;
}
buf->pool_entry = pool_entry;
for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) {
buf->buffer->element[i].length = PAGE_SIZE;
- buf->buffer->element[i].addr = pool_entry->elements[i];
+ buf->buffer->element[i].addr =
+ virt_to_phys(pool_entry->elements[i]);
if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1)
buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY;
else
while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) &&
buffer->element[e].addr) {
- unsigned long phys_aob_addr;
+ unsigned long phys_aob_addr = buffer->element[e].addr;
- phys_aob_addr = (unsigned long) buffer->element[e].addr;
qeth_qdio_handle_aob(card, phys_aob_addr);
++e;
}
elem_length = min_t(unsigned int, length,
PAGE_SIZE - offset_in_page(data));
- buffer->element[element].addr = data;
+ buffer->element[element].addr = virt_to_phys(data);
buffer->element[element].length = elem_length;
length -= elem_length;
if (is_first_elem) {
elem_length = min_t(unsigned int, length,
PAGE_SIZE - offset_in_page(data));
- buffer->element[element].addr = data;
+ buffer->element[element].addr = virt_to_phys(data);
buffer->element[element].length = elem_length;
buffer->element[element].eflags =
SBAL_EFLAGS_MIDDLE_FRAG;
int element = buf->next_element_to_fill;
is_first_elem = false;
- buffer->element[element].addr = hdr;
+ buffer->element[element].addr = virt_to_phys(hdr);
buffer->element[element].length = hd_len;
buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG;
/* remember to free cache-allocated qeth_hdr: */
if (card->options.cq == QETH_CQ_ENABLED) {
int offset = QDIO_MAX_BUFFERS_PER_Q *
(card->qdio.no_in_queues - 1);
- for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) {
- in_sbal_ptrs[offset + i] = (struct qdio_buffer *)
- virt_to_phys(card->qdio.c_q->bufs[i].buffer);
- }
+
+ for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++)
+ in_sbal_ptrs[offset + i] =
+ card->qdio.c_q->bufs[i].buffer;
queue_start_poll[card->qdio.no_in_queues - 1] = NULL;
}
rc = -ENOMEM;
goto out_free_qib_param;
}
- for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) {
- in_sbal_ptrs[i] = (struct qdio_buffer *)
- virt_to_phys(card->qdio.in_q->bufs[i].buffer);
- }
+
+ for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++)
+ in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer;
queue_start_poll = kcalloc(card->qdio.no_in_queues, sizeof(void *),
GFP_KERNEL);
rc = -ENOMEM;
goto out_free_queue_start_poll;
}
+
for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i)
- for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j, ++k) {
- out_sbal_ptrs[k] = (struct qdio_buffer *)virt_to_phys(
- card->qdio.out_qs[i]->bufs[j]->buffer);
- }
+ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++)
+ out_sbal_ptrs[k] =
+ card->qdio.out_qs[i]->bufs[j]->buffer;
memset(&init_data, 0, sizeof(struct qdio_initialize));
init_data.cdev = CARD_DDEV(card);
offset = 0;
}
- hdr = element->addr + offset;
+ hdr = phys_to_virt(element->addr) + offset;
offset += sizeof(*hdr);
skb = NULL;
}
use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) ||
- ((skb_len >= card->options.rx_sg_cb) &&
+ (skb_len > card->options.rx_sg_cb &&
!atomic_read(&card->force_alloc_skb) &&
!IS_OSN(card));
walk_packet:
while (skb_len) {
int data_len = min(skb_len, (int)(element->length - offset));
- char *data = element->addr + offset;
+ char *data = phys_to_virt(element->addr) + offset;
skb_len -= data_len;
offset += data_len;
{
int work_done = 0;
- WARN_ON_ONCE(!budget);
*done = false;
while (budget) {
QETH_CARD_TEXT(card, 2, "vniccsch");
- /* do not change anything if BridgePort is enabled */
- if (qeth_bridgeport_is_in_use(card))
- return -EBUSY;
-
/* check if characteristic and enable/disable are supported */
if (!(card->options.vnicc.sup_chars & vnicc) ||
!(card->options.vnicc.set_char_sup & vnicc))
return -EOPNOTSUPP;
+ if (qeth_bridgeport_is_in_use(card))
+ return -EBUSY;
+
/* set enable/disable command and store wanted characteristic */
if (state) {
cmd = IPA_VNICC_ENABLE;
QETH_CARD_TEXT(card, 2, "vniccgch");
- /* do not get anything if BridgePort is enabled */
- if (qeth_bridgeport_is_in_use(card))
- return -EBUSY;
-
/* check if characteristic is supported */
if (!(card->options.vnicc.sup_chars & vnicc))
return -EOPNOTSUPP;
+ if (qeth_bridgeport_is_in_use(card))
+ return -EBUSY;
+
/* if card is ready, query current VNICC state */
if (qeth_card_hw_is_reachable(card))
rc = qeth_l2_vnicc_query_chars(card);
QETH_CARD_TEXT(card, 2, "vniccsto");
- /* do not change anything if BridgePort is enabled */
- if (qeth_bridgeport_is_in_use(card))
- return -EBUSY;
-
/* check if characteristic and set_timeout are supported */
if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
!(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
return -EOPNOTSUPP;
+ if (qeth_bridgeport_is_in_use(card))
+ return -EBUSY;
+
/* do we need to do anything? */
if (card->options.vnicc.learning_timeout == timeout)
return rc;
QETH_CARD_TEXT(card, 2, "vniccgto");
- /* do not get anything if BridgePort is enabled */
- if (qeth_bridgeport_is_in_use(card))
- return -EBUSY;
-
/* check if characteristic and get_timeout are supported */
if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
!(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
return -EOPNOTSUPP;
+
+ if (qeth_bridgeport_is_in_use(card))
+ return -EBUSY;
+
/* if card is ready, get timeout. Otherwise, just return stored value */
*timeout = card->options.vnicc.learning_timeout;
if (qeth_card_hw_is_reachable(card))
for (idx = 0; idx < QDIO_MAX_ELEMENTS_PER_BUFFER; idx++) {
sbale = &sbal->element[idx];
- req_id = (unsigned long) sbale->addr;
+ req_id = sbale->addr;
fsf_req = zfcp_reqlist_find_rm(adapter->req_list, req_id);
if (!fsf_req) {
u8 cb_util;
u8 a_util;
u8 res2;
- u16 temperature;
+ s16 temperature;
u16 vcc;
u16 tx_bias;
u16 tx_power;
memset(pl, 0,
ZFCP_QDIO_MAX_SBALS_PER_REQ * sizeof(void *));
sbale = qdio->res_q[idx]->element;
- req_id = (u64) sbale->addr;
+ req_id = sbale->addr;
scount = min(sbale->scount + 1,
ZFCP_QDIO_MAX_SBALS_PER_REQ + 1);
/* incl. signaling SBAL */
q_req->sbal_number);
return -EINVAL;
}
- sbale->addr = sg_virt(sg);
+ sbale->addr = sg_phys(sg);
sbale->length = sg->length;
}
return 0;
sbale->length = 0;
sbale->eflags = SBAL_EFLAGS_LAST_ENTRY;
sbale->sflags = 0;
- sbale->addr = NULL;
+ sbale->addr = 0;
}
if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q))
% QDIO_MAX_BUFFERS_PER_Q;
sbale = zfcp_qdio_sbale_req(qdio, q_req);
- sbale->addr = (void *) req_id;
+ sbale->addr = req_id;
sbale->eflags = 0;
sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype;
if (unlikely(!data))
return;
sbale++;
- sbale->addr = data;
+ sbale->addr = virt_to_phys(data);
sbale->length = len;
}
BUG_ON(q_req->sbale_curr == qdio->max_sbale_per_sbal - 1);
q_req->sbale_curr++;
sbale = zfcp_qdio_sbale_curr(qdio, q_req);
- sbale->addr = data;
+ sbale->addr = virt_to_phys(data);
sbale->length = len;
}
static ZFCP_DEV_ATTR(adapter_diag_sfp, _name, 0400, \
zfcp_sysfs_adapter_diag_sfp_##_name##_show, NULL)
-ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 5, "%hu");
+ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 6, "%hd");
ZFCP_DEFINE_DIAG_SFP_ATTR(vcc, vcc, 5, "%hu");
ZFCP_DEFINE_DIAG_SFP_ATTR(tx_bias, tx_bias, 5, "%hu");
ZFCP_DEFINE_DIAG_SFP_ATTR(tx_power, tx_power, 5, "%hu");
}
out:
kref_put(&rdata->kref, fc_rport_destroy);
+ if (!IS_ERR(fp))
+ fc_frame_free(fp);
}
/**
fusion->io_request_frames =
dma_pool_alloc(fusion->io_request_frames_pool,
- GFP_KERNEL, &fusion->io_request_frames_phys);
+ GFP_KERNEL | __GFP_NOWARN,
+ &fusion->io_request_frames_phys);
if (!fusion->io_request_frames) {
if (instance->max_fw_cmds >= (MEGASAS_REDUCE_QD_COUNT * 2)) {
instance->max_fw_cmds -= MEGASAS_REDUCE_QD_COUNT;
fusion->io_request_frames =
dma_pool_alloc(fusion->io_request_frames_pool,
- GFP_KERNEL,
+ GFP_KERNEL | __GFP_NOWARN,
&fusion->io_request_frames_phys);
if (!fusion->io_request_frames) {
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct scsi_disk *sdkp = scsi_disk(disk);
+ sector_t capacity = logical_to_sectors(sdkp->device, sdkp->capacity);
unsigned int nr, i;
unsigned char *buf;
size_t offset, buflen = 0;
/* Not a zoned device */
return -EOPNOTSUPP;
+ if (!capacity)
+ /* Device gone or invalid */
+ return -ENODEV;
+
buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen);
if (!buf)
return -ENOMEM;
- while (zone_idx < nr_zones && sector < get_capacity(disk)) {
+ while (zone_idx < nr_zones && sector < capacity) {
ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
sectors_to_logical(sdkp->device, sector), true);
if (ret)
.release = sr_block_release,
.ioctl = sr_block_ioctl,
#ifdef CONFIG_COMPAT
- .ioctl = sr_block_compat_ioctl,
+ .compat_ioctl = sr_block_compat_ioctl,
#endif
.check_events = sr_block_check_events,
.revalidate_disk = sr_block_revalidate_disk,
It is, in theory, a good memory allocator for low-memory devices,
because it can discard shared memory units when under memory pressure.
-config ANDROID_VSOC
- tristate "Android Virtual SoC support"
- depends on PCI_MSI
- help
- This option adds support for the Virtual SoC driver needed to boot
- a 'cuttlefish' Android image inside QEmu. The driver interacts with
- a QEmu ivshmem device. If built as a module, it will be called vsoc.
-
source "drivers/staging/android/ion/Kconfig"
endif # if ANDROID
obj-y += ion/
obj-$(CONFIG_ASHMEM) += ashmem.o
-obj-$(CONFIG_ANDROID_VSOC) += vsoc.o
- Split /dev/ion up into multiple nodes (e.g. /dev/ion/heap0)
- Better test framework (integration with VGEM was suggested)
-vsoc.c, uapi/vsoc_shm.h
- - The current driver uses the same wait queue for all of the futexes in a
- region. This will cause false wakeups in regions with a large number of
- waiting threads. We should eventually use multiple queues and select the
- queue based on the region.
- - Add debugfs support for examining the permissions of regions.
- - Remove VSOC_WAIT_FOR_INCOMING_INTERRUPT ioctl. This functionality has been
- superseded by the futex and is there for legacy reasons.
-
Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com>
_calc_vm_trans(prot, PROT_EXEC, VM_MAYEXEC);
}
+static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ /* do not allow to mmap ashmem backing shmem file directly */
+ return -EPERM;
+}
+
+static unsigned long
+ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
{
+ static struct file_operations vmfile_fops;
struct ashmem_area *asma = file->private_data;
int ret = 0;
}
vmfile->f_mode |= FMODE_LSEEK;
asma->file = vmfile;
+ /*
+ * override mmap operation of the vmfile so that it can't be
+ * remapped which would lead to creation of a new vma with no
+ * asma permission checks. Have to override get_unmapped_area
+ * as well to prevent VM_BUG_ON check for f_ops modification.
+ */
+ if (!vmfile_fops.mmap) {
+ vmfile_fops = *vmfile->f_op;
+ vmfile_fops.mmap = ashmem_vmfile_mmap;
+ vmfile_fops.get_unmapped_area =
+ ashmem_vmfile_get_unmapped_area;
+ }
+ vmfile->f_op = &vmfile_fops;
}
get_file(asma->file);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2017 Google, Inc.
- *
- */
-
-#ifndef _UAPI_LINUX_VSOC_SHM_H
-#define _UAPI_LINUX_VSOC_SHM_H
-
-#include <linux/types.h>
-
-/**
- * A permission is a token that permits a receiver to read and/or write an area
- * of memory within a Vsoc region.
- *
- * An fd_scoped permission grants both read and write access, and can be
- * attached to a file description (see open(2)).
- * Ownership of the area can then be shared by passing a file descriptor
- * among processes.
- *
- * begin_offset and end_offset define the area of memory that is controlled by
- * the permission. owner_offset points to a word, also in shared memory, that
- * controls ownership of the area.
- *
- * ownership of the region expires when the associated file description is
- * released.
- *
- * At most one permission can be attached to each file description.
- *
- * This is useful when implementing HALs like gralloc that scope and pass
- * ownership of shared resources via file descriptors.
- *
- * The caller is responsibe for doing any fencing.
- *
- * The calling process will normally identify a currently free area of
- * memory. It will construct a proposed fd_scoped_permission_arg structure:
- *
- * begin_offset and end_offset describe the area being claimed
- *
- * owner_offset points to the location in shared memory that indicates the
- * owner of the area.
- *
- * owned_value is the value that will be stored in owner_offset iff the
- * permission can be granted. It must be different than VSOC_REGION_FREE.
- *
- * Two fd_scoped_permission structures are compatible if they vary only by
- * their owned_value fields.
- *
- * The driver ensures that, for any group of simultaneous callers proposing
- * compatible fd_scoped_permissions, it will accept exactly one of the
- * propopsals. The other callers will get a failure with errno of EAGAIN.
- *
- * A process receiving a file descriptor can identify the region being
- * granted using the VSOC_GET_FD_SCOPED_PERMISSION ioctl.
- */
-struct fd_scoped_permission {
- __u32 begin_offset;
- __u32 end_offset;
- __u32 owner_offset;
- __u32 owned_value;
-};
-
-/*
- * This value represents a free area of memory. The driver expects to see this
- * value at owner_offset when creating a permission otherwise it will not do it,
- * and will write this value back once the permission is no longer needed.
- */
-#define VSOC_REGION_FREE ((__u32)0)
-
-/**
- * ioctl argument for VSOC_CREATE_FD_SCOPE_PERMISSION
- */
-struct fd_scoped_permission_arg {
- struct fd_scoped_permission perm;
- __s32 managed_region_fd;
-};
-
-#define VSOC_NODE_FREE ((__u32)0)
-
-/*
- * Describes a signal table in shared memory. Each non-zero entry in the
- * table indicates that the receiver should signal the futex at the given
- * offset. Offsets are relative to the region, not the shared memory window.
- *
- * interrupt_signalled_offset is used to reliably signal interrupts across the
- * vmm boundary. There are two roles: transmitter and receiver. For example,
- * in the host_to_guest_signal_table the host is the transmitter and the
- * guest is the receiver. The protocol is as follows:
- *
- * 1. The transmitter should convert the offset of the futex to an offset
- * in the signal table [0, (1 << num_nodes_lg2))
- * The transmitter can choose any appropriate hashing algorithm, including
- * hash = futex_offset & ((1 << num_nodes_lg2) - 1)
- *
- * 3. The transmitter should atomically compare and swap futex_offset with 0
- * at hash. There are 3 possible outcomes
- * a. The swap fails because the futex_offset is already in the table.
- * The transmitter should stop.
- * b. Some other offset is in the table. This is a hash collision. The
- * transmitter should move to another table slot and try again. One
- * possible algorithm:
- * hash = (hash + 1) & ((1 << num_nodes_lg2) - 1)
- * c. The swap worked. Continue below.
- *
- * 3. The transmitter atomically swaps 1 with the value at the
- * interrupt_signalled_offset. There are two outcomes:
- * a. The prior value was 1. In this case an interrupt has already been
- * posted. The transmitter is done.
- * b. The prior value was 0, indicating that the receiver may be sleeping.
- * The transmitter will issue an interrupt.
- *
- * 4. On waking the receiver immediately exchanges a 0 with the
- * interrupt_signalled_offset. If it receives a 0 then this a spurious
- * interrupt. That may occasionally happen in the current protocol, but
- * should be rare.
- *
- * 5. The receiver scans the signal table by atomicaly exchanging 0 at each
- * location. If a non-zero offset is returned from the exchange the
- * receiver wakes all sleepers at the given offset:
- * futex((int*)(region_base + old_value), FUTEX_WAKE, MAX_INT);
- *
- * 6. The receiver thread then does a conditional wait, waking immediately
- * if the value at interrupt_signalled_offset is non-zero. This catches cases
- * here additional signals were posted while the table was being scanned.
- * On the guest the wait is handled via the VSOC_WAIT_FOR_INCOMING_INTERRUPT
- * ioctl.
- */
-struct vsoc_signal_table_layout {
- /* log_2(Number of signal table entries) */
- __u32 num_nodes_lg2;
- /*
- * Offset to the first signal table entry relative to the start of the
- * region
- */
- __u32 futex_uaddr_table_offset;
- /*
- * Offset to an atomic_t / atomic uint32_t. A non-zero value indicates
- * that one or more offsets are currently posted in the table.
- * semi-unique access to an entry in the table
- */
- __u32 interrupt_signalled_offset;
-};
-
-#define VSOC_REGION_WHOLE ((__s32)0)
-#define VSOC_DEVICE_NAME_SZ 16
-
-/**
- * Each HAL would (usually) talk to a single device region
- * Mulitple entities care about these regions:
- * - The ivshmem_server will populate the regions in shared memory
- * - The guest kernel will read the region, create minor device nodes, and
- * allow interested parties to register for FUTEX_WAKE events in the region
- * - HALs will access via the minor device nodes published by the guest kernel
- * - Host side processes will access the region via the ivshmem_server:
- * 1. Pass name to ivshmem_server at a UNIX socket
- * 2. ivshmemserver will reply with 2 fds:
- * - host->guest doorbell fd
- * - guest->host doorbell fd
- * - fd for the shared memory region
- * - region offset
- * 3. Start a futex receiver thread on the doorbell fd pointed at the
- * signal_nodes
- */
-struct vsoc_device_region {
- __u16 current_version;
- __u16 min_compatible_version;
- __u32 region_begin_offset;
- __u32 region_end_offset;
- __u32 offset_of_region_data;
- struct vsoc_signal_table_layout guest_to_host_signal_table;
- struct vsoc_signal_table_layout host_to_guest_signal_table;
- /* Name of the device. Must always be terminated with a '\0', so
- * the longest supported device name is 15 characters.
- */
- char device_name[VSOC_DEVICE_NAME_SZ];
- /* There are two ways that permissions to access regions are handled:
- * - When subdivided_by is VSOC_REGION_WHOLE, any process that can
- * open the device node for the region gains complete access to it.
- * - When subdivided is set processes that open the region cannot
- * access it. Access to a sub-region must be established by invoking
- * the VSOC_CREATE_FD_SCOPE_PERMISSION ioctl on the region
- * referenced in subdivided_by, providing a fileinstance
- * (represented by a fd) opened on this region.
- */
- __u32 managed_by;
-};
-
-/*
- * The vsoc layout descriptor.
- * The first 4K should be reserved for the shm header and region descriptors.
- * The regions should be page aligned.
- */
-
-struct vsoc_shm_layout_descriptor {
- __u16 major_version;
- __u16 minor_version;
-
- /* size of the shm. This may be redundant but nice to have */
- __u32 size;
-
- /* number of shared memory regions */
- __u32 region_count;
-
- /* The offset to the start of region descriptors */
- __u32 vsoc_region_desc_offset;
-};
-
-/*
- * This specifies the current version that should be stored in
- * vsoc_shm_layout_descriptor.major_version and
- * vsoc_shm_layout_descriptor.minor_version.
- * It should be updated only if the vsoc_device_region and
- * vsoc_shm_layout_descriptor structures have changed.
- * Versioning within each region is transferred
- * via the min_compatible_version and current_version fields in
- * vsoc_device_region. The driver does not consult these fields: they are left
- * for the HALs and host processes and will change independently of the layout
- * version.
- */
-#define CURRENT_VSOC_LAYOUT_MAJOR_VERSION 2
-#define CURRENT_VSOC_LAYOUT_MINOR_VERSION 0
-
-#define VSOC_CREATE_FD_SCOPED_PERMISSION \
- _IOW(0xF5, 0, struct fd_scoped_permission)
-#define VSOC_GET_FD_SCOPED_PERMISSION _IOR(0xF5, 1, struct fd_scoped_permission)
-
-/*
- * This is used to signal the host to scan the guest_to_host_signal_table
- * for new futexes to wake. This sends an interrupt if one is not already
- * in flight.
- */
-#define VSOC_MAYBE_SEND_INTERRUPT_TO_HOST _IO(0xF5, 2)
-
-/*
- * When this returns the guest will scan host_to_guest_signal_table to
- * check for new futexes to wake.
- */
-/* TODO(ghartman): Consider moving this to the bottom half */
-#define VSOC_WAIT_FOR_INCOMING_INTERRUPT _IO(0xF5, 3)
-
-/*
- * Guest HALs will use this to retrieve the region description after
- * opening their device node.
- */
-#define VSOC_DESCRIBE_REGION _IOR(0xF5, 4, struct vsoc_device_region)
-
-/*
- * Wake any threads that may be waiting for a host interrupt on this region.
- * This is mostly used during shutdown.
- */
-#define VSOC_SELF_INTERRUPT _IO(0xF5, 5)
-
-/*
- * This is used to signal the host to scan the guest_to_host_signal_table
- * for new futexes to wake. This sends an interrupt unconditionally.
- */
-#define VSOC_SEND_INTERRUPT_TO_HOST _IO(0xF5, 6)
-
-enum wait_types {
- VSOC_WAIT_UNDEFINED = 0,
- VSOC_WAIT_IF_EQUAL = 1,
- VSOC_WAIT_IF_EQUAL_TIMEOUT = 2
-};
-
-/*
- * Wait for a condition to be true
- *
- * Note, this is sized and aligned so the 32 bit and 64 bit layouts are
- * identical.
- */
-struct vsoc_cond_wait {
- /* Input: Offset of the 32 bit word to check */
- __u32 offset;
- /* Input: Value that will be compared with the offset */
- __u32 value;
- /* Monotonic time to wake at in seconds */
- __u64 wake_time_sec;
- /* Input: Monotonic time to wait in nanoseconds */
- __u32 wake_time_nsec;
- /* Input: Type of wait */
- __u32 wait_type;
- /* Output: Number of times the thread woke before returning. */
- __u32 wakes;
- /* Ensure that we're 8-byte aligned and 8 byte length for 32/64 bit
- * compatibility.
- */
- __u32 reserved_1;
-};
-
-#define VSOC_COND_WAIT _IOWR(0xF5, 7, struct vsoc_cond_wait)
-
-/* Wake any local threads waiting at the offset given in arg */
-#define VSOC_COND_WAKE _IO(0xF5, 8)
-
-#endif /* _UAPI_LINUX_VSOC_SHM_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * drivers/android/staging/vsoc.c
- *
- * Android Virtual System on a Chip (VSoC) driver
- *
- * Copyright (C) 2017 Google, Inc.
- *
- * Author: ghartman@google.com
- *
- * Based on drivers/char/kvm_ivshmem.c - driver for KVM Inter-VM shared memory
- * Copyright 2009 Cam Macdonell <cam@cs.ualberta.ca>
- *
- * Based on cirrusfb.c and 8139cp.c:
- * Copyright 1999-2001 Jeff Garzik
- * Copyright 2001-2004 Jeff Garzik
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/freezer.h>
-#include <linux/futex.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/pci.h>
-#include <linux/proc_fs.h>
-#include <linux/sched.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/interrupt.h>
-#include <linux/cdev.h>
-#include <linux/file.h>
-#include "uapi/vsoc_shm.h"
-
-#define VSOC_DEV_NAME "vsoc"
-
-/*
- * Description of the ivshmem-doorbell PCI device used by QEmu. These
- * constants follow docs/specs/ivshmem-spec.txt, which can be found in
- * the QEmu repository. This was last reconciled with the version that
- * came out with 2.8
- */
-
-/*
- * These constants are determined KVM Inter-VM shared memory device
- * register offsets
- */
-enum {
- INTR_MASK = 0x00, /* Interrupt Mask */
- INTR_STATUS = 0x04, /* Interrupt Status */
- IV_POSITION = 0x08, /* VM ID */
- DOORBELL = 0x0c, /* Doorbell */
-};
-
-static const int REGISTER_BAR; /* Equal to 0 */
-static const int MAX_REGISTER_BAR_LEN = 0x100;
-/*
- * The MSI-x BAR is not used directly.
- *
- * static const int MSI_X_BAR = 1;
- */
-static const int SHARED_MEMORY_BAR = 2;
-
-struct vsoc_region_data {
- char name[VSOC_DEVICE_NAME_SZ + 1];
- wait_queue_head_t interrupt_wait_queue;
- /* TODO(b/73664181): Use multiple futex wait queues */
- wait_queue_head_t futex_wait_queue;
- /* Flag indicating that an interrupt has been signalled by the host. */
- atomic_t *incoming_signalled;
- /* Flag indicating the guest has signalled the host. */
- atomic_t *outgoing_signalled;
- bool irq_requested;
- bool device_created;
-};
-
-struct vsoc_device {
- /* Kernel virtual address of REGISTER_BAR. */
- void __iomem *regs;
- /* Physical address of SHARED_MEMORY_BAR. */
- phys_addr_t shm_phys_start;
- /* Kernel virtual address of SHARED_MEMORY_BAR. */
- void __iomem *kernel_mapped_shm;
- /* Size of the entire shared memory window in bytes. */
- size_t shm_size;
- /*
- * Pointer to the virtual address of the shared memory layout structure.
- * This is probably identical to kernel_mapped_shm, but saving this
- * here saves a lot of annoying casts.
- */
- struct vsoc_shm_layout_descriptor *layout;
- /*
- * Points to a table of region descriptors in the kernel's virtual
- * address space. Calculated from
- * vsoc_shm_layout_descriptor.vsoc_region_desc_offset
- */
- struct vsoc_device_region *regions;
- /* Head of a list of permissions that have been granted. */
- struct list_head permissions;
- struct pci_dev *dev;
- /* Per-region (and therefore per-interrupt) information. */
- struct vsoc_region_data *regions_data;
- /*
- * Table of msi-x entries. This has to be separated from struct
- * vsoc_region_data because the kernel deals with them as an array.
- */
- struct msix_entry *msix_entries;
- /* Mutex that protectes the permission list */
- struct mutex mtx;
- /* Major number assigned by the kernel */
- int major;
- /* Character device assigned by the kernel */
- struct cdev cdev;
- /* Device class assigned by the kernel */
- struct class *class;
- /*
- * Flags that indicate what we've initialized. These are used to do an
- * orderly cleanup of the device.
- */
- bool enabled_device;
- bool requested_regions;
- bool cdev_added;
- bool class_added;
- bool msix_enabled;
-};
-
-static struct vsoc_device vsoc_dev;
-
-/*
- * TODO(ghartman): Add a /sys filesystem entry that summarizes the permissions.
- */
-
-struct fd_scoped_permission_node {
- struct fd_scoped_permission permission;
- struct list_head list;
-};
-
-struct vsoc_private_data {
- struct fd_scoped_permission_node *fd_scoped_permission_node;
-};
-
-static long vsoc_ioctl(struct file *, unsigned int, unsigned long);
-static int vsoc_mmap(struct file *, struct vm_area_struct *);
-static int vsoc_open(struct inode *, struct file *);
-static int vsoc_release(struct inode *, struct file *);
-static ssize_t vsoc_read(struct file *, char __user *, size_t, loff_t *);
-static ssize_t vsoc_write(struct file *, const char __user *, size_t, loff_t *);
-static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin);
-static int
-do_create_fd_scoped_permission(struct vsoc_device_region *region_p,
- struct fd_scoped_permission_node *np,
- struct fd_scoped_permission_arg __user *arg);
-static void
-do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p,
- struct fd_scoped_permission *perm);
-static long do_vsoc_describe_region(struct file *,
- struct vsoc_device_region __user *);
-static ssize_t vsoc_get_area(struct file *filp, __u32 *perm_off);
-
-/**
- * Validate arguments on entry points to the driver.
- */
-inline int vsoc_validate_inode(struct inode *inode)
-{
- if (iminor(inode) >= vsoc_dev.layout->region_count) {
- dev_err(&vsoc_dev.dev->dev,
- "describe_region: invalid region %d\n", iminor(inode));
- return -ENODEV;
- }
- return 0;
-}
-
-inline int vsoc_validate_filep(struct file *filp)
-{
- int ret = vsoc_validate_inode(file_inode(filp));
-
- if (ret)
- return ret;
- if (!filp->private_data) {
- dev_err(&vsoc_dev.dev->dev,
- "No private data on fd, region %d\n",
- iminor(file_inode(filp)));
- return -EBADFD;
- }
- return 0;
-}
-
-/* Converts from shared memory offset to virtual address */
-static inline void *shm_off_to_virtual_addr(__u32 offset)
-{
- return (void __force *)vsoc_dev.kernel_mapped_shm + offset;
-}
-
-/* Converts from shared memory offset to physical address */
-static inline phys_addr_t shm_off_to_phys_addr(__u32 offset)
-{
- return vsoc_dev.shm_phys_start + offset;
-}
-
-/**
- * Convenience functions to obtain the region from the inode or file.
- * Dangerous to call before validating the inode/file.
- */
-static
-inline struct vsoc_device_region *vsoc_region_from_inode(struct inode *inode)
-{
- return &vsoc_dev.regions[iminor(inode)];
-}
-
-static
-inline struct vsoc_device_region *vsoc_region_from_filep(struct file *inode)
-{
- return vsoc_region_from_inode(file_inode(inode));
-}
-
-static inline uint32_t vsoc_device_region_size(struct vsoc_device_region *r)
-{
- return r->region_end_offset - r->region_begin_offset;
-}
-
-static const struct file_operations vsoc_ops = {
- .owner = THIS_MODULE,
- .open = vsoc_open,
- .mmap = vsoc_mmap,
- .read = vsoc_read,
- .unlocked_ioctl = vsoc_ioctl,
- .compat_ioctl = vsoc_ioctl,
- .write = vsoc_write,
- .llseek = vsoc_lseek,
- .release = vsoc_release,
-};
-
-static struct pci_device_id vsoc_id_table[] = {
- {0x1af4, 0x1110, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
- {0},
-};
-
-MODULE_DEVICE_TABLE(pci, vsoc_id_table);
-
-static void vsoc_remove_device(struct pci_dev *pdev);
-static int vsoc_probe_device(struct pci_dev *pdev,
- const struct pci_device_id *ent);
-
-static struct pci_driver vsoc_pci_driver = {
- .name = "vsoc",
- .id_table = vsoc_id_table,
- .probe = vsoc_probe_device,
- .remove = vsoc_remove_device,
-};
-
-static int
-do_create_fd_scoped_permission(struct vsoc_device_region *region_p,
- struct fd_scoped_permission_node *np,
- struct fd_scoped_permission_arg __user *arg)
-{
- struct file *managed_filp;
- s32 managed_fd;
- atomic_t *owner_ptr = NULL;
- struct vsoc_device_region *managed_region_p;
-
- if (copy_from_user(&np->permission,
- &arg->perm, sizeof(np->permission)) ||
- copy_from_user(&managed_fd,
- &arg->managed_region_fd, sizeof(managed_fd))) {
- return -EFAULT;
- }
- managed_filp = fdget(managed_fd).file;
- /* Check that it's a valid fd, */
- if (!managed_filp || vsoc_validate_filep(managed_filp))
- return -EPERM;
- /* EEXIST if the given fd already has a permission. */
- if (((struct vsoc_private_data *)managed_filp->private_data)->
- fd_scoped_permission_node)
- return -EEXIST;
- managed_region_p = vsoc_region_from_filep(managed_filp);
- /* Check that the provided region is managed by this one */
- if (&vsoc_dev.regions[managed_region_p->managed_by] != region_p)
- return -EPERM;
- /* The area must be well formed and have non-zero size */
- if (np->permission.begin_offset >= np->permission.end_offset)
- return -EINVAL;
- /* The area must fit in the memory window */
- if (np->permission.end_offset >
- vsoc_device_region_size(managed_region_p))
- return -ERANGE;
- /* The area must be in the region data section */
- if (np->permission.begin_offset <
- managed_region_p->offset_of_region_data)
- return -ERANGE;
- /* The area must be page aligned */
- if (!PAGE_ALIGNED(np->permission.begin_offset) ||
- !PAGE_ALIGNED(np->permission.end_offset))
- return -EINVAL;
- /* Owner offset must be naturally aligned in the window */
- if (np->permission.owner_offset &
- (sizeof(np->permission.owner_offset) - 1))
- return -EINVAL;
- /* The owner flag must reside in the owner memory */
- if (np->permission.owner_offset + sizeof(np->permission.owner_offset) >
- vsoc_device_region_size(region_p))
- return -ERANGE;
- /* The owner flag must reside in the data section */
- if (np->permission.owner_offset < region_p->offset_of_region_data)
- return -EINVAL;
- /* The owner value must change to claim the memory */
- if (np->permission.owned_value == VSOC_REGION_FREE)
- return -EINVAL;
- owner_ptr =
- (atomic_t *)shm_off_to_virtual_addr(region_p->region_begin_offset +
- np->permission.owner_offset);
- /* We've already verified that this is in the shared memory window, so
- * it should be safe to write to this address.
- */
- if (atomic_cmpxchg(owner_ptr,
- VSOC_REGION_FREE,
- np->permission.owned_value) != VSOC_REGION_FREE) {
- return -EBUSY;
- }
- ((struct vsoc_private_data *)managed_filp->private_data)->
- fd_scoped_permission_node = np;
- /* The file offset needs to be adjusted if the calling
- * process did any read/write operations on the fd
- * before creating the permission.
- */
- if (managed_filp->f_pos) {
- if (managed_filp->f_pos > np->permission.end_offset) {
- /* If the offset is beyond the permission end, set it
- * to the end.
- */
- managed_filp->f_pos = np->permission.end_offset;
- } else {
- /* If the offset is within the permission interval
- * keep it there otherwise reset it to zero.
- */
- if (managed_filp->f_pos < np->permission.begin_offset) {
- managed_filp->f_pos = 0;
- } else {
- managed_filp->f_pos -=
- np->permission.begin_offset;
- }
- }
- }
- return 0;
-}
-
-static void
-do_destroy_fd_scoped_permission_node(struct vsoc_device_region *owner_region_p,
- struct fd_scoped_permission_node *node)
-{
- if (node) {
- do_destroy_fd_scoped_permission(owner_region_p,
- &node->permission);
- mutex_lock(&vsoc_dev.mtx);
- list_del(&node->list);
- mutex_unlock(&vsoc_dev.mtx);
- kfree(node);
- }
-}
-
-static void
-do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p,
- struct fd_scoped_permission *perm)
-{
- atomic_t *owner_ptr = NULL;
- int prev = 0;
-
- if (!perm)
- return;
- owner_ptr = (atomic_t *)shm_off_to_virtual_addr
- (owner_region_p->region_begin_offset + perm->owner_offset);
- prev = atomic_xchg(owner_ptr, VSOC_REGION_FREE);
- if (prev != perm->owned_value)
- dev_err(&vsoc_dev.dev->dev,
- "%x-%x: owner (%s) %x: expected to be %x was %x",
- perm->begin_offset, perm->end_offset,
- owner_region_p->device_name, perm->owner_offset,
- perm->owned_value, prev);
-}
-
-static long do_vsoc_describe_region(struct file *filp,
- struct vsoc_device_region __user *dest)
-{
- struct vsoc_device_region *region_p;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- region_p = vsoc_region_from_filep(filp);
- if (copy_to_user(dest, region_p, sizeof(*region_p)))
- return -EFAULT;
- return 0;
-}
-
-/**
- * Implements the inner logic of cond_wait. Copies to and from userspace are
- * done in the helper function below.
- */
-static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg)
-{
- DEFINE_WAIT(wait);
- u32 region_number = iminor(file_inode(filp));
- struct vsoc_region_data *data = vsoc_dev.regions_data + region_number;
- struct hrtimer_sleeper timeout, *to = NULL;
- int ret = 0;
- struct vsoc_device_region *region_p = vsoc_region_from_filep(filp);
- atomic_t *address = NULL;
- ktime_t wake_time;
-
- /* Ensure that the offset is aligned */
- if (arg->offset & (sizeof(uint32_t) - 1))
- return -EADDRNOTAVAIL;
- /* Ensure that the offset is within shared memory */
- if (((uint64_t)arg->offset) + region_p->region_begin_offset +
- sizeof(uint32_t) > region_p->region_end_offset)
- return -E2BIG;
- address = shm_off_to_virtual_addr(region_p->region_begin_offset +
- arg->offset);
-
- /* Ensure that the type of wait is valid */
- switch (arg->wait_type) {
- case VSOC_WAIT_IF_EQUAL:
- break;
- case VSOC_WAIT_IF_EQUAL_TIMEOUT:
- to = &timeout;
- break;
- default:
- return -EINVAL;
- }
-
- if (to) {
- /* Copy the user-supplied timesec into the kernel structure.
- * We do things this way to flatten differences between 32 bit
- * and 64 bit timespecs.
- */
- if (arg->wake_time_nsec >= NSEC_PER_SEC)
- return -EINVAL;
- wake_time = ktime_set(arg->wake_time_sec, arg->wake_time_nsec);
-
- hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS);
- hrtimer_set_expires_range_ns(&to->timer, wake_time,
- current->timer_slack_ns);
- }
-
- while (1) {
- prepare_to_wait(&data->futex_wait_queue, &wait,
- TASK_INTERRUPTIBLE);
- /*
- * Check the sentinel value after prepare_to_wait. If the value
- * changes after this check the writer will call signal,
- * changing the task state from INTERRUPTIBLE to RUNNING. That
- * will ensure that schedule() will eventually schedule this
- * task.
- */
- if (atomic_read(address) != arg->value) {
- ret = 0;
- break;
- }
- if (to) {
- hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
- if (likely(to->task))
- freezable_schedule();
- hrtimer_cancel(&to->timer);
- if (!to->task) {
- ret = -ETIMEDOUT;
- break;
- }
- } else {
- freezable_schedule();
- }
- /* Count the number of times that we woke up. This is useful
- * for unit testing.
- */
- ++arg->wakes;
- if (signal_pending(current)) {
- ret = -EINTR;
- break;
- }
- }
- finish_wait(&data->futex_wait_queue, &wait);
- if (to)
- destroy_hrtimer_on_stack(&to->timer);
- return ret;
-}
-
-/**
- * Handles the details of copying from/to userspace to ensure that the copies
- * happen on all of the return paths of cond_wait.
- */
-static int do_vsoc_cond_wait(struct file *filp,
- struct vsoc_cond_wait __user *untrusted_in)
-{
- struct vsoc_cond_wait arg;
- int rval = 0;
-
- if (copy_from_user(&arg, untrusted_in, sizeof(arg)))
- return -EFAULT;
- /* wakes is an out parameter. Initialize it to something sensible. */
- arg.wakes = 0;
- rval = handle_vsoc_cond_wait(filp, &arg);
- if (copy_to_user(untrusted_in, &arg, sizeof(arg)))
- return -EFAULT;
- return rval;
-}
-
-static int do_vsoc_cond_wake(struct file *filp, uint32_t offset)
-{
- struct vsoc_device_region *region_p = vsoc_region_from_filep(filp);
- u32 region_number = iminor(file_inode(filp));
- struct vsoc_region_data *data = vsoc_dev.regions_data + region_number;
- /* Ensure that the offset is aligned */
- if (offset & (sizeof(uint32_t) - 1))
- return -EADDRNOTAVAIL;
- /* Ensure that the offset is within shared memory */
- if (((uint64_t)offset) + region_p->region_begin_offset +
- sizeof(uint32_t) > region_p->region_end_offset)
- return -E2BIG;
- /*
- * TODO(b/73664181): Use multiple futex wait queues.
- * We need to wake every sleeper when the condition changes. Typically
- * only a single thread will be waiting on the condition, but there
- * are exceptions. The worst case is about 10 threads.
- */
- wake_up_interruptible_all(&data->futex_wait_queue);
- return 0;
-}
-
-static long vsoc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
- int rv = 0;
- struct vsoc_device_region *region_p;
- u32 reg_num;
- struct vsoc_region_data *reg_data;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- region_p = vsoc_region_from_filep(filp);
- reg_num = iminor(file_inode(filp));
- reg_data = vsoc_dev.regions_data + reg_num;
- switch (cmd) {
- case VSOC_CREATE_FD_SCOPED_PERMISSION:
- {
- struct fd_scoped_permission_node *node = NULL;
-
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- /* We can't allocate memory for the permission */
- if (!node)
- return -ENOMEM;
- INIT_LIST_HEAD(&node->list);
- rv = do_create_fd_scoped_permission
- (region_p,
- node,
- (struct fd_scoped_permission_arg __user *)arg);
- if (!rv) {
- mutex_lock(&vsoc_dev.mtx);
- list_add(&node->list, &vsoc_dev.permissions);
- mutex_unlock(&vsoc_dev.mtx);
- } else {
- kfree(node);
- return rv;
- }
- }
- break;
-
- case VSOC_GET_FD_SCOPED_PERMISSION:
- {
- struct fd_scoped_permission_node *node =
- ((struct vsoc_private_data *)filp->private_data)->
- fd_scoped_permission_node;
- if (!node)
- return -ENOENT;
- if (copy_to_user
- ((struct fd_scoped_permission __user *)arg,
- &node->permission, sizeof(node->permission)))
- return -EFAULT;
- }
- break;
-
- case VSOC_MAYBE_SEND_INTERRUPT_TO_HOST:
- if (!atomic_xchg(reg_data->outgoing_signalled, 1)) {
- writel(reg_num, vsoc_dev.regs + DOORBELL);
- return 0;
- } else {
- return -EBUSY;
- }
- break;
-
- case VSOC_SEND_INTERRUPT_TO_HOST:
- writel(reg_num, vsoc_dev.regs + DOORBELL);
- return 0;
- case VSOC_WAIT_FOR_INCOMING_INTERRUPT:
- wait_event_interruptible
- (reg_data->interrupt_wait_queue,
- (atomic_read(reg_data->incoming_signalled) != 0));
- break;
-
- case VSOC_DESCRIBE_REGION:
- return do_vsoc_describe_region
- (filp,
- (struct vsoc_device_region __user *)arg);
-
- case VSOC_SELF_INTERRUPT:
- atomic_set(reg_data->incoming_signalled, 1);
- wake_up_interruptible(®_data->interrupt_wait_queue);
- break;
-
- case VSOC_COND_WAIT:
- return do_vsoc_cond_wait(filp,
- (struct vsoc_cond_wait __user *)arg);
- case VSOC_COND_WAKE:
- return do_vsoc_cond_wake(filp, arg);
-
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static ssize_t vsoc_read(struct file *filp, char __user *buffer, size_t len,
- loff_t *poffset)
-{
- __u32 area_off;
- const void *area_p;
- ssize_t area_len;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- area_len = vsoc_get_area(filp, &area_off);
- area_p = shm_off_to_virtual_addr(area_off);
- area_p += *poffset;
- area_len -= *poffset;
- if (area_len <= 0)
- return 0;
- if (area_len < len)
- len = area_len;
- if (copy_to_user(buffer, area_p, len))
- return -EFAULT;
- *poffset += len;
- return len;
-}
-
-static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin)
-{
- ssize_t area_len = 0;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- area_len = vsoc_get_area(filp, NULL);
- switch (origin) {
- case SEEK_SET:
- break;
-
- case SEEK_CUR:
- if (offset > 0 && offset + filp->f_pos < 0)
- return -EOVERFLOW;
- offset += filp->f_pos;
- break;
-
- case SEEK_END:
- if (offset > 0 && offset + area_len < 0)
- return -EOVERFLOW;
- offset += area_len;
- break;
-
- case SEEK_DATA:
- if (offset >= area_len)
- return -EINVAL;
- if (offset < 0)
- offset = 0;
- break;
-
- case SEEK_HOLE:
- /* Next hole is always the end of the region, unless offset is
- * beyond that
- */
- if (offset < area_len)
- offset = area_len;
- break;
-
- default:
- return -EINVAL;
- }
-
- if (offset < 0 || offset > area_len)
- return -EINVAL;
- filp->f_pos = offset;
-
- return offset;
-}
-
-static ssize_t vsoc_write(struct file *filp, const char __user *buffer,
- size_t len, loff_t *poffset)
-{
- __u32 area_off;
- void *area_p;
- ssize_t area_len;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- area_len = vsoc_get_area(filp, &area_off);
- area_p = shm_off_to_virtual_addr(area_off);
- area_p += *poffset;
- area_len -= *poffset;
- if (area_len <= 0)
- return 0;
- if (area_len < len)
- len = area_len;
- if (copy_from_user(area_p, buffer, len))
- return -EFAULT;
- *poffset += len;
- return len;
-}
-
-static irqreturn_t vsoc_interrupt(int irq, void *region_data_v)
-{
- struct vsoc_region_data *region_data =
- (struct vsoc_region_data *)region_data_v;
- int reg_num = region_data - vsoc_dev.regions_data;
-
- if (unlikely(!region_data))
- return IRQ_NONE;
-
- if (unlikely(reg_num < 0 ||
- reg_num >= vsoc_dev.layout->region_count)) {
- dev_err(&vsoc_dev.dev->dev,
- "invalid irq @%p reg_num=0x%04x\n",
- region_data, reg_num);
- return IRQ_NONE;
- }
- if (unlikely(vsoc_dev.regions_data + reg_num != region_data)) {
- dev_err(&vsoc_dev.dev->dev,
- "irq not aligned @%p reg_num=0x%04x\n",
- region_data, reg_num);
- return IRQ_NONE;
- }
- wake_up_interruptible(®ion_data->interrupt_wait_queue);
- return IRQ_HANDLED;
-}
-
-static int vsoc_probe_device(struct pci_dev *pdev,
- const struct pci_device_id *ent)
-{
- int result;
- int i;
- resource_size_t reg_size;
- dev_t devt;
-
- vsoc_dev.dev = pdev;
- result = pci_enable_device(pdev);
- if (result) {
- dev_err(&pdev->dev,
- "pci_enable_device failed %s: error %d\n",
- pci_name(pdev), result);
- return result;
- }
- vsoc_dev.enabled_device = true;
- result = pci_request_regions(pdev, "vsoc");
- if (result < 0) {
- dev_err(&pdev->dev, "pci_request_regions failed\n");
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
- vsoc_dev.requested_regions = true;
- /* Set up the control registers in BAR 0 */
- reg_size = pci_resource_len(pdev, REGISTER_BAR);
- if (reg_size > MAX_REGISTER_BAR_LEN)
- vsoc_dev.regs =
- pci_iomap(pdev, REGISTER_BAR, MAX_REGISTER_BAR_LEN);
- else
- vsoc_dev.regs = pci_iomap(pdev, REGISTER_BAR, reg_size);
-
- if (!vsoc_dev.regs) {
- dev_err(&pdev->dev,
- "cannot map registers of size %zu\n",
- (size_t)reg_size);
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
-
- /* Map the shared memory in BAR 2 */
- vsoc_dev.shm_phys_start = pci_resource_start(pdev, SHARED_MEMORY_BAR);
- vsoc_dev.shm_size = pci_resource_len(pdev, SHARED_MEMORY_BAR);
-
- dev_info(&pdev->dev, "shared memory @ DMA %pa size=0x%zx\n",
- &vsoc_dev.shm_phys_start, vsoc_dev.shm_size);
- vsoc_dev.kernel_mapped_shm = pci_iomap_wc(pdev, SHARED_MEMORY_BAR, 0);
- if (!vsoc_dev.kernel_mapped_shm) {
- dev_err(&vsoc_dev.dev->dev, "cannot iomap region\n");
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
-
- vsoc_dev.layout = (struct vsoc_shm_layout_descriptor __force *)
- vsoc_dev.kernel_mapped_shm;
- dev_info(&pdev->dev, "major_version: %d\n",
- vsoc_dev.layout->major_version);
- dev_info(&pdev->dev, "minor_version: %d\n",
- vsoc_dev.layout->minor_version);
- dev_info(&pdev->dev, "size: 0x%x\n", vsoc_dev.layout->size);
- dev_info(&pdev->dev, "regions: %d\n", vsoc_dev.layout->region_count);
- if (vsoc_dev.layout->major_version !=
- CURRENT_VSOC_LAYOUT_MAJOR_VERSION) {
- dev_err(&vsoc_dev.dev->dev,
- "driver supports only major_version %d\n",
- CURRENT_VSOC_LAYOUT_MAJOR_VERSION);
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
- result = alloc_chrdev_region(&devt, 0, vsoc_dev.layout->region_count,
- VSOC_DEV_NAME);
- if (result) {
- dev_err(&vsoc_dev.dev->dev, "alloc_chrdev_region failed\n");
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
- vsoc_dev.major = MAJOR(devt);
- cdev_init(&vsoc_dev.cdev, &vsoc_ops);
- vsoc_dev.cdev.owner = THIS_MODULE;
- result = cdev_add(&vsoc_dev.cdev, devt, vsoc_dev.layout->region_count);
- if (result) {
- dev_err(&vsoc_dev.dev->dev, "cdev_add error\n");
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
- vsoc_dev.cdev_added = true;
- vsoc_dev.class = class_create(THIS_MODULE, VSOC_DEV_NAME);
- if (IS_ERR(vsoc_dev.class)) {
- dev_err(&vsoc_dev.dev->dev, "class_create failed\n");
- vsoc_remove_device(pdev);
- return PTR_ERR(vsoc_dev.class);
- }
- vsoc_dev.class_added = true;
- vsoc_dev.regions = (struct vsoc_device_region __force *)
- ((void *)vsoc_dev.layout +
- vsoc_dev.layout->vsoc_region_desc_offset);
- vsoc_dev.msix_entries =
- kcalloc(vsoc_dev.layout->region_count,
- sizeof(vsoc_dev.msix_entries[0]), GFP_KERNEL);
- if (!vsoc_dev.msix_entries) {
- dev_err(&vsoc_dev.dev->dev,
- "unable to allocate msix_entries\n");
- vsoc_remove_device(pdev);
- return -ENOSPC;
- }
- vsoc_dev.regions_data =
- kcalloc(vsoc_dev.layout->region_count,
- sizeof(vsoc_dev.regions_data[0]), GFP_KERNEL);
- if (!vsoc_dev.regions_data) {
- dev_err(&vsoc_dev.dev->dev,
- "unable to allocate regions' data\n");
- vsoc_remove_device(pdev);
- return -ENOSPC;
- }
- for (i = 0; i < vsoc_dev.layout->region_count; ++i)
- vsoc_dev.msix_entries[i].entry = i;
-
- result = pci_enable_msix_exact(vsoc_dev.dev, vsoc_dev.msix_entries,
- vsoc_dev.layout->region_count);
- if (result) {
- dev_info(&pdev->dev, "pci_enable_msix failed: %d\n", result);
- vsoc_remove_device(pdev);
- return -ENOSPC;
- }
- /* Check that all regions are well formed */
- for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
- const struct vsoc_device_region *region = vsoc_dev.regions + i;
-
- if (!PAGE_ALIGNED(region->region_begin_offset) ||
- !PAGE_ALIGNED(region->region_end_offset)) {
- dev_err(&vsoc_dev.dev->dev,
- "region %d not aligned (%x:%x)", i,
- region->region_begin_offset,
- region->region_end_offset);
- vsoc_remove_device(pdev);
- return -EFAULT;
- }
- if (region->region_begin_offset >= region->region_end_offset ||
- region->region_end_offset > vsoc_dev.shm_size) {
- dev_err(&vsoc_dev.dev->dev,
- "region %d offsets are wrong: %x %x %zx",
- i, region->region_begin_offset,
- region->region_end_offset, vsoc_dev.shm_size);
- vsoc_remove_device(pdev);
- return -EFAULT;
- }
- if (region->managed_by >= vsoc_dev.layout->region_count) {
- dev_err(&vsoc_dev.dev->dev,
- "region %d has invalid owner: %u",
- i, region->managed_by);
- vsoc_remove_device(pdev);
- return -EFAULT;
- }
- }
- vsoc_dev.msix_enabled = true;
- for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
- const struct vsoc_device_region *region = vsoc_dev.regions + i;
- size_t name_sz = sizeof(vsoc_dev.regions_data[i].name) - 1;
- const struct vsoc_signal_table_layout *h_to_g_signal_table =
- ®ion->host_to_guest_signal_table;
- const struct vsoc_signal_table_layout *g_to_h_signal_table =
- ®ion->guest_to_host_signal_table;
-
- vsoc_dev.regions_data[i].name[name_sz] = '\0';
- memcpy(vsoc_dev.regions_data[i].name, region->device_name,
- name_sz);
- dev_info(&pdev->dev, "region %d name=%s\n",
- i, vsoc_dev.regions_data[i].name);
- init_waitqueue_head
- (&vsoc_dev.regions_data[i].interrupt_wait_queue);
- init_waitqueue_head(&vsoc_dev.regions_data[i].futex_wait_queue);
- vsoc_dev.regions_data[i].incoming_signalled =
- shm_off_to_virtual_addr(region->region_begin_offset) +
- h_to_g_signal_table->interrupt_signalled_offset;
- vsoc_dev.regions_data[i].outgoing_signalled =
- shm_off_to_virtual_addr(region->region_begin_offset) +
- g_to_h_signal_table->interrupt_signalled_offset;
- result = request_irq(vsoc_dev.msix_entries[i].vector,
- vsoc_interrupt, 0,
- vsoc_dev.regions_data[i].name,
- vsoc_dev.regions_data + i);
- if (result) {
- dev_info(&pdev->dev,
- "request_irq failed irq=%d vector=%d\n",
- i, vsoc_dev.msix_entries[i].vector);
- vsoc_remove_device(pdev);
- return -ENOSPC;
- }
- vsoc_dev.regions_data[i].irq_requested = true;
- if (!device_create(vsoc_dev.class, NULL,
- MKDEV(vsoc_dev.major, i),
- NULL, vsoc_dev.regions_data[i].name)) {
- dev_err(&vsoc_dev.dev->dev, "device_create failed\n");
- vsoc_remove_device(pdev);
- return -EBUSY;
- }
- vsoc_dev.regions_data[i].device_created = true;
- }
- return 0;
-}
-
-/*
- * This should undo all of the allocations in the probe function in reverse
- * order.
- *
- * Notes:
- *
- * The device may have been partially initialized, so double check
- * that the allocations happened.
- *
- * This function may be called multiple times, so mark resources as freed
- * as they are deallocated.
- */
-static void vsoc_remove_device(struct pci_dev *pdev)
-{
- int i;
- /*
- * pdev is the first thing to be set on probe and the last thing
- * to be cleared here. If it's NULL then there is no cleanup.
- */
- if (!pdev || !vsoc_dev.dev)
- return;
- dev_info(&pdev->dev, "remove_device\n");
- if (vsoc_dev.regions_data) {
- for (i = 0; i < vsoc_dev.layout->region_count; ++i) {
- if (vsoc_dev.regions_data[i].device_created) {
- device_destroy(vsoc_dev.class,
- MKDEV(vsoc_dev.major, i));
- vsoc_dev.regions_data[i].device_created = false;
- }
- if (vsoc_dev.regions_data[i].irq_requested)
- free_irq(vsoc_dev.msix_entries[i].vector, NULL);
- vsoc_dev.regions_data[i].irq_requested = false;
- }
- kfree(vsoc_dev.regions_data);
- vsoc_dev.regions_data = NULL;
- }
- if (vsoc_dev.msix_enabled) {
- pci_disable_msix(pdev);
- vsoc_dev.msix_enabled = false;
- }
- kfree(vsoc_dev.msix_entries);
- vsoc_dev.msix_entries = NULL;
- vsoc_dev.regions = NULL;
- if (vsoc_dev.class_added) {
- class_destroy(vsoc_dev.class);
- vsoc_dev.class_added = false;
- }
- if (vsoc_dev.cdev_added) {
- cdev_del(&vsoc_dev.cdev);
- vsoc_dev.cdev_added = false;
- }
- if (vsoc_dev.major && vsoc_dev.layout) {
- unregister_chrdev_region(MKDEV(vsoc_dev.major, 0),
- vsoc_dev.layout->region_count);
- vsoc_dev.major = 0;
- }
- vsoc_dev.layout = NULL;
- if (vsoc_dev.kernel_mapped_shm) {
- pci_iounmap(pdev, vsoc_dev.kernel_mapped_shm);
- vsoc_dev.kernel_mapped_shm = NULL;
- }
- if (vsoc_dev.regs) {
- pci_iounmap(pdev, vsoc_dev.regs);
- vsoc_dev.regs = NULL;
- }
- if (vsoc_dev.requested_regions) {
- pci_release_regions(pdev);
- vsoc_dev.requested_regions = false;
- }
- if (vsoc_dev.enabled_device) {
- pci_disable_device(pdev);
- vsoc_dev.enabled_device = false;
- }
- /* Do this last: it indicates that the device is not initialized. */
- vsoc_dev.dev = NULL;
-}
-
-static void __exit vsoc_cleanup_module(void)
-{
- vsoc_remove_device(vsoc_dev.dev);
- pci_unregister_driver(&vsoc_pci_driver);
-}
-
-static int __init vsoc_init_module(void)
-{
- int err = -ENOMEM;
-
- INIT_LIST_HEAD(&vsoc_dev.permissions);
- mutex_init(&vsoc_dev.mtx);
-
- err = pci_register_driver(&vsoc_pci_driver);
- if (err < 0)
- return err;
- return 0;
-}
-
-static int vsoc_open(struct inode *inode, struct file *filp)
-{
- /* Can't use vsoc_validate_filep because filp is still incomplete */
- int ret = vsoc_validate_inode(inode);
-
- if (ret)
- return ret;
- filp->private_data =
- kzalloc(sizeof(struct vsoc_private_data), GFP_KERNEL);
- if (!filp->private_data)
- return -ENOMEM;
- return 0;
-}
-
-static int vsoc_release(struct inode *inode, struct file *filp)
-{
- struct vsoc_private_data *private_data = NULL;
- struct fd_scoped_permission_node *node = NULL;
- struct vsoc_device_region *owner_region_p = NULL;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- private_data = (struct vsoc_private_data *)filp->private_data;
- if (!private_data)
- return 0;
-
- node = private_data->fd_scoped_permission_node;
- if (node) {
- owner_region_p = vsoc_region_from_inode(inode);
- if (owner_region_p->managed_by != VSOC_REGION_WHOLE) {
- owner_region_p =
- &vsoc_dev.regions[owner_region_p->managed_by];
- }
- do_destroy_fd_scoped_permission_node(owner_region_p, node);
- private_data->fd_scoped_permission_node = NULL;
- }
- kfree(private_data);
- filp->private_data = NULL;
-
- return 0;
-}
-
-/*
- * Returns the device relative offset and length of the area specified by the
- * fd scoped permission. If there is no fd scoped permission set, a default
- * permission covering the entire region is assumed, unless the region is owned
- * by another one, in which case the default is a permission with zero size.
- */
-static ssize_t vsoc_get_area(struct file *filp, __u32 *area_offset)
-{
- __u32 off = 0;
- ssize_t length = 0;
- struct vsoc_device_region *region_p;
- struct fd_scoped_permission *perm;
-
- region_p = vsoc_region_from_filep(filp);
- off = region_p->region_begin_offset;
- perm = &((struct vsoc_private_data *)filp->private_data)->
- fd_scoped_permission_node->permission;
- if (perm) {
- off += perm->begin_offset;
- length = perm->end_offset - perm->begin_offset;
- } else if (region_p->managed_by == VSOC_REGION_WHOLE) {
- /* No permission set and the regions is not owned by another,
- * default to full region access.
- */
- length = vsoc_device_region_size(region_p);
- } else {
- /* return zero length, access is denied. */
- length = 0;
- }
- if (area_offset)
- *area_offset = off;
- return length;
-}
-
-static int vsoc_mmap(struct file *filp, struct vm_area_struct *vma)
-{
- unsigned long len = vma->vm_end - vma->vm_start;
- __u32 area_off;
- phys_addr_t mem_off;
- ssize_t area_len;
- int retval = vsoc_validate_filep(filp);
-
- if (retval)
- return retval;
- area_len = vsoc_get_area(filp, &area_off);
- /* Add the requested offset */
- area_off += (vma->vm_pgoff << PAGE_SHIFT);
- area_len -= (vma->vm_pgoff << PAGE_SHIFT);
- if (area_len < len)
- return -EINVAL;
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- mem_off = shm_off_to_phys_addr(area_off);
- if (io_remap_pfn_range(vma, vma->vm_start, mem_off >> PAGE_SHIFT,
- len, vma->vm_page_prot))
- return -EAGAIN;
- return 0;
-}
-
-module_init(vsoc_init_module);
-module_exit(vsoc_cleanup_module);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Greg Hartman <ghartman@google.com>");
-MODULE_DESCRIPTION("VSoC interpretation of QEmu's ivshmem device");
-MODULE_VERSION("1.0");
list_for_each_entry_safe(module, next, &modules_list, list) {
list_del(&module->list);
- kobject_put(&module->kobj);
ida_simple_remove(&module_id, module->id);
+ kobject_put(&module->kobj);
}
is_empty = list_empty(&modules_list);
struct ieee_param *param;
uint ret = 0;
- if (p->length < sizeof(struct ieee_param) || !p->pointer) {
- ret = -EINVAL;
- goto out;
- }
+ if (!p->pointer || p->length != sizeof(struct ieee_param))
+ return -EINVAL;
param = (struct ieee_param *)rtw_malloc(p->length);
- if (!param) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!param)
+ return -ENOMEM;
if (copy_from_user(param, p->pointer, p->length)) {
kfree(param);
- ret = -EFAULT;
- goto out;
+ return -EFAULT;
}
switch (param->cmd) {
ret = -EFAULT;
kfree(param);
-
-out:
-
return ret;
}
* so, we just check hw_init_completed
*/
- if (!padapter->hw_init_completed) {
- ret = -EPERM;
- goto out;
- }
+ if (!padapter->hw_init_completed)
+ return -EPERM;
- if (!p->pointer) {
- ret = -EINVAL;
- goto out;
- }
+ if (!p->pointer || p->length != sizeof(struct ieee_param))
+ return -EINVAL;
param = (struct ieee_param *)rtw_malloc(p->length);
- if (!param) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!param)
+ return -ENOMEM;
if (copy_from_user(param, p->pointer, p->length)) {
kfree(param);
- ret = -EFAULT;
- goto out;
+ return -EFAULT;
}
switch (param->cmd) {
if (ret == 0 && copy_to_user(p->pointer, param, p->length))
ret = -EFAULT;
kfree(param);
-out:
return ret;
}
#endif
s32 ret;
struct adapter *padapter;
struct xmit_priv *pxmitpriv;
- u8 thread_name[20] = "RTWHALXT";
-
+ u8 thread_name[20];
ret = _SUCCESS;
padapter = context;
pxmitpriv = &padapter->xmitpriv;
- rtw_sprintf(thread_name, 20, "%s-"ADPT_FMT, thread_name, ADPT_ARG(padapter));
+ rtw_sprintf(thread_name, 20, "RTWHALXT-" ADPT_FMT, ADPT_ARG(padapter));
thread_enter(thread_name);
DBG_871X("start "FUNC_ADPT_FMT"\n", FUNC_ADPT_ARG(padapter));
/* down(&ieee->wx_sem); */
- if (p->length < sizeof(struct ieee_param) || !p->pointer) {
- ret = -EINVAL;
- goto out;
- }
+ if (!p->pointer || p->length != sizeof(struct ieee_param))
+ return -EINVAL;
param = rtw_malloc(p->length);
- if (param == NULL) {
- ret = -ENOMEM;
- goto out;
- }
+ if (param == NULL)
+ return -ENOMEM;
if (copy_from_user(param, p->pointer, p->length)) {
kfree(param);
- ret = -EFAULT;
- goto out;
+ return -EFAULT;
}
switch (param->cmd) {
kfree(param);
-out:
-
/* up(&ieee->wx_sem); */
-
return ret;
-
}
static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len)
* so, we just check hw_init_completed
*/
- if (!padapter->hw_init_completed) {
- ret = -EPERM;
- goto out;
- }
-
+ if (!padapter->hw_init_completed)
+ return -EPERM;
- /* if (p->length < sizeof(struct ieee_param) || !p->pointer) { */
- if (!p->pointer) {
- ret = -EINVAL;
- goto out;
- }
+ if (!p->pointer || p->length != sizeof(*param))
+ return -EINVAL;
param = rtw_malloc(p->length);
- if (param == NULL) {
- ret = -ENOMEM;
- goto out;
- }
+ if (param == NULL)
+ return -ENOMEM;
if (copy_from_user(param, p->pointer, p->length)) {
kfree(param);
- ret = -EFAULT;
- goto out;
+ return -EFAULT;
}
/* DBG_871X("%s, cmd =%d\n", __func__, param->cmd); */
if (ret == 0 && copy_to_user(p->pointer, param, p->length))
ret = -EFAULT;
-
kfree(param);
-
-out:
-
return ret;
-
}
static int rtw_wx_set_priv(struct net_device *dev,
vnt_rf_rssi_to_dbm(priv, tail->rssi, &rx_dbm);
- priv->bb_pre_ed_rssi = (u8)rx_dbm + 1;
+ priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1;
priv->current_rssi = priv->bb_pre_ed_rssi;
skb_pull(skb, sizeof(*head));
hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length,
conn->cid);
- if (target_get_sess_cmd(&cmd->se_cmd, true) < 0)
- return iscsit_add_reject_cmd(cmd,
- ISCSI_REASON_WAITING_FOR_LOGOUT, buf);
+ target_get_sess_cmd(&cmd->se_cmd, true);
cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd,
scsilun_to_int(&hdr->lun));
conn->sess->se_sess, 0, DMA_NONE,
TCM_SIMPLE_TAG, cmd->sense_buffer + 2);
- if (target_get_sess_cmd(&cmd->se_cmd, true) < 0)
- return iscsit_add_reject_cmd(cmd,
- ISCSI_REASON_WAITING_FOR_LOGOUT, buf);
+ target_get_sess_cmd(&cmd->se_cmd, true);
/*
* TASK_REASSIGN for ERL=2 / connection stays inside of
iscsit_stop_nopin_response_timer(conn);
iscsit_stop_nopin_timer(conn);
+ if (conn->conn_transport->iscsit_wait_conn)
+ conn->conn_transport->iscsit_wait_conn(conn);
+
/*
* During Connection recovery drop unacknowledged out of order
* commands for this connection, and prepare the other commands
* must wait until they have completed.
*/
iscsit_check_conn_usage_count(conn);
- target_sess_cmd_list_set_waiting(sess->se_sess);
- target_wait_for_sess_cmds(sess->se_sess);
-
- if (conn->conn_transport->iscsit_wait_conn)
- conn->conn_transport->iscsit_wait_conn(conn);
ahash_request_free(conn->conn_tx_hash);
if (conn->conn_rx_hash) {
target_remove_from_state_list(cmd);
+ /*
+ * Clear struct se_cmd->se_lun before the handoff to FE.
+ */
+ cmd->se_lun = NULL;
+
spin_lock_irqsave(&cmd->t_state_lock, flags);
/*
* Determine if frontend context caller is requesting the stopping of
return cmd->se_tfo->check_stop_free(cmd);
}
+static void transport_lun_remove_cmd(struct se_cmd *cmd)
+{
+ struct se_lun *lun = cmd->se_lun;
+
+ if (!lun)
+ return;
+
+ if (cmpxchg(&cmd->lun_ref_active, true, false))
+ percpu_ref_put(&lun->lun_ref);
+}
+
static void target_complete_failure_work(struct work_struct *work)
{
struct se_cmd *cmd = container_of(work, struct se_cmd, work);
WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0);
+ transport_lun_remove_cmd(cmd);
+
transport_cmd_check_stop_to_fabric(cmd);
}
se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST;
se_cmd->se_tfo->queue_tm_rsp(se_cmd);
+ transport_lun_remove_cmd(se_cmd);
transport_cmd_check_stop_to_fabric(se_cmd);
}
goto queue_full;
check_stop:
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
return;
transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
return;
}
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
}
if (ret)
goto queue_full;
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
return;
}
if (ret)
goto queue_full;
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
return;
}
if (ret)
goto queue_full;
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
return;
}
break;
}
+ transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
return;
*/
if (cmd->state_active)
target_remove_from_state_list(cmd);
+
+ if (cmd->se_lun)
+ transport_lun_remove_cmd(cmd);
}
if (aborted)
cmd->free_compl = &compl;
struct completion *abrt_compl = se_cmd->abrt_compl;
unsigned long flags;
- if (se_cmd->lun_ref_active)
- percpu_ref_put(&se_cmd->se_lun->lun_ref);
-
if (se_sess) {
spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
list_del_init(&se_cmd->se_cmd_list);
config AMDTEE
tristate "AMD-TEE"
default m
- depends on CRYPTO_DEV_SP_PSP
+ depends on CRYPTO_DEV_SP_PSP && CRYPTO_DEV_CCP_DD
help
This implements AMD's Trusted Execution Environment (TEE) driver.
unsigned long state)
{
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+ struct cpumask *cpus;
+ unsigned int frequency;
+ unsigned long max_capacity, capacity;
+ int ret;
/* Request state should be less than max_level */
if (WARN_ON(state > cpufreq_cdev->max_level))
cpufreq_cdev->cpufreq_state = state;
- return freq_qos_update_request(&cpufreq_cdev->qos_req,
- get_state_freq(cpufreq_cdev, state));
+ frequency = get_state_freq(cpufreq_cdev, state);
+
+ ret = freq_qos_update_request(&cpufreq_cdev->qos_req, frequency);
+
+ if (ret > 0) {
+ cpus = cpufreq_cdev->policy->cpus;
+ max_capacity = arch_scale_cpu_capacity(cpumask_first(cpus));
+ capacity = frequency * max_capacity;
+ capacity /= cpufreq_cdev->policy->cpuinfo.max_freq;
+ arch_set_thermal_pressure(cpus, max_capacity - capacity);
+ }
+
+ return ret;
}
/* Bind cpufreq callbacks to thermal cooling device ops */
return ret;
}
+static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val,
+ size_t bytes)
+{
+ return -EPERM;
+}
+
static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val,
size_t bytes)
{
config.read_only = true;
} else {
config.name = "nvm_non_active";
+ config.reg_read = tb_switch_nvm_no_read;
config.reg_write = tb_switch_nvm_write;
config.root_only = true;
}
struct device *parent,
struct tty_driver *drv, int idx)
{
- const struct tty_port_client_operations *old_ops;
struct serdev_controller *ctrl;
struct serport *serport;
int ret;
ctrl->ops = &ctrl_ops;
- old_ops = port->client_ops;
port->client_ops = &client_ops;
port->client_data = ctrl;
err_reset_data:
port->client_data = NULL;
- port->client_ops = old_ops;
+ port->client_ops = &tty_port_default_client_ops;
serdev_controller_put(ctrl);
return ERR_PTR(ret);
return -ENODEV;
serdev_controller_remove(ctrl);
- port->client_ops = NULL;
port->client_data = NULL;
+ port->client_ops = &tty_port_default_client_ops;
serdev_controller_put(ctrl);
return 0;
port.port.line = rc;
port.port.irq = irq_of_parse_and_map(np, 0);
- port.port.irqflags = IRQF_SHARED;
port.port.handle_irq = aspeed_vuart_handle_irq;
port.port.iotype = UPIO_MEM;
port.port.type = PORT_16550A;
struct hlist_head *h;
struct hlist_node *n;
struct irq_info *i;
- int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0;
+ int ret;
mutex_lock(&hash_mutex);
INIT_LIST_HEAD(&up->list);
i->head = &up->list;
spin_unlock_irq(&i->lock);
- irq_flags |= up->port.irqflags;
ret = request_irq(up->port.irq, serial8250_interrupt,
- irq_flags, up->port.name, i);
+ up->port.irqflags, up->port.name, i);
if (ret < 0)
serial_do_unlink(i, up);
}
port->type = type;
port->uartclk = clk;
- port->irqflags |= IRQF_SHARED;
if (of_property_read_bool(np, "no-loopback-test"))
port->flags |= UPF_SKIP_TEST;
}
}
+ /* Check if we need to have shared IRQs */
+ if (port->irq && (up->port.flags & UPF_SHARE_IRQ))
+ up->port.irqflags |= IRQF_SHARED;
+
if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) {
unsigned char iir1;
/*
ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
AR933X_UART_CS_HOST_INT_EN);
+ /* enable RX and TX ready overide */
+ ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
+ AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE);
+
/* reenable the UART */
ar933x_uart_rmw(up, AR933X_UART_CS_REG,
AR933X_UART_CS_IF_MODE_M << AR933X_UART_CS_IF_MODE_S,
ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
AR933X_UART_CS_HOST_INT_EN);
+ /* enable RX and TX ready overide */
+ ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
+ AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE);
+
/* Enable RX interrupts */
up->ier = AR933X_UART_INT_RX_VALID;
ar933x_uart_write(up, AR933X_UART_INT_EN_REG, up->ier);
atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
if (atmel_uart_is_half_duplex(port))
- atmel_start_rx(port);
+ if (!atomic_read(&atmel_port->tasklet_shutdown))
+ atmel_start_rx(port);
}
static int __init cpm_uart_console_init(void)
{
+ cpm_muram_init();
register_console(&cpm_scc_uart_console);
return 0;
}
sport->tx_bytes = uart_circ_chars_pending(xmit);
- if (xmit->tail < xmit->head) {
+ if (xmit->tail < xmit->head || xmit->head == 0) {
sport->dma_tx_nents = 1;
sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes);
} else {
static int handle_rx_uart(struct uart_port *uport, u32 bytes, bool drop);
static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port);
static void qcom_geni_serial_stop_rx(struct uart_port *uport);
+static void qcom_geni_serial_handle_rx(struct uart_port *uport, bool drop);
static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200,
32000000, 48000000, 64000000, 80000000,
u32 irq_en;
u32 status;
struct qcom_geni_serial_port *port = to_dev_port(uport, uport);
- u32 irq_clear = S_CMD_DONE_EN;
+ u32 s_irq_status;
irq_en = readl(uport->membase + SE_GENI_S_IRQ_EN);
irq_en &= ~(S_RX_FIFO_WATERMARK_EN | S_RX_FIFO_LAST_EN);
return;
geni_se_cancel_s_cmd(&port->se);
- qcom_geni_serial_poll_bit(uport, SE_GENI_S_CMD_CTRL_REG,
- S_GENI_CMD_CANCEL, false);
+ qcom_geni_serial_poll_bit(uport, SE_GENI_S_IRQ_STATUS,
+ S_CMD_CANCEL_EN, true);
+ /*
+ * If timeout occurs secondary engine remains active
+ * and Abort sequence is executed.
+ */
+ s_irq_status = readl(uport->membase + SE_GENI_S_IRQ_STATUS);
+ /* Flush the Rx buffer */
+ if (s_irq_status & S_RX_FIFO_LAST_EN)
+ qcom_geni_serial_handle_rx(uport, true);
+ writel(s_irq_status, uport->membase + SE_GENI_S_IRQ_CLEAR);
+
status = readl(uport->membase + SE_GENI_STATUS);
- writel(irq_clear, uport->membase + SE_GENI_S_IRQ_CLEAR);
if (status & S_GENI_CMD_ACTIVE)
qcom_geni_serial_abort_rx(uport);
}
count, DMA_TO_DEVICE);
}
+static void do_handle_rx_pio(struct tegra_uart_port *tup)
+{
+ struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port);
+ struct tty_port *port = &tup->uport.state->port;
+
+ tegra_uart_handle_rx_pio(tup, port);
+ if (tty) {
+ tty_flip_buffer_push(port);
+ tty_kref_put(tty);
+ }
+}
+
static void tegra_uart_rx_buffer_push(struct tegra_uart_port *tup,
unsigned int residue)
{
struct tty_port *port = &tup->uport.state->port;
- struct tty_struct *tty = tty_port_tty_get(port);
unsigned int count;
async_tx_ack(tup->rx_dma_desc);
/* If we are here, DMA is stopped */
tegra_uart_copy_rx_to_tty(tup, port, count);
- tegra_uart_handle_rx_pio(tup, port);
- if (tty) {
- tty_flip_buffer_push(port);
- tty_kref_put(tty);
- }
+ do_handle_rx_pio(tup);
}
static void tegra_uart_rx_dma_complete(void *args)
{
struct dma_tx_state state;
- if (!tup->rx_dma_active)
+ if (!tup->rx_dma_active) {
+ do_handle_rx_pio(tup);
return;
+ }
dmaengine_terminate_all(tup->rx_dma_chan);
dmaengine_tx_status(tup->rx_dma_chan, tup->rx_cookie, &state);
uart_handle_cts_change(&tup->uport, msr & UART_MSR_CTS);
}
-static void do_handle_rx_pio(struct tegra_uart_port *tup)
-{
- struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port);
- struct tty_port *port = &tup->uport.state->port;
-
- tegra_uart_handle_rx_pio(tup, port);
- if (tty) {
- tty_flip_buffer_push(port);
- tty_kref_put(tty);
- }
-}
-
static irqreturn_t tegra_uart_isr(int irq, void *data)
{
struct tegra_uart_port *tup = data;
}
}
-static const struct tty_port_client_operations default_client_ops = {
+const struct tty_port_client_operations tty_port_default_client_ops = {
.receive_buf = tty_port_default_receive_buf,
.write_wakeup = tty_port_default_wakeup,
};
+EXPORT_SYMBOL_GPL(tty_port_default_client_ops);
void tty_port_init(struct tty_port *port)
{
spin_lock_init(&port->lock);
port->close_delay = (50 * HZ) / 100;
port->closing_wait = (3000 * HZ) / 100;
- port->client_ops = &default_client_ops;
+ port->client_ops = &tty_port_default_client_ops;
kref_init(&port->kref);
}
EXPORT_SYMBOL(tty_port_init);
#include <linux/tty.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/console.h>
#include <linux/tty_flip.h>
+#include <linux/sched/signal.h>
+
/* Don't take this from <ctype.h>: 011-015 on the screen aren't spaces */
#define isspace(c) ((c) == ' ')
static int sel_end;
static int sel_buffer_lth;
static char *sel_buffer;
+static DEFINE_MUTEX(sel_lock);
/* clear_selection, highlight and highlight_pointer can be called
from interrupt (via scrollback/front) */
char *bp, *obp;
int i, ps, pe, multiplier;
u32 c;
- int mode;
+ int mode, ret = 0;
poke_blanked_console();
if (ps > pe) /* make sel_start <= sel_end */
swap(ps, pe);
+ mutex_lock(&sel_lock);
if (sel_cons != vc_cons[fg_console].d) {
clear_selection();
sel_cons = vc_cons[fg_console].d;
break;
case TIOCL_SELPOINTER:
highlight_pointer(pe);
- return 0;
+ goto unlock;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
/* remove the pointer */
else if (new_sel_start == sel_start)
{
if (new_sel_end == sel_end) /* no action required */
- return 0;
+ goto unlock;
else if (new_sel_end > sel_end) /* extend to right */
highlight(sel_end + 2, new_sel_end);
else /* contract from right */
if (!bp) {
printk(KERN_WARNING "selection: kmalloc() failed\n");
clear_selection();
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto unlock;
}
kfree(sel_buffer);
sel_buffer = bp;
}
}
sel_buffer_lth = bp - sel_buffer;
- return 0;
+unlock:
+ mutex_unlock(&sel_lock);
+ return ret;
}
EXPORT_SYMBOL_GPL(set_selection_kernel);
unsigned int count;
struct tty_ldisc *ld;
DECLARE_WAITQUEUE(wait, current);
+ int ret = 0;
console_lock();
poke_blanked_console();
tty_buffer_lock_exclusive(&vc->port);
add_wait_queue(&vc->paste_wait, &wait);
+ mutex_lock(&sel_lock);
while (sel_buffer && sel_buffer_lth > pasted) {
set_current_state(TASK_INTERRUPTIBLE);
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
if (tty_throttled(tty)) {
+ mutex_unlock(&sel_lock);
schedule();
+ mutex_lock(&sel_lock);
continue;
}
__set_current_state(TASK_RUNNING);
count);
pasted += count;
}
+ mutex_unlock(&sel_lock);
remove_wait_queue(&vc->paste_wait, &wait);
__set_current_state(TASK_RUNNING);
tty_buffer_unlock_exclusive(&vc->port);
tty_ldisc_deref(ld);
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(paste_selection);
WARN_CONSOLE_UNLOCKED();
set_origin(vc);
- if (vc->vc_sw->con_flush_scrollback)
+ if (vc->vc_sw->con_flush_scrollback) {
vc->vc_sw->con_flush_scrollback(vc);
- else
+ } else if (con_is_visible(vc)) {
+ /*
+ * When no con_flush_scrollback method is provided then the
+ * legacy way for flushing the scrollback buffer is to use
+ * a side effect of the con_switch method. We do it only on
+ * the foreground console as background consoles have no
+ * scrollback buffers in that case and we obviously don't
+ * want to switch to them.
+ */
+ hide_cursor(vc);
vc->vc_sw->con_switch(vc);
+ set_cursor(vc);
+ }
}
/*
return -EINVAL;
for (i = 0; i < MAX_NR_CONSOLES; i++) {
+ struct vc_data *vcp;
+
if (!vc_cons[i].d)
continue;
console_lock();
- if (v.v_vlin)
- vc_cons[i].d->vc_scan_lines = v.v_vlin;
- if (v.v_clin)
- vc_cons[i].d->vc_font.height = v.v_clin;
- vc_cons[i].d->vc_resize_user = 1;
- vc_resize(vc_cons[i].d, v.v_cols, v.v_rows);
+ vcp = vc_cons[i].d;
+ if (vcp) {
+ if (v.v_vlin)
+ vcp->vc_scan_lines = v.v_vlin;
+ if (v.v_clin)
+ vcp->vc_font.height = v.v_clin;
+ vcp->vc_resize_user = 1;
+ vc_resize(vcp, v.v_cols, v.v_rows);
+ }
console_unlock();
}
break;
struct usb_host_interface *ifp, int num_ep,
unsigned char *buffer, int size)
{
+ struct usb_device *udev = to_usb_device(ddev);
unsigned char *buffer0 = buffer;
struct usb_endpoint_descriptor *d;
struct usb_host_endpoint *endpoint;
goto skip_to_next_endpoint_or_interface_descriptor;
}
+ /* Ignore blacklisted endpoints */
+ if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) {
+ if (usb_endpoint_is_blacklisted(udev, ifp, d)) {
+ dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n",
+ cfgno, inum, asnum,
+ d->bEndpointAddress);
+ goto skip_to_next_endpoint_or_interface_descriptor;
+ }
+ }
+
endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
++ifp->desc.bNumEndpoints;
j = 255;
if (usb_endpoint_xfer_int(d)) {
i = 1;
- switch (to_usb_device(ddev)->speed) {
+ switch (udev->speed) {
case USB_SPEED_SUPER_PLUS:
case USB_SPEED_SUPER:
case USB_SPEED_HIGH:
/*
* This quirk fixes bIntervals reported in ms.
*/
- if (to_usb_device(ddev)->quirks &
- USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
+ if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
n = clamp(fls(d->bInterval) + 3, i, j);
i = j = n;
}
* This quirk fixes bIntervals reported in
* linear microframes.
*/
- if (to_usb_device(ddev)->quirks &
- USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) {
+ if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) {
n = clamp(fls(d->bInterval), i, j);
i = j = n;
}
} else if (usb_endpoint_xfer_isoc(d)) {
i = 1;
j = 16;
- switch (to_usb_device(ddev)->speed) {
+ switch (udev->speed) {
case USB_SPEED_HIGH:
n = 7; /* 8 ms = 2^(7-1) uframes */
break;
* explicitly forbidden by the USB spec. In an attempt to make
* them usable, we will try treating them as Interrupt endpoints.
*/
- if (to_usb_device(ddev)->speed == USB_SPEED_LOW &&
- usb_endpoint_xfer_bulk(d)) {
+ if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) {
dev_warn(ddev, "config %d interface %d altsetting %d "
"endpoint 0x%X is Bulk; changing to Interrupt\n",
cfgno, inum, asnum, d->bEndpointAddress);
/* Find the highest legal maxpacket size for this endpoint */
i = 0; /* additional transactions per microframe */
- switch (to_usb_device(ddev)->speed) {
+ switch (udev->speed) {
case USB_SPEED_LOW:
maxpacket_maxes = low_speed_maxpacket_maxes;
break;
* maxpacket sizes other than 512. High speed HCDs may not
* be able to handle that particular bug, so let's warn...
*/
- if (to_usb_device(ddev)->speed == USB_SPEED_HIGH
- && usb_endpoint_xfer_bulk(d)) {
+ if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) {
if (maxp != 512)
dev_warn(ddev, "config %d interface %d altsetting %d "
"bulk endpoint 0x%X has invalid maxpacket %d\n",
}
/* Parse a possible SuperSpeed endpoint companion descriptor */
- if (to_usb_device(ddev)->speed >= USB_SPEED_SUPER)
+ if (udev->speed >= USB_SPEED_SUPER)
usb_parse_ss_endpoint_companion(ddev, cfgno,
inum, asnum, endpoint, buffer, size);
#include "otg_whitelist.h"
#define USB_VENDOR_GENESYS_LOGIC 0x05e3
+#define USB_VENDOR_SMSC 0x0424
#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02
#define USB_TP_TRANSMISSION_DELAY 40 /* ns */
#define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */
#ifdef CONFIG_PM
udev->reset_resume = 1;
#endif
- /* Don't set the change_bits when the device
- * was powered off.
- */
- if (test_bit(port1, hub->power_bits))
- set_bit(port1, hub->change_bits);
} else {
/* The power session is gone; tell hub_wq */
kfree(hub->buffer);
pm_suspend_ignore_children(&intf->dev, false);
+
+ if (hub->quirk_disable_autosuspend)
+ usb_autopm_put_interface(intf);
+
kref_put(&hub->kref, hub_release);
}
if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND)
hub->quirk_check_port_auto_suspend = 1;
+ if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) {
+ hub->quirk_disable_autosuspend = 1;
+ usb_autopm_get_interface(intf);
+ }
+
if (hub_configure(hub, &desc->endpoint[0].desc) >= 0)
return 0;
}
static const struct usb_device_id hub_id_table[] = {
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS,
+ .idVendor = USB_VENDOR_SMSC,
+ .bInterfaceClass = USB_CLASS_HUB,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
| USB_DEVICE_ID_MATCH_INT_CLASS,
.idVendor = USB_VENDOR_GENESYS_LOGIC,
unsigned quiescing:1;
unsigned disconnected:1;
unsigned in_reset:1;
+ unsigned quirk_disable_autosuspend:1;
unsigned quirk_check_port_auto_suspend:1;
{ USB_DEVICE(0x0904, 0x6103), .driver_info =
USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+ /* Sound Devices USBPre2 */
+ { USB_DEVICE(0x0926, 0x0202), .driver_info =
+ USB_QUIRK_ENDPOINT_BLACKLIST },
+
/* Keytouch QWERTY Panel keyboard */
{ USB_DEVICE(0x0926, 0x3333), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
/* INTEL VALUE SSD */
{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* novation SoundControl XL */
+ { USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME },
+
{ } /* terminating entry must be last */
};
{ } /* terminating entry must be last */
};
+/*
+ * Entries for blacklisted endpoints that should be ignored when parsing
+ * configuration descriptors.
+ *
+ * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST.
+ */
+static const struct usb_device_id usb_endpoint_blacklist[] = {
+ { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
+ { }
+};
+
+bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+ struct usb_host_interface *intf,
+ struct usb_endpoint_descriptor *epd)
+{
+ const struct usb_device_id *id;
+ unsigned int address;
+
+ for (id = usb_endpoint_blacklist; id->match_flags; ++id) {
+ if (!usb_match_device(udev, id))
+ continue;
+
+ if (!usb_match_one_id_intf(udev, intf, id))
+ continue;
+
+ address = id->driver_info;
+ if (address == epd->bEndpointAddress)
+ return true;
+ }
+
+ return false;
+}
+
static bool usb_match_any_interface(struct usb_device *udev,
const struct usb_device_id *id)
{
extern void usb_detect_quirks(struct usb_device *udev);
extern void usb_detect_interface_quirks(struct usb_device *udev);
extern void usb_release_quirk_list(void);
+extern bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+ struct usb_host_interface *intf,
+ struct usb_endpoint_descriptor *epd);
extern int usb_remove_device(struct usb_device *udev);
extern int usb_get_device_descriptor(struct usb_device *dev,
else
packets = 1; /* send one packet if length is zero. */
- if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
- dev_err(hsotg->dev, "req length > maxpacket*mc\n");
- return;
- }
-
if (dir_in && index != 0)
if (hs_ep->isochronous)
epsize = DXEPTSIZ_MC(packets);
req->actual = 0;
req->status = -EINPROGRESS;
+ /* Don't queue ISOC request if length greater than mps*mc */
+ if (hs_ep->isochronous &&
+ req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
+ dev_err(hs->dev, "req length > maxpacket*mc\n");
+ return -EINVAL;
+ }
+
/* In DDMA mode for ISOC's don't queue request if length greater
* than descriptor limits.
*/
struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0];
struct dwc2_hsotg_ep *ep;
__le16 reply;
+ u16 status;
int ret;
dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__);
switch (ctrl->bRequestType & USB_RECIP_MASK) {
case USB_RECIP_DEVICE:
- /*
- * bit 0 => self powered
- * bit 1 => remote wakeup
- */
- reply = cpu_to_le16(0);
+ status = 1 << USB_DEVICE_SELF_POWERED;
+ status |= hsotg->remote_wakeup_allowed <<
+ USB_DEVICE_REMOTE_WAKEUP;
+ reply = cpu_to_le16(status);
break;
case USB_RECIP_INTERFACE:
case USB_RECIP_DEVICE:
switch (wValue) {
case USB_DEVICE_REMOTE_WAKEUP:
- hsotg->remote_wakeup_allowed = 1;
+ if (set)
+ hsotg->remote_wakeup_allowed = 1;
+ else
+ hsotg->remote_wakeup_allowed = 0;
break;
case USB_DEVICE_TEST_MODE:
return -EINVAL;
hsotg->test_mode = wIndex >> 8;
- ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
- if (ret) {
- dev_err(hsotg->dev,
- "%s: failed to send reply\n", __func__);
- return ret;
- }
break;
default:
return -ENOENT;
}
+
+ ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
+ if (ret) {
+ dev_err(hsotg->dev,
+ "%s: failed to send reply\n", __func__);
+ return ret;
+ }
break;
case USB_RECIP_ENDPOINT:
u8 epnum = event->endpoint_number;
size_t len;
int status;
- int ret;
- ret = snprintf(str, size, "ep%d%s: ", epnum >> 1,
+ len = scnprintf(str, size, "ep%d%s: ", epnum >> 1,
(epnum & 1) ? "in" : "out");
- if (ret < 0)
- return "UNKNOWN";
status = event->status;
switch (event->endpoint_event) {
case DWC3_DEPEVT_XFERCOMPLETE:
- len = strlen(str);
- snprintf(str + len, size - len, "Transfer Complete (%c%c%c)",
+ len += scnprintf(str + len, size - len,
+ "Transfer Complete (%c%c%c)",
status & DEPEVT_STATUS_SHORT ? 'S' : 's',
status & DEPEVT_STATUS_IOC ? 'I' : 'i',
status & DEPEVT_STATUS_LST ? 'L' : 'l');
- len = strlen(str);
-
if (epnum <= 1)
- snprintf(str + len, size - len, " [%s]",
+ scnprintf(str + len, size - len, " [%s]",
dwc3_ep0_state_string(ep0state));
break;
case DWC3_DEPEVT_XFERINPROGRESS:
- len = strlen(str);
-
- snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)",
+ scnprintf(str + len, size - len,
+ "Transfer In Progress [%d] (%c%c%c)",
event->parameters,
status & DEPEVT_STATUS_SHORT ? 'S' : 's',
status & DEPEVT_STATUS_IOC ? 'I' : 'i',
status & DEPEVT_STATUS_LST ? 'M' : 'm');
break;
case DWC3_DEPEVT_XFERNOTREADY:
- len = strlen(str);
-
- snprintf(str + len, size - len, "Transfer Not Ready [%d]%s",
+ len += scnprintf(str + len, size - len,
+ "Transfer Not Ready [%d]%s",
event->parameters,
status & DEPEVT_STATUS_TRANSFER_ACTIVE ?
" (Active)" : " (Not Active)");
- len = strlen(str);
-
/* Control Endpoints */
if (epnum <= 1) {
int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status);
switch (phase) {
case DEPEVT_STATUS_CONTROL_DATA:
- snprintf(str + ret, size - ret,
+ scnprintf(str + len, size - len,
" [Data Phase]");
break;
case DEPEVT_STATUS_CONTROL_STATUS:
- snprintf(str + ret, size - ret,
+ scnprintf(str + len, size - len,
" [Status Phase]");
}
}
break;
case DWC3_DEPEVT_RXTXFIFOEVT:
- snprintf(str + ret, size - ret, "FIFO");
+ scnprintf(str + len, size - len, "FIFO");
break;
case DWC3_DEPEVT_STREAMEVT:
status = event->status;
switch (status) {
case DEPEVT_STREAMEVT_FOUND:
- snprintf(str + ret, size - ret, " Stream %d Found",
+ scnprintf(str + len, size - len, " Stream %d Found",
event->parameters);
break;
case DEPEVT_STREAMEVT_NOTFOUND:
default:
- snprintf(str + ret, size - ret, " Stream Not Found");
+ scnprintf(str + len, size - len, " Stream Not Found");
break;
}
break;
case DWC3_DEPEVT_EPCMDCMPLT:
- snprintf(str + ret, size - ret, "Endpoint Command Complete");
+ scnprintf(str + len, size - len, "Endpoint Command Complete");
break;
default:
- snprintf(str, size, "UNKNOWN");
+ scnprintf(str + len, size - len, "UNKNOWN");
}
return str;
if (event->status & DEPEVT_STATUS_SHORT && !chain)
return 1;
- if (event->status & DEPEVT_STATUS_IOC)
+ if ((trb->ctrl & DWC3_TRB_CTRL_IOC) ||
+ (trb->ctrl & DWC3_TRB_CTRL_LST))
return 1;
return 0;
val = CONFIG_USB_GADGET_VBUS_DRAW;
if (!val)
return 0;
- switch (speed) {
- case USB_SPEED_SUPER:
- return DIV_ROUND_UP(val, 8);
- default:
- return DIV_ROUND_UP(val, 2);
- }
+ if (speed < USB_SPEED_SUPER)
+ return min(val, 500U) / 2;
+ else
+ /*
+ * USB 3.x supports up to 900mA, but since 900 isn't divisible
+ * by 8 the integral division will effectively cap to 896mA.
+ */
+ return min(val, 900U) / 8;
}
static int config_buf(struct usb_configuration *config,
/* when we return, be sure our power usage is valid */
power = c->MaxPower ? c->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+ if (gadget->speed < USB_SPEED_SUPER)
+ power = min(power, 500U);
+ else
+ power = min(power, 900U);
done:
usb_gadget_vbus_draw(gadget, power);
if (result >= 0 && cdev->delayed_status)
{
struct usb_composite_dev *cdev = get_gadget_data(gadget);
struct usb_function *f;
- u16 maxpower;
+ unsigned maxpower;
/* REVISIT: should we have config level
* suspend/resume callbacks?
f->resume(f);
}
- maxpower = cdev->config->MaxPower;
+ maxpower = cdev->config->MaxPower ?
+ cdev->config->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+ if (gadget->speed < USB_SPEED_SUPER)
+ maxpower = min(maxpower, 500U);
+ else
+ maxpower = min(maxpower, 900U);
- usb_gadget_vbus_draw(gadget, maxpower ?
- maxpower : CONFIG_USB_GADGET_VBUS_DRAW);
+ usb_gadget_vbus_draw(gadget, maxpower);
}
cdev->suspended = 0;
{
struct ffs_io_data *io_data = kiocb->private;
struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+ unsigned long flags;
int value;
ENTER();
- spin_lock_irq(&epfile->ffs->eps_lock);
+ spin_lock_irqsave(&epfile->ffs->eps_lock, flags);
if (likely(io_data && io_data->ep && io_data->req))
value = usb_ep_dequeue(io_data->ep, io_data->req);
else
value = -EINVAL;
- spin_unlock_irq(&epfile->ffs->eps_lock);
+ spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags);
return value;
}
ep = audio_dev->out_ep;
prm = &uac->c_prm;
config_ep_by_speed(gadget, &audio_dev->func, ep);
- req_len = prm->max_psize;
+ req_len = ep->maxpacket;
prm->ep_enabled = true;
usb_ep_enable(ep);
req->context = &prm->ureq[i];
req->length = req_len;
req->complete = u_audio_iso_complete;
- req->buf = prm->rbuf + i * prm->max_psize;
+ req->buf = prm->rbuf + i * ep->maxpacket;
}
if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC))
uac->p_pktsize = min_t(unsigned int,
uac->p_framesize *
(params->p_srate / uac->p_interval),
- prm->max_psize);
+ ep->maxpacket);
- if (uac->p_pktsize < prm->max_psize)
+ if (uac->p_pktsize < ep->maxpacket)
uac->p_pktsize_residue = uac->p_framesize *
(params->p_srate % uac->p_interval);
else
req->context = &prm->ureq[i];
req->length = req_len;
req->complete = u_audio_iso_complete;
- req->buf = prm->rbuf + i * prm->max_psize;
+ req->buf = prm->rbuf + i * ep->maxpacket;
}
if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC))
port->n_read = 0;
started = gs_start_rx(port);
- /* unblock any pending writes into our circular buffer */
if (started) {
+ gs_start_tx(port);
+ /* Unblock any pending writes into our circular buffer, in case
+ * we didn't in gs_start_tx() */
tty_wakeup(port->port.tty);
} else {
gs_free_requests(ep, head, &port->read_allocated);
/**
* xudc_stop - stops the device.
* @gadget: pointer to the usb gadget structure
- * @driver: pointer to usb gadget driver structure
*
* Return: zero always
*/
static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
u16 wLength)
{
+ struct xhci_port_cap *port_cap = NULL;
int i, ssa_count;
u32 temp;
u16 desc_size, ssp_cap_size, ssa_size = 0;
ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size;
/* does xhci support USB 3.1 Enhanced SuperSpeed */
- if (xhci->usb3_rhub.min_rev >= 0x01) {
+ for (i = 0; i < xhci->num_port_caps; i++) {
+ if (xhci->port_caps[i].maj_rev == 0x03 &&
+ xhci->port_caps[i].min_rev >= 0x01) {
+ usb3_1 = true;
+ port_cap = &xhci->port_caps[i];
+ break;
+ }
+ }
+
+ if (usb3_1) {
/* does xhci provide a PSI table for SSA speed attributes? */
- if (xhci->usb3_rhub.psi_count) {
+ if (port_cap->psi_count) {
/* two SSA entries for each unique PSI ID, RX and TX */
- ssa_count = xhci->usb3_rhub.psi_uid_count * 2;
+ ssa_count = port_cap->psi_uid_count * 2;
ssa_size = ssa_count * sizeof(u32);
ssp_cap_size -= 16; /* skip copying the default SSA */
}
desc_size += ssp_cap_size;
- usb3_1 = true;
}
memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength));
}
/* If PSI table exists, add the custom speed attributes from it */
- if (usb3_1 && xhci->usb3_rhub.psi_count) {
+ if (usb3_1 && port_cap->psi_count) {
u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp;
int offset;
/* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */
bm_attrib = (ssa_count - 1) & 0x1f;
- bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5;
+ bm_attrib |= (port_cap->psi_uid_count - 1) << 5;
put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]);
if (wLength < desc_size + ssa_size)
* USB 3.1 requires two SSA entries (RX and TX) for every link
*/
offset = desc_size;
- for (i = 0; i < xhci->usb3_rhub.psi_count; i++) {
- psi = xhci->usb3_rhub.psi[i];
+ for (i = 0; i < port_cap->psi_count; i++) {
+ psi = port_cap->psi[i];
psi &= ~USB_SSP_SUBLINK_SPEED_RSVD;
psi_exp = XHCI_EXT_PORT_PSIE(psi);
psi_mant = XHCI_EXT_PORT_PSIM(psi);
/* Allow 3 retries for everything but isoc, set CErr = 3 */
if (!usb_endpoint_xfer_isoc(&ep->desc))
err_count = 3;
- /* Some devices get this wrong */
- if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH)
- max_packet = 512;
+ /* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */
+ if (usb_endpoint_xfer_bulk(&ep->desc)) {
+ if (udev->speed == USB_SPEED_HIGH)
+ max_packet = 512;
+ if (udev->speed == USB_SPEED_FULL) {
+ max_packet = rounddown_pow_of_two(max_packet);
+ max_packet = clamp_val(max_packet, 8, 64);
+ }
+ }
/* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */
if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
avg_trb_len = 8;
xhci->usb3_rhub.num_ports = 0;
xhci->num_active_eps = 0;
kfree(xhci->usb2_rhub.ports);
- kfree(xhci->usb2_rhub.psi);
kfree(xhci->usb3_rhub.ports);
- kfree(xhci->usb3_rhub.psi);
kfree(xhci->hw_ports);
kfree(xhci->rh_bw);
kfree(xhci->ext_caps);
+ for (i = 0; i < xhci->num_port_caps; i++)
+ kfree(xhci->port_caps[i].psi);
+ kfree(xhci->port_caps);
+ xhci->num_port_caps = 0;
xhci->usb2_rhub.ports = NULL;
- xhci->usb2_rhub.psi = NULL;
xhci->usb3_rhub.ports = NULL;
- xhci->usb3_rhub.psi = NULL;
xhci->hw_ports = NULL;
xhci->rh_bw = NULL;
xhci->ext_caps = NULL;
u8 major_revision, minor_revision;
struct xhci_hub *rhub;
struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
+ struct xhci_port_cap *port_cap;
temp = readl(addr);
major_revision = XHCI_EXT_PORT_MAJOR(temp);
/* WTF? "Valid values are ‘1’ to MaxPorts" */
return;
- rhub->psi_count = XHCI_EXT_PORT_PSIC(temp);
- if (rhub->psi_count) {
- rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi),
- GFP_KERNEL, dev_to_node(dev));
- if (!rhub->psi)
- rhub->psi_count = 0;
+ port_cap = &xhci->port_caps[xhci->num_port_caps++];
+ if (xhci->num_port_caps > max_caps)
+ return;
+
+ port_cap->maj_rev = major_revision;
+ port_cap->min_rev = minor_revision;
+ port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp);
- rhub->psi_uid_count++;
- for (i = 0; i < rhub->psi_count; i++) {
- rhub->psi[i] = readl(addr + 4 + i);
+ if (port_cap->psi_count) {
+ port_cap->psi = kcalloc_node(port_cap->psi_count,
+ sizeof(*port_cap->psi),
+ GFP_KERNEL, dev_to_node(dev));
+ if (!port_cap->psi)
+ port_cap->psi_count = 0;
+
+ port_cap->psi_uid_count++;
+ for (i = 0; i < port_cap->psi_count; i++) {
+ port_cap->psi[i] = readl(addr + 4 + i);
/* count unique ID values, two consecutive entries can
* have the same ID if link is assymetric
*/
- if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) !=
- XHCI_EXT_PORT_PSIV(rhub->psi[i - 1])))
- rhub->psi_uid_count++;
+ if (i && (XHCI_EXT_PORT_PSIV(port_cap->psi[i]) !=
+ XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1])))
+ port_cap->psi_uid_count++;
xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n",
- XHCI_EXT_PORT_PSIV(rhub->psi[i]),
- XHCI_EXT_PORT_PSIE(rhub->psi[i]),
- XHCI_EXT_PORT_PLT(rhub->psi[i]),
- XHCI_EXT_PORT_PFD(rhub->psi[i]),
- XHCI_EXT_PORT_LP(rhub->psi[i]),
- XHCI_EXT_PORT_PSIM(rhub->psi[i]));
+ XHCI_EXT_PORT_PSIV(port_cap->psi[i]),
+ XHCI_EXT_PORT_PSIE(port_cap->psi[i]),
+ XHCI_EXT_PORT_PLT(port_cap->psi[i]),
+ XHCI_EXT_PORT_PFD(port_cap->psi[i]),
+ XHCI_EXT_PORT_LP(port_cap->psi[i]),
+ XHCI_EXT_PORT_PSIM(port_cap->psi[i]));
}
}
/* cache usb2 port capabilities */
continue;
}
hw_port->rhub = rhub;
+ hw_port->port_cap = port_cap;
rhub->num_ports++;
}
/* FIXME: Should we disable ports not in the Extended Capabilities? */
if (!xhci->ext_caps)
return -ENOMEM;
+ xhci->port_caps = kcalloc_node(cap_count, sizeof(*xhci->port_caps),
+ flags, dev_to_node(dev));
+ if (!xhci->port_caps)
+ return -ENOMEM;
+
offset = cap_start;
while (offset) {
#define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI 0x15ec
#define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI 0x15f0
#define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI 0x8a13
+#define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af
#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9
#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba
pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
+ pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) {
xhci->quirks |= XHCI_PME_STUCK_QUIRK;
}
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
if (!usb_hcd_is_primary_hcd(hcd))
return 0;
+ if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+ xhci_pme_acpi_rtd3_enable(pdev);
+
xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn);
/* Find any debug ports */
HCC_MAX_PSA(xhci->hcc_params) >= 4)
xhci->shared_hcd->can_do_streams = 1;
- if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
- xhci_pme_acpi_rtd3_enable(dev);
-
/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
pm_runtime_put_noidle(&dev->dev);
* Intel Lynx Point LP xHCI host.
*/
#define XHCI_MAX_REXIT_TIMEOUT_MS 20
+struct xhci_port_cap {
+ u32 *psi; /* array of protocol speed ID entries */
+ u8 psi_count;
+ u8 psi_uid_count;
+ u8 maj_rev;
+ u8 min_rev;
+};
struct xhci_port {
__le32 __iomem *addr;
int hw_portnum;
int hcd_portnum;
struct xhci_hub *rhub;
+ struct xhci_port_cap *port_cap;
};
struct xhci_hub {
/* supported prococol extended capabiliy values */
u8 maj_rev;
u8 min_rev;
- u32 *psi; /* array of protocol speed ID entries */
- u8 psi_count;
- u8 psi_uid_count;
};
/* There is one xhci_hcd structure per controller */
/* cached usb2 extened protocol capabilites */
u32 *ext_caps;
unsigned int num_ext_caps;
+ /* cached extended protocol port capabilities */
+ struct xhci_port_cap *port_caps;
+ unsigned int num_port_caps;
/* Compliance Mode Recovery Data */
struct timer_list comp_mode_recovery_timer;
u32 port_status_u0;
#define USB_DEVICE_ID_CODEMERCS_IOWPV2 0x1512
/* full speed iowarrior */
#define USB_DEVICE_ID_CODEMERCS_IOW56 0x1503
+/* fuller speed iowarrior */
+#define USB_DEVICE_ID_CODEMERCS_IOW28 0x1504
+#define USB_DEVICE_ID_CODEMERCS_IOW28L 0x1505
+#define USB_DEVICE_ID_CODEMERCS_IOW100 0x1506
+
+/* OEMed devices */
+#define USB_DEVICE_ID_CODEMERCS_IOW24SAG 0x158a
+#define USB_DEVICE_ID_CODEMERCS_IOW56AM 0x158b
/* Get a minor range for your devices from the usb maintainer */
#ifdef CONFIG_USB_DYNAMIC_MINORS
{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)},
{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)},
{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)},
+ {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)},
+ {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
+ {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)},
+ {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)},
+ {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)},
{} /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, iowarrior_ids);
}
switch (dev->product_id) {
case USB_DEVICE_ID_CODEMERCS_IOW24:
+ case USB_DEVICE_ID_CODEMERCS_IOW24SAG:
case USB_DEVICE_ID_CODEMERCS_IOWPV1:
case USB_DEVICE_ID_CODEMERCS_IOWPV2:
case USB_DEVICE_ID_CODEMERCS_IOW40:
goto exit;
break;
case USB_DEVICE_ID_CODEMERCS_IOW56:
+ case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+ case USB_DEVICE_ID_CODEMERCS_IOW28:
+ case USB_DEVICE_ID_CODEMERCS_IOW28L:
+ case USB_DEVICE_ID_CODEMERCS_IOW100:
/* The IOW56 uses asynchronous IO and more urbs */
if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
/* Wait until we are below the limit for submitted urbs */
switch (cmd) {
case IOW_WRITE:
if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
+ dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG ||
dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 ||
dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 ||
dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) {
goto error;
}
- if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+ if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) {
res = usb_find_last_int_out_endpoint(iface_desc,
&dev->int_out_endpoint);
if (res) {
/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
- (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56))
+ ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+ (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)))
/* IOWarrior56 has wMaxPacketSize different from report size */
dev->report_size = 7;
return -ENXIO;
}
+ /*
+ * Note that UTMI pad registers are shared by all PHYs, therefore
+ * devm_platform_ioremap_resource() can't be used here.
+ */
tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start,
resource_size(res));
if (!tegra_phy->pad_regs) {
return -ENXIO;
}
+ /*
+ * Note that PHY and USB controller are using shared registers,
+ * therefore devm_platform_ioremap_resource() can't be used here.
+ */
tegra_phy->regs = devm_ioremap(&pdev->dev, res->start,
resource_size(res));
if (!tegra_phy->regs) {
16 * speed - 16 * CH341_CLKRATE / (clk_div * (div + 1)))
div++;
+ /*
+ * Prefer lower base clock (fact = 0) if even divisor.
+ *
+ * Note that this makes the receiver more tolerant to errors.
+ */
+ if (fact == 1 && div % 2 == 0) {
+ div /= 2;
+ fact = 0;
+ }
+
return (0x100 - div) << 8 | fact << 2 | ps;
}
usb_sndbulkpipe(udev, port->bulk_out_endpointAddress),
transfer_buffer, 1, &actual_length, 5000);
if (ret || actual_length != 1) {
- if (actual_length != 1)
+ if (!ret)
ret = -EIO;
dev_err(&port->dev, "failed to change line speed: %d\n", ret);
}
struct scsi_cmnd *cmnd[MAX_CMNDS];
spinlock_t lock;
struct work_struct work;
+ struct work_struct scan_work; /* for async scanning */
};
enum {
spin_unlock_irqrestore(&devinfo->lock, flags);
}
+static void uas_scan_work(struct work_struct *work)
+{
+ struct uas_dev_info *devinfo =
+ container_of(work, struct uas_dev_info, scan_work);
+ struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf);
+
+ dev_dbg(&devinfo->intf->dev, "starting scan\n");
+ scsi_scan_host(shost);
+ dev_dbg(&devinfo->intf->dev, "scan complete\n");
+}
+
static void uas_add_work(struct uas_cmd_info *cmdinfo)
{
struct scsi_pointer *scp = (void *)cmdinfo;
init_usb_anchor(&devinfo->data_urbs);
spin_lock_init(&devinfo->lock);
INIT_WORK(&devinfo->work, uas_do_work);
+ INIT_WORK(&devinfo->scan_work, uas_scan_work);
result = uas_configure_endpoints(devinfo);
if (result)
if (result)
goto free_streams;
- scsi_scan_host(shost);
+ /* Submit the delayed_work for SCSI-device scanning */
+ schedule_work(&devinfo->scan_work);
+
return result;
free_streams:
usb_kill_anchored_urbs(&devinfo->data_urbs);
uas_zap_pending(devinfo, DID_NO_CONNECT);
+ /*
+ * Prevent SCSI scanning (if it hasn't started yet)
+ * or wait for the SCSI-scanning routine to stop.
+ */
+ cancel_work_sync(&devinfo->scan_work);
+
scsi_remove_host(shost);
uas_free_streams(devinfo);
scsi_host_put(shost);
static struct socket *get_raw_socket(int fd)
{
- struct {
- struct sockaddr_ll sa;
- char buf[MAX_ADDR_LEN];
- } uaddr;
int r;
struct socket *sock = sockfd_lookup(fd, &r);
goto err;
}
- r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0);
- if (r < 0)
- goto err;
-
- if (uaddr.sa.sll_family != AF_PACKET) {
+ if (sock->sk->sk_family != AF_PACKET) {
r = -EPFNOSUPPORT;
goto err;
}
config DA9062_WATCHDOG
tristate "Dialog DA9062/61 Watchdog"
depends on MFD_DA9062 || COMPILE_TEST
+ depends on I2C
select WATCHDOG_CORE
help
Support for the watchdog in the DA9062 and DA9061 PMICs.
tristate "Mediatek SoCs watchdog support"
depends on ARCH_MEDIATEK || COMPILE_TEST
select WATCHDOG_CORE
+ select RESET_CONTROLLER
help
Say Y here to include support for the watchdog timer
in Mediatek SoCs.
#include <linux/jiffies.h>
#include <linux/mfd/da9062/registers.h>
#include <linux/mfd/da9062/core.h>
+#include <linux/property.h>
#include <linux/regmap.h>
#include <linux/of.h>
struct da9062_watchdog {
struct da9062 *hw;
struct watchdog_device wdtdev;
+ bool use_sw_pm;
};
static unsigned int da9062_wdt_timeout_to_sel(unsigned int secs)
struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
int ret;
- ret = da9062_reset_watchdog_timer(wdt);
- if (ret) {
- dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n",
- ret);
- return ret;
- }
-
ret = regmap_update_bits(wdt->hw->regmap,
DA9062AA_CONTROL_D,
DA9062AA_TWDSCALE_MASK,
if (!wdt)
return -ENOMEM;
+ wdt->use_sw_pm = device_property_present(dev, "dlg,use-sw-pm");
+
wdt->hw = chip;
wdt->wdtdev.info = &da9062_watchdog_info;
static int __maybe_unused da9062_wdt_suspend(struct device *dev)
{
struct watchdog_device *wdd = dev_get_drvdata(dev);
+ struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+
+ if (!wdt->use_sw_pm)
+ return 0;
if (watchdog_active(wdd))
return da9062_wdt_stop(wdd);
static int __maybe_unused da9062_wdt_resume(struct device *dev)
{
struct watchdog_device *wdd = dev_get_drvdata(dev);
+ struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+
+ if (!wdt->use_sw_pm)
+ return 0;
if (watchdog_active(wdd))
return da9062_wdt_start(wdd);
MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+#define WDAT_DEFAULT_TIMEOUT 30
+
+static int timeout = WDAT_DEFAULT_TIMEOUT;
+module_param(timeout, int, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default="
+ __MODULE_STRING(WDAT_DEFAULT_TIMEOUT) ")");
+
static int wdat_wdt_read(struct wdat_wdt *wdat,
const struct wdat_instruction *instr, u32 *value)
{
memset(&r, 0, sizeof(r));
r.start = gas->address;
- r.end = r.start + gas->access_width - 1;
+ r.end = r.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1;
if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
r.flags = IORESOURCE_MEM;
} else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
platform_set_drvdata(pdev, wdat);
+ /*
+ * Set initial timeout so that userspace has time to configure the
+ * watchdog properly after it has opened the device. In some cases
+ * the BIOS default is too short and causes immediate reboot.
+ */
+ if (timeout * 1000 < wdat->wdd.min_hw_heartbeat_ms ||
+ timeout * 1000 > wdat->wdd.max_hw_heartbeat_ms) {
+ dev_warn(dev, "Invalid timeout %d given, using %d\n",
+ timeout, WDAT_DEFAULT_TIMEOUT);
+ timeout = WDAT_DEFAULT_TIMEOUT;
+ }
+
+ ret = wdat_wdt_set_timeout(&wdat->wdd, timeout);
+ if (ret)
+ return ret;
+
watchdog_set_nowayout(&wdat->wdd, nowayout);
return devm_watchdog_register_device(dev, &wdat->wdd);
}
* cpu.
*/
__this_cpu_write(xen_in_preemptible_hcall, false);
- _cond_resched();
+ local_irq_enable();
+ cond_resched();
+ local_irq_disable();
__this_cpu_write(xen_in_preemptible_hcall, true);
}
}
if (IS_ERR(fs_info->fs_root)) {
err = PTR_ERR(fs_info->fs_root);
btrfs_warn(fs_info, "failed to read fs tree: %d", err);
+ fs_info->fs_root = NULL;
goto fail_qgroup;
}
cond_resched();
spin_lock(&delayed_refs->lock);
}
+ btrfs_qgroup_destroy_extent_records(trans);
spin_unlock(&delayed_refs->lock);
wake_up(&fs_info->transaction_wait);
btrfs_destroy_delayed_inodes(fs_info);
- btrfs_assert_delayed_root_empty(fs_info);
btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
EXTENT_DIRTY);
ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
offset, ins, 1);
+ if (ret)
+ btrfs_pin_extent(fs_info, ins->objectid, ins->offset, 1);
btrfs_put_block_group(block_group);
return ret;
}
return -ENOMEM;
path->reada = READA_BACK;
- lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
- &cached_state);
+ if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+ &cached_state);
/*
* We want to drop from the next block forward in case this new size is
goto out;
}
- path->leave_spinning = 1;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0)
goto out;
root == fs_info->tree_root)) {
struct btrfs_ref ref = { 0 };
- btrfs_set_path_blocking(path);
bytes_deleted += extent_num_bytes;
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,
if (!ret && last_size > new_size)
last_size = new_size;
btrfs_ordered_update_i_size(inode, last_size, NULL);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start,
+ (u64)-1, &cached_state);
}
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
- &cached_state);
-
btrfs_free_path(path);
return ret;
}
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_key ins;
u64 cur_offset = start;
+ u64 clear_offset = start;
u64 i_size;
u64 cur_bytes;
u64 last_alloc = (u64)-1;
btrfs_end_transaction(trans);
break;
}
+
+ /*
+ * We've reserved this space, and thus converted it from
+ * ->bytes_may_use to ->bytes_reserved. Any error that happens
+ * from here on out we will only need to clear our reservation
+ * for the remaining unreserved area, so advance our
+ * clear_offset by our extent size.
+ */
+ clear_offset += ins.offset;
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
last_alloc = ins.offset;
if (own_trans)
btrfs_end_transaction(trans);
}
- if (cur_offset < end)
- btrfs_free_reserved_data_space(inode, NULL, cur_offset,
- end - cur_offset + 1);
+ if (clear_offset < end)
+ btrfs_free_reserved_data_space(inode, NULL, clear_offset,
+ end - clear_offset + 1);
return ret;
}
}
btrfs_start_ordered_extent(inode, ordered, 1);
end = ordered->file_offset;
+ /*
+ * If the ordered extent had an error save the error but don't
+ * exit without waiting first for all other ordered extents in
+ * the range to complete.
+ */
if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
ret = -EIO;
btrfs_put_ordered_extent(ordered);
- if (ret || end == 0 || end == start)
+ if (end == 0 || end == start)
break;
end--;
}
}
return ret;
}
+
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
+{
+ struct btrfs_qgroup_extent_record *entry;
+ struct btrfs_qgroup_extent_record *next;
+ struct rb_root *root;
+
+ root = &trans->delayed_refs.dirty_extent_root;
+ rbtree_postorder_for_each_entry_safe(entry, next, root, node) {
+ ulist_free(entry->old_roots);
+ kfree(entry);
+ }
+}
u64 last_snapshot);
int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *eb);
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
#endif
BUG_ON(!list_empty(&transaction->list));
WARN_ON(!RB_EMPTY_ROOT(
&transaction->delayed_refs.href_root.rb_root));
+ WARN_ON(!RB_EMPTY_ROOT(
+ &transaction->delayed_refs.dirty_extent_root));
if (transaction->delayed_refs.pending_csums)
btrfs_err(transaction->fs_info,
"pending csums is %llu",
if (full_path == NULL)
goto cdda_exit;
+ convert_delimiter(full_path, '\\');
+
cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path);
if (!cifs_sb_master_tlink(cifs_sb)) {
if (tcon->seal)
seq_puts(s, ",seal");
+ else if (tcon->ses->server->ignore_signature)
+ seq_puts(s, ",signloosely");
if (tcon->nocase)
seq_puts(s, ",nocase");
if (tcon->local_lease)
__u64 volatile_fid; /* volatile file id for smb2 */
__u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */
__u8 create_guid[16];
+ __u32 access;
struct cifs_pending_open *pending_open;
unsigned int epoch;
#ifdef CONFIG_CIFS_DEBUG2
return false;
}
+
+/* cifs_get_writable_file() flags */
+#define FIND_WR_ANY 0
+#define FIND_WR_FSUID_ONLY 1
+#define FIND_WR_WITH_DELETE 2
+
#define MID_FREE 0
#define MID_REQUEST_ALLOCATED 1
#define MID_REQUEST_SUBMITTED 2
extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
unsigned int bytes_written);
-extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
+extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int);
extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
- bool fsuid_only,
+ int flags,
struct cifsFileInfo **ret_file);
extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
+ int flags,
struct cifsFileInfo **ret_file);
extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
*oplock = rsp->OplockLevel;
/* cifs fid stays in le */
oparms->fid->netfid = rsp->Fid;
+ oparms->fid->access = desired_access;
/* Let caller know file was created so we can set the mode. */
/* Do we care about the CreateAction in any other cases? */
wdata2->tailsz = tailsz;
wdata2->bytes = cur_len;
- rc = cifs_get_writable_file(CIFS_I(inode), false,
+ rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY,
&wdata2->cfile);
if (!wdata2->cfile) {
cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n",
/* Return -EBADF if no handle is found and general rc otherwise */
int
-cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only,
+cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
struct cifsFileInfo **ret_file)
{
struct cifsFileInfo *open_file, *inv_file = NULL;
bool any_available = false;
int rc = -EBADF;
unsigned int refind = 0;
-
+ bool fsuid_only = flags & FIND_WR_FSUID_ONLY;
+ bool with_delete = flags & FIND_WR_WITH_DELETE;
*ret_file = NULL;
/*
continue;
if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
continue;
+ if (with_delete && !(open_file->fid.access & DELETE))
+ continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
if (!open_file->invalidHandle) {
/* found a good writable file */
}
struct cifsFileInfo *
-find_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only)
+find_writable_file(struct cifsInodeInfo *cifs_inode, int flags)
{
struct cifsFileInfo *cfile;
int rc;
- rc = cifs_get_writable_file(cifs_inode, fsuid_only, &cfile);
+ rc = cifs_get_writable_file(cifs_inode, flags, &cfile);
if (rc)
cifs_dbg(FYI, "couldn't find writable handle rc=%d", rc);
int
cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
+ int flags,
struct cifsFileInfo **ret_file)
{
struct list_head *tmp;
kfree(full_path);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
- return cifs_get_writable_file(cinode, 0, ret_file);
+ return cifs_get_writable_file(cinode, flags, ret_file);
}
spin_unlock(&tcon->open_file_lock);
if (mapping->host->i_size - offset < (loff_t)to)
to = (unsigned)(mapping->host->i_size - offset);
- rc = cifs_get_writable_file(CIFS_I(mapping->host), false, &open_file);
+ rc = cifs_get_writable_file(CIFS_I(mapping->host), FIND_WR_ANY,
+ &open_file);
if (!rc) {
bytes_written = cifs_write(open_file, open_file->pid,
write_data, to - from, &offset);
if (cfile)
cifsFileInfo_put(cfile);
- rc = cifs_get_writable_file(CIFS_I(inode), false, &cfile);
+ rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
/* in case of an error store it to return later */
if (rc)
*/
if ((fattr->cf_nlink < 1) && !tcon->unix_ext &&
!info->DeletePending) {
- cifs_dbg(1, "bogus file nlink value %u\n",
- fattr->cf_nlink);
+ cifs_dbg(VFS, "bogus file nlink value %u\n",
+ fattr->cf_nlink);
fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
}
}
struct inode *inode = d_inode(dentry);
struct super_block *sb = dentry->d_sb;
char *full_path = NULL;
+ int count = 0;
if (inode == NULL)
return -ENOENT;
full_path, inode, inode->i_count.counter,
dentry, cifs_get_time(dentry), jiffies);
+again:
if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
else
rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
xid, NULL);
-
+ if (rc == -EAGAIN && count++ < 10)
+ goto again;
out:
kfree(full_path);
free_xid(xid);
+
return rc;
}
* writebehind data than the SMB timeout for the SetPathInfo
* request would allow
*/
- open_file = find_writable_file(cifsInode, true);
+ open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
if (open_file) {
tcon = tlink_tcon(open_file->tlink);
server = tcon->ses->server;
args->ctime = NO_CHANGE_64;
args->device = 0;
- open_file = find_writable_file(cifsInode, true);
+ open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
if (open_file) {
u16 nfid = open_file->fid.netfid;
u32 npid = open_file->pid;
rc = 0;
if (attrs->ia_valid & ATTR_MTIME) {
- rc = cifs_get_writable_file(cifsInode, false, &wfile);
+ rc = cifs_get_writable_file(cifsInode, FIND_WR_ANY, &wfile);
if (!rc) {
tcon = tlink_tcon(wfile->tlink);
rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid);
struct cifs_tcon *tcon;
/* if the file is already open for write, just use that fileid */
- open_file = find_writable_file(cinode, true);
+ open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
if (open_file) {
fid.netfid = open_file->fid.netfid;
netpid = open_file->pid;
cifs_i = CIFS_I(inode);
dosattrs = cifs_i->cifsAttrs | ATTR_READONLY;
data.Attributes = cpu_to_le32(dosattrs);
- cifs_get_writable_path(tcon, name, &cfile);
+ cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile);
tmprc = smb2_compound_op(xid, tcon, cifs_sb, name,
FILE_WRITE_ATTRIBUTES, FILE_CREATE,
CREATE_NOT_FILE, ACL_NO_MODE,
{
struct cifsFileInfo *cfile;
- cifs_get_writable_path(tcon, from_name, &cfile);
+ cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile);
return smb2_set_path_attr(xid, tcon, from_name, to_name,
cifs_sb, DELETE, SMB2_OP_RENAME, cfile);
cfile->fid.persistent_fid = fid->persistent_fid;
cfile->fid.volatile_fid = fid->volatile_fid;
+ cfile->fid.access = fid->access;
#ifdef CONFIG_CIFS_DEBUG2
cfile->fid.mid = fid->mid;
#endif /* CIFS_DEBUG2 */
* some servers (Windows2016) will not reflect recent writes in
* QUERY_ALLOCATED_RANGES until SMB2_flush is called.
*/
- wrcfile = find_writable_file(cifsi, false);
+ wrcfile = find_writable_file(cifsi, FIND_WR_ANY);
if (wrcfile) {
filemap_write_and_wait(inode->i_mapping);
smb2_flush_file(xid, tcon, &wrcfile->fid);
atomic_inc(&tcon->num_remote_opens);
oparms->fid->persistent_fid = rsp->PersistentFileId;
oparms->fid->volatile_fid = rsp->VolatileFileId;
+ oparms->fid->access = oparms->desired_access;
#ifdef CONFIG_CIFS_DEBUG2
oparms->fid->mid = le64_to_cpu(rsp->sync_hdr.MessageId);
#endif /* CIFS_DEBUG2 */
struct extent_crypt_result ecr;
int rc = 0;
- BUG_ON(!crypt_stat || !crypt_stat->tfm
- || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
+ if (!crypt_stat || !crypt_stat->tfm
+ || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+ return -EINVAL;
+
if (unlikely(ecryptfs_verbosity > 0)) {
ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
crypt_stat->key_size);
* Copyright (C) 2004-2008 International Business Machines Corp.
* Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
* Trevor S. Highland <trevor.highland@gmail.com>
- * Tyler Hicks <tyhicks@ou.edu>
+ * Tyler Hicks <code@tyhicks.com>
*/
#ifndef ECRYPTFS_KERNEL_H
printk(KERN_WARNING "Tag 1 packet contains key larger "
"than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n");
rc = -EINVAL;
- goto out;
+ goto out_free;
}
memcpy((*new_auth_tok)->session_key.encrypted_key,
&data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2)));
* Copyright (C) 2004-2007 International Business Machines Corp.
* Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
* Michael C. Thompson <mcthomps@us.ibm.com>
- * Tyler Hicks <tyhicks@ou.edu>
+ * Tyler Hicks <code@tyhicks.com>
*/
#include <linux/dcache.h>
*
* Copyright (C) 2004-2008 International Business Machines Corp.
* Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com>
- * Tyler Hicks <tyhicks@ou.edu>
+ * Tyler Hicks <code@tyhicks.com>
*/
#include <linux/sched.h>
#include <linux/slab.h>
* ecryptfs_message_buf_len),
GFP_KERNEL);
if (!ecryptfs_msg_ctx_arr) {
+ kfree(ecryptfs_daemon_hash);
rc = -ENOMEM;
goto out;
}
ext4_group_t ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct buffer_head *bh_p;
if (block_group >= ngroups) {
ext4_error(sb, "block_group >= groups_count - block_group = %u,"
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
- if (!sbi->s_group_desc[group_desc]) {
+ bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc);
+ /*
+ * sbi_array_rcu_deref returns with rcu unlocked, this is ok since
+ * the pointer being dereferenced won't be dereferenced again. By
+ * looking at the usage in add_new_gdb() the value isn't modified,
+ * just the pointer, and so it remains valid.
+ */
+ if (!bh_p) {
ext4_error(sb, "Group descriptor not loaded - "
"block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
}
desc = (struct ext4_group_desc *)(
- (__u8 *)sbi->s_group_desc[group_desc]->b_data +
+ (__u8 *)bh_p->b_data +
offset * EXT4_DESC_SIZE(sb));
if (bh)
- *bh = sbi->s_group_desc[group_desc];
+ *bh = bh_p;
return desc;
}
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
- struct buffer_head **s_group_desc;
+ struct buffer_head * __rcu *s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned int s_mount_flags;
#endif
/* for buddy allocator */
- struct ext4_group_info ***s_group_info;
+ struct ext4_group_info ** __rcu *s_group_info;
struct inode *s_buddy_cache;
spinlock_t s_md_lock;
unsigned short *s_mb_offsets;
unsigned int s_extent_max_zeroout_kb;
unsigned int s_log_groups_per_flex;
- struct flex_groups *s_flex_groups;
+ struct flex_groups * __rcu *s_flex_groups;
ext4_group_t s_flex_groups_allocated;
/* workqueue for reserved extent conversions (buffered io) */
struct ratelimit_state s_warning_ratelimit_state;
struct ratelimit_state s_msg_ratelimit_state;
- /* Barrier between changing inodes' journal flags and writepages ops. */
- struct percpu_rw_semaphore s_journal_flag_rwsem;
+ /*
+ * Barrier between writepages ops and changing any inode's JOURNAL_DATA
+ * or EXTENTS flag.
+ */
+ struct percpu_rw_semaphore s_writepages_rwsem;
struct dax_device *s_daxdev;
#ifdef CONFIG_EXT4_DEBUG
unsigned long s_simulate_fail;
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+/*
+ * Returns: sbi->field[index]
+ * Used to access an array element from the following sbi fields which require
+ * rcu protection to avoid dereferencing an invalid pointer due to reassignment
+ * - s_group_desc
+ * - s_group_info
+ * - s_flex_group
+ */
+#define sbi_array_rcu_deref(sbi, field, index) \
+({ \
+ typeof(*((sbi)->field)) _v; \
+ rcu_read_lock(); \
+ _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \
+ rcu_read_unlock(); \
+ _v; \
+})
+
/*
* Simulate_fail codes
*/
extern bool ext4_empty_dir(struct inode *inode);
/* resize.c */
+extern void ext4_kvfree_array_rcu(void *to_free);
extern int ext4_group_add(struct super_block *sb,
struct ext4_new_group_data *input);
extern int ext4_group_extend(struct super_block *sb,
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
ext4_group_t group)
{
- struct ext4_group_info ***grp_info;
+ struct ext4_group_info **grp_info;
long indexv, indexh;
BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
- grp_info = EXT4_SB(sb)->s_group_info;
indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
- return grp_info[indexv][indexh];
+ grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
+ return grp_info[indexh];
}
/*
!inode_is_locked(inode));
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = newsize;
+ WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
up_write(&EXT4_I(inode)->i_data_sem);
}
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (sbi->s_log_groups_per_flex) {
- ext4_group_t f = ext4_flex_group(sbi, block_group);
+ struct flex_groups *fg;
- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ fg = sbi_array_rcu_deref(sbi, s_flex_groups,
+ ext4_flex_group(sbi, block_group));
+ atomic_inc(&fg->free_inodes);
if (is_directory)
- atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+ atomic_dec(&fg->used_dirs);
}
BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
int flex_size, struct orlov_stats *stats)
{
struct ext4_group_desc *desc;
- struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
if (flex_size > 1) {
- stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
- stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
- stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
+ struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb),
+ s_flex_groups, g);
+ stats->free_inodes = atomic_read(&fg->free_inodes);
+ stats->free_clusters = atomic64_read(&fg->free_clusters);
+ stats->used_dirs = atomic_read(&fg->used_dirs);
return;
}
if (sbi->s_log_groups_per_flex) {
ext4_group_t f = ext4_flex_group(sbi, group);
- atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+ atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
+ f)->used_dirs);
}
}
if (ext4_has_group_desc_csum(sb)) {
if (sbi->s_log_groups_per_flex) {
flex_group = ext4_flex_group(sbi, group);
- atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
+ atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups,
+ flex_group)->free_inodes);
}
inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
* truncate are avoided by checking i_size under i_data_sem.
*/
disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
- if (disksize > EXT4_I(inode)->i_disksize) {
+ if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
int err2;
loff_t i_size;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
- percpu_down_read(&sbi->s_journal_flag_rwsem);
+ percpu_down_read(&sbi->s_writepages_rwsem);
trace_ext4_writepages(inode, wbc);
/*
out_writepages:
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
- percpu_up_read(&sbi->s_journal_flag_rwsem);
+ percpu_up_read(&sbi->s_writepages_rwsem);
return ret;
}
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
- percpu_down_read(&sbi->s_journal_flag_rwsem);
+ percpu_down_read(&sbi->s_writepages_rwsem);
trace_ext4_writepages(inode, wbc);
ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
- percpu_up_read(&sbi->s_journal_flag_rwsem);
+ percpu_up_read(&sbi->s_writepages_rwsem);
return ret;
}
}
}
- percpu_down_write(&sbi->s_journal_flag_rwsem);
+ percpu_down_write(&sbi->s_writepages_rwsem);
jbd2_journal_lock_updates(journal);
/*
err = jbd2_journal_flush(journal);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
- percpu_up_write(&sbi->s_journal_flag_rwsem);
+ percpu_up_write(&sbi->s_writepages_rwsem);
return err;
}
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
- percpu_up_write(&sbi->s_journal_flag_rwsem);
+ percpu_up_write(&sbi->s_writepages_rwsem);
if (val)
up_write(&EXT4_I(inode)->i_mmap_sem);
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned size;
- struct ext4_group_info ***new_groupinfo;
+ struct ext4_group_info ***old_groupinfo, ***new_groupinfo;
size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >>
EXT4_DESC_PER_BLOCK_BITS(sb);
ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
return -ENOMEM;
}
- if (sbi->s_group_info) {
- memcpy(new_groupinfo, sbi->s_group_info,
+ rcu_read_lock();
+ old_groupinfo = rcu_dereference(sbi->s_group_info);
+ if (old_groupinfo)
+ memcpy(new_groupinfo, old_groupinfo,
sbi->s_group_info_size * sizeof(*sbi->s_group_info));
- kvfree(sbi->s_group_info);
- }
- sbi->s_group_info = new_groupinfo;
+ rcu_read_unlock();
+ rcu_assign_pointer(sbi->s_group_info, new_groupinfo);
sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
+ if (old_groupinfo)
+ ext4_kvfree_array_rcu(old_groupinfo);
ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
sbi->s_group_info_size);
return 0;
{
int i;
int metalen = 0;
+ int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb);
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_info **meta_group_info;
struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
"for a buddy group");
goto exit_meta_group_info;
}
- sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] =
- meta_group_info;
+ rcu_read_lock();
+ rcu_dereference(sbi->s_group_info)[idx] = meta_group_info;
+ rcu_read_unlock();
}
- meta_group_info =
- sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
+ meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx);
i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS);
exit_group_info:
/* If a meta_group_info table has been allocated, release it now */
if (group % EXT4_DESC_PER_BLOCK(sb) == 0) {
- kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]);
- sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL;
+ struct ext4_group_info ***group_info;
+
+ rcu_read_lock();
+ group_info = rcu_dereference(sbi->s_group_info);
+ kfree(group_info[idx]);
+ group_info[idx] = NULL;
+ rcu_read_unlock();
}
exit_meta_group_info:
return -ENOMEM;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int err;
struct ext4_group_desc *desc;
+ struct ext4_group_info ***group_info;
struct kmem_cache *cachep;
err = ext4_mb_alloc_groupinfo(sb, ngroups);
while (i-- > 0)
kmem_cache_free(cachep, ext4_get_group_info(sb, i));
i = sbi->s_group_info_size;
+ rcu_read_lock();
+ group_info = rcu_dereference(sbi->s_group_info);
while (i-- > 0)
- kfree(sbi->s_group_info[i]);
+ kfree(group_info[i]);
+ rcu_read_unlock();
iput(sbi->s_buddy_cache);
err_freesgi:
- kvfree(sbi->s_group_info);
+ rcu_read_lock();
+ kvfree(rcu_dereference(sbi->s_group_info));
+ rcu_read_unlock();
return -ENOMEM;
}
ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
int num_meta_group_infos;
- struct ext4_group_info *grinfo;
+ struct ext4_group_info *grinfo, ***group_info;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
num_meta_group_infos = (ngroups +
EXT4_DESC_PER_BLOCK(sb) - 1) >>
EXT4_DESC_PER_BLOCK_BITS(sb);
+ rcu_read_lock();
+ group_info = rcu_dereference(sbi->s_group_info);
for (i = 0; i < num_meta_group_infos; i++)
- kfree(sbi->s_group_info[i]);
- kvfree(sbi->s_group_info);
+ kfree(group_info[i]);
+ kvfree(group_info);
+ rcu_read_unlock();
}
kfree(sbi->s_mb_offsets);
kfree(sbi->s_mb_maxs);
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
atomic64_sub(ac->ac_b_ex.fe_len,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ &sbi_array_rcu_deref(sbi, s_flex_groups,
+ flex_group)->free_clusters);
}
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
atomic64_add(count_clusters,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ &sbi_array_rcu_deref(sbi, s_flex_groups,
+ flex_group)->free_clusters);
}
/*
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
atomic64_add(clusters_freed,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ &sbi_array_rcu_deref(sbi, s_flex_groups,
+ flex_group)->free_clusters);
}
ext4_mb_unload_buddy(&e4b);
int ext4_ext_migrate(struct inode *inode)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
*/
return retval;
+ percpu_down_write(&sbi->s_writepages_rwsem);
+
/*
* Worst case we can touch the allocation bitmaps, a bgd
* block, and a block to link in the orphan list. We do need
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
- return retval;
+ goto out_unlock;
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
if (IS_ERR(tmp_inode)) {
retval = PTR_ERR(tmp_inode);
ext4_journal_stop(handle);
- return retval;
+ goto out_unlock;
}
i_size_write(tmp_inode, i_size_read(inode));
/*
*/
ext4_orphan_del(NULL, tmp_inode);
retval = PTR_ERR(handle);
- goto out;
+ goto out_tmp_inode;
}
ei = EXT4_I(inode);
ext4_ext_tree_init(handle, tmp_inode);
out_stop:
ext4_journal_stop(handle);
-out:
+out_tmp_inode:
unlock_new_inode(tmp_inode);
iput(tmp_inode);
-
+out_unlock:
+ percpu_up_write(&sbi->s_writepages_rwsem);
return retval;
}
int ext4_ind_migrate(struct inode *inode)
{
struct ext4_extent_header *eh;
- struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_super_block *es = sbi->s_es;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
if (test_opt(inode->i_sb, DELALLOC))
ext4_alloc_da_blocks(inode);
+ percpu_down_write(&sbi->s_writepages_rwsem);
+
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_unlock;
+ }
down_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_ext_check_inode(inode);
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
+out_unlock:
+ percpu_up_write(&sbi->s_writepages_rwsem);
return ret;
}
/*
* We deal with the read-ahead logic here.
*/
+ cond_resched();
if (ra_ptr >= ra_max) {
/* Refill the readahead buffer */
ra_ptr = 0;
#include "ext4_jbd2.h"
+struct ext4_rcu_ptr {
+ struct rcu_head rcu;
+ void *ptr;
+};
+
+static void ext4_rcu_ptr_callback(struct rcu_head *head)
+{
+ struct ext4_rcu_ptr *ptr;
+
+ ptr = container_of(head, struct ext4_rcu_ptr, rcu);
+ kvfree(ptr->ptr);
+ kfree(ptr);
+}
+
+void ext4_kvfree_array_rcu(void *to_free)
+{
+ struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
+
+ if (ptr) {
+ ptr->ptr = to_free;
+ call_rcu(&ptr->rcu, ext4_rcu_ptr_callback);
+ return;
+ }
+ synchronize_rcu();
+ kvfree(to_free);
+}
+
int ext4_resize_begin(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
brelse(gdb);
goto out;
}
- memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data,
- gdb->b_size);
+ memcpy(gdb->b_data, sbi_array_rcu_deref(sbi,
+ s_group_desc, j)->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
err = ext4_handle_dirty_metadata(handle, NULL, gdb);
}
brelse(dind);
- o_group_desc = EXT4_SB(sb)->s_group_desc;
+ rcu_read_lock();
+ o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc);
memcpy(n_group_desc, o_group_desc,
EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+ rcu_read_unlock();
n_group_desc[gdb_num] = gdb_bh;
- EXT4_SB(sb)->s_group_desc = n_group_desc;
+ rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc);
EXT4_SB(sb)->s_gdb_count++;
- kvfree(o_group_desc);
+ ext4_kvfree_array_rcu(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
err = ext4_handle_dirty_super(handle, sb);
return err;
}
- o_group_desc = EXT4_SB(sb)->s_group_desc;
+ rcu_read_lock();
+ o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc);
memcpy(n_group_desc, o_group_desc,
EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+ rcu_read_unlock();
n_group_desc[gdb_num] = gdb_bh;
BUFFER_TRACE(gdb_bh, "get_write_access");
return err;
}
- EXT4_SB(sb)->s_group_desc = n_group_desc;
+ rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc);
EXT4_SB(sb)->s_gdb_count++;
- kvfree(o_group_desc);
+ ext4_kvfree_array_rcu(o_group_desc);
return err;
}
* use non-sparse filesystems anymore. This is already checked above.
*/
if (gdb_off) {
- gdb_bh = sbi->s_group_desc[gdb_num];
+ gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc,
+ gdb_num);
BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
/*
* get_write_access() has been called on gdb_bh by ext4_add_new_desc().
*/
- gdb_bh = sbi->s_group_desc[gdb_num];
+ gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num);
/* Update group descriptor block for new group */
gdp = (struct ext4_group_desc *)(gdb_bh->b_data +
gdb_off * EXT4_DESC_SIZE(sb));
percpu_counter_read(&sbi->s_freeclusters_counter));
if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
+ struct flex_groups *fg;
+
flex_group = ext4_flex_group(sbi, group_data[0].group);
+ fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ &fg->free_clusters);
atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
- &sbi->s_flex_groups[flex_group].free_inodes);
+ &fg->free_inodes);
}
/*
for (; gdb_num <= gdb_num_end; gdb_num++) {
struct buffer_head *gdb_bh;
- gdb_bh = sbi->s_group_desc[gdb_num];
+ gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc,
+ gdb_num);
if (old_gdb == gdb_bh->b_blocknr)
continue;
update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head **group_desc;
+ struct flex_groups **flex_groups;
int aborted = 0;
int i, err;
if (!sb_rdonly(sb))
ext4_commit_super(sb, 1);
+ rcu_read_lock();
+ group_desc = rcu_dereference(sbi->s_group_desc);
for (i = 0; i < sbi->s_gdb_count; i++)
- brelse(sbi->s_group_desc[i]);
- kvfree(sbi->s_group_desc);
- kvfree(sbi->s_flex_groups);
+ brelse(group_desc[i]);
+ kvfree(group_desc);
+ flex_groups = rcu_dereference(sbi->s_flex_groups);
+ if (flex_groups) {
+ for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+ kvfree(flex_groups[i]);
+ kvfree(flex_groups);
+ }
+ rcu_read_unlock();
percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
- percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+ percpu_free_rwsem(&sbi->s_writepages_rwsem);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(get_qf_name(sb, sbi, i));
int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct flex_groups *new_groups;
- int size;
+ struct flex_groups **old_groups, **new_groups;
+ int size, i, j;
if (!sbi->s_log_groups_per_flex)
return 0;
if (size <= sbi->s_flex_groups_allocated)
return 0;
- size = roundup_pow_of_two(size * sizeof(struct flex_groups));
- new_groups = kvzalloc(size, GFP_KERNEL);
+ new_groups = kvzalloc(roundup_pow_of_two(size *
+ sizeof(*sbi->s_flex_groups)), GFP_KERNEL);
if (!new_groups) {
- ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
- size / (int) sizeof(struct flex_groups));
+ ext4_msg(sb, KERN_ERR,
+ "not enough memory for %d flex group pointers", size);
return -ENOMEM;
}
-
- if (sbi->s_flex_groups) {
- memcpy(new_groups, sbi->s_flex_groups,
- (sbi->s_flex_groups_allocated *
- sizeof(struct flex_groups)));
- kvfree(sbi->s_flex_groups);
+ for (i = sbi->s_flex_groups_allocated; i < size; i++) {
+ new_groups[i] = kvzalloc(roundup_pow_of_two(
+ sizeof(struct flex_groups)),
+ GFP_KERNEL);
+ if (!new_groups[i]) {
+ for (j = sbi->s_flex_groups_allocated; j < i; j++)
+ kvfree(new_groups[j]);
+ kvfree(new_groups);
+ ext4_msg(sb, KERN_ERR,
+ "not enough memory for %d flex groups", size);
+ return -ENOMEM;
+ }
}
- sbi->s_flex_groups = new_groups;
- sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
+ rcu_read_lock();
+ old_groups = rcu_dereference(sbi->s_flex_groups);
+ if (old_groups)
+ memcpy(new_groups, old_groups,
+ (sbi->s_flex_groups_allocated *
+ sizeof(struct flex_groups *)));
+ rcu_read_unlock();
+ rcu_assign_pointer(sbi->s_flex_groups, new_groups);
+ sbi->s_flex_groups_allocated = size;
+ if (old_groups)
+ ext4_kvfree_array_rcu(old_groups);
return 0;
}
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
+ struct flex_groups *fg;
ext4_group_t flex_group;
int i, err;
gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
- atomic_add(ext4_free_inodes_count(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_inodes);
+ fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
+ atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes);
atomic64_add(ext4_free_group_clusters(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_clusters);
- atomic_add(ext4_used_dirs_count(sb, gdp),
- &sbi->s_flex_groups[flex_group].used_dirs);
+ &fg->free_clusters);
+ atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs);
}
return 1;
return 0;
}
-#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2)
+#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
if (!readonly && (ext4_has_feature_quota(sb) ||
ext4_has_feature_project(sb))) {
ext4_msg(sb, KERN_ERR,
{
struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
char *orig_data = kstrdup(data, GFP_KERNEL);
- struct buffer_head *bh;
+ struct buffer_head *bh, **group_desc;
struct ext4_super_block *es = NULL;
struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+ struct flex_groups **flex_groups;
ext4_fsblk_t block;
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
goto failed_mount;
}
}
- sbi->s_group_desc = kvmalloc_array(db_count,
- sizeof(struct buffer_head *),
- GFP_KERNEL);
+ rcu_assign_pointer(sbi->s_group_desc,
+ kvmalloc_array(db_count,
+ sizeof(struct buffer_head *),
+ GFP_KERNEL));
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
ret = -ENOMEM;
}
for (i = 0; i < db_count; i++) {
+ struct buffer_head *bh;
+
block = descriptor_loc(sb, logical_sb_block, i);
- sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
- if (!sbi->s_group_desc[i]) {
+ bh = sb_bread_unmovable(sb, block);
+ if (!bh) {
ext4_msg(sb, KERN_ERR,
"can't read group descriptor %d", i);
db_count = i;
goto failed_mount2;
}
+ rcu_read_lock();
+ rcu_dereference(sbi->s_group_desc)[i] = bh;
+ rcu_read_unlock();
}
sbi->s_gdb_count = db_count;
if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
- err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+ err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
ext4_unregister_li_request(sb);
failed_mount6:
ext4_mb_release(sb);
- if (sbi->s_flex_groups)
- kvfree(sbi->s_flex_groups);
+ rcu_read_lock();
+ flex_groups = rcu_dereference(sbi->s_flex_groups);
+ if (flex_groups) {
+ for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+ kvfree(flex_groups[i]);
+ kvfree(flex_groups);
+ }
+ rcu_read_unlock();
percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
- percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+ percpu_free_rwsem(&sbi->s_writepages_rwsem);
failed_mount5:
ext4_ext_release(sb);
ext4_release_system_zone(sb);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
+ rcu_read_lock();
+ group_desc = rcu_dereference(sbi->s_group_desc);
for (i = 0; i < db_count; i++)
- brelse(sbi->s_group_desc[i]);
- kvfree(sbi->s_group_desc);
+ brelse(group_desc[i]);
+ kvfree(group_desc);
+ rcu_read_unlock();
failed_mount:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
} while (1);
}
-static inline void io_worker_spin_for_work(struct io_wqe *wqe)
-{
- int i = 0;
-
- while (++i < 1000) {
- if (io_wqe_run_queue(wqe))
- break;
- if (need_resched())
- break;
- cpu_relax();
- }
-}
-
static int io_wqe_worker(void *data)
{
struct io_worker *worker = data;
struct io_wqe *wqe = worker->wqe;
struct io_wq *wq = wqe->wq;
- bool did_work;
io_worker_start(wqe, worker);
- did_work = false;
while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
set_current_state(TASK_INTERRUPTIBLE);
loop:
- if (did_work)
- io_worker_spin_for_work(wqe);
spin_lock_irq(&wqe->lock);
if (io_wqe_run_queue(wqe)) {
__set_current_state(TASK_RUNNING);
io_worker_handle_work(worker);
- did_work = true;
goto loop;
}
- did_work = false;
/* drops the lock on success, retry */
if (__io_worker_idle(wqe, worker)) {
__release(&wqe->lock);
pid_t task_pid;
};
-#define INIT_IO_WORK(work, _func) \
- do { \
- (work)->list.next = NULL; \
- (work)->func = _func; \
- (work)->files = NULL; \
- (work)->mm = NULL; \
- (work)->creds = NULL; \
- (work)->fs = NULL; \
- (work)->flags = 0; \
- } while (0) \
+#define INIT_IO_WORK(work, _func) \
+ do { \
+ *(work) = (struct io_wq_work){ .func = _func }; \
+ } while (0) \
typedef void (get_work_fn)(struct io_wq_work *);
typedef void (put_work_fn)(struct io_wq_work *);
struct file **files;
};
-enum {
- FFD_F_ATOMIC,
-};
-
struct fixed_file_data {
struct fixed_file_table *table;
struct io_ring_ctx *ctx;
struct percpu_ref refs;
struct llist_head put_llist;
- unsigned long state;
struct work_struct ref_work;
struct completion done;
};
{
struct io_ring_ctx *ctx = req->ctx;
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ io_cleanup_req(req);
+
kfree(req->io);
if (req->file) {
if (req->flags & REQ_F_FIXED_FILE)
{
__io_req_aux_free(req);
- if (req->flags & REQ_F_NEED_CLEANUP)
- io_cleanup_req(req);
-
if (req->flags & REQ_F_INFLIGHT) {
struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
__attribute__((nonnull))
static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
{
- io_req_find_next(req, nxtptr);
-
- if (refcount_dec_and_test(&req->refs))
+ if (refcount_dec_and_test(&req->refs)) {
+ io_req_find_next(req, nxtptr);
__io_free_req(req);
+ }
}
static void io_put_req(struct io_kiocb *req)
mutex_unlock(&ctx->uring_lock);
}
-static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
- long min)
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
{
int iters = 0, ret = 0;
+ /*
+ * We disallow the app entering submit/complete with polling, but we
+ * still need to lock the ring to prevent racing with polled issue
+ * that got punted to a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
do {
int tmin = 0;
ret = 0;
} while (min && !*nr_events && !need_resched());
- return ret;
-}
-
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
- long min)
-{
- int ret;
-
- /*
- * We disallow the app entering submit/complete with polling, but we
- * still need to lock the ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
- ret = __io_iopoll_check(ctx, nr_events, min);
mutex_unlock(&ctx->uring_lock);
return ret;
}
list_add(&req->list, &ctx->poll_list);
else
list_add_tail(&req->list, &ctx->poll_list);
+
+ if ((ctx->flags & IORING_SETUP_SQPOLL) &&
+ wq_has_sleeper(&ctx->sqo_wait))
+ wake_up(&ctx->sqo_wait);
}
static void io_file_put(struct io_submit_state *state)
ssize_t ret;
ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
*iovec = NULL;
- return ret;
+ return ret < 0 ? ret : sqe_len;
}
if (req->io) {
struct io_kiocb *nxt = NULL;
int ret;
+ if (io_req_cancelled(req))
+ return;
+
ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
req->sync.len);
if (ret < 0)
struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
struct io_kiocb *nxt = NULL;
+ /* not cancellable, don't do io_req_cancelled() */
__io_close_finish(req, &nxt);
if (nxt)
io_wq_assign_next(workptr, nxt);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
+#ifdef CONFIG_COMPAT
+ if (req->ctx->compat)
+ sr->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+
if (!io || req->opcode == IORING_OP_SEND)
return 0;
/* iovec is already imported */
if (req->io)
return -EAGAIN;
if (io_alloc_async_ctx(req)) {
- if (kmsg && kmsg->iov != kmsg->fast_iov)
+ if (kmsg->iov != kmsg->fast_iov)
kfree(kmsg->iov);
return -ENOMEM;
}
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
+#ifdef CONFIG_COMPAT
+ if (req->ctx->compat)
+ sr->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+
if (!io || req->opcode == IORING_OP_RECV)
return 0;
/* iovec is already imported */
if (req->io)
return -EAGAIN;
if (io_alloc_async_ctx(req)) {
- if (kmsg && kmsg->iov != kmsg->fast_iov)
+ if (kmsg->iov != kmsg->fast_iov)
kfree(kmsg->iov);
return -ENOMEM;
}
{
struct io_kiocb *linked_timeout;
struct io_kiocb *nxt = NULL;
+ const struct cred *old_creds = NULL;
int ret;
again:
linked_timeout = io_prep_linked_timeout(req);
+ if (req->work.creds && req->work.creds != current_cred()) {
+ if (old_creds)
+ revert_creds(old_creds);
+ if (old_creds == req->work.creds)
+ old_creds = NULL; /* restored original creds */
+ else
+ old_creds = override_creds(req->work.creds);
+ }
+
ret = io_issue_sqe(req, sqe, &nxt, true);
/*
err:
/* drop submission reference */
- io_put_req(req);
+ io_put_req_find_next(req, &nxt);
if (linked_timeout) {
if (!ret)
goto punt;
goto again;
}
+ if (old_creds)
+ revert_creds(old_creds);
}
static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct io_submit_state *state, struct io_kiocb **link)
{
- const struct cred *old_creds = NULL;
struct io_ring_ctx *ctx = req->ctx;
unsigned int sqe_flags;
int ret, id;
id = READ_ONCE(sqe->personality);
if (id) {
- const struct cred *personality_creds;
-
- personality_creds = idr_find(&ctx->personality_idr, id);
- if (unlikely(!personality_creds)) {
+ req->work.creds = idr_find(&ctx->personality_idr, id);
+ if (unlikely(!req->work.creds)) {
ret = -EINVAL;
goto err_req;
}
- old_creds = override_creds(personality_creds);
+ get_cred(req->work.creds);
}
/* same numerical values with corresponding REQ_F_*, safe to copy */
err_req:
io_cqring_add_event(req, ret);
io_double_put_req(req);
- if (old_creds)
- revert_creds(old_creds);
return false;
}
}
}
- if (old_creds)
- revert_creds(old_creds);
return true;
}
const struct cred *old_cred;
mm_segment_t old_fs;
DEFINE_WAIT(wait);
- unsigned inflight;
unsigned long timeout;
- int ret;
+ int ret = 0;
complete(&ctx->completions[1]);
set_fs(USER_DS);
old_cred = override_creds(ctx->creds);
- ret = timeout = inflight = 0;
+ timeout = jiffies + ctx->sq_thread_idle;
while (!kthread_should_park()) {
unsigned int to_submit;
- if (inflight) {
+ if (!list_empty(&ctx->poll_list)) {
unsigned nr_events = 0;
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- /*
- * inflight is the count of the maximum possible
- * entries we submitted, but it can be smaller
- * if we dropped some of them. If we don't have
- * poll entries available, then we know that we
- * have nothing left to poll for. Reset the
- * inflight count to zero in that case.
- */
- mutex_lock(&ctx->uring_lock);
- if (!list_empty(&ctx->poll_list))
- __io_iopoll_check(ctx, &nr_events, 0);
- else
- inflight = 0;
- mutex_unlock(&ctx->uring_lock);
- } else {
- /*
- * Normal IO, just pretend everything completed.
- * We don't have to poll completions for that.
- */
- nr_events = inflight;
- }
-
- inflight -= nr_events;
- if (!inflight)
+ mutex_lock(&ctx->uring_lock);
+ if (!list_empty(&ctx->poll_list))
+ io_iopoll_getevents(ctx, &nr_events, 0);
+ else
timeout = jiffies + ctx->sq_thread_idle;
+ mutex_unlock(&ctx->uring_lock);
}
to_submit = io_sqring_entries(ctx);
* to enter the kernel to reap and flush events.
*/
if (!to_submit || ret == -EBUSY) {
+ /*
+ * Drop cur_mm before scheduling, we can't hold it for
+ * long periods (or over schedule()). Do this before
+ * adding ourselves to the waitqueue, as the unuse/drop
+ * may sleep.
+ */
+ if (cur_mm) {
+ unuse_mm(cur_mm);
+ mmput(cur_mm);
+ cur_mm = NULL;
+ }
+
/*
* We're polling. If we're within the defined idle
* period, then let us spin without work before going
* more IO, we should wait for the application to
* reap events and wake us up.
*/
- if (inflight ||
+ if (!list_empty(&ctx->poll_list) ||
(!time_after(jiffies, timeout) && ret != -EBUSY &&
!percpu_ref_is_dying(&ctx->refs))) {
cond_resched();
continue;
}
+ prepare_to_wait(&ctx->sqo_wait, &wait,
+ TASK_INTERRUPTIBLE);
+
/*
- * Drop cur_mm before scheduling, we can't hold it for
- * long periods (or over schedule()). Do this before
- * adding ourselves to the waitqueue, as the unuse/drop
- * may sleep.
+ * While doing polled IO, before going to sleep, we need
+ * to check if there are new reqs added to poll_list, it
+ * is because reqs may have been punted to io worker and
+ * will be added to poll_list later, hence check the
+ * poll_list again.
*/
- if (cur_mm) {
- unuse_mm(cur_mm);
- mmput(cur_mm);
- cur_mm = NULL;
+ if ((ctx->flags & IORING_SETUP_IOPOLL) &&
+ !list_empty_careful(&ctx->poll_list)) {
+ finish_wait(&ctx->sqo_wait, &wait);
+ continue;
}
- prepare_to_wait(&ctx->sqo_wait, &wait,
- TASK_INTERRUPTIBLE);
-
/* Tell userspace we may need a wakeup call */
ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
/* make sure to read SQ tail after writing flags */
mutex_lock(&ctx->uring_lock);
ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
mutex_unlock(&ctx->uring_lock);
- if (ret > 0)
- inflight += ret;
+ timeout = jiffies + ctx->sq_thread_idle;
}
set_fs(old_fs);
data = container_of(work, struct fixed_file_data, ref_work);
io_ring_file_ref_flush(data);
- percpu_ref_get(&data->refs);
percpu_ref_switch_to_percpu(&data->refs);
}
{
struct fixed_file_data *data;
+ /*
+ * Juggle reference to ensure we hit zero, if needed, so we can
+ * switch back to percpu mode
+ */
data = container_of(ref, struct fixed_file_data, refs);
- clear_bit(FFD_F_ATOMIC, &data->state);
+ percpu_ref_put(&data->refs);
+ percpu_ref_get(&data->refs);
}
static bool io_queue_file_removal(struct fixed_file_data *data,
llist_add(&pfile->llist, &data->put_llist);
if (pfile == &pfile_stack) {
- if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
- percpu_ref_put(&data->refs);
- percpu_ref_switch_to_atomic(&data->refs,
- io_atomic_switch);
- }
+ percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
wait_for_completion(&done);
flush_work(&data->ref_work);
return false;
up->offset++;
}
- if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
- percpu_ref_put(&data->refs);
+ if (ref_switch)
percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
- }
return done ? done : err;
}
io_sqe_buffer_unregister(ctx);
io_sqe_files_unregister(ctx);
io_eventfd_unregister(ctx);
+ idr_destroy(&ctx->personality_idr);
#if defined(CONFIG_UNIX)
if (ctx->ring_sock) {
return submitted ? submitted : ret;
}
+#ifdef CONFIG_PROC_FS
static int io_uring_show_cred(int id, void *p, void *data)
{
const struct cred *cred = p;
percpu_ref_put(&ctx->refs);
}
}
+#endif
static const struct file_operations io_uring_fops = {
.release = io_uring_release,
#endif
.poll = io_uring_poll,
.fasync = io_uring_fasync,
+#ifdef CONFIG_PROC_FS
.show_fdinfo = io_uring_show_fdinfo,
+#endif
};
static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
char *frozen_buffer = NULL;
unsigned long start_lock, time_lock;
- if (is_handle_aborted(handle))
- return -EROFS;
journal = transaction->t_journal;
jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
/* For undo access buffer must have data copied */
if (undo && !jh->b_committed_data)
goto out;
- if (jh->b_transaction != handle->h_transaction &&
- jh->b_next_transaction != handle->h_transaction)
+ if (READ_ONCE(jh->b_transaction) != handle->h_transaction &&
+ READ_ONCE(jh->b_next_transaction) != handle->h_transaction)
goto out;
/*
* There are two reasons for the barrier here:
struct journal_head *jh;
int rc;
+ if (is_handle_aborted(handle))
+ return -EROFS;
+
if (jbd2_write_access_granted(handle, bh, false))
return 0;
struct journal_head *jh;
char *committed_data = NULL;
+ if (is_handle_aborted(handle))
+ return -EROFS;
+
if (jbd2_write_access_granted(handle, bh, true))
return 0;
* our jh reference and thus __jbd2_journal_file_buffer() must not
* take a new one.
*/
- jh->b_transaction = jh->b_next_transaction;
- jh->b_next_transaction = NULL;
+ WRITE_ONCE(jh->b_transaction, jh->b_next_transaction);
+ WRITE_ONCE(jh->b_next_transaction, NULL);
if (buffer_freed(bh))
jlist = BJ_Forget;
else if (jh->b_modified)
if (file->f_mode & FMODE_WRITE)
pipe->writers--;
- if (pipe->readers || pipe->writers) {
- wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLHUP);
- wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM | EPOLLERR | EPOLLHUP);
+ /* Was that the last reader or writer, but not the other side? */
+ if (!pipe->readers != !pipe->writers) {
+ wake_up_interruptible_all(&pipe->rd_wait);
+ wake_up_interruptible_all(&pipe->wr_wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
static void wake_up_partner(struct pipe_inode_info *pipe)
{
- wake_up_interruptible(&pipe->rd_wait);
- wake_up_interruptible(&pipe->wr_wait);
+ wake_up_interruptible_all(&pipe->rd_wait);
+ wake_up_interruptible_all(&pipe->wr_wait);
}
static int fifo_open(struct inode *inode, struct file *filp)
err_wr:
if (!--pipe->writers)
- wake_up_interruptible(&pipe->rd_wait);
+ wake_up_interruptible_all(&pipe->rd_wait);
ret = -ERESTARTSYS;
goto err;
pipe->max_usage = nr_slots;
pipe->tail = tail;
pipe->head = head;
- wake_up_interruptible_all(&pipe->rd_wait);
- wake_up_interruptible_all(&pipe->wr_wait);
+
+ /* This might have made more room for writers */
+ wake_up_interruptible(&pipe->wr_wait);
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
tristate "zonefs filesystem support"
depends on BLOCK
depends on BLK_DEV_ZONED
+ select FS_IOMAP
help
zonefs is a simple file system which exposes zones of a zoned block
device (e.g. host-managed or host-aware SMR disk drives) as files.
ssize_t ret;
/*
- * For async direct IOs to sequential zone files, ignore IOCB_NOWAIT
+ * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
* as this can cause write reordering (e.g. the first aio gets EAGAIN
* on the inode lock but the second goes through but is now unaligned).
*/
- if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb)
- && (iocb->ki_flags & IOCB_NOWAIT))
- iocb->ki_flags &= ~IOCB_NOWAIT;
+ if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) &&
+ (iocb->ki_flags & IOCB_NOWAIT))
+ return -EOPNOTSUPP;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!inode_trylock(inode))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void))
+ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
acpi_get_gpe_device(u32 gpe_index,
strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE)
/*
- * Algorithm to obtain access bit width.
+ * Algorithm to obtain access bit or byte width.
* Can be used with access_width of struct acpi_generic_address and access_size of
* struct acpi_resource_generic_register.
*/
#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + 2))
+#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) - 1))
/*******************************************************************************
*
return per_cpu(freq_scale, cpu);
}
+DECLARE_PER_CPU(unsigned long, thermal_pressure);
+
+static inline unsigned long topology_get_thermal_pressure(int cpu)
+{
+ return per_cpu(thermal_pressure, cpu);
+}
+
+void arch_set_thermal_pressure(struct cpumask *cpus,
+ unsigned long th_pressure);
+
struct cpu_topology {
int thread_id;
int core_id;
unsigned int sg_reserved_size;
int node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
- struct blk_trace *blk_trace;
+ struct blk_trace __rcu *blk_trace;
struct mutex blk_trace_mutex;
#endif
/*
**/
#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \
do { \
- struct blk_trace *bt = (q)->blk_trace; \
+ struct blk_trace *bt; \
+ \
+ rcu_read_lock(); \
+ bt = rcu_dereference((q)->blk_trace); \
if (unlikely(bt)) \
__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
+ rcu_read_unlock(); \
} while (0)
#define blk_add_trace_msg(q, fmt, ...) \
blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__)
static inline bool blk_trace_note_message_enabled(struct request_queue *q)
{
- struct blk_trace *bt = q->blk_trace;
- if (likely(!bt))
- return false;
- return bt->act_mask & BLK_TC_NOTIFY;
+ struct blk_trace *bt;
+ bool ret;
+
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ ret = bt && (bt->act_mask & BLK_TC_NOTIFY);
+ rcu_read_unlock();
+ return ret;
}
extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
#include <linux/kernel.h>
#include <linux/types.h>
+#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n"
+#define BOOTCONFIG_MAGIC_LEN 12
+
/* XBC tree node */
struct xbc_node {
u16 next;
} _sifields;
} compat_siginfo_t;
-/*
- * These functions operate on 32- or 64-bit specs depending on
- * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments.
- */
-extern int compat_get_timespec(struct timespec *, const void __user *);
-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 *);
-
struct compat_iovec {
compat_uptr_t iov_base;
compat_size_t iov_len;
int get_compat_sigevent(struct sigevent *event,
const struct compat_sigevent __user *u_event);
-static inline int old_timeval32_compare(struct old_timeval32 *lhs,
- struct old_timeval32 *rhs)
-{
- if (lhs->tv_sec < rhs->tv_sec)
- return -1;
- if (lhs->tv_sec > rhs->tv_sec)
- return 1;
- return lhs->tv_usec - rhs->tv_usec;
-}
-
-static inline int old_timespec32_compare(struct old_timespec32 *lhs,
- struct old_timespec32 *rhs)
-{
- if (lhs->tv_sec < rhs->tv_sec)
- return -1;
- if (lhs->tv_sec > rhs->tv_sec)
- return 1;
- return lhs->tv_nsec - rhs->tv_nsec;
-}
-
extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat);
/*
return 0;
}
+static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
+ const struct cpumask *src2p) {
+ return cpumask_next_and(-1, src1p, src2p);
+}
+
#define for_each_cpu(cpu, mask) \
for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
#define for_each_cpu_not(cpu, mask) \
int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
unsigned int cpumask_local_spread(unsigned int i, int node);
+int cpumask_any_and_distribute(const struct cpumask *src1p,
+ const struct cpumask *src2p);
/**
* for_each_cpu - iterate over every cpu in a mask
};
#define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */
-#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */
+#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */
#define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */
#define HID_OUTPUT_FIFO_SIZE 64
int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
unsigned int data_len);
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
+#else
+#define icmpv6_ndo_send icmpv6_send
+#endif
+
#else
static inline void icmpv6_send(struct sk_buff *skb,
u8 type, u8 code, __u32 info)
{
-
}
-#endif
-#if IS_ENABLED(CONFIG_NF_NAT)
-void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
-#else
-#define icmpv6_ndo_send icmpv6_send
+static inline void icmpv6_ndo_send(struct sk_buff *skb,
+ u8 type, u8 code, __u32 info)
+{
+}
#endif
extern int icmpv6_init(void);
BUG();
}
-static int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid)
{
return -EINVAL;
}
IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0),
/* Irq domain name was allocated in __irq_domain_add() */
- IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6),
+ IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1),
/* Irq domain is an IPI domain with virq per cpu */
IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2),
*/
#define ktime_sub_ns(kt, nsval) ((kt) - (nsval))
-/* convert a timespec to ktime_t format: */
-static inline ktime_t timespec_to_ktime(struct timespec ts)
-{
- return ktime_set(ts.tv_sec, ts.tv_nsec);
-}
-
/* convert a timespec64 to ktime_t format: */
static inline ktime_t timespec64_to_ktime(struct timespec64 ts)
{
return ktime_set(ts.tv_sec, ts.tv_nsec);
}
-/* convert a timeval to ktime_t format: */
-static inline ktime_t timeval_to_ktime(struct timeval tv)
-{
- return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
-}
-
-/* Map the ktime_t to timespec conversion to ns_to_timespec function */
-#define ktime_to_timespec(kt) ns_to_timespec((kt))
-
/* Map the ktime_t to timespec conversion to ns_to_timespec function */
#define ktime_to_timespec64(kt) ns_to_timespec64((kt))
-/* 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 */
static inline s64 ktime_to_ns(const ktime_t kt)
{
extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs);
-/**
- * ktime_to_timespec_cond - convert a ktime_t variable to timespec
- * format only if the variable contains data
- * @kt: the ktime_t variable to convert
- * @ts: the timespec variable to store the result in
- *
- * Return: %true if there was a successful conversion, %false if kt was 0.
- */
-static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt,
- struct timespec *ts)
-{
- if (kt) {
- *ts = ktime_to_timespec(kt);
- return true;
- } else {
- return false;
- }
-}
-
/**
* ktime_to_timespec64_cond - convert a ktime_t variable to timespec64
* format only if the variable contains data
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_post_init_vm(struct kvm *kvm);
+void kvm_arch_pre_destroy_vm(struct kvm *kvm);
#ifndef __KVM_HAVE_ARCH_VM_ALLOC
/*
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
struct kvm_vcpu *kvm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
bool kvm_arch_has_irq_bypass(void);
u8 nic_rx_multi_path_tirs[0x1];
u8 nic_rx_multi_path_tirs_fts[0x1];
u8 allow_sniffer_and_nic_rx_shared_tir[0x1];
- u8 reserved_at_3[0x1d];
+ u8 reserved_at_3[0x4];
+ u8 sw_owner_reformat_supported[0x1];
+ u8 reserved_at_8[0x18];
+
u8 encap_general_header[0x1];
u8 reserved_at_21[0xa];
u8 log_max_packet_reformat_context[0x5];
#define NET_RX_SUCCESS 0 /* keep 'em coming, baby */
#define NET_RX_DROP 1 /* packet dropped */
+#define MAX_NEST_DEV 8
+
/*
* Transmit return codes: transmit return codes originate from three different
* namespaces:
ldev; \
ldev = netdev_lower_get_next(dev, &(iter)))
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
- struct list_head **iter);
-
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
u32 timeout;
u8 packets_op;
u8 bytes_op;
+ bool target;
};
struct ip_set;
/* Return true if "b" set is the same as "a"
* according to the create set parameters */
bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+ /* Region-locking is used */
+ bool region_lock;
+};
+
+struct ip_set_region {
+ spinlock_t lock; /* Region lock */
+ size_t ext_size; /* Size of the dynamic extensions */
+ u32 elements; /* Number of elements vs timeout */
};
/* The core set type structure */
}
#define IP_SET_INIT_KEXT(skb, opt, set) \
- { .bytes = (skb)->len, .packets = 1, \
+ { .bytes = (skb)->len, .packets = 1, .target = true,\
.timeout = ip_set_adt_opt_timeout(opt, set) }
#define IP_SET_INIT_UEXT(set) \
void psi_init(void);
void psi_task_change(struct task_struct *task, int clear, int set);
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+ bool sleep);
void psi_memstall_tick(struct task_struct *task, int cpu);
void psi_memstall_enter(unsigned long *flags);
NR_IOWAIT,
NR_MEMSTALL,
NR_RUNNING,
- NR_PSI_TASK_COUNTS = 3,
+ /*
+ * This can't have values other than 0 or 1 and could be
+ * implemented as a bit flag. But for now we still have room
+ * in the first cacheline of psi_group_cpu, and this way we
+ * don't have to special case any state tracking for it.
+ */
+ NR_ONCPU,
+ NR_PSI_TASK_COUNTS = 4,
};
/* Task state bitmasks */
#define TSK_IOWAIT (1 << NR_IOWAIT)
#define TSK_MEMSTALL (1 << NR_MEMSTALL)
#define TSK_RUNNING (1 << NR_RUNNING)
+#define TSK_ONCPU (1 << NR_ONCPU)
/* Resources that workloads could be stalled on */
enum psi_res {
}
}
+/* after that hlist_nulls_del will work */
+static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
+{
+ n->pprev = &n->next;
+ n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
+}
+
/**
* hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
* @tpos: the type * to use as a loop cursor.
} __attribute__((__aligned__(sizeof(u64))));
/*
- * The load_avg/util_avg accumulates an infinite geometric series
- * (see __update_load_avg() in kernel/sched/fair.c).
+ * The load/runnable/util_avg accumulates an infinite geometric series
+ * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
*
* [load_avg definition]
*
* load_avg = runnable% * scale_load_down(load)
*
- * where runnable% is the time ratio that a sched_entity is runnable.
- * For cfs_rq, it is the aggregated load_avg of all runnable and
- * blocked sched_entities.
+ * [runnable_avg definition]
+ *
+ * runnable_avg = runnable% * SCHED_CAPACITY_SCALE
*
* [util_avg definition]
*
* util_avg = running% * SCHED_CAPACITY_SCALE
*
- * where running% is the time ratio that a sched_entity is running on
- * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
- * and blocked sched_entities.
+ * where runnable% is the time ratio that a sched_entity is runnable and
+ * running% the time ratio that a sched_entity is running.
+ *
+ * For cfs_rq, they are the aggregated values of all runnable and blocked
+ * sched_entities.
*
- * load_avg and util_avg don't direcly factor frequency scaling and CPU
- * capacity scaling. The scaling is done through the rq_clock_pelt that
- * is used for computing those signals (see update_rq_clock_pelt())
+ * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * capacity scaling. The scaling is done through the rq_clock_pelt that is used
+ * for computing those signals (see update_rq_clock_pelt())
*
* N.B., the above ratios (runnable% and running%) themselves are in the
* range of [0, 1]. To do fixed point arithmetics, we therefore scale them
struct sched_avg {
u64 last_update_time;
u64 load_sum;
- u64 runnable_load_sum;
+ u64 runnable_sum;
u32 util_sum;
u32 period_contrib;
unsigned long load_avg;
- unsigned long runnable_load_avg;
+ unsigned long runnable_avg;
unsigned long util_avg;
struct util_est util_est;
} ____cacheline_aligned;
struct sched_entity {
/* For load-balancing: */
struct load_weight load;
- unsigned long runnable_weight;
struct rb_node run_node;
struct list_head group_node;
unsigned int on_rq;
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
+ /* cached value of my_q->h_nr_running */
+ unsigned long runnable_weight;
#endif
#ifdef CONFIG_SMP
unsigned frozen:1;
#endif
#ifdef CONFIG_BLK_CGROUP
- /* to be used once the psi infrastructure lands upstream. */
unsigned use_memdelay:1;
#endif
+#ifdef CONFIG_PSI
+ /* Stalled due to lack of memory */
+ unsigned in_memstall:1;
+#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
-#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */
#define PF_UMH 0x02000000 /* I'm an Usermodehelper process */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
}
#endif
+#ifndef arch_scale_thermal_pressure
+static __always_inline
+unsigned long arch_scale_thermal_pressure(int cpu)
+{
+ return 0;
+}
+#endif
+
static inline int task_node(const struct task_struct *p)
{
return cpu_to_node(task_cpu(p));
* @next: Next buffer in list
* @prev: Previous buffer in list
* @tstamp: Time we arrived/left
+ * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point
+ * for retransmit timer
* @rbnode: RB tree node, alternative to next/prev for netem/tcp
+ * @list: queue head
* @sk: Socket we are owned by
+ * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in
+ * fragmentation management
* @dev: Device we arrived on/are leaving by
+ * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
* @cb: Control buffer. Free for use by every layer. Put private vars here
* @_skb_refdst: destination entry (with norefcount bit)
* @sp: the security path, used for xfrm
* @pkt_type: Packet class
* @fclone: skbuff clone status
* @ipvs_property: skbuff is owned by ipvs
+ * @inner_protocol_type: whether the inner protocol is
+ * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
+ * @remcsum_offload: remote checksum offload is enabled
* @offload_fwd_mark: Packet was L2-forwarded in hardware
* @offload_l3_fwd_mark: Packet was L3-forwarded in hardware
* @tc_skip_classify: do not classify packet. set by IFB device
* @tc_index: Traffic control index
* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
+ * @head_frag: skb was allocated from page fragments,
+ * not allocated by kmalloc() or vmalloc().
* @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
* @active_extensions: active extensions (skb_ext_id types)
* @ndisc_nodetype: router type (from link layer)
* @wifi_acked_valid: wifi_acked was set
* @wifi_acked: whether frame was acked on wifi or not
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
+ * @encapsulation: indicates the inner headers in the skbuff are valid
+ * @encap_hdr_csum: software checksum is needed
+ * @csum_valid: checksum is already valid
* @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
+ * @csum_complete_sw: checksum was completed by software
+ * @csum_level: indicates the number of consecutive checksums found in
+ * the packet minus one that have been verified as
+ * CHECKSUM_UNNECESSARY (max 3)
* @dst_pending_confirm: need to confirm neighbour
* @decrypted: Decrypted SKB
* @napi_id: id of the NAPI struct this skb came from
+ * @sender_cpu: (aka @napi_id) source CPU in XPS
* @secmark: security marking
* @mark: Generic packet mark
+ * @reserved_tailroom: (aka @mark) number of bytes of free space available
+ * at the tail of an sk_buff
+ * @vlan_present: VLAN tag is present
* @vlan_proto: vlan encapsulation protocol
* @vlan_tci: vlan tag control information
* @inner_protocol: Protocol (encapsulation)
+ * @inner_ipproto: (aka @inner_protocol) stores ipproto when
+ * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
* @inner_transport_header: Inner transport layer header (encapsulation)
* @inner_network_header: Network layer header (encapsulation)
* @inner_mac_header: Link layer header (encapsulation)
#endif
#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset)
+ /* private: */
__u8 __cloned_offset[0];
+ /* public: */
__u8 cloned:1,
nohdr:1,
fclone:2,
#endif
#define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset)
+ /* private: */
__u8 __pkt_type_offset[0];
+ /* public: */
__u8 pkt_type:3;
__u8 ignore_df:1;
__u8 nf_trace:1;
#define PKT_VLAN_PRESENT_BIT 0
#endif
#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset)
+ /* private: */
__u8 __pkt_vlan_present_offset[0];
+ /* public: */
__u8 vlan_present:1;
__u8 csum_complete_sw:1;
__u8 csum_level:2;
size_t size, enum dma_data_direction dir,
enum dma_sync_target target);
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
+ size_t size, enum dma_data_direction dir, unsigned long attrs);
+
#ifdef CONFIG_SWIOTLB
extern enum swiotlb_force swiotlb_force;
extern phys_addr_t io_tlb_start, io_tlb_end;
return paddr >= io_tlb_start && paddr < io_tlb_end;
}
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
- size_t size, enum dma_data_direction dir, unsigned long attrs);
void __init swiotlb_exit(void);
unsigned int swiotlb_max_segment(void);
size_t swiotlb_max_mapping_size(struct device *dev);
{
return false;
}
-static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys,
- dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- return false;
-}
static inline void swiotlb_exit(void)
{
}
/*
* A maximum of 4 million PIDs should be enough for a while.
- * [NOTE: PID/TIDs are limited to 2^29 ~= 500+ million, see futex.h.]
+ * [NOTE: PID/TIDs are limited to 2^30 ~= 1 billion, see FUTEX_TID_MASK.]
*/
#define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \
(sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT))
#include <linux/time64.h>
#include <linux/timex.h>
-#define TIME_T_MAX (__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1)
-
typedef s32 old_time32_t;
struct old_timespec32 {
int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *);
int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *);
-#if __BITS_PER_LONG == 64
-
-/* timespec64 is defined as timespec here */
-static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
-{
- return *(const struct timespec *)&ts64;
-}
-
-static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
-{
- return *(const struct timespec64 *)&ts;
-}
-
-#else
-static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
-{
- struct timespec ret;
-
- ret.tv_sec = (time_t)ts64.tv_sec;
- ret.tv_nsec = ts64.tv_nsec;
- return ret;
-}
-
-static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
-{
- struct timespec64 ret;
-
- ret.tv_sec = ts.tv_sec;
- ret.tv_nsec = ts.tv_nsec;
- return ret;
-}
-#endif
-
-static inline int timespec_equal(const struct timespec *a,
- const struct timespec *b)
-{
- return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec);
-}
-
-/*
- * lhs < rhs: return <0
- * lhs == rhs: return 0
- * lhs > rhs: return >0
- */
-static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs)
-{
- if (lhs->tv_sec < rhs->tv_sec)
- return -1;
- if (lhs->tv_sec > rhs->tv_sec)
- return 1;
- return lhs->tv_nsec - rhs->tv_nsec;
-}
-
-/*
- * Returns true if the timespec is norm, false if denorm:
- */
-static inline bool timespec_valid(const struct timespec *ts)
-{
- /* Dates before 1970 are bogus */
- if (ts->tv_sec < 0)
- return false;
- /* Can't have more nanoseconds then a second */
- if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
- return false;
- return true;
-}
-
-/**
- * timespec_to_ns - Convert timespec to nanoseconds
- * @ts: pointer to the timespec variable to be converted
- *
- * Returns the scalar nanosecond representation of the timespec
- * parameter.
- */
-static inline s64 timespec_to_ns(const struct timespec *ts)
-{
- return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
-}
-
/**
- * ns_to_timespec - Convert nanoseconds to timespec
- * @nsec: the nanoseconds value to be converted
- *
- * Returns the timespec representation of the nsec parameter.
- */
-extern struct timespec ns_to_timespec(const s64 nsec);
-
-/**
- * timespec_add_ns - Adds nanoseconds to a timespec
- * @a: pointer to timespec to be incremented
- * @ns: unsigned nanoseconds value to be added
- *
- * This must always be inlined because its used from the x86-64 vdso,
- * which cannot call other kernel functions.
- */
-static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
-{
- a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
- a->tv_nsec = ns;
-}
-
-static inline unsigned long mktime(const unsigned int year,
- const unsigned int mon, const unsigned int day,
- const unsigned int hour, const unsigned int min,
- const unsigned int sec)
-{
- return mktime64(year, mon, day, hour, min, sec);
-}
-
-static inline bool timeval_valid(const struct timeval *tv)
-{
- /* Dates before 1970 are bogus */
- if (tv->tv_sec < 0)
- return false;
-
- /* Can't have more microseconds then a second */
- if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
- return false;
-
- return true;
-}
-
-/**
- * timeval_to_ns - Convert timeval to nanoseconds
- * @ts: pointer to the timeval variable to be converted
- *
- * Returns the scalar nanosecond representation of the timeval
- * parameter.
- */
-static inline s64 timeval_to_ns(const struct timeval *tv)
-{
- return ((s64) tv->tv_sec * NSEC_PER_SEC) +
- tv->tv_usec * NSEC_PER_USEC;
-}
-
-/**
- * ns_to_timeval - Convert nanoseconds to timeval
+ * ns_to_kernel_old_timeval - Convert nanoseconds to timeval
* @nsec: the nanoseconds value to be converted
*
* Returns the timeval representation of the nsec parameter.
*/
-extern struct timeval ns_to_timeval(const s64 nsec);
extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec);
-/*
- * Old names for the 32-bit time_t interfaces, these will be removed
- * when everything uses the new names.
- */
-#define compat_time_t old_time32_t
-#define compat_timeval old_timeval32
-#define compat_timespec old_timespec32
-#define compat_itimerspec old_itimerspec32
-#define ns_to_compat_timeval ns_to_old_timeval32
-#define get_compat_itimerspec64 get_old_itimerspec32
-#define put_compat_itimerspec64 put_old_itimerspec32
-#define compat_get_timespec64 get_old_timespec32
-#define compat_put_timespec64 put_old_timespec32
-
#endif
return ktime_get_real_seconds();
}
-static inline void getnstimeofday(struct timespec *ts)
-{
- struct timespec64 ts64;
-
- ktime_get_real_ts64(&ts64);
- *ts = timespec64_to_timespec(ts64);
-}
-
-static inline void ktime_get_ts(struct timespec *ts)
-{
- struct timespec64 ts64;
-
- ktime_get_ts64(&ts64);
- *ts = timespec64_to_timespec(ts64);
-}
-
-static inline void getrawmonotonic(struct timespec *ts)
-{
- struct timespec64 ts64;
-
- ktime_get_raw_ts64(&ts64);
- *ts = timespec64_to_timespec(ts64);
-}
-
-static inline void getboottime(struct timespec *ts)
-{
- struct timespec64 ts64;
-
- getboottime64(&ts64);
- *ts = timespec64_to_timespec(ts64);
-}
-
#endif
void (*write_wakeup)(struct tty_port *port);
};
+extern const struct tty_port_client_operations tty_port_default_client_ops;
+
struct tty_port {
struct tty_bufhead buf; /* Locked internally */
struct tty_struct *tty; /* Back pointer */
typedef __kernel_ptrdiff_t ptrdiff_t;
#endif
-#ifndef _TIME_T
-#define _TIME_T
-typedef __kernel_old_time_t time_t;
-#endif
-
#ifndef _CLOCK_T
#define _CLOCK_T
typedef __kernel_clock_t clock_t;
/* Hub needs extra delay after resetting its port. */
#define USB_QUIRK_HUB_SLOW_RESET BIT(14)
+/* device has blacklisted endpoints */
+#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15)
+
#endif /* __LINUX_USB_QUIRKS_H */
#include <linux/types.h>
#include <linux/in6.h>
#include <linux/siphash.h>
+#include <linux/string.h>
#include <uapi/linux/if_ether.h>
struct sk_buff;
void *data_end;
};
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+ struct flow_dissector_key_basic *key_basic)
+{
+ memset(key_control, 0, sizeof(*key_control));
+ memset(key_basic, 0, sizeof(*key_basic));
+}
+
#endif
* struct sock_common - minimal network layer representation of sockets
* @skc_daddr: Foreign IPv4 addr
* @skc_rcv_saddr: Bound local IPv4 addr
+ * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
* @skc_hash: hash value used with various protocol lookup tables
* @skc_u16hashes: two u16 hash values used by UDP lookup tables
* @skc_dport: placeholder for inet_dport/tw_dport
* @skc_num: placeholder for inet_num/tw_num
+ * @skc_portpair: __u32 union of @skc_dport & @skc_num
* @skc_family: network address family
* @skc_state: Connection state
* @skc_reuse: %SO_REUSEADDR setting
* @skc_reuseport: %SO_REUSEPORT setting
+ * @skc_ipv6only: socket is IPV6 only
+ * @skc_net_refcnt: socket is using net ref counting
* @skc_bound_dev_if: bound device index if != 0
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
* @skc_prot: protocol handlers inside a network family
* @skc_net: reference to the network namespace of this socket
+ * @skc_v6_daddr: IPV6 destination address
+ * @skc_v6_rcv_saddr: IPV6 source address
+ * @skc_cookie: socket's cookie value
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
* @skc_flags: place holder for sk_flags
* %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ * @skc_listener: connection request listener socket (aka rsk_listener)
+ * [union with @skc_flags]
+ * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
+ * [union with @skc_flags]
* @skc_incoming_cpu: record/match cpu processing incoming packets
+ * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
+ * [union with @skc_incoming_cpu]
+ * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
+ * [union with @skc_incoming_cpu]
* @skc_refcnt: reference count
*
* This is the minimal network layer representation of sockets, the header
* @sk_dst_cache: destination cache
* @sk_dst_pending_confirm: need to confirm neighbour
* @sk_policy: flow policy
+ * @sk_rx_skb_cache: cache copy of recently accessed RX skb
* @sk_receive_queue: incoming packets
* @sk_wmem_alloc: transmit queue bytes committed
* @sk_tsq_flags: TCP Small Queues flags
* @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
+ * @sk_route_forced_caps: static, forced route capabilities
+ * (set in tcp_init_sock())
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
* @sk_frag: cached page frag
* @sk_peek_off: current peek_offset value
* @sk_send_head: front of stuff to transmit
+ * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
+ * @sk_tx_skb_cache: cache copy of recently accessed TX skb
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_cgrp_data: cgroup data for this cgroup
* @sk_write_space: callback to indicate there is bf sending space available
* @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
* @sk_backlog_rcv: callback to process the backlog
+ * @sk_validate_xmit_skb: ptr to an optional validate function
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
+ * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage
* @sk_rcu: used during RCU grace period
* @sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
* @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+ * @sk_txtime_report_errors: set report errors mode for SO_TXTIME
* @sk_txtime_unused: unused txtime flags
*/
struct sock {
struct sk_filter __rcu *sk_filter;
union {
struct socket_wq __rcu *sk_wq;
+ /* private: */
struct socket_wq *sk_wq_raw;
+ /* public: */
};
#ifdef CONFIG_XFRM
struct xfrm_policy __rcu *sk_policy[2];
* sk_wmem_alloc_get - returns write allocations
* @sk: socket
*
- * Returns sk_wmem_alloc minus initial offset of one
+ * Return: sk_wmem_alloc minus initial offset of one
*/
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
* sk_rmem_alloc_get - returns read allocations
* @sk: socket
*
- * Returns sk_rmem_alloc
+ * Return: sk_rmem_alloc
*/
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
* sk_has_allocations - check if allocations are outstanding
* @sk: socket
*
- * Returns true if socket has write or read allocations
+ * Return: true if socket has write or read allocations
*/
static inline bool sk_has_allocations(const struct sock *sk)
{
* skwq_has_sleeper - check if there are any waiting processes
* @wq: struct socket_wq
*
- * Returns true if socket_wq has waiting processes
+ * Return: true if socket_wq has waiting processes
*
* The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
* barrier call. They were added due to the race found within the tcp code.
* gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
* inside other socket operations and end up recursing into sk_page_frag()
* while it's already in use.
+ *
+ * Return: a per task page_frag if context allows that,
+ * otherwise a per socket one.
*/
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
&skb_shinfo(skb)->tskey);
}
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
/**
* sk_eat_skb - Release a skb if it is no longer needed
* @sk: socket to eat this skb from
* This routine must be called with interrupts disabled or with the socket
* locked so that the sk_buff queue operation is ok.
*/
-DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
{
__skb_unlink(skb, &sk->sk_receive_queue);
#define ISCSI_REASON_BOOKMARK_INVALID 9
#define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10
#define ISCSI_REASON_NEGOTIATION_RESET 11
-#define ISCSI_REASON_WAITING_FOR_LOGOUT 12
/* Max. number of Key=Value pairs in a text message */
#define MAX_KEY_VALUE_PAIRS 8192
struct list_head list; /* list of all substream for given stream */
int stream; /* direction */
int number; /* substream number */
- unsigned int opened: 1, /* open flag */
- append: 1, /* append flag (merge more streams) */
- active_sensing: 1; /* send active sensing when close */
+ bool opened; /* open flag */
+ bool append; /* append flag (merge more streams) */
+ bool active_sensing; /* send active sensing when close */
int use_count; /* use counter (for output) */
size_t bytes;
struct snd_rawmidi *rmidi;
struct snd_ctl_elem_value *ucontrol);
int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol);
-int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol);
int snd_soc_dapm_info_pin_switch(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_info *uinfo);
int snd_soc_dapm_get_pin_switch(struct snd_kcontrol *kcontrol,
);
#endif /* CONFIG_DETECT_HUNG_TASK */
-DECLARE_EVENT_CLASS(sched_move_task_template,
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes.
+ */
+TRACE_EVENT(sched_move_numa,
TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
__entry->dst_cpu, __entry->dst_nid)
);
-/*
- * Tracks migration of tasks from one runqueue to another. Can be used to
- * detect if automatic NUMA balancing is bouncing between nodes
- */
-DEFINE_EVENT(sched_move_task_template, sched_move_numa,
- TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
- TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
- TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
- TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-TRACE_EVENT(sched_swap_numa,
+DECLARE_EVENT_CLASS(sched_numa_pair_template,
TP_PROTO(struct task_struct *src_tsk, int src_cpu,
struct task_struct *dst_tsk, int dst_cpu),
__entry->src_ngid = task_numa_group_id(src_tsk);
__entry->src_cpu = src_cpu;
__entry->src_nid = cpu_to_node(src_cpu);
- __entry->dst_pid = task_pid_nr(dst_tsk);
- __entry->dst_tgid = task_tgid_nr(dst_tsk);
- __entry->dst_ngid = task_numa_group_id(dst_tsk);
+ __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0;
+ __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0;
+ __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0;
__entry->dst_cpu = dst_cpu;
- __entry->dst_nid = cpu_to_node(dst_cpu);
+ __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1;
),
TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
__entry->dst_cpu, __entry->dst_nid)
);
+DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa,
+
+ TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+ struct task_struct *dst_tsk, int dst_cpu),
+
+ TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
+DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa,
+
+ TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+ struct task_struct *dst_tsk, int dst_cpu),
+
+ TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
+
/*
* Tracepoint for waking a polling cpu without an IPI.
*/
TP_PROTO(struct rq *rq),
TP_ARGS(rq));
+DECLARE_TRACE(pelt_thermal_tp,
+ TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
+
DECLARE_TRACE(pelt_irq_tp,
TP_PROTO(struct rq *rq),
TP_ARGS(rq));
typedef __kernel_long_t __kernel_off_t;
typedef long long __kernel_loff_t;
typedef __kernel_long_t __kernel_old_time_t;
+#ifndef __KERNEL__
typedef __kernel_long_t __kernel_time_t;
+#endif
typedef long long __kernel_time64_t;
typedef __kernel_long_t __kernel_clock_t;
typedef int __kernel_timer_t;
* supports redirection to the egress interface, and accepts no
* flag at all.
*
- * The same effect can be attained with the more generic
- * **bpf_redirect_map**\ (), which requires specific maps to be
- * used but offers better performance.
+ * The same effect can also be attained with the more generic
+ * **bpf_redirect_map**\ (), which uses a BPF map to store the
+ * redirect target instead of providing it directly to the helper.
* Return
* For XDP, the helper returns **XDP_REDIRECT** on success or
* **XDP_ABORTED** on error. For other program types, the values
* the caller. Any higher bits in the *flags* argument must be
* unset.
*
- * When used to redirect packets to net devices, this helper
- * provides a high performance increase over **bpf_redirect**\ ().
- * This is due to various implementation details of the underlying
- * mechanisms, one of which is the fact that **bpf_redirect_map**\
- * () tries to send packet as a "bulk" to the device.
+ * See also bpf_redirect(), which only supports redirecting to an
+ * ifindex, but doesn't require a map to do so.
* Return
- * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * **XDP_REDIRECT** on success, or the value of the two lower bits
+ * of the **flags* argument on error.
*
* int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
* Description
IPS_UNTRACKED_BIT = 12,
IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
+#ifdef __KERNEL__
+ /* Re-purposed for in-kernel use:
+ * Tags a conntrack entry that clashed with an existing entry
+ * on insert.
+ */
+ IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT,
+ IPS_NAT_CLASH = IPS_UNTRACKED,
+#endif
+
/* Conntrack got a helper explicitly attached via CT target. */
IPS_HELPER_BIT = 13,
IPS_HELPER = (1 << IPS_HELPER_BIT),
*/
IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
- IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
+ IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED |
+ IPS_OFFLOAD),
__IPS_MAX_BIT = 15,
};
static __always_inline unsigned long __swab(const unsigned long y)
{
-#if BITS_PER_LONG == 64
+#if __BITS_PER_LONG == 64
return __swab64(y);
-#else /* BITS_PER_LONG == 32 */
+#else /* __BITS_PER_LONG == 32 */
return __swab32(y);
#endif
}
#include <linux/types.h>
#include <linux/time_types.h>
+#ifndef __KERNEL__
#ifndef _STRUCT_TIMESPEC
#define _STRUCT_TIMESPEC
struct timespec {
__kernel_suseconds_t tv_usec; /* microseconds */
};
+struct itimerspec {
+ struct timespec it_interval;/* timer period */
+ struct timespec it_value; /* timer expiration */
+};
+
+struct itimerval {
+ struct timeval it_interval;/* timer interval */
+ struct timeval it_value; /* current value */
+};
+#endif
+
struct timezone {
int tz_minuteswest; /* minutes west of Greenwich */
int tz_dsttime; /* type of dst correction */
#define ITIMER_VIRTUAL 1
#define ITIMER_PROF 2
-struct itimerspec {
- struct timespec it_interval; /* timer period */
- struct timespec it_value; /* timer expiration */
-};
-
-struct itimerval {
- struct timeval it_interval; /* timer interval */
- struct timeval it_value; /* current value */
-};
-
/*
* The IDs of the various system clocks (for POSIX.1b interval timers):
*/
* ACA (Accessory Charger Adapters)
*/
enum usb_charger_type {
- UNKNOWN_TYPE,
- SDP_TYPE,
- DCP_TYPE,
- CDP_TYPE,
- ACA_TYPE,
+ UNKNOWN_TYPE = 0,
+ SDP_TYPE = 1,
+ DCP_TYPE = 2,
+ CDP_TYPE = 3,
+ ACA_TYPE = 4,
};
/* USB charger state */
enum usb_charger_state {
- USB_CHARGER_DEFAULT,
- USB_CHARGER_PRESENT,
- USB_CHARGER_ABSENT,
+ USB_CHARGER_DEFAULT = 0,
+ USB_CHARGER_PRESENT = 1,
+ USB_CHARGER_ABSENT = 2,
};
#endif /* _UAPI__LINUX_USB_CHARGER_H */
depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING
depends on SMP
+config SCHED_THERMAL_PRESSURE
+ bool "Enable periodic averaging of thermal pressure"
+ depends on SMP
+
config BSD_PROCESS_ACCT
bool "BSD Process Accounting"
depends on MULTIUSER
config BOOT_CONFIG
bool "Boot config support"
- depends on BLK_DEV_INITRD
- default y
+ select BLK_DEV_INITRD
help
Extra boot config allows system admin to pass a config file as
complemental extension of kernel cmdline when booting.
The boot config file must be attached at the end of initramfs
- with checksum and size.
+ with checksum, size and magic word.
See <file:Documentation/admin-guide/bootconfig.rst> for details.
If unsure, say Y.
{
struct xbc_node *knode, *vnode;
char *end = buf + size;
- char c = '\"';
const char *val;
int ret;
return ret;
vnode = xbc_node_get_child(knode);
- ret = snprintf(buf, rest(buf, end), "%s%c", xbc_namebuf,
- vnode ? '=' : ' ');
- if (ret < 0)
- return ret;
- buf += ret;
- if (!vnode)
+ if (!vnode) {
+ ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf);
+ if (ret < 0)
+ return ret;
+ buf += ret;
continue;
-
- c = '\"';
+ }
xbc_array_for_each_value(vnode, val) {
- ret = snprintf(buf, rest(buf, end), "%c%s", c, val);
+ ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ",
+ xbc_namebuf, val);
if (ret < 0)
return ret;
buf += ret;
- c = ',';
}
- if (rest(buf, end) > 2)
- strcpy(buf, "\" ");
- buf += 2;
}
return buf - (end - size);
return new_cmdline;
}
-u32 boot_config_checksum(unsigned char *p, u32 size)
+static u32 boot_config_checksum(unsigned char *p, u32 size)
{
u32 ret = 0;
if (!initrd_end)
goto not_found;
- hdr = (u32 *)(initrd_end - 8);
+ data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
+ if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+ goto not_found;
+
+ hdr = (u32 *)(data - 8);
size = hdr[0];
csum = hdr[1];
}
#else
#define setup_boot_config(cmdline) do { } while (0)
+
+static int __init warn_bootconfig(char *str)
+{
+ pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n");
+ return 0;
+}
+early_param("bootconfig", warn_bootconfig);
+
#endif
/* Change NUL term back to "=", to make "param" the whole string. */
ipc_assert_locked_object(&sma->sem_perm);
list_del(&un->list_id);
- /* we are the last process using this ulp, acquiring ulp->lock
- * isn't required. Besides that, we are also protected against
- * IPC_RMID as we hold sma->sem_perm lock now
- */
+ spin_lock(&ulp->lock);
list_del_rcu(&un->list_proc);
+ spin_unlock(&ulp->lock);
/* perform adjustments registered in un */
for (i = 0; i < sma->sem_nsems; i++) {
audit_log_end(ab);
}
-static int audit_set_feature(struct sk_buff *skb)
+static int audit_set_feature(struct audit_features *uaf)
{
- struct audit_features *uaf;
int i;
BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names));
- uaf = nlmsg_data(nlmsg_hdr(skb));
/* if there is ever a version 2 we should handle that here */
{
u32 seq;
void *data;
+ int data_len;
int err;
struct audit_buffer *ab;
u16 msg_type = nlh->nlmsg_type;
seq = nlh->nlmsg_seq;
data = nlmsg_data(nlh);
+ data_len = nlmsg_len(nlh);
switch (msg_type) {
case AUDIT_GET: {
struct audit_status s;
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
- memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+ memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
if (s.mask & AUDIT_STATUS_ENABLED) {
err = audit_set_enabled(s.enabled);
if (err < 0)
return err;
break;
case AUDIT_SET_FEATURE:
- err = audit_set_feature(skb);
+ if (data_len < sizeof(struct audit_features))
+ return -EINVAL;
+ err = audit_set_feature(data);
if (err)
return err;
break;
err = audit_filter(msg_type, AUDIT_FILTER_USER);
if (err == 1) { /* match or error */
+ char *str = data;
+
err = 0;
if (msg_type == AUDIT_USER_TTY) {
err = tty_audit_push();
break;
}
audit_log_user_recv_msg(&ab, msg_type);
- if (msg_type != AUDIT_USER_TTY)
+ if (msg_type != AUDIT_USER_TTY) {
+ /* ensure NULL termination */
+ str[data_len - 1] = '\0';
audit_log_format(ab, " msg='%.*s'",
AUDIT_MESSAGE_TEXT_MAX,
- (char *)data);
- else {
- int size;
-
+ str);
+ } else {
audit_log_format(ab, " data=");
- size = nlmsg_len(nlh);
- if (size > 0 &&
- ((unsigned char *)data)[size - 1] == '\0')
- size--;
- audit_log_n_untrustedstring(ab, data, size);
+ if (data_len > 0 && str[data_len - 1] == '\0')
+ data_len--;
+ audit_log_n_untrustedstring(ab, str, data_len);
}
audit_log_end(ab);
}
break;
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
- if (nlmsg_len(nlh) < sizeof(struct audit_rule_data))
+ if (data_len < sizeof(struct audit_rule_data))
return -EINVAL;
if (audit_enabled == AUDIT_LOCKED) {
audit_log_common_recv_msg(audit_context(), &ab,
audit_log_end(ab);
return -EPERM;
}
- err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh));
+ err = audit_rule_change(msg_type, seq, data, data_len);
break;
case AUDIT_LIST_RULES:
err = audit_list_rules_send(skb, seq);
case AUDIT_MAKE_EQUIV: {
void *bufp = data;
u32 sizes[2];
- size_t msglen = nlmsg_len(nlh);
+ size_t msglen = data_len;
char *old, *new;
err = -EINVAL;
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
- memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+ memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
/* check if new data is valid */
if ((s.enabled != 0 && s.enabled != 1) ||
(s.log_passwd != 0 && s.log_passwd != 1))
bufp = data->buf;
for (i = 0; i < data->field_count; i++) {
struct audit_field *f = &entry->rule.fields[i];
+ u32 f_val;
err = -EINVAL;
goto exit_free;
f->type = data->fields[i];
- f->val = data->values[i];
+ f_val = data->values[i];
/* Support legacy tests for a valid loginuid */
- if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
+ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) {
f->type = AUDIT_LOGINUID_SET;
- f->val = 0;
+ f_val = 0;
entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
}
case AUDIT_SUID:
case AUDIT_FSUID:
case AUDIT_OBJ_UID:
- f->uid = make_kuid(current_user_ns(), f->val);
+ f->uid = make_kuid(current_user_ns(), f_val);
if (!uid_valid(f->uid))
goto exit_free;
break;
case AUDIT_SGID:
case AUDIT_FSGID:
case AUDIT_OBJ_GID:
- f->gid = make_kgid(current_user_ns(), f->val);
+ f->gid = make_kgid(current_user_ns(), f_val);
if (!gid_valid(f->gid))
goto exit_free;
break;
case AUDIT_ARCH:
+ f->val = f_val;
entry->rule.arch_f = f;
break;
case AUDIT_SUBJ_USER:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
- str = audit_unpack_string(&bufp, &remain, f->val);
- if (IS_ERR(str))
+ str = audit_unpack_string(&bufp, &remain, f_val);
+ if (IS_ERR(str)) {
+ err = PTR_ERR(str);
goto exit_free;
- entry->rule.buflen += f->val;
-
+ }
+ entry->rule.buflen += f_val;
+ f->lsm_str = str;
err = security_audit_rule_init(f->type, f->op, str,
(void **)&f->lsm_rule);
/* Keep currently invalid fields around in case they
pr_warn("audit rule for LSM \'%s\' is invalid\n",
str);
err = 0;
- }
- if (err) {
- kfree(str);
+ } else if (err)
goto exit_free;
- } else
- f->lsm_str = str;
break;
case AUDIT_WATCH:
- str = audit_unpack_string(&bufp, &remain, f->val);
- if (IS_ERR(str))
+ str = audit_unpack_string(&bufp, &remain, f_val);
+ if (IS_ERR(str)) {
+ err = PTR_ERR(str);
goto exit_free;
- entry->rule.buflen += f->val;
-
- err = audit_to_watch(&entry->rule, str, f->val, f->op);
+ }
+ err = audit_to_watch(&entry->rule, str, f_val, f->op);
if (err) {
kfree(str);
goto exit_free;
}
+ entry->rule.buflen += f_val;
break;
case AUDIT_DIR:
- str = audit_unpack_string(&bufp, &remain, f->val);
- if (IS_ERR(str))
+ str = audit_unpack_string(&bufp, &remain, f_val);
+ if (IS_ERR(str)) {
+ err = PTR_ERR(str);
goto exit_free;
- entry->rule.buflen += f->val;
-
+ }
err = audit_make_tree(&entry->rule, str, f->op);
kfree(str);
if (err)
goto exit_free;
+ entry->rule.buflen += f_val;
break;
case AUDIT_INODE:
+ f->val = f_val;
err = audit_to_inode(&entry->rule, f);
if (err)
goto exit_free;
break;
case AUDIT_FILTERKEY:
- if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN)
+ if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN)
goto exit_free;
- str = audit_unpack_string(&bufp, &remain, f->val);
- if (IS_ERR(str))
+ str = audit_unpack_string(&bufp, &remain, f_val);
+ if (IS_ERR(str)) {
+ err = PTR_ERR(str);
goto exit_free;
- entry->rule.buflen += f->val;
+ }
+ entry->rule.buflen += f_val;
entry->rule.filterkey = str;
break;
case AUDIT_EXE:
- if (entry->rule.exe || f->val > PATH_MAX)
+ if (entry->rule.exe || f_val > PATH_MAX)
goto exit_free;
- str = audit_unpack_string(&bufp, &remain, f->val);
+ str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
- entry->rule.buflen += f->val;
-
- audit_mark = audit_alloc_mark(&entry->rule, str, f->val);
+ audit_mark = audit_alloc_mark(&entry->rule, str, f_val);
if (IS_ERR(audit_mark)) {
kfree(str);
err = PTR_ERR(audit_mark);
goto exit_free;
}
+ entry->rule.buflen += f_val;
entry->rule.exe = audit_mark;
break;
+ default:
+ f->val = f_val;
+ break;
}
}
* EFAULT - verifier bug
* 0 - 99% match. The last 1% is validated by the verifier.
*/
-int btf_check_func_type_match(struct bpf_verifier_log *log,
- struct btf *btf1, const struct btf_type *t1,
- struct btf *btf2, const struct btf_type *t2)
+static int btf_check_func_type_match(struct bpf_verifier_log *log,
+ struct btf *btf1, const struct btf_type *t1,
+ struct btf *btf2, const struct btf_type *t2)
{
const struct btf_param *args1, *args2;
const char *fn1, *fn2, *s1, *s2;
union {
struct bpf_htab *htab;
struct pcpu_freelist_node fnode;
+ struct htab_elem *batch_flink;
};
};
};
bpf_map_area_free(htab->elems);
}
+/* The LRU list has a lock (lru_lock). Each htab bucket has a lock
+ * (bucket_lock). If both locks need to be acquired together, the lock
+ * order is always lru_lock -> bucket_lock and this only happens in
+ * bpf_lru_list.c logic. For example, certain code path of
+ * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(),
+ * will acquire lru_lock first followed by acquiring bucket_lock.
+ *
+ * In hashtab.c, to avoid deadlock, lock acquisition of
+ * bucket_lock followed by lru_lock is not allowed. In such cases,
+ * bucket_lock needs to be released first before acquiring lru_lock.
+ */
static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
u32 hash)
{
void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
u32 batch, max_count, size, bucket_size;
+ struct htab_elem *node_to_free = NULL;
u64 elem_map_flags, map_flags;
struct hlist_nulls_head *head;
struct hlist_nulls_node *n;
- unsigned long flags;
+ unsigned long flags = 0;
+ bool locked = false;
struct htab_elem *l;
struct bucket *b;
int ret = 0;
dst_val = values;
b = &htab->buckets[batch];
head = &b->head;
- raw_spin_lock_irqsave(&b->lock, flags);
+ /* do not grab the lock unless need it (bucket_cnt > 0). */
+ if (locked)
+ raw_spin_lock_irqsave(&b->lock, flags);
bucket_cnt = 0;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
bucket_cnt++;
+ if (bucket_cnt && !locked) {
+ locked = true;
+ goto again_nocopy;
+ }
+
if (bucket_cnt > (max_count - total)) {
if (total == 0)
ret = -ENOSPC;
+ /* Note that since bucket_cnt > 0 here, it is implicit
+ * that the locked was grabbed, so release it.
+ */
raw_spin_unlock_irqrestore(&b->lock, flags);
rcu_read_unlock();
this_cpu_dec(bpf_prog_active);
if (bucket_cnt > bucket_size) {
bucket_size = bucket_cnt;
+ /* Note that since bucket_cnt > 0 here, it is implicit
+ * that the locked was grabbed, so release it.
+ */
raw_spin_unlock_irqrestore(&b->lock, flags);
rcu_read_unlock();
this_cpu_dec(bpf_prog_active);
goto alloc;
}
+ /* Next block is only safe to run if you have grabbed the lock */
+ if (!locked)
+ goto next_batch;
+
hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
memcpy(dst_key, l->key, key_size);
}
if (do_delete) {
hlist_nulls_del_rcu(&l->hash_node);
- if (is_lru_map)
- bpf_lru_push_free(&htab->lru, &l->lru_node);
- else
+
+ /* bpf_lru_push_free() will acquire lru_lock, which
+ * may cause deadlock. See comments in function
+ * prealloc_lru_pop(). Let us do bpf_lru_push_free()
+ * after releasing the bucket lock.
+ */
+ if (is_lru_map) {
+ l->batch_flink = node_to_free;
+ node_to_free = l;
+ } else {
free_htab_elem(htab, l);
+ }
}
dst_key += key_size;
dst_val += value_size;
}
raw_spin_unlock_irqrestore(&b->lock, flags);
+ locked = false;
+
+ while (node_to_free) {
+ l = node_to_free;
+ node_to_free = node_to_free->batch_flink;
+ bpf_lru_push_free(&htab->lru, &l->lru_node);
+ }
+
+next_batch:
/* If we are not copying data, we can go to next bucket and avoid
* unlocking the rcu.
*/
ulen = info->jited_prog_len;
info->jited_prog_len = aux->offload->jited_len;
- if (info->jited_prog_len & ulen) {
+ if (info->jited_prog_len && ulen) {
uinsns = u64_to_user_ptr(info->jited_prog_insns);
ulen = min_t(u32, info->jited_prog_len, ulen);
if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
#include <linux/uaccess.h>
-static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv)
-{
- return (!access_ok(ctv, sizeof(*ctv)) ||
- __get_user(tv->tv_sec, &ctv->tv_sec) ||
- __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv)
-{
- return (!access_ok(ctv, sizeof(*ctv)) ||
- __put_user(tv->tv_sec, &ctv->tv_sec) ||
- __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts)
-{
- return (!access_ok(cts, sizeof(*cts)) ||
- __get_user(ts->tv_sec, &cts->tv_sec) ||
- __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts)
-{
- return (!access_ok(cts, sizeof(*cts)) ||
- __put_user(ts->tv_sec, &cts->tv_sec) ||
- __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-int compat_get_timeval(struct timeval *tv, const void __user *utv)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0;
- else
- return __compat_get_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_get_timeval);
-
-int compat_put_timeval(const struct timeval *tv, void __user *utv)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0;
- else
- return __compat_put_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_put_timeval);
-
-int compat_get_timespec(struct timespec *ts, const void __user *uts)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
- else
- return __compat_get_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_get_timespec);
-
-int compat_put_timespec(const struct timespec *ts, void __user *uts)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
- else
- return __compat_put_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_put_timespec);
-
#ifdef __ARCH_WANT_SYS_SIGPROCMASK
/*
phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
phys_addr_t mask = align - 1;
unsigned long node = rmem->fdt_node;
+ bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
struct cma *cma;
int err;
+ if (size_cmdline != -1 && default_cma) {
+ pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n",
+ rmem->name);
+ return -EBUSY;
+ }
+
if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
of_get_flat_dt_prop(node, "no-map", NULL))
return -EINVAL;
/* Architecture specific contiguous memory fixup. */
dma_contiguous_early_fixup(rmem->base, rmem->size);
- if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+ if (default_cma)
dma_contiguous_set_default(cma);
rmem->ops = &rmem_cma_ops;
*/
unsigned int zone_dma_bits __ro_after_init = 24;
-static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
- if (!dev->dma_mask) {
- dev_err_once(dev, "DMA map on device without dma_mask\n");
- } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
- dev_err_once(dev,
- "overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
- &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
- }
- WARN_ON_ONCE(1);
-}
-
static inline dma_addr_t phys_to_dma_direct(struct device *dev,
phys_addr_t phys)
{
EXPORT_SYMBOL(dma_direct_unmap_sg);
#endif
-static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
- size_t size)
-{
- return swiotlb_force != SWIOTLB_FORCE &&
- dma_capable(dev, dma_addr, size, true);
-}
-
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)
phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dma_addr = phys_to_dma(dev, phys);
- if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
- !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
- report_addr(dev, dma_addr, size);
+ if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+ return swiotlb_map(dev, phys, size, dir, attrs);
+
+ if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+ if (swiotlb_force != SWIOTLB_NO_FORCE)
+ return swiotlb_map(dev, phys, size, dir, attrs);
+
+ dev_WARN_ONCE(dev, 1,
+ "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+ &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
return DMA_MAPPING_ERROR;
}
dma_addr_t dma_addr = paddr;
if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
- report_addr(dev, dma_addr, size);
+ dev_err_once(dev,
+ "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+ &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+ WARN_ON_ONCE(1);
return DMA_MAPPING_ERROR;
}
}
#endif /* CONFIG_MMU */
-/*
- * 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.
- */
int dma_direct_supported(struct device *dev, u64 mask)
{
- u64 min_mask;
+ u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
- if (IS_ENABLED(CONFIG_ZONE_DMA))
- min_mask = DMA_BIT_MASK(zone_dma_bits);
- else
- min_mask = DMA_BIT_MASK(32);
-
- min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
+ /*
+ * 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 1;
/*
* This check needs to be against the actual bit mask value, so
* use __phys_to_dma() here so that the SME encryption mask isn't
* part of the check.
*/
+ if (IS_ENABLED(CONFIG_ZONE_DMA))
+ min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
return mask >= __phys_to_dma(dev, min_mask);
}
#include <linux/cache.h>
#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/spinlock.h>
}
/*
- * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
* to the device copy the data into it as well.
*/
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
- size_t size, enum dma_data_direction dir, unsigned long attrs)
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
{
- trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
+ phys_addr_t swiotlb_addr;
+ dma_addr_t dma_addr;
- if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
- dev_warn_ratelimited(dev,
- "Cannot do DMA to address %pa\n", phys);
- return false;
- }
+ trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+ swiotlb_force);
- /* Oh well, have to allocate and map a bounce buffer. */
- *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
- *phys, size, size, dir, attrs);
- if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
- return false;
+ swiotlb_addr = swiotlb_tbl_map_single(dev,
+ __phys_to_dma(dev, io_tlb_start),
+ paddr, size, size, dir, attrs);
+ if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+ return DMA_MAPPING_ERROR;
/* Ensure that the address returned is DMA'ble */
- *dma_addr = __phys_to_dma(dev, *phys);
- if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
- swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
+ dma_addr = __phys_to_dma(dev, swiotlb_addr);
+ if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+ swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC);
- return false;
+ dev_WARN_ONCE(dev, 1,
+ "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+ &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+ return DMA_MAPPING_ERROR;
}
- return true;
+ if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(swiotlb_addr, size, dir);
+ return dma_addr;
}
size_t swiotlb_max_mapping_size(struct device *dev)
extern bool irq_can_set_affinity_usr(unsigned int irq);
-extern int irq_select_affinity_usr(unsigned int irq);
-
extern void irq_set_thread_affinity(struct irq_desc *desc);
extern int irq_do_set_affinity(struct irq_data *data,
{
return irq_select_affinity(irq_desc_get_irq(desc));
}
-#endif
+#endif /* CONFIG_AUTO_IRQ_AFFINITY */
+#endif /* CONFIG_SMP */
-/*
- * Called when a bogus affinity is set via /proc/irq
- */
-int irq_select_affinity_usr(unsigned int irq)
-{
- struct irq_desc *desc = irq_to_desc(irq);
- unsigned long flags;
- int ret;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- ret = irq_setup_affinity(desc);
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- return ret;
-}
-#endif
/**
* irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
return show_irq_affinity(AFFINITY_LIST, m);
}
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+ /*
+ * If the interrupt is started up already then this fails. The
+ * interrupt is assigned to an online CPU already. There is no
+ * point to move it around randomly. Tell user space that the
+ * selected mask is bogus.
+ *
+ * If not then any change to the affinity is pointless because the
+ * startup code invokes irq_setup_affinity() which will select
+ * a online CPU anyway.
+ */
+ return -EINVAL;
+}
+#else
+/* ALPHA magic affinity auto selector. Keep it for historical reasons. */
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+ return irq_select_affinity(irq);
+}
+#endif
static ssize_t write_irq_affinity(int type, struct file *file,
const char __user *buffer, size_t count, loff_t *pos)
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
+ /*
+ * Thread is going to call schedule(), do not preempt it,
+ * or the caller of kthread_park() may spend more time in
+ * wait_task_inactive().
+ */
+ preempt_disable();
complete(&self->parked);
- schedule();
+ schedule_preempt_disabled();
+ preempt_enable();
}
__set_current_state(TASK_RUNNING);
}
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
+ /*
+ * Thread is going to call schedule(), do not preempt it,
+ * or the creator may spend more time in wait_task_inactive().
+ */
+ preempt_disable();
complete(done);
- schedule();
+ schedule_preempt_disabled();
+ preempt_enable();
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
* hibernation for allocations made while saving the image and for device
* drivers, in case they need to allocate memory from their hibernation
* callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough
- * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through
+ * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through
* /sys/power/reserved_size, respectively). To make this happen, we compute the
* total number of available page frames and allocate at least
*
if (task_has_idle_policy(p)) {
load->weight = scale_load(WEIGHT_IDLEPRIO);
load->inv_weight = WMULT_IDLEPRIO;
- p->se.runnable_weight = load->weight;
return;
}
} else {
load->weight = scale_load(sched_prio_to_weight[prio]);
load->inv_weight = sched_prio_to_wmult[prio];
- p->se.runnable_weight = load->weight;
}
}
if (cpumask_equal(p->cpus_ptr, new_mask))
goto out;
- dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+ /*
+ * Picking a ~random cpu helps in cases where we are changing affinity
+ * for groups of tasks (ie. cpuset), so that load balancing is not
+ * immediately required to distribute the tasks within their new mask.
+ */
+ dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
if (dest_cpu >= nr_cpu_ids) {
ret = -EINVAL;
goto out;
return ns;
}
+DEFINE_PER_CPU(unsigned long, thermal_pressure);
+
+void arch_set_thermal_pressure(struct cpumask *cpus,
+ unsigned long th_pressure)
+{
+ int cpu;
+
+ for_each_cpu(cpu, cpus)
+ WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
+}
+
/*
* This function gets called by the timer code, with HZ frequency.
* We call it with interrupts disabled.
struct rq *rq = cpu_rq(cpu);
struct task_struct *curr = rq->curr;
struct rq_flags rf;
+ unsigned long thermal_pressure;
+ arch_scale_freq_tick();
sched_clock_tick();
rq_lock(rq, &rf);
update_rq_clock(rq);
+ thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+ update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
curr->sched_class->task_tick(rq, curr, 0);
calc_global_load_tick(rq);
psi_task_tick(rq);
if (cpu_is_offline(cpu))
goto out_unlock;
- curr = rq->curr;
update_rq_clock(rq);
if (!is_idle_task(curr)) {
*/
++*switch_count;
+ psi_sched_switch(prev, next, !task_on_rq_queued(prev));
+
trace_sched_switch(preempt, prev, next);
/* Also unlocks the rq: */
return cpupri;
}
+static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
+ struct cpumask *lowest_mask, int idx)
+{
+ struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
+ int skip = 0;
+
+ if (!atomic_read(&(vec)->count))
+ skip = 1;
+ /*
+ * When looking at the vector, we need to read the counter,
+ * do a memory barrier, then read the mask.
+ *
+ * Note: This is still all racey, but we can deal with it.
+ * Ideally, we only want to look at masks that are set.
+ *
+ * If a mask is not set, then the only thing wrong is that we
+ * did a little more work than necessary.
+ *
+ * If we read a zero count but the mask is set, because of the
+ * memory barriers, that can only happen when the highest prio
+ * task for a run queue has left the run queue, in which case,
+ * it will be followed by a pull. If the task we are processing
+ * fails to find a proper place to go, that pull request will
+ * pull this task if the run queue is running at a lower
+ * priority.
+ */
+ smp_rmb();
+
+ /* Need to do the rmb for every iteration */
+ if (skip)
+ return 0;
+
+ if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
+ return 0;
+
+ if (lowest_mask) {
+ cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
+
+ /*
+ * We have to ensure that we have at least one bit
+ * still set in the array, since the map could have
+ * been concurrently emptied between the first and
+ * second reads of vec->mask. If we hit this
+ * condition, simply act as though we never hit this
+ * priority level and continue on.
+ */
+ if (cpumask_empty(lowest_mask))
+ return 0;
+ }
+
+ return 1;
+}
+
+int cpupri_find(struct cpupri *cp, struct task_struct *p,
+ struct cpumask *lowest_mask)
+{
+ return cpupri_find_fitness(cp, p, lowest_mask, NULL);
+}
+
/**
- * cpupri_find - find the best (lowest-pri) CPU in the system
+ * cpupri_find_fitness - find the best (lowest-pri) CPU in the system
* @cp: The cpupri context
* @p: The task
* @lowest_mask: A mask to fill in with selected CPUs (or NULL)
*
* Return: (int)bool - CPUs were found
*/
-int cpupri_find(struct cpupri *cp, struct task_struct *p,
+int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask,
bool (*fitness_fn)(struct task_struct *p, int cpu))
{
- int idx = 0;
int task_pri = convert_prio(p->prio);
+ int idx, cpu;
BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
for (idx = 0; idx < task_pri; idx++) {
- struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
- int skip = 0;
-
- if (!atomic_read(&(vec)->count))
- skip = 1;
- /*
- * When looking at the vector, we need to read the counter,
- * do a memory barrier, then read the mask.
- *
- * Note: This is still all racey, but we can deal with it.
- * Ideally, we only want to look at masks that are set.
- *
- * If a mask is not set, then the only thing wrong is that we
- * did a little more work than necessary.
- *
- * If we read a zero count but the mask is set, because of the
- * memory barriers, that can only happen when the highest prio
- * task for a run queue has left the run queue, in which case,
- * it will be followed by a pull. If the task we are processing
- * fails to find a proper place to go, that pull request will
- * pull this task if the run queue is running at a lower
- * priority.
- */
- smp_rmb();
- /* Need to do the rmb for every iteration */
- if (skip)
+ if (!__cpupri_find(cp, p, lowest_mask, idx))
continue;
- if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
- continue;
+ if (!lowest_mask || !fitness_fn)
+ return 1;
- if (lowest_mask) {
- int cpu;
-
- cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
-
- /*
- * We have to ensure that we have at least one bit
- * still set in the array, since the map could have
- * been concurrently emptied between the first and
- * second reads of vec->mask. If we hit this
- * condition, simply act as though we never hit this
- * priority level and continue on.
- */
- if (cpumask_empty(lowest_mask))
- continue;
-
- if (!fitness_fn)
- return 1;
-
- /* Ensure the capacity of the CPUs fit the task */
- for_each_cpu(cpu, lowest_mask) {
- if (!fitness_fn(p, cpu))
- cpumask_clear_cpu(cpu, lowest_mask);
- }
-
- /*
- * If no CPU at the current priority can fit the task
- * continue looking
- */
- if (cpumask_empty(lowest_mask))
- continue;
+ /* Ensure the capacity of the CPUs fit the task */
+ for_each_cpu(cpu, lowest_mask) {
+ if (!fitness_fn(p, cpu))
+ cpumask_clear_cpu(cpu, lowest_mask);
}
+ /*
+ * If no CPU at the current priority can fit the task
+ * continue looking
+ */
+ if (cpumask_empty(lowest_mask))
+ continue;
+
return 1;
}
+ /*
+ * If we failed to find a fitting lowest_mask, kick off a new search
+ * but without taking into account any fitness criteria this time.
+ *
+ * This rule favours honouring priority over fitting the task in the
+ * correct CPU (Capacity Awareness being the only user now).
+ * The idea is that if a higher priority task can run, then it should
+ * run even if this ends up being on unfitting CPU.
+ *
+ * The cost of this trade-off is not entirely clear and will probably
+ * be good for some workloads and bad for others.
+ *
+ * The main idea here is that if some CPUs were overcommitted, we try
+ * to spread which is what the scheduler traditionally did. Sys admins
+ * must do proper RT planning to avoid overloading the system if they
+ * really care.
+ */
+ if (fitness_fn)
+ return cpupri_find(cp, p, lowest_mask);
+
return 0;
}
#ifdef CONFIG_SMP
int cpupri_find(struct cpupri *cp, struct task_struct *p,
- struct cpumask *lowest_mask,
- bool (*fitness_fn)(struct task_struct *p, int cpu));
+ struct cpumask *lowest_mask);
+int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
+ struct cpumask *lowest_mask,
+ bool (*fitness_fn)(struct task_struct *p, int cpu));
void cpupri_set(struct cpupri *cp, int cpu, int pri);
int cpupri_init(struct cpupri *cp);
void cpupri_cleanup(struct cpupri *cp);
} while (read_seqcount_retry(&vtime->seqcount, seq));
}
-static int vtime_state_check(struct vtime *vtime, int cpu)
+static int vtime_state_fetch(struct vtime *vtime, int cpu)
{
+ int state = READ_ONCE(vtime->state);
+
/*
* We raced against a context switch, fetch the
* kcpustat task again.
*
* Case 1) is ok but 2) is not. So wait for a safe VTIME state.
*/
- if (vtime->state == VTIME_INACTIVE)
+ if (state == VTIME_INACTIVE)
return -EAGAIN;
- return 0;
+ return state;
}
static u64 kcpustat_user_vtime(struct vtime *vtime)
{
struct vtime *vtime = &tsk->vtime;
unsigned int seq;
- int err;
do {
+ int state;
+
seq = read_seqcount_begin(&vtime->seqcount);
- err = vtime_state_check(vtime, cpu);
- if (err < 0)
- return err;
+ state = vtime_state_fetch(vtime, cpu);
+ if (state < 0)
+ return state;
*val = cpustat[usage];
*/
switch (usage) {
case CPUTIME_SYSTEM:
- if (vtime->state == VTIME_SYS)
+ if (state == VTIME_SYS)
*val += vtime->stime + vtime_delta(vtime);
break;
case CPUTIME_USER:
*val += kcpustat_user_vtime(vtime);
break;
case CPUTIME_GUEST:
- if (vtime->state == VTIME_GUEST && task_nice(tsk) <= 0)
+ if (state == VTIME_GUEST && task_nice(tsk) <= 0)
*val += vtime->gtime + vtime_delta(vtime);
break;
case CPUTIME_GUEST_NICE:
- if (vtime->state == VTIME_GUEST && task_nice(tsk) > 0)
+ if (state == VTIME_GUEST && task_nice(tsk) > 0)
*val += vtime->gtime + vtime_delta(vtime);
break;
default:
{
struct vtime *vtime = &tsk->vtime;
unsigned int seq;
- int err;
do {
u64 *cpustat;
u64 delta;
+ int state;
seq = read_seqcount_begin(&vtime->seqcount);
- err = vtime_state_check(vtime, cpu);
- if (err < 0)
- return err;
+ state = vtime_state_fetch(vtime, cpu);
+ if (state < 0)
+ return state;
*dst = *src;
cpustat = dst->cpustat;
/* Task is sleeping, dead or idle, nothing to add */
- if (vtime->state < VTIME_SYS)
+ if (state < VTIME_SYS)
continue;
delta = vtime_delta(vtime);
* Task runs either in user (including guest) or kernel space,
* add pending nohz time to the right place.
*/
- if (vtime->state == VTIME_SYS) {
+ if (state == VTIME_SYS) {
cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
- } else if (vtime->state == VTIME_USER) {
+ } else if (state == VTIME_USER) {
if (task_nice(tsk) > 0)
cpustat[CPUTIME_NICE] += vtime->utime + delta;
else
cpustat[CPUTIME_USER] += vtime->utime + delta;
} else {
- WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+ WARN_ON_ONCE(state != VTIME_GUEST);
if (task_nice(tsk) > 0) {
cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
cpustat[CPUTIME_NICE] += vtime->gtime + delta;
}
} while (read_seqcount_retry(&vtime->seqcount, seq));
- return err;
+ return 0;
}
void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
__sub_running_bw(dl_se->dl_bw, dl_rq);
}
-void dl_change_utilization(struct task_struct *p, u64 new_bw)
+static void dl_change_utilization(struct task_struct *p, u64 new_bw)
{
struct rq *rq;
return dl_rq->root.rb_leftmost == &dl_se->rb_node;
}
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
+
void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
{
raw_spin_lock_init(&dl_b->dl_runtime_lock);
return ret;
}
-void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
{
if (global_rt_runtime() == RUNTIME_INF) {
dl_rq->bw_ratio = 1 << RATIO_SHIFT;
}
P(se->load.weight);
- P(se->runnable_weight);
#ifdef CONFIG_SMP
P(se->avg.load_avg);
P(se->avg.util_avg);
- P(se->avg.runnable_load_avg);
+ P(se->avg.runnable_avg);
#endif
#undef PN_SCHEDSTAT
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
#ifdef CONFIG_SMP
- SEQ_printf(m, " .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight);
SEQ_printf(m, " .%-30s: %lu\n", "load_avg",
cfs_rq->avg.load_avg);
- SEQ_printf(m, " .%-30s: %lu\n", "runnable_load_avg",
- cfs_rq->avg.runnable_load_avg);
+ SEQ_printf(m, " .%-30s: %lu\n", "runnable_avg",
+ cfs_rq->avg.runnable_avg);
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
cfs_rq->avg.util_avg);
SEQ_printf(m, " .%-30s: %u\n", "util_est_enqueued",
cfs_rq->removed.load_avg);
SEQ_printf(m, " .%-30s: %ld\n", "removed.util_avg",
cfs_rq->removed.util_avg);
- SEQ_printf(m, " .%-30s: %ld\n", "removed.runnable_sum",
- cfs_rq->removed.runnable_sum);
+ SEQ_printf(m, " .%-30s: %ld\n", "removed.runnable_avg",
+ cfs_rq->removed.runnable_avg);
#ifdef CONFIG_FAIR_GROUP_SCHED
SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib",
cfs_rq->tg_load_avg_contrib);
"nr_involuntary_switches", (long long)p->nivcsw);
P(se.load.weight);
- P(se.runnable_weight);
#ifdef CONFIG_SMP
P(se.avg.load_sum);
- P(se.avg.runnable_load_sum);
+ P(se.avg.runnable_sum);
P(se.avg.util_sum);
P(se.avg.load_avg);
- P(se.avg.runnable_load_avg);
+ P(se.avg.runnable_avg);
P(se.avg.util_avg);
P(se.avg.last_update_time);
P(se.avg.util_est.ewma);
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+int sched_thermal_decay_shift;
+static int __init setup_sched_thermal_decay_shift(char *str)
+{
+ int _shift = 0;
+
+ if (kstrtoint(str, 0, &_shift))
+ pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");
+
+ sched_thermal_decay_shift = clamp(_shift, 0, 10);
+ return 1;
+}
+__setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
+
#ifdef CONFIG_SMP
/*
* For asym packing, by default the lower numbered CPU has higher priority.
* nothing has been attached to the task group yet.
*/
if (entity_is_task(se))
- sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
-
- se->runnable_weight = se->load.weight;
+ sa->load_avg = scale_load_down(se->load.weight);
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
}
}
+ sa->runnable_avg = cpu_scale;
+
if (p->sched_class != &fair_sched_class) {
/*
* For !fair tasks do:
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-
-static unsigned long cpu_runnable_load(struct rq *rq)
-{
- return cfs_rq_runnable_load_avg(&rq->cfs);
-}
+/*
+ * 'numa_type' describes the node at the moment of load balancing.
+ */
+enum numa_type {
+ /* The node has spare capacity that can be used to run more tasks. */
+ node_has_spare = 0,
+ /*
+ * The node is fully used and the tasks don't compete for more CPU
+ * cycles. Nevertheless, some tasks might wait before running.
+ */
+ node_fully_busy,
+ /*
+ * The node is overloaded and can't provide expected CPU cycles to all
+ * tasks.
+ */
+ node_overloaded
+};
/* Cached statistics for all CPUs within a node */
struct numa_stats {
unsigned long load;
-
+ unsigned long util;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
+ unsigned int nr_running;
+ unsigned int weight;
+ enum numa_type node_type;
+ int idle_cpu;
};
-/*
- * XXX borrowed from update_sg_lb_stats
- */
-static void update_numa_stats(struct numa_stats *ns, int nid)
+static inline bool is_core_idle(int cpu)
{
- int cpu;
+#ifdef CONFIG_SCHED_SMT
+ int sibling;
- memset(ns, 0, sizeof(*ns));
- for_each_cpu(cpu, cpumask_of_node(nid)) {
- struct rq *rq = cpu_rq(cpu);
+ for_each_cpu(sibling, cpu_smt_mask(cpu)) {
+ if (cpu == sibling)
+ continue;
- ns->load += cpu_runnable_load(rq);
- ns->compute_capacity += capacity_of(cpu);
+ if (!idle_cpu(cpu))
+ return false;
}
+#endif
+ return true;
}
struct task_numa_env {
int best_cpu;
};
+static unsigned long cpu_load(struct rq *rq);
+static unsigned long cpu_util(int cpu);
+static inline long adjust_numa_imbalance(int imbalance, int src_nr_running);
+
+static inline enum
+numa_type numa_classify(unsigned int imbalance_pct,
+ struct numa_stats *ns)
+{
+ if ((ns->nr_running > ns->weight) &&
+ ((ns->compute_capacity * 100) < (ns->util * imbalance_pct)))
+ return node_overloaded;
+
+ if ((ns->nr_running < ns->weight) ||
+ ((ns->compute_capacity * 100) > (ns->util * imbalance_pct)))
+ return node_has_spare;
+
+ return node_fully_busy;
+}
+
+#ifdef CONFIG_SCHED_SMT
+/* Forward declarations of select_idle_sibling helpers */
+static inline bool test_idle_cores(int cpu, bool def);
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+ if (!static_branch_likely(&sched_smt_present) ||
+ idle_core >= 0 || !test_idle_cores(cpu, false))
+ return idle_core;
+
+ /*
+ * Prefer cores instead of packing HT siblings
+ * and triggering future load balancing.
+ */
+ if (is_core_idle(cpu))
+ idle_core = cpu;
+
+ return idle_core;
+}
+#else
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+ return idle_core;
+}
+#endif
+
+/*
+ * Gather all necessary information to make NUMA balancing placement
+ * decisions that are compatible with standard load balancer. This
+ * borrows code and logic from update_sg_lb_stats but sharing a
+ * common implementation is impractical.
+ */
+static void update_numa_stats(struct task_numa_env *env,
+ struct numa_stats *ns, int nid,
+ bool find_idle)
+{
+ int cpu, idle_core = -1;
+
+ memset(ns, 0, sizeof(*ns));
+ ns->idle_cpu = -1;
+
+ rcu_read_lock();
+ for_each_cpu(cpu, cpumask_of_node(nid)) {
+ struct rq *rq = cpu_rq(cpu);
+
+ ns->load += cpu_load(rq);
+ ns->util += cpu_util(cpu);
+ ns->nr_running += rq->cfs.h_nr_running;
+ ns->compute_capacity += capacity_of(cpu);
+
+ if (find_idle && !rq->nr_running && idle_cpu(cpu)) {
+ if (READ_ONCE(rq->numa_migrate_on) ||
+ !cpumask_test_cpu(cpu, env->p->cpus_ptr))
+ continue;
+
+ if (ns->idle_cpu == -1)
+ ns->idle_cpu = cpu;
+
+ idle_core = numa_idle_core(idle_core, cpu);
+ }
+ }
+ rcu_read_unlock();
+
+ ns->weight = cpumask_weight(cpumask_of_node(nid));
+
+ ns->node_type = numa_classify(env->imbalance_pct, ns);
+
+ if (idle_core >= 0)
+ ns->idle_cpu = idle_core;
+}
+
static void task_numa_assign(struct task_numa_env *env,
struct task_struct *p, long imp)
{
struct rq *rq = cpu_rq(env->dst_cpu);
- /* Bail out if run-queue part of active NUMA balance. */
- if (xchg(&rq->numa_migrate_on, 1))
+ /* Check if run-queue part of active NUMA balance. */
+ if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1)) {
+ int cpu;
+ int start = env->dst_cpu;
+
+ /* Find alternative idle CPU. */
+ for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) {
+ if (cpu == env->best_cpu || !idle_cpu(cpu) ||
+ !cpumask_test_cpu(cpu, env->p->cpus_ptr)) {
+ continue;
+ }
+
+ env->dst_cpu = cpu;
+ rq = cpu_rq(env->dst_cpu);
+ if (!xchg(&rq->numa_migrate_on, 1))
+ goto assign;
+ }
+
+ /* Failed to find an alternative idle CPU */
return;
+ }
+assign:
/*
* Clear previous best_cpu/rq numa-migrate flag, since task now
* found a better CPU to move/swap.
*/
- if (env->best_cpu != -1) {
+ if (env->best_cpu != -1 && env->best_cpu != env->dst_cpu) {
rq = cpu_rq(env->best_cpu);
WRITE_ONCE(rq->numa_migrate_on, 0);
}
* into account that it might be best if task running on the dst_cpu should
* be exchanged with the source task
*/
-static void task_numa_compare(struct task_numa_env *env,
+static bool task_numa_compare(struct task_numa_env *env,
long taskimp, long groupimp, bool maymove)
{
struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
int dist = env->dist;
long moveimp = imp;
long load;
+ bool stopsearch = false;
if (READ_ONCE(dst_rq->numa_migrate_on))
- return;
+ return false;
rcu_read_lock();
cur = rcu_dereference(dst_rq->curr);
* Because we have preemption enabled we can get migrated around and
* end try selecting ourselves (current == env->p) as a swap candidate.
*/
- if (cur == env->p)
+ if (cur == env->p) {
+ stopsearch = true;
goto unlock;
+ }
if (!cur) {
if (maymove && moveimp >= env->best_imp)
goto unlock;
}
+ /* Skip this swap candidate if cannot move to the source cpu. */
+ if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
+ goto unlock;
+
+ /*
+ * Skip this swap candidate if it is not moving to its preferred
+ * node and the best task is.
+ */
+ if (env->best_task &&
+ env->best_task->numa_preferred_nid == env->src_nid &&
+ cur->numa_preferred_nid != env->src_nid) {
+ 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 remote accesses that would be expected to
* be incurred if the tasks were swapped.
- */
- /* Skip this swap candidate if cannot move to the source cpu */
- if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
- goto unlock;
-
- /*
+ *
* If dst and source tasks are in the same NUMA group, or not
* in any group then look only at task weights.
*/
task_weight(cur, env->dst_nid, dist);
}
+ /* Discourage picking a task already on its preferred node */
+ if (cur->numa_preferred_nid == env->dst_nid)
+ imp -= imp / 16;
+
+ /*
+ * Encourage picking a task that moves to its preferred node.
+ * This potentially makes imp larger than it's maximum of
+ * 1998 (see SMALLIMP and task_weight for why) but in this
+ * case, it does not matter.
+ */
+ if (cur->numa_preferred_nid == env->src_nid)
+ imp += imp / 8;
+
if (maymove && moveimp > imp && moveimp > env->best_imp) {
imp = moveimp;
cur = NULL;
goto assign;
}
+ /*
+ * Prefer swapping with a task moving to its preferred node over a
+ * task that is not.
+ */
+ if (env->best_task && cur->numa_preferred_nid == env->src_nid &&
+ env->best_task->numa_preferred_nid != env->src_nid) {
+ goto assign;
+ }
+
/*
* If the NUMA importance is less than SMALLIMP,
* task migration might only result in ping pong
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.
- */
+ /* Evaluate an idle CPU for a task numa move. */
if (!cur) {
+ int cpu = env->dst_stats.idle_cpu;
+
+ /* Nothing cached so current CPU went idle since the search. */
+ if (cpu < 0)
+ cpu = env->dst_cpu;
+
/*
- * select_idle_siblings() uses an per-CPU cpumask that
- * can be used from IRQ context.
+ * If the CPU is no longer truly idle and the previous best CPU
+ * is, keep using it.
*/
- local_irq_disable();
- env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
- env->dst_cpu);
- local_irq_enable();
+ if (!idle_cpu(cpu) && env->best_cpu >= 0 &&
+ idle_cpu(env->best_cpu)) {
+ cpu = env->best_cpu;
+ }
+
+ env->dst_cpu = cpu;
}
task_numa_assign(env, cur, imp);
+
+ /*
+ * If a move to idle is allowed because there is capacity or load
+ * balance improves then stop the search. While a better swap
+ * candidate may exist, a search is not free.
+ */
+ if (maymove && !cur && env->best_cpu >= 0 && idle_cpu(env->best_cpu))
+ stopsearch = true;
+
+ /*
+ * If a swap candidate must be identified and the current best task
+ * moves its preferred node then stop the search.
+ */
+ if (!maymove && env->best_task &&
+ env->best_task->numa_preferred_nid == env->src_nid) {
+ stopsearch = true;
+ }
unlock:
rcu_read_unlock();
+
+ return stopsearch;
}
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.
+ * If dst node has spare capacity, then check if there is an
+ * imbalance that would be overruled by the load balancer.
*/
- maymove = !load_too_imbalanced(src_load, dst_load, env);
+ if (env->dst_stats.node_type == node_has_spare) {
+ unsigned int imbalance;
+ int src_running, dst_running;
+
+ /*
+ * Would movement cause an imbalance? Note that if src has
+ * more running tasks that the imbalance is ignored as the
+ * move improves the imbalance from the perspective of the
+ * CPU load balancer.
+ * */
+ src_running = env->src_stats.nr_running - 1;
+ dst_running = env->dst_stats.nr_running + 1;
+ imbalance = max(0, dst_running - src_running);
+ imbalance = adjust_numa_imbalance(imbalance, src_running);
+
+ /* Use idle CPU if there is no imbalance */
+ if (!imbalance) {
+ maymove = true;
+ if (env->dst_stats.idle_cpu >= 0) {
+ env->dst_cpu = env->dst_stats.idle_cpu;
+ task_numa_assign(env, NULL, 0);
+ return;
+ }
+ }
+ } else {
+ long src_load, dst_load, load;
+ /*
+ * If the improvement from just moving env->p direction is better
+ * than swapping tasks around, check if a move is possible.
+ */
+ load = task_h_load(env->p);
+ dst_load = env->dst_stats.load + load;
+ src_load = env->src_stats.load - load;
+ 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 */
continue;
env->dst_cpu = cpu;
- task_numa_compare(env, taskimp, groupimp, maymove);
+ if (task_numa_compare(env, taskimp, groupimp, maymove))
+ break;
}
}
dist = env.dist = node_distance(env.src_nid, env.dst_nid);
taskweight = task_weight(p, env.src_nid, dist);
groupweight = group_weight(p, env.src_nid, dist);
- update_numa_stats(&env.src_stats, env.src_nid);
+ update_numa_stats(&env, &env.src_stats, env.src_nid, false);
taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
- update_numa_stats(&env.dst_stats, env.dst_nid);
+ update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
/* Try to find a spot on the preferred nid. */
task_numa_find_cpu(&env, taskimp, groupimp);
env.dist = dist;
env.dst_nid = nid;
- update_numa_stats(&env.dst_stats, env.dst_nid);
+ update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
task_numa_find_cpu(&env, taskimp, groupimp);
}
}
}
/* No better CPU than the current one was found. */
- if (env.best_cpu == -1)
+ if (env.best_cpu == -1) {
+ trace_sched_stick_numa(p, env.src_cpu, NULL, -1);
return -EAGAIN;
+ }
best_rq = cpu_rq(env.best_cpu);
if (env.best_task == NULL) {
ret = migrate_task_to(p, env.best_cpu);
WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
- trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
+ trace_sched_stick_numa(p, env.src_cpu, NULL, env.best_cpu);
return ret;
}
WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
- trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
+ trace_sched_stick_numa(p, env.src_cpu, env.best_task, env.best_cpu);
put_task_struct(env.best_task);
return ret;
}
} while (0)
#ifdef CONFIG_SMP
-static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- cfs_rq->runnable_weight += se->runnable_weight;
-
- cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
- cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
-}
-
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- cfs_rq->runnable_weight -= se->runnable_weight;
-
- sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
- sub_positive(&cfs_rq->avg.runnable_load_sum,
- se_runnable(se) * se->avg.runnable_load_sum);
-}
-
static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
}
#else
static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
- unsigned long weight, unsigned long runnable)
+ unsigned long weight)
{
if (se->on_rq) {
/* commit outstanding execution time */
if (cfs_rq->curr == se)
update_curr(cfs_rq);
account_entity_dequeue(cfs_rq, se);
- dequeue_runnable_load_avg(cfs_rq, se);
}
dequeue_load_avg(cfs_rq, se);
- se->runnable_weight = runnable;
update_load_set(&se->load, weight);
#ifdef CONFIG_SMP
u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib;
se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
- se->avg.runnable_load_avg =
- div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
} while (0);
#endif
enqueue_load_avg(cfs_rq, se);
- if (se->on_rq) {
+ if (se->on_rq)
account_entity_enqueue(cfs_rq, se);
- enqueue_runnable_load_avg(cfs_rq, se);
- }
+
}
void reweight_task(struct task_struct *p, int prio)
struct load_weight *load = &se->load;
unsigned long weight = scale_load(sched_prio_to_weight[prio]);
- reweight_entity(cfs_rq, se, weight, weight);
+ reweight_entity(cfs_rq, se, weight);
load->inv_weight = sched_prio_to_wmult[prio];
}
*/
return clamp_t(long, shares, MIN_SHARES, tg_shares);
}
-
-/*
- * This calculates the effective runnable weight for a group entity based on
- * the group entity weight calculated above.
- *
- * Because of the above approximation (2), our group entity weight is
- * an load_avg based ratio (3). This means that it includes blocked load and
- * does not represent the runnable weight.
- *
- * Approximate the group entity's runnable weight per ratio from the group
- * runqueue:
- *
- * grq->avg.runnable_load_avg
- * ge->runnable_weight = ge->load.weight * -------------------------- (7)
- * grq->avg.load_avg
- *
- * However, analogous to above, since the avg numbers are slow, this leads to
- * transients in the from-idle case. Instead we use:
- *
- * ge->runnable_weight = ge->load.weight *
- *
- * max(grq->avg.runnable_load_avg, grq->runnable_weight)
- * ----------------------------------------------------- (8)
- * max(grq->avg.load_avg, grq->load.weight)
- *
- * Where these max() serve both to use the 'instant' values to fix the slow
- * from-idle and avoid the /0 on to-idle, similar to (6).
- */
-static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
-{
- long runnable, load_avg;
-
- load_avg = max(cfs_rq->avg.load_avg,
- scale_load_down(cfs_rq->load.weight));
-
- runnable = max(cfs_rq->avg.runnable_load_avg,
- scale_load_down(cfs_rq->runnable_weight));
-
- runnable *= shares;
- if (load_avg)
- runnable /= load_avg;
-
- return clamp_t(long, runnable, MIN_SHARES, shares);
-}
#endif /* CONFIG_SMP */
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
static void update_cfs_group(struct sched_entity *se)
{
struct cfs_rq *gcfs_rq = group_cfs_rq(se);
- long shares, runnable;
+ long shares;
if (!gcfs_rq)
return;
return;
#ifndef CONFIG_SMP
- runnable = shares = READ_ONCE(gcfs_rq->tg->shares);
+ shares = READ_ONCE(gcfs_rq->tg->shares);
if (likely(se->load.weight == shares))
return;
#else
shares = calc_group_shares(gcfs_rq);
- runnable = calc_group_runnable(gcfs_rq, shares);
#endif
- reweight_entity(cfs_rq_of(se), se, shares, runnable);
+ reweight_entity(cfs_rq_of(se), se, shares);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
* _IFF_ we look at the pure running and runnable sums. Because they
* represent the very same entity, just at different points in the hierarchy.
*
- * Per the above update_tg_cfs_util() is trivial and simply copies the running
- * sum over (but still wrong, because the group entity and group rq do not have
- * their PELT windows aligned).
+ * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial
+ * and simply copies the running/runnable sum over (but still wrong, because
+ * the group entity and group rq do not have their PELT windows aligned).
*
- * However, update_tg_cfs_runnable() is more complex. So we have:
+ * However, update_tg_cfs_load() is more complex. So we have:
*
* ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg (2)
*
static inline void
update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
+{
+ long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /*
+ * The relation between sum and avg is:
+ *
+ * LOAD_AVG_MAX - 1024 + sa->period_contrib
+ *
+ * however, the PELT windows are not aligned between grq and gse.
+ */
+
+ /* Set new sched_entity's runnable */
+ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
+ se->avg.runnable_sum = se->avg.runnable_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq runnable */
+ add_positive(&cfs_rq->avg.runnable_avg, delta);
+ cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * LOAD_AVG_MAX;
+}
+
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
- unsigned long runnable_load_avg, load_avg;
- u64 runnable_load_sum, load_sum = 0;
+ unsigned long load_avg;
+ u64 load_sum = 0;
s64 delta_sum;
if (!runnable_sum)
se->avg.load_avg = load_avg;
add_positive(&cfs_rq->avg.load_avg, delta_avg);
add_positive(&cfs_rq->avg.load_sum, delta_sum);
-
- runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
- runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
-
- if (se->on_rq) {
- delta_sum = runnable_load_sum -
- se_weight(se) * se->avg.runnable_load_sum;
- delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
- add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
- add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
- }
-
- se->avg.runnable_load_sum = runnable_sum;
- se->avg.runnable_load_avg = runnable_load_avg;
}
static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
update_tg_cfs_util(cfs_rq, se, gcfs_rq);
update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
+ update_tg_cfs_load(cfs_rq, se, gcfs_rq);
trace_pelt_cfs_tp(cfs_rq);
trace_pelt_se_tp(se);
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
- unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
+ unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0;
struct sched_avg *sa = &cfs_rq->avg;
int decayed = 0;
raw_spin_lock(&cfs_rq->removed.lock);
swap(cfs_rq->removed.util_avg, removed_util);
swap(cfs_rq->removed.load_avg, removed_load);
- swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+ swap(cfs_rq->removed.runnable_avg, removed_runnable);
cfs_rq->removed.nr = 0;
raw_spin_unlock(&cfs_rq->removed.lock);
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * divider);
- add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+ r = removed_runnable;
+ sub_positive(&sa->runnable_avg, r);
+ sub_positive(&sa->runnable_sum, r * divider);
+
+ /*
+ * removed_runnable is the unweighted version of removed_load so we
+ * can use it to estimate removed_load_sum.
+ */
+ add_tg_cfs_propagate(cfs_rq,
+ -(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT);
decayed = 1;
}
*/
se->avg.util_sum = se->avg.util_avg * divider;
+ se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
se->avg.load_sum = divider;
if (se_weight(se)) {
se->avg.load_sum =
div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
}
- se->avg.runnable_load_sum = se->avg.load_sum;
-
enqueue_load_avg(cfs_rq, se);
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+ cfs_rq->avg.runnable_avg += se->avg.runnable_avg;
+ cfs_rq->avg.runnable_sum += se->avg.runnable_sum;
add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
dequeue_load_avg(cfs_rq, se);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+ sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
+ sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
++cfs_rq->removed.nr;
cfs_rq->removed.util_avg += se->avg.util_avg;
cfs_rq->removed.load_avg += se->avg.load_avg;
- cfs_rq->removed.runnable_sum += se->avg.load_sum; /* == runnable_sum */
+ cfs_rq->removed.runnable_avg += se->avg.runnable_avg;
raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
}
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
+static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq)
{
- return cfs_rq->avg.runnable_load_avg;
+ return cfs_rq->avg.runnable_avg;
}
static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
#endif
}
+static inline bool cfs_bandwidth_used(void);
/*
* MIGRATION
* - Add its new weight to cfs_rq->load.weight
*/
update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+ se_update_runnable(se);
update_cfs_group(se);
- enqueue_runnable_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
if (flags & ENQUEUE_WAKEUP)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
- if (cfs_rq->nr_running == 1) {
+ /*
+ * When bandwidth control is enabled, cfs might have been removed
+ * because of a parent been throttled but cfs->nr_running > 1. Try to
+ * add it unconditionnally.
+ */
+ if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
list_add_leaf_cfs_rq(cfs_rq);
+
+ if (cfs_rq->nr_running == 1)
check_enqueue_throttle(cfs_rq);
- }
}
static void __clear_buddies_last(struct sched_entity *se)
* of its group cfs_rq.
*/
update_load_avg(cfs_rq, se, UPDATE_TG);
- dequeue_runnable_load_avg(cfs_rq, se);
+ se_update_runnable(se);
update_stats_dequeue(cfs_rq, se, flags);
if (!se->on_rq)
break;
- if (dequeue)
+ if (dequeue) {
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+ } else {
+ update_load_avg(qcfs_rq, se, 0);
+ se_update_runnable(se);
+ }
+
qcfs_rq->h_nr_running -= task_delta;
qcfs_rq->idle_h_nr_running -= idle_task_delta;
enqueue = 0;
cfs_rq = cfs_rq_of(se);
- if (enqueue)
+ if (enqueue) {
enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+ } else {
+ update_load_avg(cfs_rq, se, 0);
+ se_update_runnable(se);
+ }
+
cfs_rq->h_nr_running += task_delta;
cfs_rq->idle_h_nr_running += idle_task_delta;
break;
}
- assert_list_leaf_cfs_rq(rq);
-
if (!se)
add_nr_running(rq, task_delta);
+ /*
+ * The cfs_rq_throttled() breaks in the above iteration can result in
+ * incomplete leaf list maintenance, resulting in triggering the
+ * assertion below.
+ */
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ list_add_leaf_cfs_rq(cfs_rq);
+ }
+
+ assert_list_leaf_cfs_rq(rq);
+
/* Determine whether we need to wake up potentially idle CPU: */
if (rq->curr == rq->idle && rq->cfs.nr_running)
resched_curr(rq);
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, flags);
- /*
- * end evaluation on encountering a throttled cfs_rq
- *
- * note: in the case of encountering a throttled cfs_rq we will
- * post the final h_nr_running increment below.
- */
- if (cfs_rq_throttled(cfs_rq))
- break;
cfs_rq->h_nr_running++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto enqueue_throttle;
+
flags = ENQUEUE_WAKEUP;
}
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
+
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
+ update_cfs_group(se);
+
cfs_rq->h_nr_running++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
- break;
-
- update_load_avg(cfs_rq, se, UPDATE_TG);
- update_cfs_group(se);
+ goto enqueue_throttle;
}
+enqueue_throttle:
if (!se) {
add_nr_running(rq, 1);
/*
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
- /*
- * end evaluation on encountering a throttled cfs_rq
- *
- * note: in the case of encountering a throttled cfs_rq we will
- * post the final h_nr_running decrement below.
- */
- if (cfs_rq_throttled(cfs_rq))
- break;
cfs_rq->h_nr_running--;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto dequeue_throttle;
+
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
/* Avoid re-evaluating load for this entity: */
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
+
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
+ update_cfs_group(se);
+
cfs_rq->h_nr_running--;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
- break;
+ goto dequeue_throttle;
- update_load_avg(cfs_rq, se, UPDATE_TG);
- update_cfs_group(se);
}
+dequeue_throttle:
if (!se)
sub_nr_running(rq, 1);
return load;
}
+static unsigned long cpu_runnable(struct rq *rq)
+{
+ return cfs_rq_runnable_avg(&rq->cfs);
+}
+
+static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p)
+{
+ struct cfs_rq *cfs_rq;
+ unsigned int runnable;
+
+ /* Task has no contribution or is new */
+ if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+ return cpu_runnable(rq);
+
+ cfs_rq = &rq->cfs;
+ runnable = READ_ONCE(cfs_rq->avg.runnable_avg);
+
+ /* Discount task's runnable from CPU's runnable */
+ lsub_positive(&runnable, p->se.avg.runnable_avg);
+
+ return runnable;
+}
+
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
bool idle = true;
for_each_cpu(cpu, cpu_smt_mask(core)) {
- __cpumask_clear_cpu(cpu, cpus);
- if (!available_idle_cpu(cpu))
+ if (!available_idle_cpu(cpu)) {
idle = false;
+ break;
+ }
}
+ cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
if (idle)
return core;
return cpu;
}
+/*
+ * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which
+ * the task fits. If no CPU is big enough, but there are idle ones, try to
+ * maximize capacity.
+ */
+static int
+select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
+{
+ unsigned long best_cap = 0;
+ int cpu, best_cpu = -1;
+ struct cpumask *cpus;
+
+ sync_entity_load_avg(&p->se);
+
+ cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+
+ for_each_cpu_wrap(cpu, cpus, target) {
+ unsigned long cpu_cap = capacity_of(cpu);
+
+ if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
+ continue;
+ if (task_fits_capacity(p, cpu_cap))
+ return cpu;
+
+ if (cpu_cap > best_cap) {
+ best_cap = cpu_cap;
+ best_cpu = cpu;
+ }
+ }
+
+ return best_cpu;
+}
+
/*
* Try and locate an idle core/thread in the LLC cache domain.
*/
struct sched_domain *sd;
int i, recent_used_cpu;
+ /*
+ * For asymmetric CPU capacity systems, our domain of interest is
+ * sd_asym_cpucapacity rather than sd_llc.
+ */
+ if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+ /*
+ * On an asymmetric CPU capacity system where an exclusive
+ * cpuset defines a symmetric island (i.e. one unique
+ * capacity_orig value through the cpuset), the key will be set
+ * but the CPUs within that cpuset will not have a domain with
+ * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+ * capacity path.
+ */
+ if (!sd)
+ goto symmetric;
+
+ i = select_idle_capacity(p, sd, target);
+ return ((unsigned)i < nr_cpumask_bits) ? i : target;
+ }
+
+symmetric:
if (available_idle_cpu(target) || sched_idle_cpu(target))
return target;
return min_t(unsigned long, util, capacity_orig_of(cpu));
}
-/*
- * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
- * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
- *
- * In that case WAKE_AFFINE doesn't make sense and we'll let
- * BALANCE_WAKE sort things out.
- */
-static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
-{
- long min_cap, max_cap;
-
- if (!static_branch_unlikely(&sched_asym_cpucapacity))
- return 0;
-
- min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
- max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
-
- /* Minimum capacity is close to max, no need to abort wake_affine */
- if (max_cap - min_cap < max_cap >> 3)
- return 0;
-
- /* Bring task utilization in sync with prev_cpu */
- sync_entity_load_avg(&p->se);
-
- return !task_fits_capacity(p, min_cap);
-}
-
/*
* Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
* to @dst_cpu.
new_cpu = prev_cpu;
}
- want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
- cpumask_test_cpu(cpu, p->cpus_ptr);
+ want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr);
}
rcu_read_lock();
if (READ_ONCE(rq->avg_dl.util_avg))
return true;
+ if (thermal_load_avg(rq))
+ return true;
+
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
if (READ_ONCE(rq->avg_irq.util_avg))
return true;
{
const struct sched_class *curr_class;
u64 now = rq_clock_pelt(rq);
+ unsigned long thermal_pressure;
bool decayed;
/*
*/
curr_class = rq->curr->sched_class;
+ thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+
decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+ update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
update_irq_load_avg(rq, 0);
if (others_have_blocked(rq))
if (cfs_rq->avg.util_sum)
return false;
- if (cfs_rq->avg.runnable_load_sum)
+ if (cfs_rq->avg.runnable_sum)
return false;
return true;
unsigned long avg_load; /*Avg load across the CPUs of the group */
unsigned long group_load; /* Total load over the CPUs of the group */
unsigned long group_capacity;
- unsigned long group_util; /* Total utilization of the group */
+ unsigned long group_util; /* Total utilization over the CPUs of the group */
+ unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
unsigned int sum_nr_running; /* Nr of tasks running in the group */
unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
unsigned int idle_cpus;
if (unlikely(irq >= max))
return 1;
+ /*
+ * avg_rt.util_avg and avg_dl.util_avg track binary signals
+ * (running and not running) with weights 0 and 1024 respectively.
+ * avg_thermal.load_avg tracks thermal pressure and the weighted
+ * average uses the actual delta max capacity(load).
+ */
used = READ_ONCE(rq->avg_rt.util_avg);
used += READ_ONCE(rq->avg_dl.util_avg);
+ used += thermal_load_avg(rq);
if (unlikely(used >= max))
return 1;
if (sgs->sum_nr_running < sgs->group_weight)
return true;
+ if ((sgs->group_capacity * imbalance_pct) <
+ (sgs->group_runnable * 100))
+ return false;
+
if ((sgs->group_capacity * 100) >
(sgs->group_util * imbalance_pct))
return true;
(sgs->group_util * imbalance_pct))
return true;
+ if ((sgs->group_capacity * imbalance_pct) <
+ (sgs->group_runnable * 100))
+ return true;
+
return false;
}
sgs->group_load += cpu_load(rq);
sgs->group_util += cpu_util(i);
+ sgs->group_runnable += cpu_runnable(rq);
sgs->sum_h_nr_running += rq->cfs.h_nr_running;
nr_running = rq->nr_running;
sgs->group_load += cpu_load_without(rq, p);
sgs->group_util += cpu_util_without(i, p);
+ sgs->group_runnable += cpu_runnable_without(rq, p);
local = task_running_on_cpu(i, p);
sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;
sgs->group_capacity = group->sgc->capacity;
+ sgs->group_weight = group->group_weight;
+
sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
/*
* Computing avg_load makes sense only when group is fully busy or
* overloaded
*/
- if (sgs->group_type < group_fully_busy)
+ if (sgs->group_type == group_fully_busy ||
+ sgs->group_type == group_overloaded)
sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
sgs->group_capacity;
}
}
}
+static inline long adjust_numa_imbalance(int imbalance, int src_nr_running)
+{
+ unsigned int imbalance_min;
+
+ /*
+ * Allow a small imbalance based on a simple pair of communicating
+ * tasks that remain local when the source domain is almost idle.
+ */
+ imbalance_min = 2;
+ if (src_nr_running <= imbalance_min)
+ return 0;
+
+ return imbalance;
+}
+
/**
* calculate_imbalance - Calculate the amount of imbalance present within the
* groups of a given sched_domain during load balance.
}
/* Consider allowing a small imbalance between NUMA groups */
- if (env->sd->flags & SD_NUMA) {
- unsigned int imbalance_min;
-
- /*
- * Compute an allowed imbalance based on a simple
- * pair of communicating tasks that should remain
- * local and ignore them.
- *
- * NOTE: Generally this would have been based on
- * the domain size and this was evaluated. However,
- * the benefit is similar across a range of workloads
- * and machines but scaling by the domain size adds
- * the risk that lower domains have to be rebalanced.
- */
- imbalance_min = 2;
- if (busiest->sum_nr_running <= imbalance_min)
- env->imbalance = 0;
- }
+ if (env->sd->flags & SD_NUMA)
+ env->imbalance = adjust_numa_imbalance(env->imbalance,
+ busiest->sum_nr_running);
return;
}
case migrate_util:
util = cpu_util(cpu_of(rq));
+ /*
+ * Don't try to pull utilization from a CPU with one
+ * running task. Whatever its utilization, we will fail
+ * detach the task.
+ */
+ if (nr_running <= 1)
+ continue;
+
if (busiest_util < util) {
busiest_util = util;
busiest = rq;
*/
if (periods) {
sa->load_sum = decay_load(sa->load_sum, periods);
- sa->runnable_load_sum =
- decay_load(sa->runnable_load_sum, periods);
+ sa->runnable_sum =
+ decay_load(sa->runnable_sum, periods);
sa->util_sum = decay_load((u64)(sa->util_sum), periods);
/*
if (load)
sa->load_sum += load * contrib;
if (runnable)
- sa->runnable_load_sum += runnable * contrib;
+ sa->runnable_sum += runnable * contrib << SCHED_CAPACITY_SHIFT;
if (running)
sa->util_sum += contrib << SCHED_CAPACITY_SHIFT;
}
static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+___update_load_avg(struct sched_avg *sa, unsigned long load)
{
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->runnable_avg = div_u64(sa->runnable_sum, divider);
WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
}
* sched_entity:
*
* task:
- * se_runnable() == se_weight()
+ * se_weight() = se->load.weight
+ * se_runnable() = !!on_rq
*
* 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
+ * se_runnable() = grq->h_nr_running
*
- * load_sum := runnable_sum
- * load_avg = se_weight(se) * runnable_avg
+ * runnable_sum = se_runnable() * runnable = grq->runnable_sum
+ * runnable_avg = runnable_sum
*
- * runnable_load_sum := runnable_sum
- * runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
+ * load_sum := runnable
+ * load_avg = se_weight(se) * load_sum
*
* cfq_rq:
*
+ * runnable_sum = \Sum se->avg.runnable_sum
+ * runnable_avg = \Sum se->avg.runnable_avg
+ *
* 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, struct sched_entity *se)
{
if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ ___update_load_avg(&se->avg, se_weight(se));
trace_pelt_se_tp(se);
return 1;
}
int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (___update_load_sum(now, &se->avg, !!se->on_rq, !!se->on_rq,
+ if (___update_load_sum(now, &se->avg, !!se->on_rq, se_runnable(se),
cfs_rq->curr == se)) {
- ___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+ ___update_load_avg(&se->avg, se_weight(se));
cfs_se_util_change(&se->avg);
trace_pelt_se_tp(se);
return 1;
{
if (___update_load_sum(now, &cfs_rq->avg,
scale_load_down(cfs_rq->load.weight),
- scale_load_down(cfs_rq->runnable_weight),
+ cfs_rq->h_nr_running,
cfs_rq->curr != NULL)) {
- ___update_load_avg(&cfs_rq->avg, 1, 1);
+ ___update_load_avg(&cfs_rq->avg, 1);
trace_pelt_cfs_tp(cfs_rq);
return 1;
}
*
* 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
+ * runnable_sum = util_sum
*
- * load_avg and runnable_load_avg are not supported and meaningless.
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
running,
running)) {
- ___update_load_avg(&rq->avg_rt, 1, 1);
+ ___update_load_avg(&rq->avg_rt, 1);
trace_pelt_rt_tp(rq);
return 1;
}
*
* 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
+ * runnable_sum = util_sum
+ *
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
running,
running)) {
- ___update_load_avg(&rq->avg_dl, 1, 1);
+ ___update_load_avg(&rq->avg_dl, 1);
trace_pelt_dl_tp(rq);
return 1;
}
return 0;
}
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+/*
+ * thermal:
+ *
+ * load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked
+ *
+ * util_avg and runnable_load_avg are not supported and meaningless.
+ *
+ * Unlike rt/dl utilization tracking that track time spent by a cpu
+ * running a rt/dl task through util_avg, the average thermal pressure is
+ * tracked through load_avg. This is because thermal pressure signal is
+ * time weighted "delta" capacity unlike util_avg which is binary.
+ * "delta capacity" = actual capacity -
+ * capped capacity a cpu due to a thermal event.
+ */
+
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+ if (___update_load_sum(now, &rq->avg_thermal,
+ capacity,
+ capacity,
+ capacity)) {
+ ___update_load_avg(&rq->avg_thermal, 1);
+ trace_pelt_thermal_tp(rq);
+ return 1;
+ }
+
+ return 0;
+}
+#endif
+
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
/*
* 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
+ * runnable_sum = util_sum
+ *
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
1);
if (ret) {
- ___update_load_avg(&rq->avg_irq, 1, 1);
+ ___update_load_avg(&rq->avg_irq, 1);
trace_pelt_irq_tp(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);
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+ return READ_ONCE(rq->avg_thermal.load_avg);
+}
+#else
+static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+ return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+ return 0;
+}
+#endif
+
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
int update_irq_load_avg(struct rq *rq, u64 running);
#else
return 0;
}
+static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+ return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+ return 0;
+}
+
static inline int
update_irq_load_avg(struct rq *rq, u64 running)
{
case PSI_MEM_FULL:
return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
case PSI_CPU_SOME:
- return tasks[NR_RUNNING] > 1;
+ return tasks[NR_RUNNING] > tasks[NR_ONCPU];
case PSI_NONIDLE:
return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
tasks[NR_RUNNING];
groupc->times[PSI_NONIDLE] += delta;
}
-static u32 psi_group_change(struct psi_group *group, int cpu,
- unsigned int clear, unsigned int set)
+static void psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set,
+ bool wake_clock)
{
struct psi_group_cpu *groupc;
+ u32 state_mask = 0;
unsigned int t, m;
enum psi_states s;
- u32 state_mask = 0;
groupc = per_cpu_ptr(group->pcpu, cpu);
if (!(m & (1 << t)))
continue;
if (groupc->tasks[t] == 0 && !psi_bug) {
- printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+ printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
cpu, t, groupc->tasks[0],
groupc->tasks[1], groupc->tasks[2],
- clear, set);
+ groupc->tasks[3], clear, set);
psi_bug = 1;
}
groupc->tasks[t]--;
write_seqcount_end(&groupc->seq);
- return state_mask;
+ if (state_mask & group->poll_states)
+ psi_schedule_poll_work(group, 1);
+
+ if (wake_clock && !delayed_work_pending(&group->avgs_work))
+ schedule_delayed_work(&group->avgs_work, PSI_FREQ);
}
static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
return &psi_system;
}
-void psi_task_change(struct task_struct *task, int clear, int set)
+static void psi_flags_change(struct task_struct *task, int clear, int set)
{
- int cpu = task_cpu(task);
- struct psi_group *group;
- bool wake_clock = true;
- void *iter = NULL;
-
- if (!task->pid)
- return;
-
if (((task->psi_flags & set) ||
(task->psi_flags & clear) != clear) &&
!psi_bug) {
printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
- task->pid, task->comm, cpu,
+ task->pid, task->comm, task_cpu(task),
task->psi_flags, clear, set);
psi_bug = 1;
}
task->psi_flags &= ~clear;
task->psi_flags |= set;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+ int cpu = task_cpu(task);
+ struct psi_group *group;
+ bool wake_clock = true;
+ void *iter = NULL;
+
+ if (!task->pid)
+ return;
+
+ psi_flags_change(task, clear, set);
/*
* Periodic aggregation shuts off if there is a period of no
wq_worker_last_func(task) == psi_avgs_work))
wake_clock = false;
- while ((group = iterate_groups(task, &iter))) {
- u32 state_mask = psi_group_change(group, cpu, clear, set);
+ while ((group = iterate_groups(task, &iter)))
+ psi_group_change(group, cpu, clear, set, wake_clock);
+}
+
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+ bool sleep)
+{
+ struct psi_group *group, *common = NULL;
+ int cpu = task_cpu(prev);
+ void *iter;
+
+ if (next->pid) {
+ psi_flags_change(next, 0, TSK_ONCPU);
+ /*
+ * When moving state between tasks, the group that
+ * contains them both does not change: we can stop
+ * updating the tree once we reach the first common
+ * ancestor. Iterate @next's ancestors until we
+ * encounter @prev's state.
+ */
+ iter = NULL;
+ while ((group = iterate_groups(next, &iter))) {
+ if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+ common = group;
+ break;
+ }
+
+ psi_group_change(group, cpu, 0, TSK_ONCPU, true);
+ }
+ }
+
+ /*
+ * If this is a voluntary sleep, dequeue will have taken care
+ * of the outgoing TSK_ONCPU alongside TSK_RUNNING already. We
+ * only need to deal with it during preemption.
+ */
+ if (sleep)
+ return;
- if (state_mask & group->poll_states)
- psi_schedule_poll_work(group, 1);
+ if (prev->pid) {
+ psi_flags_change(prev, TSK_ONCPU, 0);
- if (wake_clock && !delayed_work_pending(&group->avgs_work))
- schedule_delayed_work(&group->avgs_work, PSI_FREQ);
+ iter = NULL;
+ while ((group = iterate_groups(prev, &iter)) && group != common)
+ psi_group_change(group, cpu, TSK_ONCPU, 0, true);
}
}
if (static_branch_likely(&psi_disabled))
return;
- *flags = current->flags & PF_MEMSTALL;
+ *flags = current->in_memstall;
if (*flags)
return;
/*
- * PF_MEMSTALL setting & accounting needs to be atomic wrt
+ * in_memstall setting & accounting needs to be atomic wrt
* changes to the task's scheduling state, otherwise we can
* race with CPU migration.
*/
rq = this_rq_lock_irq(&rf);
- current->flags |= PF_MEMSTALL;
+ current->in_memstall = 1;
psi_task_change(current, 0, TSK_MEMSTALL);
rq_unlock_irq(rq, &rf);
if (*flags)
return;
/*
- * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+ * in_memstall clearing & accounting needs to be atomic wrt
* changes to the task's scheduling state, otherwise we could
* race with CPU migration.
*/
rq = this_rq_lock_irq(&rf);
- current->flags &= ~PF_MEMSTALL;
+ current->in_memstall = 0;
psi_task_change(current, TSK_MEMSTALL, 0);
rq_unlock_irq(rq, &rf);
rq = task_rq_lock(task, &rf);
- if (task_on_rq_queued(task))
+ if (task_on_rq_queued(task)) {
task_flags = TSK_RUNNING;
- else if (task->in_iowait)
+ if (task_current(rq, task))
+ task_flags |= TSK_ONCPU;
+ } else if (task->in_iowait)
task_flags = TSK_IOWAIT;
- if (task->flags & PF_MEMSTALL)
+ if (task->in_memstall)
task_flags |= TSK_MEMSTALL;
if (task_flags)
if (test || !rt_task_fits_capacity(p, cpu)) {
int target = find_lowest_rq(p);
+ /*
+ * Bail out if we were forcing a migration to find a better
+ * fitting CPU but our search failed.
+ */
+ if (!test && target != -1 && !rt_task_fits_capacity(p, target))
+ goto out_unlock;
+
/*
* Don't bother moving it if the destination CPU is
* not running a lower priority task.
p->prio < cpu_rq(target)->rt.highest_prio.curr)
cpu = target;
}
+
+out_unlock:
rcu_read_unlock();
out:
* let's hope p can move out.
*/
if (rq->curr->nr_cpus_allowed == 1 ||
- !cpupri_find(&rq->rd->cpupri, rq->curr, NULL, NULL))
+ !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
return;
/*
* see if it is pushed or pulled somewhere else.
*/
if (p->nr_cpus_allowed != 1 &&
- cpupri_find(&rq->rd->cpupri, p, NULL, NULL))
+ cpupri_find(&rq->rd->cpupri, p, NULL))
return;
/*
static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
if (!task_running(rq, p) &&
- cpumask_test_cpu(cpu, p->cpus_ptr) &&
- rt_task_fits_capacity(p, cpu))
+ cpumask_test_cpu(cpu, p->cpus_ptr))
return 1;
return 0;
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ int ret;
/* Make sure the mask is initialized first */
if (unlikely(!lowest_mask))
if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
- if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask,
- rt_task_fits_capacity))
+ /*
+ * If we're on asym system ensure we consider the different capacities
+ * of the CPUs when searching for the lowest_mask.
+ */
+ if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+
+ ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
+ task, lowest_mask,
+ rt_task_fits_capacity);
+ } else {
+
+ ret = cpupri_find(&task_rq(task)->rd->cpupri,
+ task, lowest_mask);
+ }
+
+ if (!ret)
return -1; /* No targets found */
/*
(rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio);
- if (need_to_push || !rt_task_fits_capacity(p, cpu_of(rq)))
+ if (need_to_push)
push_rt_tasks(rq);
}
*/
if (task_on_rq_queued(p) && rq->curr != p) {
#ifdef CONFIG_SMP
- bool need_to_push = rq->rt.overloaded ||
- !rt_task_fits_capacity(p, cpu_of(rq));
-
- if (p->nr_cpus_allowed > 1 && need_to_push)
+ if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
rt_queue_push_tasks(rq);
#endif /* CONFIG_SMP */
if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
*/
static DEFINE_MUTEX(rt_constraints_mutex);
-/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
- struct task_struct *g, *p;
+ struct task_struct *task;
+ struct css_task_iter it;
+ int ret = 0;
/*
* Autogroups do not have RT tasks; see autogroup_create().
if (task_group_is_autogroup(tg))
return 0;
- for_each_process_thread(g, p) {
- if (rt_task(p) && task_group(p) == tg)
- return 1;
- }
+ css_task_iter_start(&tg->css, 0, &it);
+ while (!ret && (task = css_task_iter_next(&it)))
+ ret |= rt_task(task);
+ css_task_iter_end(&it);
- return 0;
+ return ret;
}
struct rt_schedulable_data {
return -EINVAL;
/*
- * Ensure we don't starve existing RT tasks.
+ * Ensure we don't starve existing RT tasks if runtime turns zero.
*/
- if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+ if (rt_bandwidth_enabled() && !runtime &&
+ tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
return -EBUSY;
total = to_ratio(period, runtime);
return -EINVAL;
mutex_lock(&rt_constraints_mutex);
- read_lock(&tasklist_lock);
err = __rt_schedulable(tg, rt_period, rt_runtime);
if (err)
goto unlock;
}
raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
- read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
return err;
int ret = 0;
mutex_lock(&rt_constraints_mutex);
- read_lock(&tasklist_lock);
ret = __rt_schedulable(NULL, 0, 0);
- read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
return ret;
#ifdef CONFIG_64BIT
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+ unsigned long __w = (w); \
+ if (__w) \
+ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+ __w; \
+})
#else
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) (w)
dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}
-extern void dl_change_utilization(struct task_struct *p, u64 new_bw);
extern void init_dl_bw(struct dl_bw *dl_b);
extern int sched_dl_global_validate(void);
extern void sched_dl_do_global(void);
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
- unsigned long runnable_weight;
unsigned int nr_running;
unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
int nr;
unsigned long load_avg;
unsigned long util_avg;
- unsigned long runnable_sum;
+ unsigned long runnable_avg;
} removed;
#ifdef CONFIG_FAIR_GROUP_SCHED
#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)
+
+static inline void se_update_runnable(struct sched_entity *se)
+{
+ if (!entity_is_task(se))
+ se->runnable_weight = se->my_q->h_nr_running;
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ return !!se->on_rq;
+ else
+ return se->runnable_weight;
+}
+
#else
#define entity_is_task(se) 1
+
+static inline void se_update_runnable(struct sched_entity *se) {}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ return !!se->on_rq;
+}
#endif
#ifdef CONFIG_SMP
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 sched_avg avg_dl;
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
struct sched_avg avg_irq;
+#endif
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+ struct sched_avg avg_thermal;
#endif
u64 idle_stamp;
u64 avg_idle;
return rq->clock_task;
}
+/**
+ * By default the decay is the default pelt decay period.
+ * The decay shift can change the decay period in
+ * multiples of 32.
+ * Decay shift Decay period(ms)
+ * 0 32
+ * 1 64
+ * 2 128
+ * 3 256
+ * 4 512
+ */
+extern int sched_thermal_decay_shift;
+
+static inline u64 rq_clock_thermal(struct rq *rq)
+{
+ return rq_clock_task(rq) >> sched_thermal_decay_shift;
+}
+
static inline void rq_clock_skip_update(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
__sd; __sd = __sd->parent)
-#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
-
/**
* highest_flag_domain - Return highest sched_domain containing flag.
* @cpu: The CPU whose highest level of sched domain is to
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
#define BW_SHIFT 20
#define BW_UNIT (1 << BW_SHIFT)
#endif /* CONFIG_SCHED_HRTICK */
+#ifndef arch_scale_freq_tick
+static __always_inline
+void arch_scale_freq_tick(void)
+{
+}
+#endif
+
#ifndef arch_scale_freq_capacity
static __always_inline
unsigned long arch_scale_freq_capacity(int cpu)
return;
if (!wakeup || p->sched_psi_wake_requeue) {
- if (p->flags & PF_MEMSTALL)
+ if (p->in_memstall)
set |= TSK_MEMSTALL;
if (p->sched_psi_wake_requeue)
p->sched_psi_wake_requeue = 0;
return;
if (!sleep) {
- if (p->flags & PF_MEMSTALL)
+ if (p->in_memstall)
clear |= TSK_MEMSTALL;
} else {
+ /*
+ * When a task sleeps, schedule() dequeues it before
+ * switching to the next one. Merge the clearing of
+ * TSK_RUNNING and TSK_ONCPU to save an unnecessary
+ * psi_task_change() call in psi_sched_switch().
+ */
+ clear |= TSK_ONCPU;
+
if (p->in_iowait)
set |= TSK_IOWAIT;
}
* deregister its sleep-persistent psi states from the old
* queue, and let psi_enqueue() know it has to requeue.
*/
- if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+ if (unlikely(p->in_iowait || p->in_memstall)) {
struct rq_flags rf;
struct rq *rq;
int clear = 0;
if (p->in_iowait)
clear |= TSK_IOWAIT;
- if (p->flags & PF_MEMSTALL)
+ if (p->in_memstall)
clear |= TSK_MEMSTALL;
rq = __task_rq_lock(p, &rf);
}
}
+static inline void psi_sched_switch(struct task_struct *prev,
+ struct task_struct *next,
+ bool sleep)
+{
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ psi_task_switch(prev, next, sleep);
+}
+
static inline void psi_task_tick(struct rq *rq)
{
if (static_branch_likely(&psi_disabled))
return;
- if (unlikely(rq->curr->flags & PF_MEMSTALL))
+ if (unlikely(rq->curr->in_memstall))
psi_memstall_tick(rq->curr, cpu_of(rq));
}
#else /* CONFIG_PSI */
static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_sched_switch(struct task_struct *prev,
+ struct task_struct *next,
+ bool sleep) {}
static inline void psi_task_tick(struct rq *rq) {}
#endif /* CONFIG_PSI */
* EAS can be used on a root domain if it meets all the following conditions:
* 1. an Energy Model (EM) is available;
* 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
- * 3. the EM complexity is low enough to keep scheduling overheads low;
- * 4. schedutil is driving the frequency of all CPUs of the rd;
+ * 3. no SMT is detected.
+ * 4. the EM complexity is low enough to keep scheduling overheads low;
+ * 5. schedutil is driving the frequency of all CPUs of the rd;
*
* The complexity of the Energy Model is defined as:
*
goto free;
}
+ /* EAS definitely does *not* handle SMT */
+ if (sched_smt_active()) {
+ pr_warn("rd %*pbl: Disabling EAS, SMT is not supported\n",
+ cpumask_pr_args(cpu_map));
+ goto free;
+ }
+
for_each_cpu(i, cpu_map) {
/* Skip already covered CPUs. */
if (find_pd(pd, i))
* Convert topological properties into behaviour.
*/
- if (sd->flags & SD_ASYM_CPUCAPACITY) {
- struct sched_domain *t = sd;
-
- /*
- * Don't attempt to spread across CPUs of different capacities.
- */
- if (sd->child)
- sd->child->flags &= ~SD_PREFER_SIBLING;
-
- for_each_lower_domain(t)
- t->flags |= SD_BALANCE_WAKE;
- }
+ /* Don't attempt to spread across CPUs of different capacities. */
+ if ((sd->flags & SD_ASYM_CPUCAPACITY) && sd->child)
+ sd->child->flags &= ~SD_PREFER_SIBLING;
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->imbalance_pct = 110;
{
struct sigqueue *q = NULL;
struct user_struct *user;
+ int sigpending;
/*
* Protect access to @t credentials. This can go away when all
* callers hold rcu read lock.
+ *
+ * NOTE! A pending signal will hold on to the user refcount,
+ * and we get/put the refcount only when the sigpending count
+ * changes from/to zero.
*/
rcu_read_lock();
- user = get_uid(__task_cred(t)->user);
- atomic_inc(&user->sigpending);
+ user = __task_cred(t)->user;
+ sigpending = atomic_inc_return(&user->sigpending);
+ if (sigpending == 1)
+ get_uid(user);
rcu_read_unlock();
- if (override_rlimit ||
- atomic_read(&user->sigpending) <=
- task_rlimit(t, RLIMIT_SIGPENDING)) {
+ if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
q = kmem_cache_alloc(sigqueue_cachep, flags);
} else {
print_dropped_signal(sig);
}
if (unlikely(q == NULL)) {
- atomic_dec(&user->sigpending);
- free_uid(user);
+ if (atomic_dec_and_test(&user->sigpending))
+ free_uid(user);
} else {
INIT_LIST_HEAD(&q->list);
q->flags = 0;
{
if (q->flags & SIGQUEUE_PREALLOC)
return;
- atomic_dec(&q->user->sigpending);
- free_uid(q->user);
+ if (atomic_dec_and_test(&q->user->sigpending))
+ free_uid(q->user);
kmem_cache_free(sigqueue_cachep, q);
}
.extra2 = &maxolduid,
},
#ifdef CONFIG_S390
-#ifdef CONFIG_MATHEMU
- {
- .procname = "ieee_emulation_warnings",
- .data = &sysctl_ieee_emulation_warnings,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
{
.procname = "userprocess_debug",
.data = &show_unhandled_signals,
}
EXPORT_SYMBOL(mktime64);
-/**
- * ns_to_timespec - Convert nanoseconds to timespec
- * @nsec: the nanoseconds value to be converted
- *
- * Returns the timespec representation of the nsec parameter.
- */
-struct timespec ns_to_timespec(const s64 nsec)
-{
- struct timespec ts;
- s32 rem;
-
- if (!nsec)
- return (struct timespec) {0, 0};
-
- ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
- if (unlikely(rem < 0)) {
- ts.tv_sec--;
- rem += NSEC_PER_SEC;
- }
- ts.tv_nsec = rem;
-
- return ts;
-}
-EXPORT_SYMBOL(ns_to_timespec);
-
-/**
- * ns_to_timeval - Convert nanoseconds to timeval
- * @nsec: the nanoseconds value to be converted
- *
- * Returns the timeval representation of the nsec parameter.
- */
-struct timeval ns_to_timeval(const s64 nsec)
-{
- struct timespec ts = ns_to_timespec(nsec);
- struct timeval tv;
-
- tv.tv_sec = ts.tv_sec;
- tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
-
- return tv;
-}
-EXPORT_SYMBOL(ns_to_timeval);
-
struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec)
{
struct timespec64 ts = ns_to_timespec64(nsec);
config BOOTTIME_TRACING
bool "Boot-time Tracing support"
- depends on BOOT_CONFIG && TRACING
- default y
+ depends on TRACING
+ select BOOT_CONFIG
help
Enable developer to setup ftrace subsystem via supplemental
kernel cmdline at boot time for debugging (tracing) driver
static void blk_trace_cleanup(struct blk_trace *bt)
{
+ synchronize_rcu();
blk_trace_free(bt);
put_probe_ref();
}
static int __blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (bt == NULL)
return -EINVAL;
void blk_trace_shutdown(struct request_queue *q)
{
mutex_lock(&q->blk_trace_mutex);
-
- if (q->blk_trace) {
+ if (rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex))) {
__blk_trace_startstop(q, 0);
__blk_trace_remove(q);
}
#ifdef CONFIG_BLK_CGROUP
static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ /* We don't use the 'bt' value here except as an optimization... */
+ bt = rcu_dereference_protected(q->blk_trace, 1);
if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
return 0;
static void blk_add_trace_rq(struct request *rq, int error,
unsigned int nr_bytes, u32 what, u64 cgid)
{
- struct blk_trace *bt = rq->q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(rq->q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
if (blk_rq_is_passthrough(rq))
what |= BLK_TC_ACT(BLK_TC_PC);
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
rq->cmd_flags, what, error, 0, NULL, cgid);
+ rcu_read_unlock();
}
static void blk_add_trace_rq_insert(void *ignore,
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
u32 what, int error)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio_op(bio), bio->bi_opf, what, error, 0, NULL,
blk_trace_bio_get_cgid(q, bio));
+ rcu_read_unlock();
}
static void blk_add_trace_bio_bounce(void *ignore,
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
NULL, 0);
+ rcu_read_unlock();
}
}
if (bio)
blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
else {
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
0, 0, NULL, 0);
+ rcu_read_unlock();
}
}
static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt)
__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+ rcu_read_unlock();
}
static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
unsigned int depth, bool explicit)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(depth);
u32 what;
__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
}
+ rcu_read_unlock();
}
static void blk_add_trace_split(void *ignore,
struct request_queue *q, struct bio *bio,
unsigned int pdu)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
if (bt) {
__be64 rpdu = cpu_to_be64(pdu);
BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
&rpdu, blk_trace_bio_get_cgid(q, bio));
}
+ rcu_read_unlock();
}
/**
struct request_queue *q, struct bio *bio,
dev_t dev, sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(bio_dev(bio));
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
+ rcu_read_unlock();
}
/**
struct request *rq, dev_t dev,
sector_t from)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
struct blk_io_trace_remap r;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
r.device_from = cpu_to_be32(dev);
r.device_to = cpu_to_be32(disk_devt(rq->rq_disk));
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+ rcu_read_unlock();
}
/**
struct request *rq,
void *data, size_t len)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt;
- if (likely(!bt))
+ rcu_read_lock();
+ bt = rcu_dereference(q->blk_trace);
+ if (likely(!bt)) {
+ rcu_read_unlock();
return;
+ }
__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
BLK_TA_DRV_DATA, 0, len, data,
blk_trace_request_get_cgid(q, rq));
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
return -EINVAL;
put_probe_ref();
+ synchronize_rcu();
blk_trace_free(bt);
return 0;
}
struct hd_struct *p = dev_to_part(dev);
struct request_queue *q;
struct block_device *bdev;
+ struct blk_trace *bt;
ssize_t ret = -ENXIO;
bdev = bdget(part_devt(p));
mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ ret = sprintf(buf, "%u\n", !!bt);
goto out_unlock_bdev;
}
- if (q->blk_trace == NULL)
+ if (bt == NULL)
ret = sprintf(buf, "disabled\n");
else if (attr == &dev_attr_act_mask)
- ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+ ret = blk_trace_mask2str(buf, bt->act_mask);
else if (attr == &dev_attr_pid)
- ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+ ret = sprintf(buf, "%u\n", bt->pid);
else if (attr == &dev_attr_start_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+ ret = sprintf(buf, "%llu\n", bt->start_lba);
else if (attr == &dev_attr_end_lba)
- ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+ ret = sprintf(buf, "%llu\n", bt->end_lba);
out_unlock_bdev:
mutex_unlock(&q->blk_trace_mutex);
struct block_device *bdev;
struct request_queue *q;
struct hd_struct *p;
+ struct blk_trace *bt;
u64 value;
ssize_t ret = -EINVAL;
mutex_lock(&q->blk_trace_mutex);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
if (attr == &dev_attr_enable) {
- if (!!value == !!q->blk_trace) {
+ if (!!value == !!bt) {
ret = 0;
goto out_unlock_bdev;
}
}
ret = 0;
- if (q->blk_trace == NULL)
+ if (bt == NULL)
ret = blk_trace_setup_queue(q, bdev);
if (ret == 0) {
if (attr == &dev_attr_act_mask)
- q->blk_trace->act_mask = value;
+ bt->act_mask = value;
else if (attr == &dev_attr_pid)
- q->blk_trace->pid = value;
+ bt->pid = value;
else if (attr == &dev_attr_start_lba)
- q->blk_trace->start_lba = value;
+ bt->start_lba = value;
else if (attr == &dev_attr_end_lba)
- q->blk_trace->end_lba = value;
+ bt->end_lba = value;
}
out_unlock_bdev:
/* Create some bogus values just for testing */
vals[0] = 777; /* next_pid_field */
- vals[1] = (u64)"hula hoops"; /* next_comm_field */
+ vals[1] = (u64)(long)"hula hoops"; /* next_comm_field */
vals[2] = 1000000; /* ts_ns */
vals[3] = 1000; /* ts_ms */
- vals[4] = smp_processor_id(); /* cpu */
- vals[5] = (u64)"thneed"; /* my_string_field */
+ vals[4] = raw_smp_processor_id(); /* cpu */
+ vals[5] = (u64)(long)"thneed"; /* my_string_field */
vals[6] = 598; /* my_int_field */
/* Now generate a gen_synth_test event */
/* Create some bogus values just for testing */
vals[0] = 777; /* next_pid_field */
- vals[1] = (u64)"tiddlywinks"; /* next_comm_field */
+ vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */
vals[2] = 1000000; /* ts_ns */
vals[3] = 1000; /* ts_ms */
- vals[4] = smp_processor_id(); /* cpu */
- vals[5] = (u64)"thneed_2.0"; /* my_string_field */
+ vals[4] = raw_smp_processor_id(); /* cpu */
+ vals[5] = (u64)(long)"thneed_2.0"; /* my_string_field */
vals[6] = 399; /* my_int_field */
/* Now trace an empty_synth_test event */
/* Create some bogus values just for testing */
vals[0] = 777; /* next_pid_field */
- vals[1] = (u64)"tiddlywinks"; /* next_comm_field */
+ vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */
vals[2] = 1000000; /* ts_ns */
vals[3] = 1000; /* ts_ms */
- vals[4] = smp_processor_id(); /* cpu */
- vals[5] = (u64)"thneed"; /* my_string_field */
+ vals[4] = raw_smp_processor_id(); /* cpu */
+ vals[5] = (u64)(long)"thneed"; /* my_string_field */
vals[6] = 398; /* my_int_field */
/* Now generate a create_synth_test event */
goto out;
/* next_comm_field */
- ret = synth_event_add_next_val((u64)"slinky", &trace_state);
+ ret = synth_event_add_next_val((u64)(long)"slinky", &trace_state);
if (ret)
goto out;
goto out;
/* cpu */
- ret = synth_event_add_next_val(smp_processor_id(), &trace_state);
+ ret = synth_event_add_next_val(raw_smp_processor_id(), &trace_state);
if (ret)
goto out;
/* my_string_field */
- ret = synth_event_add_next_val((u64)"thneed_2.01", &trace_state);
+ ret = synth_event_add_next_val((u64)(long)"thneed_2.01", &trace_state);
if (ret)
goto out;
if (ret)
goto out;
- ret = synth_event_add_val("cpu", smp_processor_id(), &trace_state);
+ ret = synth_event_add_val("cpu", raw_smp_processor_id(), &trace_state);
if (ret)
goto out;
if (ret)
goto out;
- ret = synth_event_add_val("next_comm_field", (u64)"silly putty",
+ ret = synth_event_add_val("next_comm_field", (u64)(long)"silly putty",
&trace_state);
if (ret)
goto out;
- ret = synth_event_add_val("my_string_field", (u64)"thneed_9",
+ ret = synth_event_add_val("my_string_field", (u64)(long)"thneed_9",
&trace_state);
if (ret)
goto out;
/* Trace some bogus values just for testing */
ret = synth_event_trace(create_synth_test, 7, /* number of values */
- 444, /* next_pid_field */
- (u64)"clackers", /* next_comm_field */
- 1000000, /* ts_ns */
- 1000, /* ts_ms */
- smp_processor_id(), /* cpu */
- (u64)"Thneed", /* my_string_field */
- 999); /* my_int_field */
+ (u64)444, /* next_pid_field */
+ (u64)(long)"clackers", /* next_comm_field */
+ (u64)1000000, /* ts_ns */
+ (u64)1000, /* ts_ms */
+ (u64)raw_smp_processor_id(), /* cpu */
+ (u64)(long)"Thneed", /* my_string_field */
+ (u64)999); /* my_int_field */
return ret;
}
pr_info("Running postponed tracer tests:\n");
+ tracing_selftest_running = true;
list_for_each_entry_safe(p, n, &postponed_selftests, list) {
/* This loop can take minutes when sanitizers are enabled, so
* lets make sure we allow RCU processing.
list_del(&p->list);
kfree(p);
}
+ tracing_selftest_running = false;
out:
mutex_unlock(&trace_types_lock);
return fmt;
}
+static void print_synth_event_num_val(struct trace_seq *s,
+ char *print_fmt, char *name,
+ int size, u64 val, char *space)
+{
+ switch (size) {
+ case 1:
+ trace_seq_printf(s, print_fmt, name, (u8)val, space);
+ break;
+
+ case 2:
+ trace_seq_printf(s, print_fmt, name, (u16)val, space);
+ break;
+
+ case 4:
+ trace_seq_printf(s, print_fmt, name, (u32)val, space);
+ break;
+
+ default:
+ trace_seq_printf(s, print_fmt, name, val, space);
+ break;
+ }
+}
+
static enum print_line_t print_synth_event(struct trace_iterator *iter,
int flags,
struct trace_event *event)
} else {
struct trace_print_flags __flags[] = {
__def_gfpflag_names, {-1, NULL} };
+ char *space = (i == se->n_fields - 1 ? "" : " ");
- trace_seq_printf(s, print_fmt, se->fields[i]->name,
- entry->fields[n_u64],
- i == se->n_fields - 1 ? "" : " ");
+ print_synth_event_num_val(s, print_fmt,
+ se->fields[i]->name,
+ se->fields[i]->size,
+ entry->fields[n_u64],
+ space);
if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
trace_seq_puts(s, " (");
int entry_size, fields_size = 0;
int ret = 0;
+ memset(trace_state, '\0', sizeof(*trace_state));
+
/*
* Normal event tracing doesn't get called at all unless the
* ENABLED bit is set (which attaches the probe thus allowing
return ret;
}
+ if (n_vals != state.event->n_fields) {
+ ret = -EINVAL;
+ goto out;
+ }
+
va_start(args, n_vals);
for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
u64 val;
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
- state.entry->fields[n_u64] = val;
+ struct synth_field *field = state.event->fields[i];
+
+ switch (field->size) {
+ case 1:
+ *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ break;
+
+ default:
+ state.entry->fields[n_u64] = val;
+ break;
+ }
n_u64++;
}
}
va_end(args);
-
+out:
__synth_event_trace_end(&state);
return ret;
return ret;
}
+ if (n_vals != state.event->n_fields) {
+ ret = -EINVAL;
+ goto out;
+ }
+
for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
if (state.event->fields[i]->is_string) {
char *str_val = (char *)(long)vals[i];
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
- state.entry->fields[n_u64] = vals[i];
+ struct synth_field *field = state.event->fields[i];
+ u64 val = vals[i];
+
+ switch (field->size) {
+ case 1:
+ *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ break;
+
+ default:
+ state.entry->fields[n_u64] = val;
+ break;
+ }
n_u64++;
}
}
-
+out:
__synth_event_trace_end(&state);
return ret;
if (!trace_state)
return -EINVAL;
- memset(trace_state, '\0', sizeof(*trace_state));
-
ret = __synth_event_trace_start(file, trace_state);
if (ret == -ENOENT)
ret = 0; /* just disabled, not really an error */
str_field = (char *)&entry->fields[field->offset];
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
- } else
- entry->fields[field->offset] = val;
+ } else {
+ switch (field->size) {
+ case 1:
+ *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
+ break;
+
+ default:
+ trace_state->entry->fields[field->offset] = val;
+ break;
+ }
+ }
out:
return ret;
}
static int __init __xbc_add_key(char *k)
{
- struct xbc_node *node;
+ struct xbc_node *node, *child;
if (!xbc_valid_keyword(k))
return xbc_parse_error("Invalid keyword", k);
if (!last_parent) /* the first level */
node = find_match_node(xbc_nodes, k);
- else
- node = find_match_node(xbc_node_get_child(last_parent), k);
+ else {
+ child = xbc_node_get_child(last_parent);
+ if (child && xbc_node_is_value(child))
+ return xbc_parse_error("Subkey is mixed with value", k);
+ node = find_match_node(child, k);
+ }
if (node)
last_parent = node;
return __xbc_add_key(k);
}
-static int __init xbc_parse_kv(char **k, char *v)
+static int __init xbc_parse_kv(char **k, char *v, int op)
{
struct xbc_node *prev_parent = last_parent;
- struct xbc_node *node;
+ struct xbc_node *child;
char *next;
int c, ret;
if (ret)
return ret;
+ child = xbc_node_get_child(last_parent);
+ if (child) {
+ if (xbc_node_is_key(child))
+ return xbc_parse_error("Value is mixed with subkey", v);
+ else if (op == '=')
+ return xbc_parse_error("Value is redefined", v);
+ }
+
c = __xbc_parse_value(&v, &next);
if (c < 0)
return c;
- node = xbc_add_sibling(v, XBC_VALUE);
- if (!node)
+ if (!xbc_add_sibling(v, XBC_VALUE))
return -ENOMEM;
if (c == ',') { /* Array */
p = buf;
do {
- q = strpbrk(p, "{}=;\n#");
+ q = strpbrk(p, "{}=+;\n#");
if (!q) {
p = skip_spaces(p);
if (*p != '\0')
c = *q;
*q++ = '\0';
switch (c) {
+ case '+':
+ if (*q++ != '=') {
+ ret = xbc_parse_error("Wrong '+' operator",
+ q - 2);
+ break;
+ }
+ /* Fall through */
case '=':
- ret = xbc_parse_kv(&p, q);
+ ret = xbc_parse_kv(&p, q, c);
break;
case '{':
ret = xbc_open_brace(&p, q);
BUG();
}
EXPORT_SYMBOL(cpumask_local_spread);
+
+static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
+
+/**
+ * Returns an arbitrary cpu within srcp1 & srcp2.
+ *
+ * Iterated calls using the same srcp1 and srcp2 will be distributed within
+ * their intersection.
+ *
+ * Returns >= nr_cpu_ids if the intersection is empty.
+ */
+int cpumask_any_and_distribute(const struct cpumask *src1p,
+ const struct cpumask *src2p)
+{
+ int next, prev;
+
+ /* NOTE: our first selection will skip 0. */
+ prev = __this_cpu_read(distribute_cpu_mask_prev);
+
+ next = cpumask_next_and(prev, src1p, src2p);
+ if (next >= nr_cpu_ids)
+ next = cpumask_first_and(src1p, src2p);
+
+ if (next < nr_cpu_ids)
+ __this_cpu_write(distribute_cpu_mask_prev, next);
+
+ return next;
+}
+EXPORT_SYMBOL(cpumask_any_and_distribute);
__le64 lens[2];
} b __aligned(16);
+ if (WARN_ON(src_len > INT_MAX))
+ return false;
+
chacha_load_key(b.k, key);
b.iv[0] = 0;
return true;
if (stack_slabs[depot_index] == NULL) {
stack_slabs[depot_index] = *prealloc;
+ *prealloc = NULL;
} else {
- stack_slabs[depot_index + 1] = *prealloc;
+ /* If this is the last depot slab, do not touch the next one. */
+ if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
+ stack_slabs[depot_index + 1] = *prealloc;
+ *prealloc = NULL;
+ }
/*
* This smp_store_release pairs with smp_load_acquire() from
* |next_slab_inited| above and in stack_depot_save().
*/
smp_store_release(&next_slab_inited, 1);
}
- *prealloc = NULL;
return true;
}
* @n: number of strings in the array or -1 for NULL terminated arrays
* @string: string to match with
*
+ * This routine will look for a string in an array of strings up to the
+ * n-th element in the array or until the first NULL element.
+ *
+ * Historically the value of -1 for @n, was used to search in arrays that
+ * are NULL terminated. However, the function does not make a distinction
+ * when finishing the search: either @n elements have been compared OR
+ * the first NULL element was found.
+ *
* Return:
* index of a @string in the @array if matches, or %-EINVAL otherwise.
*/
*
* Returns index of @str in the @array or -EINVAL, just like match_string().
* Uses sysfs_streq instead of strcmp for matching.
+ *
+ * This routine will look for a string in an array of strings up to the
+ * n-th element in the array or until the first NULL element.
+ *
+ * Historically the value of -1 for @n, was used to search in arrays that
+ * are NULL terminated. However, the function does not make a distinction
+ * when finishing the search: either @n elements have been compared OR
+ * the first NULL element was found.
*/
int __sysfs_match_string(const char * const *array, size_t n, const char *str)
{
if (mem_cgroup_is_root(memcg))
continue;
ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
- if (ret)
+ if (ret) {
+ mem_cgroup_iter_break(NULL, memcg);
goto unlock;
+ }
}
unlock:
if (!ret)
bool downgraded = false;
LIST_HEAD(uf);
- brk = untagged_addr(brk);
-
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
struct file *file = NULL;
unsigned long retval;
- addr = untagged_addr(addr);
-
if (!(flags & MAP_ANONYMOUS)) {
audit_mmap_fd(fd, flags);
file = fget(fd);
LIST_HEAD(uf_unmap);
addr = untagged_addr(addr);
- new_addr = untagged_addr(new_addr);
if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
return ret;
{"always", SHMEM_HUGE_ALWAYS },
{"within_size", SHMEM_HUGE_WITHIN_SIZE },
{"advise", SHMEM_HUGE_ADVISE },
- {"deny", SHMEM_HUGE_DENY },
- {"force", SHMEM_HUGE_FORCE },
{}
};
* Poison uninitialized struct pages in order to catch invalid flags
* combinations.
*/
- page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+ page_init_poison(memmap, sizeof(struct page) * nr_pages);
ms = __nr_to_section(section_nr);
set_section_nid(section_nr, nid);
mapping = swap_file->f_mapping;
inode = mapping->host;
- /* If S_ISREG(inode->i_mode) will do inode_lock(inode); */
+ /* will take i_rwsem; */
error = claim_swapfile(p, inode);
if (unlikely(error))
goto bad_swap;
/*
* Scan types proportional to swappiness and
* their relative recent reclaim efficiency.
- * Make sure we don't miss the last page
- * because of a round-off error.
+ * Make sure we don't miss the last page on
+ * the offlined memory cgroups because of a
+ * round-off error.
*/
- scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+ scan = mem_cgroup_online(memcg) ?
+ div64_u64(scan * fraction[file], denominator) :
+ DIV64_U64_ROUND_UP(scan * fraction[file],
denominator);
break;
case SCAN_FILE:
depends on NETFILTER_ADVANCED
select NETFILTER_FAMILY_BRIDGE
select SKB_EXTENSIONS
- default m
---help---
Enabling this option will let arptables resp. iptables see bridged
ARP resp. IP traffic. If you want a bridging firewall, you probably
const struct nf_br_ops *nf_ops;
u8 state = BR_STATE_FORWARDING;
const unsigned char *dest;
- struct ethhdr *eth;
u16 vid = 0;
rcu_read_lock();
BR_INPUT_SKB_CB(skb)->frag_max_size = 0;
skb_reset_mac_header(skb);
- eth = eth_hdr(skb);
skb_pull(skb, ETH_HLEN);
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state))
goto out;
if (IS_ENABLED(CONFIG_INET) &&
- (eth->h_proto == htons(ETH_P_ARP) ||
- eth->h_proto == htons(ETH_P_RARP)) &&
+ (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) ||
+ eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) &&
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
br_do_proxy_suppress_arp(skb, br, vid, NULL);
} else if (IS_ENABLED(CONFIG_IPV6) &&
{
struct net_bridge_port *p;
- list_for_each_entry_rcu(p, &br->port_list, list) {
+ list_for_each_entry_rcu(p, &br->port_list, list,
+ lockdep_is_held(&br->lock)) {
if (p->port_no == port_no)
return p;
}
#include "net-sysfs.h"
#define MAX_GRO_SKBS 8
-#define MAX_NEST_DEV 8
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
name_node = netdev_name_node_lookup(net, name);
if (!name_node)
return -ENOENT;
+ /* lookup might have found our primary name or a name belonging
+ * to another device.
+ */
+ if (name_node == dev->name_node || name_node->dev != dev)
+ return -EINVAL;
+
__netdev_name_node_alt_destroy(name_node);
return 0;
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
+ if (hash >= qoffset)
+ hash -= qoffset;
while (unlikely(hash >= qcount))
hash -= qcount;
return hash + qoffset;
qdisc_calculate_pkt_len(skb, q);
if (q->flags & TCQ_F_NOLOCK) {
- if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
- qdisc_run_begin(q)) {
- if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
- &q->state))) {
- __qdisc_drop(skb, &to_free);
- rc = NET_XMIT_DROP;
- goto end_run;
- }
- qdisc_bstats_cpu_update(q, skb);
-
- rc = NET_XMIT_SUCCESS;
- if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
- __qdisc_run(q);
-
-end_run:
- qdisc_run_end(q);
- } else {
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
- qdisc_run(q);
- }
+ rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ qdisc_run(q);
if (unlikely(to_free))
kfree_skb_list(to_free);
return 0;
}
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
- struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
{
struct netdev_adjacent *lower;
return lower->dev;
}
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
static u8 __netdev_upper_depth(struct net_device *dev)
{
static struct devlink_dpipe_table *
devlink_dpipe_table_find(struct list_head *dpipe_tables,
- const char *table_name)
+ const char *table_name, struct devlink *devlink)
{
struct devlink_dpipe_table *table;
-
- list_for_each_entry_rcu(table, dpipe_tables, list) {
+ list_for_each_entry_rcu(table, dpipe_tables, list,
+ lockdep_is_held(&devlink->lock)) {
if (!strcmp(table->name, table_name))
return table;
}
table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
- table_name);
+ table_name, devlink);
if (!table)
return -EINVAL;
struct devlink_dpipe_table *table;
table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
- table_name);
+ table_name, devlink);
if (!table)
return -EINVAL;
rcu_read_lock();
table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
- table_name);
+ table_name, devlink);
enabled = false;
if (table)
enabled = table->counters_enabled;
void *priv, bool counter_control_extern)
{
struct devlink_dpipe_table *table;
-
- if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
- return -EEXIST;
+ int err = 0;
if (WARN_ON(!table_ops->size_get))
return -EINVAL;
+ mutex_lock(&devlink->lock);
+
+ if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name,
+ devlink)) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
table = kzalloc(sizeof(*table), GFP_KERNEL);
- if (!table)
- return -ENOMEM;
+ if (!table) {
+ err = -ENOMEM;
+ goto unlock;
+ }
table->name = table_name;
table->table_ops = table_ops;
table->priv = priv;
table->counter_control_extern = counter_control_extern;
- mutex_lock(&devlink->lock);
list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+unlock:
mutex_unlock(&devlink->lock);
- return 0;
+ return err;
}
EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
mutex_lock(&devlink->lock);
table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
- table_name);
+ table_name, devlink);
if (!table)
goto unlock;
list_del_rcu(&table->list);
mutex_lock(&devlink->lock);
table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
- table_name);
+ table_name, devlink);
if (!table) {
err = -EINVAL;
goto out;
frh = nlmsg_data(nlh);
frh->family = ops->family;
- frh->table = rule->table;
+ frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
if (nla_put_u32(skb, FRA_TABLE, rule->table))
goto nla_put_failure;
if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
if (err)
return err;
- alt_ifname = nla_data(attr);
+ alt_ifname = nla_strdup(attr, GFP_KERNEL);
+ if (!alt_ifname)
+ return -ENOMEM;
+
if (cmd == RTM_NEWLINKPROP) {
- alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
- if (!alt_ifname)
- return -ENOMEM;
err = netdev_name_node_alt_create(dev, alt_ifname);
- if (err) {
- kfree(alt_ifname);
- return err;
- }
+ if (!err)
+ alt_ifname = NULL;
} else if (cmd == RTM_DELLINKPROP) {
err = netdev_name_node_alt_destroy(dev, alt_ifname);
- if (err)
- return err;
} else {
- WARN_ON(1);
- return 0;
+ WARN_ON_ONCE(1);
+ err = -EINVAL;
}
- *changed = true;
- return 0;
+ kfree(alt_ifname);
+ if (!err)
+ *changed = true;
+ return err;
}
static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,
return NULL;
}
- /* use OR instead of assignment to avoid clearing of bits in mask */
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
return NULL;
}
- /* use OR instead of assignment to avoid clearing of bits in mask */
if (nc->page.pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
typeof(IPPROTO_IP) proto,
unsigned int off)
{
- switch (proto) {
- int err;
+ int err;
+ switch (proto) {
case IPPROTO_TCP:
err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
off + MAX_TCP_HDR_LEN);
static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = {
[ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT },
[ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG },
- [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 },
+ [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32,
+ ETHNL_MAX_BITSET_SIZE),
[ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED },
[ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY },
[ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY },
"mask only allowed in compact bitset");
return -EINVAL;
}
+
no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
+ if (no_mask)
+ ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
bool old_val, new_val;
#ifndef _NET_ETHTOOL_BITSET_H
#define _NET_ETHTOOL_BITSET_H
+#define ETHNL_MAX_BITSET_SIZE S16_MAX
+
typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN];
int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact);
new_node->seq_out[i] = seq_out;
spin_lock_bh(&hsr->list_lock);
- list_for_each_entry_rcu(node, node_db, mac_list) {
+ list_for_each_entry_rcu(node, node_db, mac_list,
+ lockdep_is_held(&hsr->list_lock)) {
if (ether_addr_equal(node->macaddress_A, addr))
goto out;
if (ether_addr_equal(node->macaddress_B, addr))
{
unsigned char optbuf[sizeof(struct ip_options) + 40];
struct ip_options *opt = (struct ip_options *)optbuf;
+ int res;
if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
return;
memset(opt, 0, sizeof(struct ip_options));
opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
- if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
return;
if (gateway)
{
struct request_sock *req;
- tcp_try_undo_loss(sk, false);
+ /* If we are still handling the SYNACK RTO, see if timestamp ECR allows
+ * undo. If peer SACKs triggered fast recovery, we can't undo here.
+ */
+ if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
+ tcp_try_undo_loss(sk, false);
/* Reset rtx states to prevent spurious retransmits_timed_out() */
tcp_sk(sk)->retrans_stamp = 0;
inet->inet_dport = 0;
sock_rps_reset_rxhash(sk);
sk->sk_bound_dev_if = 0;
- if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
inet_reset_saddr(sk);
+ if (sk->sk_prot->rehash &&
+ (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+ sk->sk_prot->rehash(sk);
+ }
if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
sk->sk_prot->unhash(sk);
found++;
break;
}
- if (rt_can_ecmp)
- fallback_ins = fallback_ins ?: ins;
+ fallback_ins = fallback_ins ?: ins;
goto next_iter;
}
}
if (fallback_ins && !found) {
- /* No ECMP-able route found, replace first non-ECMP one */
+ /* No matching route with same ecmp-able-ness found, replace
+ * first matching route
+ */
ins = fallback_ins;
iter = rcu_dereference_protected(*ins,
lockdep_is_held(&rt->fib6_table->tb6_lock));
return -ENOENT;
switch (type) {
- struct ipv6_tlv_tnl_enc_lim *tel;
- __u32 teli;
case ICMPV6_DEST_UNREACH:
net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
t->parms.name);
break;
}
return 0;
- case ICMPV6_PARAMPROB:
+ case ICMPV6_PARAMPROB: {
+ struct ipv6_tlv_tnl_enc_lim *tel;
+ __u32 teli;
+
teli = 0;
if (code == ICMPV6_HDR_FIELD)
teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
t->parms.name);
}
return 0;
+ }
case ICMPV6_PKT_TOOBIG:
ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
return 0;
err = 0;
switch (*type) {
- struct ipv6_tlv_tnl_enc_lim *tel;
- __u32 mtu, teli;
case ICMPV6_DEST_UNREACH:
net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
t->parms.name);
rel_msg = 1;
}
break;
- case ICMPV6_PARAMPROB:
+ case ICMPV6_PARAMPROB: {
+ struct ipv6_tlv_tnl_enc_lim *tel;
+ __u32 teli;
+
teli = 0;
if ((*code) == ICMPV6_HDR_FIELD)
teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
t->parms.name);
}
break;
- case ICMPV6_PKT_TOOBIG:
+ }
+ case ICMPV6_PKT_TOOBIG: {
+ __u32 mtu;
+
ip6_update_pmtu(skb, net, htonl(*info), 0, 0,
sock_net_uid(net, NULL));
mtu = *info - offset;
rel_msg = 1;
}
break;
+ }
case NDISC_REDIRECT:
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
retv = -EBUSY;
break;
}
- } else if (sk->sk_protocol != IPPROTO_TCP)
+ } else if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_prot != &tcpv6_prot) {
+ retv = -EBUSY;
+ break;
+ }
break;
-
+ } else {
+ break;
+ }
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
NLM_F_REPLACE);
+ cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
nhn++;
}
(auth_transaction == 2 &&
ifmgd->auth_data->expected_transaction == 2)) {
if (!ieee80211_mark_sta_auth(sdata, bssid))
- goto out_err;
+ return; /* ignore frame -- wait for timeout */
} else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE &&
auth_transaction == 2) {
sdata_info(sdata, "SAE peer confirmed\n");
}
cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
- return;
- out_err:
- mutex_unlock(&sdata->local->sta_mtx);
- /* ignore frame -- wait for timeout */
}
#define case_WLAN(type) \
lockdep_assert_held(&local->sta_mtx);
- list_for_each_entry_rcu(sta, &local->sta_list, list) {
+ list_for_each_entry(sta, &local->sta_list, list) {
if (sdata != sta->sdata &&
(!sta->sdata->bss || sta->sdata->bss != sdata->bss))
continue;
depends on INET
select SKB_EXTENSIONS
select CRYPTO_LIB_SHA256
+ select CRYPTO
help
Multipath TCP (MPTCP) connections send and receive data over multiple
subflows in order to utilize multiple network paths. Each subflow
}
}
+static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
+{
+ return 0;
+}
+
static int __mptcp_init_sock(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
__set_bit(MPTCP_SEND_SPACE, &msk->flags);
msk->first = NULL;
+ inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
return 0;
}
char __user *optval, unsigned int optlen)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- int ret = -EOPNOTSUPP;
struct socket *ssock;
- struct sock *ssk;
pr_debug("msk=%p", msk);
/* @@ the meaning of setsockopt() when the socket is connected and
- * there are multiple subflows is not defined.
+ * there are multiple subflows is not yet defined. It is up to the
+ * MPTCP-level socket to configure the subflows until the subflow
+ * is in TCP fallback, when TCP socket options are passed through
+ * to the one remaining subflow.
*/
lock_sock(sk);
- ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
- if (IS_ERR(ssock)) {
- release_sock(sk);
- return ret;
- }
+ ssock = __mptcp_tcp_fallback(msk);
+ if (ssock)
+ return tcp_setsockopt(ssock->sk, level, optname, optval,
+ optlen);
- ssk = ssock->sk;
- sock_hold(ssk);
release_sock(sk);
- ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
- sock_put(ssk);
-
- return ret;
+ return -EOPNOTSUPP;
}
static int mptcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *option)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- int ret = -EOPNOTSUPP;
struct socket *ssock;
- struct sock *ssk;
pr_debug("msk=%p", msk);
- /* @@ the meaning of getsockopt() when the socket is connected and
- * there are multiple subflows is not defined.
+ /* @@ the meaning of setsockopt() when the socket is connected and
+ * there are multiple subflows is not yet defined. It is up to the
+ * MPTCP-level socket to configure the subflows until the subflow
+ * is in TCP fallback, when socket options are passed through
+ * to the one remaining subflow.
*/
lock_sock(sk);
- ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
- if (IS_ERR(ssock)) {
- release_sock(sk);
- return ret;
- }
+ ssock = __mptcp_tcp_fallback(msk);
+ if (ssock)
+ return tcp_getsockopt(ssock->sk, level, optname, optval,
+ option);
- ssk = ssock->sk;
- sock_hold(ssk);
release_sock(sk);
- ret = tcp_getsockopt(ssk, level, optname, optval, option);
- sock_put(ssk);
-
- return ret;
+ return -EOPNOTSUPP;
}
static int mptcp_get_port(struct sock *sk, unsigned short snum)
#define MPTCP_DSS_FLAG_MASK (0x1F)
/* MPTCP socket flags */
-#define MPTCP_DATA_READY BIT(0)
-#define MPTCP_SEND_SPACE BIT(1)
+#define MPTCP_DATA_READY 0
+#define MPTCP_SEND_SPACE 1
/* MPTCP connection sock */
struct mptcp_sock {
return set;
}
+static inline void
+ip_set_lock(struct ip_set *set)
+{
+ if (!set->variant->region_lock)
+ spin_lock_bh(&set->lock);
+}
+
+static inline void
+ip_set_unlock(struct ip_set *set)
+{
+ if (!set->variant->region_lock)
+ spin_unlock_bh(&set->lock);
+}
+
int
ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
if (ret == -EAGAIN) {
/* Type requests element to be completed */
pr_debug("element must be completed, ADD is triggered\n");
- spin_lock_bh(&set->lock);
+ ip_set_lock(set);
set->variant->kadt(set, skb, par, IPSET_ADD, opt);
- spin_unlock_bh(&set->lock);
+ ip_set_unlock(set);
ret = 1;
} else {
/* --return-nomatch: invert matched element */
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
return -IPSET_ERR_TYPE_MISMATCH;
- spin_lock_bh(&set->lock);
+ ip_set_lock(set);
ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
- spin_unlock_bh(&set->lock);
+ ip_set_unlock(set);
return ret;
}
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
return -IPSET_ERR_TYPE_MISMATCH;
- spin_lock_bh(&set->lock);
+ ip_set_lock(set);
ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
- spin_unlock_bh(&set->lock);
+ ip_set_unlock(set);
return ret;
}
{
pr_debug("set: %s\n", set->name);
- spin_lock_bh(&set->lock);
+ ip_set_lock(set);
set->variant->flush(set);
- spin_unlock_bh(&set->lock);
+ ip_set_unlock(set);
}
static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb,
bool eexist = flags & IPSET_FLAG_EXIST, retried = false;
do {
- spin_lock_bh(&set->lock);
+ ip_set_lock(set);
ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
- spin_unlock_bh(&set->lock);
+ ip_set_unlock(set);
retried = true;
} while (ret == -EAGAIN &&
set->variant->resize &&
#include <linux/rcupdate.h>
#include <linux/jhash.h>
#include <linux/types.h>
+#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/ipset/ip_set.h>
-#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c)
-#define ipset_dereference_protected(p, set) \
- __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock))
-
-#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1)
+#define __ipset_dereference(p) \
+ rcu_dereference_protected(p, 1)
+#define ipset_dereference_nfnl(p) \
+ rcu_dereference_protected(p, \
+ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
+#define ipset_dereference_set(p, set) \
+ rcu_dereference_protected(p, \
+ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \
+ lockdep_is_held(&(set)->lock))
+#define ipset_dereference_bh_nfnl(p) \
+ rcu_dereference_bh_check(p, \
+ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
/* Hashing which uses arrays to resolve clashing. The hash table is resized
* (doubled) when searching becomes too long.
__aligned(__alignof__(u64));
};
+/* Region size for locking == 2^HTABLE_REGION_BITS */
+#define HTABLE_REGION_BITS 10
+#define ahash_numof_locks(htable_bits) \
+ ((htable_bits) < HTABLE_REGION_BITS ? 1 \
+ : jhash_size((htable_bits) - HTABLE_REGION_BITS))
+#define ahash_sizeof_regions(htable_bits) \
+ (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
+#define ahash_region(n, htable_bits) \
+ ((n) % ahash_numof_locks(htable_bits))
+#define ahash_bucket_start(h, htable_bits) \
+ ((htable_bits) < HTABLE_REGION_BITS ? 0 \
+ : (h) * jhash_size(HTABLE_REGION_BITS))
+#define ahash_bucket_end(h, htable_bits) \
+ ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \
+ : ((h) + 1) * jhash_size(HTABLE_REGION_BITS))
+
+struct htable_gc {
+ struct delayed_work dwork;
+ struct ip_set *set; /* Set the gc belongs to */
+ u32 region; /* Last gc run position */
+};
+
/* The hash table: the table size stored here in order to make resizing easy */
struct htable {
atomic_t ref; /* References for resizing */
- atomic_t uref; /* References for dumping */
+ atomic_t uref; /* References for dumping and gc */
u8 htable_bits; /* size of hash table == 2^htable_bits */
+ u32 maxelem; /* Maxelem per region */
+ struct ip_set_region *hregion; /* Region locks and ext sizes */
struct hbucket __rcu *bucket[0]; /* hashtable buckets */
};
#define NLEN 0
#endif /* IP_SET_HASH_WITH_NETS */
+#define SET_ELEM_EXPIRED(set, d) \
+ (SET_WITH_TIMEOUT(set) && \
+ ip_set_timeout_expired(ext_timeout(d, set)))
+
#endif /* _IP_SET_HASH_GEN_H */
#ifndef MTYPE
#undef mtype_test_cidrs
#undef mtype_test
#undef mtype_uref
-#undef mtype_expire
#undef mtype_resize
+#undef mtype_ext_size
+#undef mtype_resize_ad
#undef mtype_head
#undef mtype_list
+#undef mtype_gc_do
#undef mtype_gc
#undef mtype_gc_init
#undef mtype_variant
#define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs)
#define mtype_test IPSET_TOKEN(MTYPE, _test)
#define mtype_uref IPSET_TOKEN(MTYPE, _uref)
-#define mtype_expire IPSET_TOKEN(MTYPE, _expire)
#define mtype_resize IPSET_TOKEN(MTYPE, _resize)
+#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size)
+#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad)
#define mtype_head IPSET_TOKEN(MTYPE, _head)
#define mtype_list IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do)
#define mtype_gc IPSET_TOKEN(MTYPE, _gc)
#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init)
#define mtype_variant IPSET_TOKEN(MTYPE, _variant)
/* The generic hash structure */
struct htype {
struct htable __rcu *table; /* the hash table */
- struct timer_list gc; /* garbage collection when timeout enabled */
- struct ip_set *set; /* attached to this ip_set */
+ struct htable_gc gc; /* gc workqueue */
u32 maxelem; /* max elements in the hash */
u32 initval; /* random jhash init value */
#ifdef IP_SET_HASH_WITH_MARKMASK
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask; /* netmask value for subnets to store */
#endif
+ struct list_head ad; /* Resize add|del backlist */
struct mtype_elem next; /* temporary storage for uadd */
#ifdef IP_SET_HASH_WITH_NETS
struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */
#endif
};
+/* ADD|DEL entries saved during resize */
+struct mtype_resize_ad {
+ struct list_head list;
+ enum ipset_adt ad; /* ADD|DEL element */
+ struct mtype_elem d; /* Element value */
+ struct ip_set_ext ext; /* Extensions for ADD */
+ struct ip_set_ext mext; /* Target extensions for ADD */
+ u32 flags; /* Flags for ADD */
+};
+
#ifdef IP_SET_HASH_WITH_NETS
/* Network cidr size book keeping when the hash stores different
* sized networks. cidr == real cidr + 1 to support /0.
*/
static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
{
int i, j;
+ spin_lock_bh(&set->lock);
/* Add in increasing prefix order, so larger cidr first */
for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) {
if (j != -1) {
j = i;
} else if (h->nets[i].cidr[n] == cidr) {
h->nets[CIDR_POS(cidr)].nets[n]++;
- return;
+ goto unlock;
}
}
if (j != -1) {
}
h->nets[i].cidr[n] = cidr;
h->nets[CIDR_POS(cidr)].nets[n] = 1;
+unlock:
+ spin_unlock_bh(&set->lock);
}
static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
{
u8 i, j, net_end = NLEN - 1;
+ spin_lock_bh(&set->lock);
for (i = 0; i < NLEN; i++) {
if (h->nets[i].cidr[n] != cidr)
continue;
h->nets[CIDR_POS(cidr)].nets[n]--;
if (h->nets[CIDR_POS(cidr)].nets[n] > 0)
- return;
+ goto unlock;
for (j = i; j < net_end && h->nets[j].cidr[n]; j++)
h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
h->nets[j].cidr[n] = 0;
- return;
+ goto unlock;
}
+unlock:
+ spin_unlock_bh(&set->lock);
}
#endif
static size_t
mtype_ahash_memsize(const struct htype *h, const struct htable *t)
{
- return sizeof(*h) + sizeof(*t);
+ return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits);
}
/* Get the ith element from the array block n */
struct htype *h = set->data;
struct htable *t;
struct hbucket *n;
- u32 i;
-
- t = ipset_dereference_protected(h->table, set);
- for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = __ipset_dereference_protected(hbucket(t, i), 1);
- if (!n)
- continue;
- if (set->extensions & IPSET_EXT_DESTROY)
- mtype_ext_cleanup(set, n);
- /* FIXME: use slab cache */
- rcu_assign_pointer(hbucket(t, i), NULL);
- kfree_rcu(n, rcu);
+ u32 r, i;
+
+ t = ipset_dereference_nfnl(h->table);
+ for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) {
+ spin_lock_bh(&t->hregion[r].lock);
+ for (i = ahash_bucket_start(r, t->htable_bits);
+ i < ahash_bucket_end(r, t->htable_bits); i++) {
+ n = __ipset_dereference(hbucket(t, i));
+ if (!n)
+ continue;
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set, n);
+ /* FIXME: use slab cache */
+ rcu_assign_pointer(hbucket(t, i), NULL);
+ kfree_rcu(n, rcu);
+ }
+ t->hregion[r].ext_size = 0;
+ t->hregion[r].elements = 0;
+ spin_unlock_bh(&t->hregion[r].lock);
}
#ifdef IP_SET_HASH_WITH_NETS
memset(h->nets, 0, sizeof(h->nets));
#endif
- set->elements = 0;
- set->ext_size = 0;
}
/* Destroy the hashtable part of the set */
u32 i;
for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = __ipset_dereference_protected(hbucket(t, i), 1);
+ n = __ipset_dereference(hbucket(t, i));
if (!n)
continue;
if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
kfree(n);
}
+ ip_set_free(t->hregion);
ip_set_free(t);
}
mtype_destroy(struct ip_set *set)
{
struct htype *h = set->data;
+ struct list_head *l, *lt;
if (SET_WITH_TIMEOUT(set))
- del_timer_sync(&h->gc);
+ cancel_delayed_work_sync(&h->gc.dwork);
- mtype_ahash_destroy(set,
- __ipset_dereference_protected(h->table, 1), true);
+ mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+ list_for_each_safe(l, lt, &h->ad) {
+ list_del(l);
+ kfree(l);
+ }
kfree(h);
set->data = NULL;
}
-static void
-mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
-{
- struct htype *h = set->data;
-
- timer_setup(&h->gc, gc, 0);
- mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
- pr_debug("gc initialized, run in every %u\n",
- IPSET_GC_PERIOD(set->timeout));
-}
-
static bool
mtype_same_set(const struct ip_set *a, const struct ip_set *b)
{
a->extensions == b->extensions;
}
-/* Delete expired elements from the hashtable */
static void
-mtype_expire(struct ip_set *set, struct htype *h)
+mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)
{
- struct htable *t;
struct hbucket *n, *tmp;
struct mtype_elem *data;
u32 i, j, d;
#ifdef IP_SET_HASH_WITH_NETS
u8 k;
#endif
+ u8 htable_bits = t->htable_bits;
- t = ipset_dereference_protected(h->table, set);
- for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = __ipset_dereference_protected(hbucket(t, i), 1);
+ spin_lock_bh(&t->hregion[r].lock);
+ for (i = ahash_bucket_start(r, htable_bits);
+ i < ahash_bucket_end(r, htable_bits); i++) {
+ n = __ipset_dereference(hbucket(t, i));
if (!n)
continue;
for (j = 0, d = 0; j < n->pos; j++) {
smp_mb__after_atomic();
#ifdef IP_SET_HASH_WITH_NETS
for (k = 0; k < IPSET_NET_COUNT; k++)
- mtype_del_cidr(h,
+ mtype_del_cidr(set, h,
NCIDR_PUT(DCIDR_GET(data->cidr, k)),
k);
#endif
+ t->hregion[r].elements--;
ip_set_ext_destroy(set, data);
- set->elements--;
d++;
}
if (d >= AHASH_INIT_SIZE) {
if (d >= n->size) {
+ t->hregion[r].ext_size -=
+ ext_size(n->size, dsize);
rcu_assign_pointer(hbucket(t, i), NULL);
kfree_rcu(n, rcu);
continue;
}
tmp = kzalloc(sizeof(*tmp) +
- (n->size - AHASH_INIT_SIZE) * dsize,
- GFP_ATOMIC);
+ (n->size - AHASH_INIT_SIZE) * dsize,
+ GFP_ATOMIC);
if (!tmp)
- /* Still try to delete expired elements */
+ /* Still try to delete expired elements. */
continue;
tmp->size = n->size - AHASH_INIT_SIZE;
for (j = 0, d = 0; j < n->pos; j++) {
if (!test_bit(j, n->used))
continue;
data = ahash_data(n, j, dsize);
- memcpy(tmp->value + d * dsize, data, dsize);
+ memcpy(tmp->value + d * dsize,
+ data, dsize);
set_bit(d, tmp->used);
d++;
}
tmp->pos = d;
- set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
+ t->hregion[r].ext_size -=
+ ext_size(AHASH_INIT_SIZE, dsize);
rcu_assign_pointer(hbucket(t, i), tmp);
kfree_rcu(n, rcu);
}
}
+ spin_unlock_bh(&t->hregion[r].lock);
}
static void
-mtype_gc(struct timer_list *t)
+mtype_gc(struct work_struct *work)
{
- struct htype *h = from_timer(h, t, gc);
- struct ip_set *set = h->set;
+ struct htable_gc *gc;
+ struct ip_set *set;
+ struct htype *h;
+ struct htable *t;
+ u32 r, numof_locks;
+ unsigned int next_run;
+
+ gc = container_of(work, struct htable_gc, dwork.work);
+ set = gc->set;
+ h = set->data;
- pr_debug("called\n");
spin_lock_bh(&set->lock);
- mtype_expire(set, h);
+ t = ipset_dereference_set(h->table, set);
+ atomic_inc(&t->uref);
+ numof_locks = ahash_numof_locks(t->htable_bits);
+ r = gc->region++;
+ if (r >= numof_locks) {
+ r = gc->region = 0;
+ }
+ next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks;
+ if (next_run < HZ/10)
+ next_run = HZ/10;
spin_unlock_bh(&set->lock);
- h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
- add_timer(&h->gc);
+ mtype_gc_do(set, h, t, r);
+
+ if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+ pr_debug("Table destroy after resize by expire: %p\n", t);
+ mtype_ahash_destroy(set, t, false);
+ }
+
+ queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run);
+
+}
+
+static void
+mtype_gc_init(struct htable_gc *gc)
+{
+ INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc);
+ queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
}
+static int
+mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags);
+static int
+mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags);
+
/* Resize a hash: create a new hash table with doubling the hashsize
* and inserting the elements to it. Repeat until we succeed or
* fail due to memory pressures.
struct htype *h = set->data;
struct htable *t, *orig;
u8 htable_bits;
- size_t extsize, dsize = set->dsize;
+ size_t dsize = set->dsize;
#ifdef IP_SET_HASH_WITH_NETS
u8 flags;
struct mtype_elem *tmp;
struct mtype_elem *data;
struct mtype_elem *d;
struct hbucket *n, *m;
- u32 i, j, key;
+ struct list_head *l, *lt;
+ struct mtype_resize_ad *x;
+ u32 i, j, r, nr, key;
int ret;
#ifdef IP_SET_HASH_WITH_NETS
if (!tmp)
return -ENOMEM;
#endif
- rcu_read_lock_bh();
- orig = rcu_dereference_bh_nfnl(h->table);
+ orig = ipset_dereference_bh_nfnl(h->table);
htable_bits = orig->htable_bits;
- rcu_read_unlock_bh();
retry:
ret = 0;
ret = -ENOMEM;
goto out;
}
+ t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits));
+ if (!t->hregion) {
+ kfree(t);
+ ret = -ENOMEM;
+ goto out;
+ }
t->htable_bits = htable_bits;
+ t->maxelem = h->maxelem / ahash_numof_locks(htable_bits);
+ for (i = 0; i < ahash_numof_locks(htable_bits); i++)
+ spin_lock_init(&t->hregion[i].lock);
- spin_lock_bh(&set->lock);
- orig = __ipset_dereference_protected(h->table, 1);
- /* There can't be another parallel resizing, but dumping is possible */
+ /* There can't be another parallel resizing,
+ * but dumping, gc, kernel side add/del are possible
+ */
+ orig = ipset_dereference_bh_nfnl(h->table);
atomic_set(&orig->ref, 1);
atomic_inc(&orig->uref);
- extsize = 0;
pr_debug("attempt to resize set %s from %u to %u, t %p\n",
set->name, orig->htable_bits, htable_bits, orig);
- for (i = 0; i < jhash_size(orig->htable_bits); i++) {
- n = __ipset_dereference_protected(hbucket(orig, i), 1);
- if (!n)
- continue;
- for (j = 0; j < n->pos; j++) {
- if (!test_bit(j, n->used))
+ for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) {
+ /* Expire may replace a hbucket with another one */
+ rcu_read_lock_bh();
+ for (i = ahash_bucket_start(r, orig->htable_bits);
+ i < ahash_bucket_end(r, orig->htable_bits); i++) {
+ n = __ipset_dereference(hbucket(orig, i));
+ if (!n)
continue;
- data = ahash_data(n, j, dsize);
+ for (j = 0; j < n->pos; j++) {
+ if (!test_bit(j, n->used))
+ continue;
+ data = ahash_data(n, j, dsize);
+ if (SET_ELEM_EXPIRED(set, data))
+ continue;
#ifdef IP_SET_HASH_WITH_NETS
- /* We have readers running parallel with us,
- * so the live data cannot be modified.
- */
- flags = 0;
- memcpy(tmp, data, dsize);
- data = tmp;
- mtype_data_reset_flags(data, &flags);
+ /* We have readers running parallel with us,
+ * so the live data cannot be modified.
+ */
+ flags = 0;
+ memcpy(tmp, data, dsize);
+ data = tmp;
+ mtype_data_reset_flags(data, &flags);
#endif
- key = HKEY(data, h->initval, htable_bits);
- m = __ipset_dereference_protected(hbucket(t, key), 1);
- if (!m) {
- m = kzalloc(sizeof(*m) +
+ key = HKEY(data, h->initval, htable_bits);
+ m = __ipset_dereference(hbucket(t, key));
+ nr = ahash_region(key, htable_bits);
+ if (!m) {
+ m = kzalloc(sizeof(*m) +
AHASH_INIT_SIZE * dsize,
GFP_ATOMIC);
- if (!m) {
- ret = -ENOMEM;
- goto cleanup;
- }
- m->size = AHASH_INIT_SIZE;
- extsize += ext_size(AHASH_INIT_SIZE, dsize);
- RCU_INIT_POINTER(hbucket(t, key), m);
- } else if (m->pos >= m->size) {
- struct hbucket *ht;
-
- if (m->size >= AHASH_MAX(h)) {
- ret = -EAGAIN;
- } else {
- ht = kzalloc(sizeof(*ht) +
+ if (!m) {
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ m->size = AHASH_INIT_SIZE;
+ t->hregion[nr].ext_size +=
+ ext_size(AHASH_INIT_SIZE,
+ dsize);
+ RCU_INIT_POINTER(hbucket(t, key), m);
+ } else if (m->pos >= m->size) {
+ struct hbucket *ht;
+
+ if (m->size >= AHASH_MAX(h)) {
+ ret = -EAGAIN;
+ } else {
+ ht = kzalloc(sizeof(*ht) +
(m->size + AHASH_INIT_SIZE)
* dsize,
GFP_ATOMIC);
- if (!ht)
- ret = -ENOMEM;
+ if (!ht)
+ ret = -ENOMEM;
+ }
+ if (ret < 0)
+ goto cleanup;
+ memcpy(ht, m, sizeof(struct hbucket) +
+ m->size * dsize);
+ ht->size = m->size + AHASH_INIT_SIZE;
+ t->hregion[nr].ext_size +=
+ ext_size(AHASH_INIT_SIZE,
+ dsize);
+ kfree(m);
+ m = ht;
+ RCU_INIT_POINTER(hbucket(t, key), ht);
}
- if (ret < 0)
- goto cleanup;
- memcpy(ht, m, sizeof(struct hbucket) +
- m->size * dsize);
- ht->size = m->size + AHASH_INIT_SIZE;
- extsize += ext_size(AHASH_INIT_SIZE, dsize);
- kfree(m);
- m = ht;
- RCU_INIT_POINTER(hbucket(t, key), ht);
- }
- d = ahash_data(m, m->pos, dsize);
- memcpy(d, data, dsize);
- set_bit(m->pos++, m->used);
+ d = ahash_data(m, m->pos, dsize);
+ memcpy(d, data, dsize);
+ set_bit(m->pos++, m->used);
+ t->hregion[nr].elements++;
#ifdef IP_SET_HASH_WITH_NETS
- mtype_data_reset_flags(d, &flags);
+ mtype_data_reset_flags(d, &flags);
#endif
+ }
}
+ rcu_read_unlock_bh();
}
- rcu_assign_pointer(h->table, t);
- set->ext_size = extsize;
- spin_unlock_bh(&set->lock);
+ /* There can't be any other writer. */
+ rcu_assign_pointer(h->table, t);
/* Give time to other readers of the set */
synchronize_rcu();
pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
orig->htable_bits, orig, t->htable_bits, t);
- /* If there's nobody else dumping the table, destroy it */
+ /* Add/delete elements processed by the SET target during resize.
+ * Kernel-side add cannot trigger a resize and userspace actions
+ * are serialized by the mutex.
+ */
+ list_for_each_safe(l, lt, &h->ad) {
+ x = list_entry(l, struct mtype_resize_ad, list);
+ if (x->ad == IPSET_ADD) {
+ mtype_add(set, &x->d, &x->ext, &x->mext, x->flags);
+ } else {
+ mtype_del(set, &x->d, NULL, NULL, 0);
+ }
+ list_del(l);
+ kfree(l);
+ }
+ /* If there's nobody else using the table, destroy it */
if (atomic_dec_and_test(&orig->uref)) {
pr_debug("Table destroy by resize %p\n", orig);
mtype_ahash_destroy(set, orig, false);
return ret;
cleanup:
+ rcu_read_unlock_bh();
atomic_set(&orig->ref, 0);
atomic_dec(&orig->uref);
- spin_unlock_bh(&set->lock);
mtype_ahash_destroy(set, t, false);
if (ret == -EAGAIN)
goto retry;
goto out;
}
+/* Get the current number of elements and ext_size in the set */
+static void
+mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size)
+{
+ struct htype *h = set->data;
+ const struct htable *t;
+ u32 i, j, r;
+ struct hbucket *n;
+ struct mtype_elem *data;
+
+ t = rcu_dereference_bh(h->table);
+ for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) {
+ for (i = ahash_bucket_start(r, t->htable_bits);
+ i < ahash_bucket_end(r, t->htable_bits); i++) {
+ n = rcu_dereference_bh(hbucket(t, i));
+ if (!n)
+ continue;
+ for (j = 0; j < n->pos; j++) {
+ if (!test_bit(j, n->used))
+ continue;
+ data = ahash_data(n, j, set->dsize);
+ if (!SET_ELEM_EXPIRED(set, data))
+ (*elements)++;
+ }
+ }
+ *ext_size += t->hregion[r].ext_size;
+ }
+}
+
/* Add an element to a hash and update the internal counters when succeeded,
* otherwise report the proper error code.
*/
const struct mtype_elem *d = value;
struct mtype_elem *data;
struct hbucket *n, *old = ERR_PTR(-ENOENT);
- int i, j = -1;
+ int i, j = -1, ret;
bool flag_exist = flags & IPSET_FLAG_EXIST;
bool deleted = false, forceadd = false, reuse = false;
- u32 key, multi = 0;
+ u32 r, key, multi = 0, elements, maxelem;
- if (set->elements >= h->maxelem) {
- if (SET_WITH_TIMEOUT(set))
- /* FIXME: when set is full, we slow down here */
- mtype_expire(set, h);
- if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set))
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ key = HKEY(value, h->initval, t->htable_bits);
+ r = ahash_region(key, t->htable_bits);
+ atomic_inc(&t->uref);
+ elements = t->hregion[r].elements;
+ maxelem = t->maxelem;
+ if (elements >= maxelem) {
+ u32 e;
+ if (SET_WITH_TIMEOUT(set)) {
+ rcu_read_unlock_bh();
+ mtype_gc_do(set, h, t, r);
+ rcu_read_lock_bh();
+ }
+ maxelem = h->maxelem;
+ elements = 0;
+ for (e = 0; e < ahash_numof_locks(t->htable_bits); e++)
+ elements += t->hregion[e].elements;
+ if (elements >= maxelem && SET_WITH_FORCEADD(set))
forceadd = true;
}
+ rcu_read_unlock_bh();
- t = ipset_dereference_protected(h->table, set);
- key = HKEY(value, h->initval, t->htable_bits);
- n = __ipset_dereference_protected(hbucket(t, key), 1);
+ spin_lock_bh(&t->hregion[r].lock);
+ n = rcu_dereference_bh(hbucket(t, key));
if (!n) {
- if (forceadd || set->elements >= h->maxelem)
+ if (forceadd || elements >= maxelem)
goto set_full;
old = NULL;
n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize,
GFP_ATOMIC);
- if (!n)
- return -ENOMEM;
+ if (!n) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
n->size = AHASH_INIT_SIZE;
- set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
+ t->hregion[r].ext_size +=
+ ext_size(AHASH_INIT_SIZE, set->dsize);
goto copy_elem;
}
for (i = 0; i < n->pos; i++) {
}
data = ahash_data(n, i, set->dsize);
if (mtype_data_equal(data, d, &multi)) {
- if (flag_exist ||
- (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, set)))) {
+ if (flag_exist || SET_ELEM_EXPIRED(set, data)) {
/* Just the extensions could be overwritten */
j = i;
goto overwrite_extensions;
}
- return -IPSET_ERR_EXIST;
+ ret = -IPSET_ERR_EXIST;
+ goto unlock;
}
/* Reuse first timed out entry */
- if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, set)) &&
- j == -1) {
+ if (SET_ELEM_EXPIRED(set, data) && j == -1) {
j = i;
reuse = true;
}
}
if (reuse || forceadd) {
+ if (j == -1)
+ j = 0;
data = ahash_data(n, j, set->dsize);
if (!deleted) {
#ifdef IP_SET_HASH_WITH_NETS
for (i = 0; i < IPSET_NET_COUNT; i++)
- mtype_del_cidr(h,
+ mtype_del_cidr(set, h,
NCIDR_PUT(DCIDR_GET(data->cidr, i)),
i);
#endif
ip_set_ext_destroy(set, data);
- set->elements--;
+ t->hregion[r].elements--;
}
goto copy_data;
}
- if (set->elements >= h->maxelem)
+ if (elements >= maxelem)
goto set_full;
/* Create a new slot */
if (n->pos >= n->size) {
if (n->size >= AHASH_MAX(h)) {
/* Trigger rehashing */
mtype_data_next(&h->next, d);
- return -EAGAIN;
+ ret = -EAGAIN;
+ goto resize;
}
old = n;
n = kzalloc(sizeof(*n) +
(old->size + AHASH_INIT_SIZE) * set->dsize,
GFP_ATOMIC);
- if (!n)
- return -ENOMEM;
+ if (!n) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
memcpy(n, old, sizeof(struct hbucket) +
old->size * set->dsize);
n->size = old->size + AHASH_INIT_SIZE;
- set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
+ t->hregion[r].ext_size +=
+ ext_size(AHASH_INIT_SIZE, set->dsize);
}
copy_elem:
j = n->pos++;
data = ahash_data(n, j, set->dsize);
copy_data:
- set->elements++;
+ t->hregion[r].elements++;
#ifdef IP_SET_HASH_WITH_NETS
for (i = 0; i < IPSET_NET_COUNT; i++)
- mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i);
+ mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i);
#endif
memcpy(data, d, sizeof(struct mtype_elem));
overwrite_extensions:
if (old)
kfree_rcu(old, rcu);
}
+ ret = 0;
+resize:
+ spin_unlock_bh(&t->hregion[r].lock);
+ if (atomic_read(&t->ref) && ext->target) {
+ /* Resize is in process and kernel side add, save values */
+ struct mtype_resize_ad *x;
+
+ x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC);
+ if (!x)
+ /* Don't bother */
+ goto out;
+ x->ad = IPSET_ADD;
+ memcpy(&x->d, value, sizeof(struct mtype_elem));
+ memcpy(&x->ext, ext, sizeof(struct ip_set_ext));
+ memcpy(&x->mext, mext, sizeof(struct ip_set_ext));
+ x->flags = flags;
+ spin_lock_bh(&set->lock);
+ list_add_tail(&x->list, &h->ad);
+ spin_unlock_bh(&set->lock);
+ }
+ goto out;
- return 0;
set_full:
if (net_ratelimit())
pr_warn("Set %s is full, maxelem %u reached\n",
- set->name, h->maxelem);
- return -IPSET_ERR_HASH_FULL;
+ set->name, maxelem);
+ ret = -IPSET_ERR_HASH_FULL;
+unlock:
+ spin_unlock_bh(&t->hregion[r].lock);
+out:
+ if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+ pr_debug("Table destroy after resize by add: %p\n", t);
+ mtype_ahash_destroy(set, t, false);
+ }
+ return ret;
}
/* Delete an element from the hash and free up space if possible.
const struct mtype_elem *d = value;
struct mtype_elem *data;
struct hbucket *n;
- int i, j, k, ret = -IPSET_ERR_EXIST;
+ struct mtype_resize_ad *x = NULL;
+ int i, j, k, r, ret = -IPSET_ERR_EXIST;
u32 key, multi = 0;
size_t dsize = set->dsize;
- t = ipset_dereference_protected(h->table, set);
+ /* Userspace add and resize is excluded by the mutex.
+ * Kernespace add does not trigger resize.
+ */
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
key = HKEY(value, h->initval, t->htable_bits);
- n = __ipset_dereference_protected(hbucket(t, key), 1);
+ r = ahash_region(key, t->htable_bits);
+ atomic_inc(&t->uref);
+ rcu_read_unlock_bh();
+
+ spin_lock_bh(&t->hregion[r].lock);
+ n = rcu_dereference_bh(hbucket(t, key));
if (!n)
goto out;
for (i = 0, k = 0; i < n->pos; i++) {
data = ahash_data(n, i, dsize);
if (!mtype_data_equal(data, d, &multi))
continue;
- if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, set)))
+ if (SET_ELEM_EXPIRED(set, data))
goto out;
ret = 0;
smp_mb__after_atomic();
if (i + 1 == n->pos)
n->pos--;
- set->elements--;
+ t->hregion[r].elements--;
#ifdef IP_SET_HASH_WITH_NETS
for (j = 0; j < IPSET_NET_COUNT; j++)
- mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)),
- j);
+ mtype_del_cidr(set, h,
+ NCIDR_PUT(DCIDR_GET(d->cidr, j)), j);
#endif
ip_set_ext_destroy(set, data);
+ if (atomic_read(&t->ref) && ext->target) {
+ /* Resize is in process and kernel side del,
+ * save values
+ */
+ x = kzalloc(sizeof(struct mtype_resize_ad),
+ GFP_ATOMIC);
+ if (x) {
+ x->ad = IPSET_DEL;
+ memcpy(&x->d, value,
+ sizeof(struct mtype_elem));
+ x->flags = flags;
+ }
+ }
for (; i < n->pos; i++) {
if (!test_bit(i, n->used))
k++;
}
if (n->pos == 0 && k == 0) {
- set->ext_size -= ext_size(n->size, dsize);
+ t->hregion[r].ext_size -= ext_size(n->size, dsize);
rcu_assign_pointer(hbucket(t, key), NULL);
kfree_rcu(n, rcu);
} else if (k >= AHASH_INIT_SIZE) {
k++;
}
tmp->pos = k;
- set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
+ t->hregion[r].ext_size -=
+ ext_size(AHASH_INIT_SIZE, dsize);
rcu_assign_pointer(hbucket(t, key), tmp);
kfree_rcu(n, rcu);
}
}
out:
+ spin_unlock_bh(&t->hregion[r].lock);
+ if (x) {
+ spin_lock_bh(&set->lock);
+ list_add(&x->list, &h->ad);
+ spin_unlock_bh(&set->lock);
+ }
+ if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+ pr_debug("Table destroy after resize by del: %p\n", t);
+ mtype_ahash_destroy(set, t, false);
+ }
return ret;
}
int i, ret = 0;
u32 key, multi = 0;
+ rcu_read_lock_bh();
t = rcu_dereference_bh(h->table);
#ifdef IP_SET_HASH_WITH_NETS
/* If we test an IP address and not a network address,
goto out;
}
out:
+ rcu_read_unlock_bh();
return ret;
}
const struct htable *t;
struct nlattr *nested;
size_t memsize;
+ u32 elements = 0;
+ size_t ext_size = 0;
u8 htable_bits;
- /* If any members have expired, set->elements will be wrong
- * mytype_expire function will update it with the right count.
- * we do not hold set->lock here, so grab it first.
- * set->elements can still be incorrect in the case of a huge set,
- * because elements might time out during the listing.
- */
- if (SET_WITH_TIMEOUT(set)) {
- spin_lock_bh(&set->lock);
- mtype_expire(set, h);
- spin_unlock_bh(&set->lock);
- }
-
rcu_read_lock_bh();
- t = rcu_dereference_bh_nfnl(h->table);
- memsize = mtype_ahash_memsize(h, t) + set->ext_size;
+ t = rcu_dereference_bh(h->table);
+ mtype_ext_size(set, &elements, &ext_size);
+ memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size;
htable_bits = t->htable_bits;
rcu_read_unlock_bh();
#endif
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
- nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements)))
+ nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
goto nla_put_failure;
if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
if (start) {
rcu_read_lock_bh();
- t = rcu_dereference_bh_nfnl(h->table);
+ t = ipset_dereference_bh_nfnl(h->table);
atomic_inc(&t->uref);
cb->args[IPSET_CB_PRIVATE] = (unsigned long)t;
rcu_read_unlock_bh();
} else if (cb->args[IPSET_CB_PRIVATE]) {
t = (struct htable *)cb->args[IPSET_CB_PRIVATE];
if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
- /* Resizing didn't destroy the hash table */
- pr_debug("Table destroy by dump: %p\n", t);
+ pr_debug("Table destroy after resize "
+ " by dump: %p\n", t);
mtype_ahash_destroy(set, t, false);
}
cb->args[IPSET_CB_PRIVATE] = 0;
if (!test_bit(i, n->used))
continue;
e = ahash_data(n, i, set->dsize);
- if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, set)))
+ if (SET_ELEM_EXPIRED(set, e))
continue;
pr_debug("list hash %lu hbucket %p i %u, data %p\n",
cb->args[IPSET_CB_ARG0], n, i, e);
.uref = mtype_uref,
.resize = mtype_resize,
.same_set = mtype_same_set,
+ .region_lock = true,
};
#ifdef IP_SET_EMIT_CREATE
size_t hsize;
struct htype *h;
struct htable *t;
+ u32 i;
pr_debug("Create set %s with family %s\n",
set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
kfree(h);
return -ENOMEM;
}
+ t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits));
+ if (!t->hregion) {
+ kfree(t);
+ kfree(h);
+ return -ENOMEM;
+ }
+ h->gc.set = set;
+ for (i = 0; i < ahash_numof_locks(hbits); i++)
+ spin_lock_init(&t->hregion[i].lock);
h->maxelem = maxelem;
#ifdef IP_SET_HASH_WITH_NETMASK
h->netmask = netmask;
get_random_bytes(&h->initval, sizeof(h->initval));
t->htable_bits = hbits;
+ t->maxelem = h->maxelem / ahash_numof_locks(hbits);
RCU_INIT_POINTER(h->table, t);
- h->set = set;
+ INIT_LIST_HEAD(&h->ad);
set->data = h;
#ifndef IP_SET_PROTO_UNDEF
if (set->family == NFPROTO_IPV4) {
#ifndef IP_SET_PROTO_UNDEF
if (set->family == NFPROTO_IPV4)
#endif
- IPSET_TOKEN(HTYPE, 4_gc_init)(set,
- IPSET_TOKEN(HTYPE, 4_gc));
+ IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc);
#ifndef IP_SET_PROTO_UNDEF
else
- IPSET_TOKEN(HTYPE, 6_gc_init)(set,
- IPSET_TOKEN(HTYPE, 6_gc));
+ IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc);
#endif
}
pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
}
}
-/* Resolve race on insertion if this protocol allows this. */
+static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
+{
+ struct nf_conn_tstamp *tstamp;
+
+ atomic_inc(&ct->ct_general.use);
+ ct->status |= IPS_CONFIRMED;
+
+ /* set conntrack timestamp, if enabled. */
+ tstamp = nf_conn_tstamp_find(ct);
+ if (tstamp)
+ tstamp->start = ktime_get_real_ns();
+}
+
+static int __nf_ct_resolve_clash(struct sk_buff *skb,
+ struct nf_conntrack_tuple_hash *h)
+{
+ /* This is the conntrack entry already in hashes that won race. */
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *loser_ct;
+
+ loser_ct = nf_ct_get(skb, &ctinfo);
+
+ if (nf_ct_is_dying(ct))
+ return NF_DROP;
+
+ if (!atomic_inc_not_zero(&ct->ct_general.use))
+ return NF_DROP;
+
+ if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
+ nf_ct_match(ct, loser_ct)) {
+ struct net *net = nf_ct_net(ct);
+
+ nf_ct_acct_merge(ct, ctinfo, loser_ct);
+ nf_ct_add_to_dying_list(loser_ct);
+ nf_conntrack_put(&loser_ct->ct_general);
+ nf_ct_set(skb, ct, ctinfo);
+
+ NF_CT_STAT_INC(net, insert_failed);
+ return NF_ACCEPT;
+ }
+
+ nf_ct_put(ct);
+ return NF_DROP;
+}
+
+/**
+ * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry
+ *
+ * @skb: skb that causes the collision
+ * @repl_idx: hash slot for reply direction
+ *
+ * Called when origin or reply direction had a clash.
+ * The skb can be handled without packet drop provided the reply direction
+ * is unique or there the existing entry has the identical tuple in both
+ * directions.
+ *
+ * Caller must hold conntrack table locks to prevent concurrent updates.
+ *
+ * Returns NF_DROP if the clash could not be handled.
+ */
+static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
+{
+ struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb);
+ const struct nf_conntrack_zone *zone;
+ struct nf_conntrack_tuple_hash *h;
+ struct hlist_nulls_node *n;
+ struct net *net;
+
+ zone = nf_ct_zone(loser_ct);
+ net = nf_ct_net(loser_ct);
+
+ /* Reply direction must never result in a clash, unless both origin
+ * and reply tuples are identical.
+ */
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) {
+ if (nf_ct_key_equal(h,
+ &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ zone, net))
+ return __nf_ct_resolve_clash(skb, h);
+ }
+
+ /* We want the clashing entry to go away real soon: 1 second timeout. */
+ loser_ct->timeout = nfct_time_stamp + HZ;
+
+ /* IPS_NAT_CLASH removes the entry automatically on the first
+ * reply. Also prevents UDP tracker from moving the entry to
+ * ASSURED state, i.e. the entry can always be evicted under
+ * pressure.
+ */
+ loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH;
+
+ __nf_conntrack_insert_prepare(loser_ct);
+
+ /* fake add for ORIGINAL dir: we want lookups to only find the entry
+ * already in the table. This also hides the clashing entry from
+ * ctnetlink iteration, i.e. conntrack -L won't show them.
+ */
+ hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+
+ hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
+ &nf_conntrack_hash[repl_idx]);
+ return NF_ACCEPT;
+}
+
+/**
+ * nf_ct_resolve_clash - attempt to handle clash without packet drop
+ *
+ * @skb: skb that causes the clash
+ * @h: tuplehash of the clashing entry already in table
+ * @hash_reply: hash slot for reply direction
+ *
+ * A conntrack entry can be inserted to the connection tracking table
+ * if there is no existing entry with an identical tuple.
+ *
+ * If there is one, @skb (and the assocated, unconfirmed conntrack) has
+ * to be dropped. In case @skb is retransmitted, next conntrack lookup
+ * will find the already-existing entry.
+ *
+ * The major problem with such packet drop is the extra delay added by
+ * the packet loss -- it will take some time for a retransmit to occur
+ * (or the sender to time out when waiting for a reply).
+ *
+ * This function attempts to handle the situation without packet drop.
+ *
+ * If @skb has no NAT transformation or if the colliding entries are
+ * exactly the same, only the to-be-confirmed conntrack entry is discarded
+ * and @skb is associated with the conntrack entry already in the table.
+ *
+ * Failing that, the new, unconfirmed conntrack is still added to the table
+ * provided that the collision only occurs in the ORIGINAL direction.
+ * The new entry will be added after the existing one in the hash list,
+ * so packets in the ORIGINAL direction will continue to match the existing
+ * entry. The new entry will also have a fixed timeout so it expires --
+ * due to the collision, it will not see bidirectional traffic.
+ *
+ * Returns NF_DROP if the clash could not be resolved.
+ */
static __cold noinline int
-nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
- enum ip_conntrack_info ctinfo,
- struct nf_conntrack_tuple_hash *h)
+nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h,
+ u32 reply_hash)
{
/* This is the conntrack entry already in hashes that won race. */
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
const struct nf_conntrack_l4proto *l4proto;
- enum ip_conntrack_info oldinfo;
- struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *loser_ct;
+ struct net *net;
+ int ret;
+
+ loser_ct = nf_ct_get(skb, &ctinfo);
+ net = nf_ct_net(loser_ct);
l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct));
- if (l4proto->allow_clash &&
- !nf_ct_is_dying(ct) &&
- atomic_inc_not_zero(&ct->ct_general.use)) {
- if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
- nf_ct_match(ct, loser_ct)) {
- nf_ct_acct_merge(ct, ctinfo, loser_ct);
- nf_conntrack_put(&loser_ct->ct_general);
- nf_ct_set(skb, ct, oldinfo);
- return NF_ACCEPT;
- }
- nf_ct_put(ct);
- }
+ if (!l4proto->allow_clash)
+ goto drop;
+
+ ret = __nf_ct_resolve_clash(skb, h);
+ if (ret == NF_ACCEPT)
+ return ret;
+
+ ret = nf_ct_resolve_clash_harder(skb, reply_hash);
+ if (ret == NF_ACCEPT)
+ return ret;
+
+drop:
+ nf_ct_add_to_dying_list(loser_ct);
NF_CT_STAT_INC(net, drop);
+ NF_CT_STAT_INC(net, insert_failed);
return NF_DROP;
}
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct nf_conn_help *help;
- struct nf_conn_tstamp *tstamp;
struct hlist_nulls_node *n;
enum ip_conntrack_info ctinfo;
struct net *net;
if (unlikely(nf_ct_is_dying(ct))) {
nf_ct_add_to_dying_list(ct);
+ NF_CT_STAT_INC(net, insert_failed);
goto dying;
}
setting time, otherwise we'd get timer wrap in
weird delay cases. */
ct->timeout += nfct_time_stamp;
- atomic_inc(&ct->ct_general.use);
- ct->status |= IPS_CONFIRMED;
- /* set conntrack timestamp, if enabled. */
- tstamp = nf_conn_tstamp_find(ct);
- if (tstamp)
- tstamp->start = ktime_get_real_ns();
+ __nf_conntrack_insert_prepare(ct);
/* Since the lookup is lockless, hash insertion must be done after
* starting the timer and setting the CONFIRMED bit. The RCU barriers
return NF_ACCEPT;
out:
- nf_ct_add_to_dying_list(ct);
- ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
+ ret = nf_ct_resolve_clash(skb, h, reply_hash);
dying:
nf_conntrack_double_unlock(hash, reply_hash);
- NF_CT_STAT_INC(net, insert_failed);
local_bh_enable();
return ret;
}
return false;
}
+static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct,
+ struct sk_buff *skb,
+ enum ip_conntrack_info ctinfo,
+ u32 extra_jiffies)
+{
+ if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY &&
+ ct->status & IPS_NAT_CLASH))
+ nf_ct_kill(ct);
+ else
+ nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies);
+}
+
/* Returns verdict for packet, and may modify conntracktype */
int nf_conntrack_udp_packet(struct nf_conn *ct,
struct sk_buff *skb,
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
- nf_ct_refresh_acct(ct, ctinfo, skb,
- timeouts[UDP_CT_UNREPLIED]);
+ nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+ timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
- nf_ct_refresh_acct(ct, ctinfo, skb,
- timeouts[UDP_CT_UNREPLIED]);
+ nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+ timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
{
int err;
- if (!nf_flowtable_hw_offload(flowtable))
- return 0;
-
if (!dev->netdev_ops->ndo_setup_tc)
return -EOPNOTSUPP;
struct flow_block_offload bo;
int err;
+ if (!nf_flowtable_hw_offload(flowtable))
+ return 0;
+
err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack);
if (err < 0)
return err;
* ::
*
* rule indices in last field: 0 1
- * map to elements: 0x42 0x66
+ * map to elements: 0x66 0x42
*
*
* Matching
* ::
*
* rule indices in last field: 0 1
- * map to elements: 0x42 0x66
+ * map to elements: 0x66 0x42
*
* the matching element is at 0x42.
*
return -1;
}
- if (unlikely(match_only)) {
+ if (match_only) {
bitmap_clear(map, i, 1);
return i;
}
static void nft_pipapo_remove(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem)
{
- const u8 *data = (const u8 *)elem->key.val.data;
struct nft_pipapo *priv = nft_set_priv(set);
struct nft_pipapo_match *m = priv->clone;
+ struct nft_pipapo_elem *e = elem->priv;
int rules_f0, first_rule = 0;
- struct nft_pipapo_elem *e;
+ const u8 *data;
+
+ data = (const u8 *)nft_set_ext_key(&e->ext);
e = pipapo_get(net, set, data, 0);
if (IS_ERR(e))
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/mutex.h>
#include <linux/kernel.h>
+#include <linux/refcount.h>
#include <uapi/linux/netfilter/xt_hashlimit.h>
#define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \
struct xt_hashlimit_htable {
struct hlist_node node; /* global list of all htables */
- int use;
+ refcount_t use;
u_int8_t family;
bool rnd_initialized;
for (i = 0; i < hinfo->cfg.size; i++)
INIT_HLIST_HEAD(&hinfo->hash[i]);
- hinfo->use = 1;
+ refcount_set(&hinfo->use, 1);
hinfo->count = 0;
hinfo->family = family;
hinfo->rnd_initialized = false;
remove_proc_entry(hinfo->name, parent);
}
-static void htable_destroy(struct xt_hashlimit_htable *hinfo)
-{
- cancel_delayed_work_sync(&hinfo->gc_work);
- htable_remove_proc_entry(hinfo);
- htable_selective_cleanup(hinfo, true);
- kfree(hinfo->name);
- vfree(hinfo);
-}
-
static struct xt_hashlimit_htable *htable_find_get(struct net *net,
const char *name,
u_int8_t family)
hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) {
if (!strcmp(name, hinfo->name) &&
hinfo->family == family) {
- hinfo->use++;
+ refcount_inc(&hinfo->use);
return hinfo;
}
}
static void htable_put(struct xt_hashlimit_htable *hinfo)
{
- mutex_lock(&hashlimit_mutex);
- if (--hinfo->use == 0) {
+ if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) {
hlist_del(&hinfo->node);
- htable_destroy(hinfo);
+ htable_remove_proc_entry(hinfo);
+ mutex_unlock(&hashlimit_mutex);
+
+ cancel_delayed_work_sync(&hinfo->gc_work);
+ htable_selective_cleanup(hinfo, true);
+ kfree(hinfo->name);
+ vfree(hinfo);
}
- mutex_unlock(&hashlimit_mutex);
}
/* The algorithm used is the Simple Token Bucket Filter (TBF)
return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3);
}
+#define HASHLIMIT_MAX_SIZE 1048576
+
static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
struct xt_hashlimit_htable **hinfo,
struct hashlimit_cfg3 *cfg,
if (cfg->gc_interval == 0 || cfg->expire == 0)
return -EINVAL;
+ if (cfg->size > HASHLIMIT_MAX_SIZE) {
+ cfg->size = HASHLIMIT_MAX_SIZE;
+ pr_info_ratelimited("size too large, truncated to %u\n", cfg->size);
+ }
+ if (cfg->max > HASHLIMIT_MAX_SIZE) {
+ cfg->max = HASHLIMIT_MAX_SIZE;
+ pr_info_ratelimited("max too large, truncated to %u\n", cfg->max);
+ }
if (par->family == NFPROTO_IPV4) {
if (cfg->srcmask > 32 || cfg->dstmask > 32)
return -EINVAL;
if (domain != NULL) {
bkt = netlbl_domhsh_hash(domain);
bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt];
- list_for_each_entry_rcu(iter, bkt_list, list)
+ list_for_each_entry_rcu(iter, bkt_list, list,
+ lockdep_is_held(&netlbl_domhsh_lock))
if (iter->valid &&
netlbl_family_match(iter->family, family) &&
strcmp(iter->domain, domain) == 0)
bkt = netlbl_unlhsh_hash(ifindex);
bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt];
- list_for_each_entry_rcu(iter, bkt_list, list)
+ list_for_each_entry_rcu(iter, bkt_list, list,
+ lockdep_is_held(&netlbl_unlhsh_lock))
if (iter->valid && iter->ifindex == ifindex)
return iter;
if (nlk->netlink_bind && groups) {
int group;
- for (group = 0; group < nlk->ngroups; group++) {
+ /* nl_groups is a u32, so cap the maximum groups we can bind */
+ for (group = 0; group < BITS_PER_TYPE(u32); group++) {
if (!test_bit(group, &groups))
continue;
err = nlk->netlink_bind(net, group + 1);
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
if (err) {
- netlink_undo_bind(nlk->ngroups, groups, sk);
+ netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk);
goto unlock;
}
}
err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
family->policy, validate, extack);
- if (err && parallel) {
- kfree(attrbuf);
+ if (err) {
+ if (parallel)
+ kfree(attrbuf);
return ERR_PTR(err);
}
return attrbuf;
struct hlist_head *head;
head = vport_hash_bucket(dp, port_no);
- hlist_for_each_entry_rcu(vport, head, dp_hash_node) {
+ hlist_for_each_entry_rcu(vport, head, dp_hash_node,
+ lockdep_ovsl_is_held()) {
if (vport->port_no == port_no)
return vport;
}
int i;
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
- hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
+ hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+ lockdep_ovsl_is_held()) {
dev = vport->dev;
dev_headroom = netdev_get_fwd_headroom(dev);
if (dev_headroom > max_headroom)
dp->max_headroom = new_headroom;
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
- hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node)
+ hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+ lockdep_ovsl_is_held())
netdev_set_rx_headroom(vport->dev, new_headroom);
}
return -EINVAL;
switch (key_type) {
- const struct ovs_key_ipv4 *ipv4_key;
- const struct ovs_key_ipv6 *ipv6_key;
- int err;
-
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
return -EINVAL;
break;
- case OVS_KEY_ATTR_TUNNEL:
+ case OVS_KEY_ATTR_TUNNEL: {
+ int err;
+
if (masked)
return -EINVAL; /* Masked tunnel set not supported. */
if (err)
return err;
break;
+ }
+ case OVS_KEY_ATTR_IPV4: {
+ const struct ovs_key_ipv4 *ipv4_key;
- case OVS_KEY_ATTR_IPV4:
if (eth_type != htons(ETH_P_IP))
return -EINVAL;
return -EINVAL;
}
break;
+ }
+ case OVS_KEY_ATTR_IPV6: {
+ const struct ovs_key_ipv6 *ipv6_key;
- case OVS_KEY_ATTR_IPV6:
if (eth_type != htons(ETH_P_IPV6))
return -EINVAL;
return -EINVAL;
break;
-
+ }
case OVS_KEY_ATTR_TCP:
if ((eth_type != htons(ETH_P_IP) &&
eth_type != htons(ETH_P_IPV6)) ||
head = find_bucket(ti, hash);
(*n_mask_hit)++;
- hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+ hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver],
+ lockdep_ovsl_is_held()) {
if (flow->mask == mask && flow->flow_table.hash == hash &&
flow_cmp_masked_key(flow, &masked_key, &mask->range))
return flow;
hash = ufid_hash(ufid);
head = find_bucket(ti, hash);
- hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+ hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver],
+ lockdep_ovsl_is_held()) {
if (flow->ufid_table.hash == hash &&
ovs_flow_cmp_ufid(flow, ufid))
return flow;
struct hlist_head *head;
head = meter_hash_bucket(dp, meter_id);
- hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
+ hlist_for_each_entry_rcu(meter, head, dp_hash_node,
+ lockdep_ovsl_is_held()) {
if (meter->id == meter_id)
return meter;
}
struct hlist_head *bucket = hash_bucket(net, name);
struct vport *vport;
- hlist_for_each_entry_rcu(vport, bucket, hash_node)
+ hlist_for_each_entry_rcu(vport, bucket, hash_node,
+ lockdep_ovsl_is_held())
if (!strcmp(name, ovs_vport_name(vport)) &&
net_eq(ovs_dp_get_net(vport->dp), net))
return vport;
if (write)
gup_flags |= FOLL_WRITE;
- ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
+ ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
if (ret >= 0 && ret < nr_pages) {
- while (ret--)
- put_page(pages[ret]);
+ unpin_user_pages(pages, ret);
ret = -EFAULT;
}
* to release anything.
*/
if (!need_odp) {
- for (i = 0 ; i < nents; i++)
- put_page(sg_page(&sg[i]));
+ unpin_user_pages(pages, nr_pages);
kfree(sg);
}
ret = PTR_ERR(trans_private);
if (cookie_ret)
*cookie_ret = cookie;
- if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) {
+ if (args->cookie_addr &&
+ put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) {
+ if (!need_odp) {
+ unpin_user_pages(pages, nr_pages);
+ kfree(sg);
+ }
ret = -EFAULT;
goto out;
}
* is the case for a RDMA_READ which copies from remote
* to local memory
*/
- if (!ro->op_write)
- set_page_dirty(page);
- put_page(page);
+ unpin_user_pages_dirty_lock(&page, 1, !ro->op_write);
}
}
/* Mark page dirty if it was possibly modified, which
* is the case for a RDMA_READ which copies from remote
* to local memory */
- set_page_dirty(page);
- put_page(page);
+ unpin_user_pages_dirty_lock(&page, 1, true);
kfree(ao->op_notifier);
ao->op_notifier = NULL;
return ret;
err:
if (page)
- put_page(page);
+ unpin_user_page(page);
rm->atomic.op_active = 0;
kfree(rm->atomic.op_notifier);
+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
+ cookie_len /* TCA_ACT_COOKIE */
+ nla_total_size(0) /* TCA_ACT_STATS nested */
+ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */
/* TCA_STATS_BASIC */
+ nla_total_size_64bit(sizeof(struct gnet_stats_basic))
/* TCA_STATS_PKT64 */
struct cls_fl_filter *f;
list_for_each_entry_rcu(mask, &head->masks, list) {
+ flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
fl_clear_masked_range(&skb_key, mask);
skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);
return true;
}
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+ struct sctp_errhdr *err;
+
+ sctp_walk_errors(err, chunk->chunk_hdr);
+
+ return (void *)err == (void *)chunk->chunk_end;
+}
+
/**********************************************************
* These are the state functions for handling chunk events.
**********************************************************/
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ if (!sctp_err_chunk_valid(chunk))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
}
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ if (!sctp_err_chunk_valid(chunk))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Stop the T2-shutdown timer. */
sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ if (!sctp_err_chunk_valid(chunk))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
}
/* See if we have an error cause code in the chunk. */
len = ntohs(chunk->chunk_hdr->length);
- if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
- struct sctp_errhdr *err;
-
- sctp_walk_errors(err, chunk->chunk_hdr);
- if ((void *)err != (void *)chunk->chunk_end)
- return sctp_sf_pdiscard(net, ep, asoc, type, arg,
- commands);
-
+ if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
- }
sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
/* ASSOC_FAILED will DELETE_TCB. */
static int smc_connect_abort(struct smc_sock *smc, int reason_code,
int local_contact)
{
+ bool is_smcd = smc->conn.lgr->is_smcd;
+
if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(smc->conn.lgr);
- if (smc->conn.lgr->is_smcd)
+ smc_lgr_cleanup_early(&smc->conn);
+ else
+ smc_conn_free(&smc->conn);
+ if (is_smcd)
/* there is only one lgr role for SMC-D; use server lock */
mutex_unlock(&smc_server_lgr_pending);
else
mutex_unlock(&smc_client_lgr_pending);
- smc_conn_free(&smc->conn);
smc->connect_nonblock = 0;
return reason_code;
}
if (newsmcsk->sk_state == SMC_INIT)
sock_put(&new_smc->sk); /* passive closing */
newsmcsk->sk_state = SMC_CLOSED;
- smc_conn_free(&new_smc->conn);
smc_listen_out(new_smc);
}
{
/* RDMA setup failed, switch back to TCP */
if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(new_smc->conn.lgr);
+ smc_lgr_cleanup_early(&new_smc->conn);
+ else
+ smc_conn_free(&new_smc->conn);
if (reason_code < 0) { /* error, no fallback possible */
smc_listen_out_err(new_smc);
return;
}
- smc_conn_free(&new_smc->conn);
smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = reason_code;
if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
new_smc->conn.lgr->vlan_id,
new_smc->conn.lgr->smcd)) {
if (ini->cln_first_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(new_smc->conn.lgr);
- smc_conn_free(&new_smc->conn);
+ smc_lgr_cleanup_early(&new_smc->conn);
+ else
+ smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_SMCDNOTALK;
}
/* Create send and receive buffers */
if (smc_buf_create(new_smc, true)) {
if (ini->cln_first_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(new_smc->conn.lgr);
- smc_conn_free(&new_smc->conn);
+ smc_lgr_cleanup_early(&new_smc->conn);
+ else
+ smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_MEM;
}
conn->lgr = NULL;
}
+void smc_lgr_cleanup_early(struct smc_connection *conn)
+{
+ struct smc_link_group *lgr = conn->lgr;
+
+ if (!lgr)
+ return;
+
+ smc_conn_free(conn);
+ smc_lgr_forget(lgr);
+ smc_lgr_schedule_free_work_fast(lgr);
+}
+
/* Send delete link, either as client to request the initiation
* of the DELETE LINK sequence from server; or as server to
* initiate the delete processing. See smc_llc_rx_delete_link().
struct smc_clc_msg_local;
void smc_lgr_forget(struct smc_link_group *lgr);
+void smc_lgr_cleanup_early(struct smc_connection *conn);
void smc_lgr_terminate(struct smc_link_group *lgr, bool soft);
void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
void smc_conn_free(struct smc_connection *conn);
int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
-void smcd_conn_free(struct smc_connection *conn);
void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
int smc_core_init(void);
void smc_core_exit(void);
struct smc_ib_device *smcibdev;
smcibdev = ib_get_client_data(ibdev, &smc_ib_client);
+ if (!smcibdev || smcibdev->ibdev != ibdev)
+ return;
ib_set_client_data(ibdev, &smc_ib_client, NULL);
spin_lock(&smc_ib_devices.lock);
list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
u32 seq, u64 *p_record_sn)
{
u64 record_sn = context->hint_record_sn;
- struct tls_record_info *info;
+ struct tls_record_info *info, *last;
info = context->retransmit_hint;
if (!info ||
struct tls_record_info, list);
if (!info)
return NULL;
+ /* send the start_marker record if seq number is before the
+ * tls offload start marker sequence number. This record is
+ * required to handle TCP packets which are before TLS offload
+ * started.
+ * And if it's not start marker, look if this seq number
+ * belongs to the list.
+ */
+ if (likely(!tls_record_is_start_marker(info))) {
+ /* we have the first record, get the last record to see
+ * if this seq number belongs to the list.
+ */
+ last = list_last_entry(&context->records_list,
+ struct tls_record_info, list);
+
+ if (!between(seq, tls_record_start_seq(info),
+ last->end_seq))
+ return NULL;
+ }
record_sn = context->unacked_record_sn;
}
return 0;
}
+#ifdef CONFIG_PROC_FS
static void unix_show_fdinfo(struct seq_file *m, struct socket *sock)
{
struct sock *sk = sock->sk;
seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds));
}
}
+#else
+#define unix_show_fdinfo NULL
+#endif
static const struct proto_ops unix_stream_ops = {
.family = PF_UNIX,
if (vsk->transport == new_transport)
return 0;
+ /* transport->release() must be called with sock lock acquired.
+ * This path can only be taken during vsock_stream_connect(),
+ * where we have already held the sock lock.
+ * In the other cases, this function is called on a new socket
+ * which is not assigned to any transport.
+ */
vsk->transport->release(vsk);
vsock_deassign_transport(vsk);
}
vsk = vsock_sk(sk);
pending = NULL; /* Compiler warning. */
- /* The release call is supposed to use lock_sock_nested()
- * rather than lock_sock(), if a sock lock should be acquired.
- */
- if (vsk->transport)
- vsk->transport->release(vsk);
- else if (sk->sk_type == SOCK_STREAM)
- vsock_remove_sock(vsk);
-
/* When "level" is SINGLE_DEPTH_NESTING, use the nested
* version to avoid the warning "possible recursive locking
* detected". When "level" is 0, lock_sock_nested(sk, level)
* is the same as lock_sock(sk).
*/
lock_sock_nested(sk, level);
+
+ if (vsk->transport)
+ vsk->transport->release(vsk);
+ else if (sk->sk_type == SOCK_STREAM)
+ vsock_remove_sock(vsk);
+
sock_orphan(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
static void hvs_release(struct vsock_sock *vsk)
{
- struct sock *sk = sk_vsock(vsk);
bool remove_sock;
- lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
remove_sock = hvs_close_lock_held(vsk);
- release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
}
struct sock *sk = &vsk->sk;
bool remove_sock = true;
- lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
if (sk->sk_type == SOCK_STREAM)
remove_sock = virtio_transport_close(vsk);
list_del(&pkt->list);
virtio_transport_free_pkt(pkt);
}
- release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
#include <linux/netlink.h>
#include <linux/nospec.h>
#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
#include <net/net_namespace.h>
#include <net/genetlink.h>
#include <net/cfg80211.h>
err = nl80211_parse_he_obss_pd(
info->attrs[NL80211_ATTR_HE_OBSS_PD],
¶ms.he_obss_pd);
- if (err)
- return err;
+ goto out;
}
nl80211_calculate_ap_params(¶ms);
}
wdev_unlock(wdev);
+out:
kfree(params.acl);
return err;
break;
}
- if (IS_ERR(reg_rule)) {
+ if (IS_ERR_OR_NULL(reg_rule)) {
pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n",
chan->center_freq);
if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) {
static void xsk_flush(struct xdp_sock *xs)
{
xskq_prod_submit(xs->rx);
+ __xskq_cons_release(xs->umem->fq);
sock_def_readable(&xs->sk);
}
rcu_read_lock();
list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+ __xskq_cons_release(xs->tx);
xs->sk.sk_write_space(&xs->sk);
}
rcu_read_unlock();
{
/* To improve performance, only update local state here.
* Reflect this to global state when we get new entries
- * from the ring in xskq_cons_get_entries().
+ * from the ring in xskq_cons_get_entries() and whenever
+ * Rx or Tx processing are completed in the NAPI loop.
*/
q->cached_cons++;
}
DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml
quiet_cmd_dtb_check = CHECK $@
- cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ;
+ cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@
-define rule_dtc_dt_yaml
+define rule_dtc
$(call cmd_and_fixdep,dtc,yaml)
$(call cmd,dtb_check)
endef
$(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
- $(call if_changed_rule,dtc_dt_yaml)
+ $(call if_changed_rule,dtc)
dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
}
}
- foreach my $fix (@fixes) {
- vcs_add_commit_signers($fix, "blamed_fixes");
- }
-
foreach my $email (@email_to, @list_to) {
$email->[0] = deduplicate_email($email->[0]);
}
}
}
+ foreach my $fix (@fixes) {
+ vcs_add_commit_signers($fix, "blamed_fixes");
+ }
+
my @to = ();
if ($email || $email_list) {
if ($email) {
}
}
} elsif ($ptype eq "M") {
- my ($name, $address) = parse_email($pvalue);
- if ($name eq "") {
- if ($i > 0) {
- my $tv = $typevalue[$i - 1];
- if ($tv =~ m/^([A-Z]):\s*(.*)/) {
- if ($1 eq "P") {
- $name = $2;
- $pvalue = format_email($name, $address, $email_usename);
- }
- }
- }
- }
if ($email_maintainer) {
my $role = get_maintainer_role($i);
push_email_addresses($pvalue, $role);
}
} elsif ($ptype eq "R") {
- my ($name, $address) = parse_email($pvalue);
- if ($name eq "") {
- if ($i > 0) {
- my $tv = $typevalue[$i - 1];
- if ($tv =~ m/^([A-Z]):\s*(.*)/) {
- if ($1 eq "P") {
- $name = $2;
- $pvalue = format_email($name, $address, $email_usename);
- }
- }
- }
- }
if ($email_reviewer) {
my $subsystem = get_subsystem_name($i);
push_email_addresses($pvalue, "reviewer:$subsystem");
config IMA_DEFAULT_HASH_WP512
bool "WP512"
depends on CRYPTO_WP512=y && !IMA_TEMPLATE
+
+ config IMA_DEFAULT_HASH_SM3
+ bool "SM3"
+ depends on CRYPTO_SM3=y && !IMA_TEMPLATE
endchoice
config IMA_DEFAULT_HASH
default "sha256" if IMA_DEFAULT_HASH_SHA256
default "sha512" if IMA_DEFAULT_HASH_SHA512
default "wp512" if IMA_DEFAULT_HASH_WP512
+ default "sm3" if IMA_DEFAULT_HASH_SM3
config IMA_WRITE_POLICY
bool "Enable multiple writes to the IMA policy"
* Get a certificate list blob from the named EFI variable.
*/
static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid,
- unsigned long *size)
+ unsigned long *size, efi_status_t *status)
{
- efi_status_t status;
unsigned long lsize = 4;
unsigned long tmpdb[4];
void *db;
- status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
- if (status != EFI_BUFFER_TOO_SMALL) {
- pr_err("Couldn't get size: 0x%lx\n", status);
+ *status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
+ if (*status == EFI_NOT_FOUND)
+ return NULL;
+
+ if (*status != EFI_BUFFER_TOO_SMALL) {
+ pr_err("Couldn't get size: 0x%lx\n", *status);
return NULL;
}
if (!db)
return NULL;
- status = efi.get_variable(name, guid, NULL, &lsize, db);
- if (status != EFI_SUCCESS) {
+ *status = efi.get_variable(name, guid, NULL, &lsize, db);
+ if (*status != EFI_SUCCESS) {
kfree(db);
- pr_err("Error reading db var: 0x%lx\n", status);
+ pr_err("Error reading db var: 0x%lx\n", *status);
return NULL;
}
efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
void *db = NULL, *dbx = NULL, *mok = NULL;
unsigned long dbsize = 0, dbxsize = 0, moksize = 0;
+ efi_status_t status;
int rc = 0;
if (!efi.get_variable)
* an error if we can't get them.
*/
if (!uefi_check_ignore_db()) {
- db = get_cert_list(L"db", &secure_var, &dbsize);
+ db = get_cert_list(L"db", &secure_var, &dbsize, &status);
if (!db) {
- pr_err("MODSIGN: Couldn't get UEFI db list\n");
+ if (status == EFI_NOT_FOUND)
+ pr_debug("MODSIGN: db variable wasn't found\n");
+ else
+ pr_err("MODSIGN: Couldn't get UEFI db list\n");
} else {
rc = parse_efi_signature_list("UEFI:db",
db, dbsize, get_handler_for_db);
}
}
- mok = get_cert_list(L"MokListRT", &mok_var, &moksize);
+ mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status);
if (!mok) {
- pr_info("Couldn't get UEFI MokListRT\n");
+ if (status == EFI_NOT_FOUND)
+ pr_debug("MokListRT variable wasn't found\n");
+ else
+ pr_info("Couldn't get UEFI MokListRT\n");
} else {
rc = parse_efi_signature_list("UEFI:MokListRT",
mok, moksize, get_handler_for_db);
kfree(mok);
}
- dbx = get_cert_list(L"dbx", &secure_var, &dbxsize);
+ dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status);
if (!dbx) {
- pr_info("Couldn't get UEFI dbx list\n");
+ if (status == EFI_NOT_FOUND)
+ pr_debug("dbx variable wasn't found\n");
+ else
+ pr_info("Couldn't get UEFI dbx list\n");
} else {
rc = parse_efi_signature_list("UEFI:dbx",
dbx, dbxsize,
event->queue = queue;
event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK;
if (real_time) {
- event->time.time = snd_seq_timer_get_cur_time(q->timer);
+ event->time.time = snd_seq_timer_get_cur_time(q->timer, true);
event->flags |= SNDRV_SEQ_TIME_STAMP_REAL;
} else {
event->time.tick = snd_seq_timer_get_cur_tick(q->timer);
tmr = queue->timer;
status->events = queue->tickq->cells + queue->timeq->cells;
- status->time = snd_seq_timer_get_cur_time(tmr);
+ status->time = snd_seq_timer_get_cur_time(tmr, true);
status->tick = snd_seq_timer_get_cur_tick(tmr);
status->running = tmr->running;
{
unsigned long flags;
struct snd_seq_event_cell *cell;
+ snd_seq_tick_time_t cur_tick;
+ snd_seq_real_time_t cur_time;
if (q == NULL)
return;
__again:
/* Process tick queue... */
+ cur_tick = snd_seq_timer_get_cur_tick(q->timer);
for (;;) {
- cell = snd_seq_prioq_cell_out(q->tickq,
- &q->timer->tick.cur_tick);
+ cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick);
if (!cell)
break;
snd_seq_dispatch_event(cell, atomic, hop);
}
/* Process time queue... */
+ cur_time = snd_seq_timer_get_cur_time(q->timer, false);
for (;;) {
- cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time);
+ cell = snd_seq_prioq_cell_out(q->timeq, &cur_time);
if (!cell)
break;
snd_seq_dispatch_event(cell, atomic, hop);
int snd_seq_queue_set_owner(int queueid, int client, int locked)
{
struct snd_seq_queue *q = queueptr(queueid);
+ unsigned long flags;
if (q == NULL)
return -EINVAL;
return -EPERM;
}
+ spin_lock_irqsave(&q->owner_lock, flags);
q->locked = locked ? 1 : 0;
q->owner = client;
+ spin_unlock_irqrestore(&q->owner_lock, flags);
queue_access_unlock(q);
queuefree(q);
unsigned long flags;
int i;
struct snd_seq_queue *q;
+ bool matched;
for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
if ((q = queueptr(i)) == NULL)
continue;
spin_lock_irqsave(&q->owner_lock, flags);
- if (q->owner == client)
+ matched = (q->owner == client);
+ if (matched)
q->klocked = 1;
spin_unlock_irqrestore(&q->owner_lock, flags);
- if (q->owner == client) {
+ if (matched) {
if (q->timer->running)
snd_seq_timer_stop(q->timer);
snd_seq_timer_reset(q->timer);
int i, bpm;
struct snd_seq_queue *q;
struct snd_seq_timer *tmr;
+ bool locked;
+ int owner;
for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
if ((q = queueptr(i)) == NULL)
else
bpm = 0;
+ spin_lock_irq(&q->owner_lock);
+ locked = q->locked;
+ owner = q->owner;
+ spin_unlock_irq(&q->owner_lock);
+
snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name);
- snd_iprintf(buffer, "owned by client : %d\n", q->owner);
- snd_iprintf(buffer, "lock status : %s\n", q->locked ? "Locked" : "Free");
+ snd_iprintf(buffer, "owned by client : %d\n", owner);
+ snd_iprintf(buffer, "lock status : %s\n", locked ? "Locked" : "Free");
snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq));
snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq));
snd_iprintf(buffer, "timer state : %s\n", tmr->running ? "Running" : "Stopped");
}
/* return current 'real' time. use timeofday() to get better granularity. */
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+ bool adjust_ktime)
{
snd_seq_real_time_t cur_time;
unsigned long flags;
spin_lock_irqsave(&tmr->lock, flags);
cur_time = tmr->cur_time;
- if (tmr->running) {
+ if (adjust_ktime && tmr->running) {
struct timespec64 tm;
ktime_get_ts64(&tm);
high PPQ values) */
snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr)
{
- return tmr->tick.cur_tick;
+ snd_seq_tick_time_t cur_tick;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tmr->lock, flags);
+ cur_tick = tmr->tick.cur_tick;
+ spin_unlock_irqrestore(&tmr->lock, flags);
+ return cur_tick;
}
int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position);
int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position);
int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base);
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr);
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+ bool adjust_ktime);
snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr);
extern int seq_default_timer_class;
int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
struct hdac_ext_link *link)
{
+ unsigned long codec_mask;
int ret = 0;
mutex_lock(&bus->lock);
* HDA spec section 4.3 - Codec Discovery
*/
udelay(521);
- bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS);
- dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask);
- snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask);
+ codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+ dev_dbg(bus->dev, "codec_mask = 0x%lx\n", codec_mask);
+ snd_hdac_chip_writew(bus, STATESTS, codec_mask);
+ if (!bus->codec_mask)
+ bus->codec_mask = codec_mask;
}
mutex_unlock(&bus->lock);
for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) {
if (spk_alloc & (1 << i))
- j += snprintf(buf + j, buflen - j, " %s",
+ j += scnprintf(buf + j, buflen - j, " %s",
cea_speaker_allocation_names[i]);
}
buf[j] = '\0'; /* necessary when j == 0 */
for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++)
if (pcm & (AC_SUPPCM_BITS_8 << i))
- j += snprintf(buf + j, buflen - j, " %d", bits[i]);
+ j += scnprintf(buf + j, buflen - j, " %d", bits[i]);
buf[j] = '\0'; /* necessary when j == 0 */
}
for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++)
if (pcm & (1 << i))
- j += snprintf(buf + j, buflen - j, " %d",
+ j += scnprintf(buf + j, buflen - j, " %d",
alsa_rates[i]);
buf[j] = '\0'; /* necessary when j == 0 */
int i, len = 0;
mutex_lock(&codec->user_mutex);
snd_array_for_each(&codec->init_verbs, i, v) {
- len += snprintf(buf + len, PAGE_SIZE - len,
+ len += scnprintf(buf + len, PAGE_SIZE - len,
"0x%02x 0x%03x 0x%04x\n",
v->nid, v->verb, v->param);
}
int i, len = 0;
mutex_lock(&codec->user_mutex);
snd_array_for_each(&codec->hints, i, hint) {
- len += snprintf(buf + len, PAGE_SIZE - len,
+ len += scnprintf(buf + len, PAGE_SIZE - len,
"%s = %s\n", hint->key, hint->val);
}
mutex_unlock(&codec->user_mutex);
SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
struct snd_soc_card *card;
struct acp3x_platform_info *pinfo;
u32 ret, val, period_bytes, reg_val, ier_val, water_val;
+ u32 buf_size, buf_reg;
prtd = substream->private_data;
rtd = substream->runtime->private_data;
}
period_bytes = frames_to_bytes(substream->runtime,
substream->runtime->period_size);
+ buf_size = frames_to_bytes(substream->runtime,
+ substream->runtime->buffer_size);
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_RESUME:
mmACP_BT_TX_INTR_WATERMARK_SIZE;
reg_val = mmACP_BTTDM_ITER;
ier_val = mmACP_BTTDM_IER;
+ buf_reg = mmACP_BT_TX_RINGBUFSIZE;
break;
case I2S_SP_INSTANCE:
default:
mmACP_I2S_TX_INTR_WATERMARK_SIZE;
reg_val = mmACP_I2STDM_ITER;
ier_val = mmACP_I2STDM_IER;
+ buf_reg = mmACP_I2S_TX_RINGBUFSIZE;
}
} else {
switch (rtd->i2s_instance) {
mmACP_BT_RX_INTR_WATERMARK_SIZE;
reg_val = mmACP_BTTDM_IRER;
ier_val = mmACP_BTTDM_IER;
+ buf_reg = mmACP_BT_RX_RINGBUFSIZE;
break;
case I2S_SP_INSTANCE:
default:
mmACP_I2S_RX_INTR_WATERMARK_SIZE;
reg_val = mmACP_I2STDM_IRER;
ier_val = mmACP_I2STDM_IER;
+ buf_reg = mmACP_I2S_RX_RINGBUFSIZE;
}
}
rv_writel(period_bytes, rtd->acp3x_base + water_val);
+ rv_writel(buf_size, rtd->acp3x_base + buf_reg);
val = rv_readl(rtd->acp3x_base + reg_val);
val = val | BIT(0);
rv_writel(val, rtd->acp3x_base + reg_val);
{
u16 page_idx;
u32 low, high, val, acp_fifo_addr, reg_fifo_addr;
- u32 reg_ringbuf_size, reg_dma_size, reg_fifo_size;
+ u32 reg_dma_size, reg_fifo_size;
dma_addr_t addr;
addr = rtd->dma_addr;
if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
switch (rtd->i2s_instance) {
case I2S_BT_INSTANCE:
- reg_ringbuf_size = mmACP_BT_TX_RINGBUFSIZE;
reg_dma_size = mmACP_BT_TX_DMA_SIZE;
acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
BT_PB_FIFO_ADDR_OFFSET;
case I2S_SP_INSTANCE:
default:
- reg_ringbuf_size = mmACP_I2S_TX_RINGBUFSIZE;
reg_dma_size = mmACP_I2S_TX_DMA_SIZE;
acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
SP_PB_FIFO_ADDR_OFFSET;
} else {
switch (rtd->i2s_instance) {
case I2S_BT_INSTANCE:
- reg_ringbuf_size = mmACP_BT_RX_RINGBUFSIZE;
reg_dma_size = mmACP_BT_RX_DMA_SIZE;
acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
BT_CAPT_FIFO_ADDR_OFFSET;
case I2S_SP_INSTANCE:
default:
- reg_ringbuf_size = mmACP_I2S_RX_RINGBUFSIZE;
reg_dma_size = mmACP_I2S_RX_DMA_SIZE;
acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
SP_CAPT_FIFO_ADDR_OFFSET;
rtd->acp3x_base + mmACP_I2S_RX_RINGBUFADDR);
}
}
- rv_writel(MAX_BUFFER, rtd->acp3x_base + reg_ringbuf_size);
rv_writel(DMA_SIZE, rtd->acp3x_base + reg_dma_size);
rv_writel(acp_fifo_addr, rtd->acp3x_base + reg_fifo_addr);
rv_writel(FIFO_SIZE, rtd->acp3x_base + reg_fifo_size);
return -ETIMEDOUT;
}
-static int acp3x_power_off(void __iomem *acp3x_base)
-{
- u32 val;
- int timeout;
-
- rv_writel(ACP_PGFSM_CNTL_POWER_OFF_MASK,
- acp3x_base + mmACP_PGFSM_CONTROL);
- timeout = 0;
- while (++timeout < 500) {
- val = rv_readl(acp3x_base + mmACP_PGFSM_STATUS);
- if ((val & ACP_PGFSM_STATUS_MASK) == ACP_POWERED_OFF)
- return 0;
- udelay(1);
- }
- return -ETIMEDOUT;
-}
-
static int acp3x_reset(void __iomem *acp3x_base)
{
u32 val;
pr_err("ACP3x reset failed\n");
return ret;
}
- /* power off */
- ret = acp3x_power_off(acp3x_base);
- if (ret) {
- pr_err("ACP3x power off failed\n");
- return ret;
- }
return 0;
}
if SND_ATMEL_SOC
config SND_ATMEL_SOC_PDC
- tristate
+ bool
depends on HAS_DMA
config SND_ATMEL_SOC_DMA
- tristate
+ bool
select SND_SOC_GENERIC_DMAENGINE_PCM
config SND_ATMEL_SOC_SSC
snd-soc-atmel-i2s-objs := atmel-i2s.o
snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o
-obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o
-obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o
+# pdc and dma need to both be built-in if any user of
+# ssc is built-in.
+ifdef CONFIG_SND_ATMEL_SOC_PDC
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o
+endif
+ifdef CONFIG_SND_ATMEL_SOC_DMA
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o
+endif
obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o
obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o
return ret;
}
+static void hdmi_remove(struct snd_soc_component *component)
+{
+ struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
+
+ if (hcp->hcd.ops->hook_plugged_cb)
+ hcp->hcd.ops->hook_plugged_cb(component->dev->parent,
+ hcp->hcd.data, NULL, NULL);
+}
+
static const struct snd_soc_component_driver hdmi_driver = {
+ .remove = hdmi_remove,
.dapm_widgets = hdmi_widgets,
.num_dapm_widgets = ARRAY_SIZE(hdmi_widgets),
.of_xlate_dai_id = hdmi_of_xlate_dai_id,
* Copyright 2011-2012 Maxim Integrated Products
*/
-#include <linux/acpi.h>
-#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/i2c.h>
#include <linux/module.h>
-#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/pm.h>
#include <linux/pm_runtime.h>
#include <linux/regmap.h>
#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
#include <sound/jack.h>
-#include <sound/max98090.h>
#include <sound/pcm.h>
#include <sound/pcm_params.h>
#include <sound/soc.h>
#include <sound/tlv.h>
+#include <sound/max98090.h>
#include "max98090.h"
-static void max98090_shdn_save_locked(struct max98090_priv *max98090)
-{
- int shdn = 0;
-
- /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */
- regmap_read(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, &shdn);
- max98090->saved_shdn |= shdn;
- ++max98090->saved_count;
-
- if (shdn)
- regmap_write(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, 0x0);
-}
-
-static void max98090_shdn_restore_locked(struct max98090_priv *max98090)
-{
- /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */
- if (--max98090->saved_count == 0) {
- if (max98090->saved_shdn) {
- regmap_write(max98090->regmap,
- M98090_REG_DEVICE_SHUTDOWN,
- M98090_SHDNN_MASK);
- max98090->saved_shdn = 0;
- }
- }
-}
-
-static void max98090_shdn_save(struct max98090_priv *max98090)
-{
- mutex_lock_nested(&max98090->component->card->dapm_mutex,
- SND_SOC_DAPM_CLASS_RUNTIME);
- max98090_shdn_save_locked(max98090);
-}
-
-static void max98090_shdn_restore(struct max98090_priv *max98090)
-{
- max98090_shdn_restore_locked(max98090);
- mutex_unlock(&max98090->component->card->dapm_mutex);
-}
-
-static int max98090_put_volsw(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- struct snd_soc_component *component =
- snd_soc_kcontrol_component(kcontrol);
- struct max98090_priv *max98090 =
- snd_soc_component_get_drvdata(component);
- int ret;
-
- max98090_shdn_save(max98090);
- ret = snd_soc_put_volsw(kcontrol, ucontrol);
- max98090_shdn_restore(max98090);
-
- return ret;
-}
-
-static int max98090_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- struct snd_soc_component *component =
- snd_soc_dapm_kcontrol_component(kcontrol);
- struct max98090_priv *max98090 =
- snd_soc_component_get_drvdata(component);
- int ret;
-
- max98090_shdn_save(max98090);
- ret = snd_soc_dapm_put_enum_double_locked(kcontrol, ucontrol);
- max98090_shdn_restore(max98090);
-
- return ret;
-}
-
-static int max98090_put_enum_double(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- struct snd_soc_component *component =
- snd_soc_kcontrol_component(kcontrol);
- struct max98090_priv *max98090 =
- snd_soc_component_get_drvdata(component);
- int ret;
-
- max98090_shdn_save(max98090);
- ret = snd_soc_put_enum_double(kcontrol, ucontrol);
- max98090_shdn_restore(max98090);
-
- return ret;
-}
-
-static int max98090_bytes_put(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- struct snd_soc_component *component =
- snd_soc_kcontrol_component(kcontrol);
- struct max98090_priv *max98090 =
- snd_soc_component_get_drvdata(component);
- int ret;
-
- max98090_shdn_save(max98090);
- ret = snd_soc_bytes_put(kcontrol, ucontrol);
- max98090_shdn_restore(max98090);
-
- return ret;
-}
-
-static int max98090_dapm_event(struct snd_soc_dapm_widget *w,
- struct snd_kcontrol *kcontrol, int event)
-{
- struct snd_soc_component *component =
- snd_soc_dapm_to_component(w->dapm);
- struct max98090_priv *max98090 =
- snd_soc_component_get_drvdata(component);
-
- switch (event) {
- case SND_SOC_DAPM_PRE_PMU:
- case SND_SOC_DAPM_PRE_PMD:
- max98090_shdn_save_locked(max98090);
- break;
- case SND_SOC_DAPM_POST_PMU:
- case SND_SOC_DAPM_POST_PMD:
- max98090_shdn_restore_locked(max98090);
- break;
- }
-
- return 0;
-}
-
/* Allows for sparsely populated register maps */
static const struct reg_default max98090_reg[] = {
{ 0x00, 0x00 }, /* 00 Software Reset */
max98090_pwr_perf_text);
static const struct snd_kcontrol_new max98090_snd_controls[] = {
- SOC_ENUM_EXT("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
+ SOC_ENUM("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum),
- SOC_SINGLE_EXT("DMIC MIC Comp Filter Config",
- M98090_REG_DIGITAL_MIC_CONFIG,
- M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ SOC_SINGLE("DMIC MIC Comp Filter Config", M98090_REG_DIGITAL_MIC_CONFIG,
+ M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0),
SOC_SINGLE_EXT_TLV("MIC1 Boost Volume",
M98090_REG_MIC1_INPUT_LEVEL, M98090_MIC_PA1EN_SHIFT,
M98090_AVR_SHIFT, M98090_AVR_NUM - 1, 1,
max98090_av_tlv),
- SOC_ENUM_EXT("ADC Oversampling Rate", max98090_osr128_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_SINGLE_EXT("ADC Quantizer Dither", M98090_REG_ADC_CONTROL,
- M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_ENUM_EXT("ADC High Performance Mode", max98090_adchp_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
-
- SOC_SINGLE_EXT("DAC Mono Mode", M98090_REG_IO_CONFIGURATION,
- M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("SDIN Mode", M98090_REG_IO_CONFIGURATION,
- M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("SDOUT Mode", M98090_REG_IO_CONFIGURATION,
- M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION,
- M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_ENUM_EXT("Filter Mode", max98090_mode_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_SINGLE_EXT("Record Path DC Blocking", M98090_REG_FILTER_CONFIG,
- M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG,
- M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ SOC_ENUM("ADC Oversampling Rate", max98090_osr128_enum),
+ SOC_SINGLE("ADC Quantizer Dither", M98090_REG_ADC_CONTROL,
+ M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0),
+ SOC_ENUM("ADC High Performance Mode", max98090_adchp_enum),
+
+ SOC_SINGLE("DAC Mono Mode", M98090_REG_IO_CONFIGURATION,
+ M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0),
+ SOC_SINGLE("SDIN Mode", M98090_REG_IO_CONFIGURATION,
+ M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0),
+ SOC_SINGLE("SDOUT Mode", M98090_REG_IO_CONFIGURATION,
+ M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0),
+ SOC_SINGLE("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION,
+ M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1),
+ SOC_ENUM("Filter Mode", max98090_mode_enum),
+ SOC_SINGLE("Record Path DC Blocking", M98090_REG_FILTER_CONFIG,
+ M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0),
+ SOC_SINGLE("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG,
+ M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0),
SOC_SINGLE_TLV("Digital BQ Volume", M98090_REG_ADC_BIQUAD_LEVEL,
M98090_AVBQ_SHIFT, M98090_AVBQ_NUM - 1, 1, max98090_dv_tlv),
SOC_SINGLE_EXT_TLV("Digital Sidetone Volume",
SOC_SINGLE_TLV("Digital Volume", M98090_REG_DAI_PLAYBACK_LEVEL,
M98090_DV_SHIFT, M98090_DV_NUM - 1, 1,
max98090_dv_tlv),
- SND_SOC_BYTES_E("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105,
- snd_soc_bytes_get, max98090_bytes_put),
- SOC_SINGLE_EXT("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
- M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
- M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_SINGLE_EXT("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
- M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ SND_SOC_BYTES("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105),
+ SOC_SINGLE("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+ M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0),
+ SOC_SINGLE("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+ M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0),
+ SOC_SINGLE("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+ M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0),
SOC_SINGLE("Digital EQ Clipping Detection", M98090_REG_DAI_PLAYBACK_LEVEL_EQ,
M98090_EQCLPN_SHIFT, M98090_EQCLPN_NUM - 1,
1),
M98090_DVEQ_SHIFT, M98090_DVEQ_NUM - 1, 1,
max98090_dv_tlv),
- SOC_SINGLE_EXT("ALC Enable", M98090_REG_DRC_TIMING,
- M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
- SOC_ENUM_EXT("ALC Attack Time", max98090_drcatk_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_ENUM_EXT("ALC Release Time", max98090_drcrls_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
+ SOC_SINGLE("ALC Enable", M98090_REG_DRC_TIMING,
+ M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0),
+ SOC_ENUM("ALC Attack Time", max98090_drcatk_enum),
+ SOC_ENUM("ALC Release Time", max98090_drcrls_enum),
SOC_SINGLE_TLV("ALC Make Up Volume", M98090_REG_DRC_GAIN,
M98090_DRCG_SHIFT, M98090_DRCG_NUM - 1, 0,
max98090_alcmakeup_tlv),
- SOC_ENUM_EXT("ALC Compression Ratio", max98090_alccmp_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_ENUM_EXT("ALC Expansion Ratio", max98090_drcexp_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_SINGLE_EXT_TLV("ALC Compression Threshold Volume",
+ SOC_ENUM("ALC Compression Ratio", max98090_alccmp_enum),
+ SOC_ENUM("ALC Expansion Ratio", max98090_drcexp_enum),
+ SOC_SINGLE_TLV("ALC Compression Threshold Volume",
M98090_REG_DRC_COMPRESSOR, M98090_DRCTHC_SHIFT,
- M98090_DRCTHC_NUM - 1, 1,
- snd_soc_get_volsw, max98090_put_volsw, max98090_alccomp_tlv),
- SOC_SINGLE_EXT_TLV("ALC Expansion Threshold Volume",
+ M98090_DRCTHC_NUM - 1, 1, max98090_alccomp_tlv),
+ SOC_SINGLE_TLV("ALC Expansion Threshold Volume",
M98090_REG_DRC_EXPANDER, M98090_DRCTHE_SHIFT,
- M98090_DRCTHE_NUM - 1, 1,
- snd_soc_get_volsw, max98090_put_volsw, max98090_drcexp_tlv),
+ M98090_DRCTHE_NUM - 1, 1, max98090_drcexp_tlv),
- SOC_ENUM_EXT("DAC HP Playback Performance Mode",
- max98090_dac_perfmode_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_ENUM_EXT("DAC High Performance Mode", max98090_dachp_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
+ SOC_ENUM("DAC HP Playback Performance Mode",
+ max98090_dac_perfmode_enum),
+ SOC_ENUM("DAC High Performance Mode", max98090_dachp_enum),
SOC_SINGLE_TLV("Headphone Left Mixer Volume",
M98090_REG_HP_CONTROL, M98090_MIXHPLG_SHIFT,
SOC_SINGLE("Volume Adjustment Smoothing", M98090_REG_LEVEL_CONTROL,
M98090_VSENN_SHIFT, M98090_VSENN_NUM - 1, 1),
- SND_SOC_BYTES_E("Biquad Coefficients",
- M98090_REG_RECORD_BIQUAD_BASE, 15,
- snd_soc_bytes_get, max98090_bytes_put),
- SOC_SINGLE_EXT("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
- M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ SND_SOC_BYTES("Biquad Coefficients", M98090_REG_RECORD_BIQUAD_BASE, 15),
+ SOC_SINGLE("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
+ M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0),
};
static const struct snd_kcontrol_new max98091_snd_controls[] = {
M98090_DMIC34_ZEROPAD_SHIFT,
M98090_DMIC34_ZEROPAD_NUM - 1, 0),
- SOC_ENUM_EXT("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum,
- snd_soc_get_enum_double, max98090_put_enum_double),
- SOC_SINGLE_EXT("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG,
+ SOC_ENUM("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum),
+ SOC_SINGLE("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG,
M98090_FLT_DMIC34HPF_SHIFT,
- M98090_FLT_DMIC34HPF_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ M98090_FLT_DMIC34HPF_NUM - 1, 0),
SOC_SINGLE_TLV("DMIC3 Boost Volume", M98090_REG_DMIC3_VOLUME,
M98090_DMIC_AV3G_SHIFT, M98090_DMIC_AV3G_NUM - 1, 0,
SND_SOC_BYTES("DMIC34 Biquad Coefficients",
M98090_REG_DMIC34_BIQUAD_BASE, 15),
- SOC_SINGLE_EXT("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
- M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0,
- snd_soc_get_volsw, max98090_put_volsw),
+ SOC_SINGLE("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
+ M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0),
SOC_SINGLE_TLV("DMIC34 BQ PreAttenuation Volume",
M98090_REG_DMIC34_BQ_PREATTEN, M98090_AV34BQ_SHIFT,
return 0;
}
+static int max98090_shdn_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+ struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
+
+ if (event & SND_SOC_DAPM_POST_PMU)
+ max98090->shdn_pending = true;
+
+ return 0;
+
+}
+
static const char *mic1_mux_text[] = { "IN12", "IN56" };
static SOC_ENUM_SINGLE_DECL(mic1_mux_enum,
lten_mux_text);
static const struct snd_kcontrol_new max98090_ltenl_mux =
- SOC_DAPM_ENUM_EXT("LTENL Mux", ltenl_mux_enum,
- snd_soc_dapm_get_enum_double,
- max98090_dapm_put_enum_double);
+ SOC_DAPM_ENUM("LTENL Mux", ltenl_mux_enum);
static const struct snd_kcontrol_new max98090_ltenr_mux =
- SOC_DAPM_ENUM_EXT("LTENR Mux", ltenr_mux_enum,
- snd_soc_dapm_get_enum_double,
- max98090_dapm_put_enum_double);
+ SOC_DAPM_ENUM("LTENR Mux", ltenr_mux_enum);
static const char *lben_mux_text[] = { "Normal", "Loopback" };
lben_mux_text);
static const struct snd_kcontrol_new max98090_lbenl_mux =
- SOC_DAPM_ENUM_EXT("LBENL Mux", lbenl_mux_enum,
- snd_soc_dapm_get_enum_double,
- max98090_dapm_put_enum_double);
+ SOC_DAPM_ENUM("LBENL Mux", lbenl_mux_enum);
static const struct snd_kcontrol_new max98090_lbenr_mux =
- SOC_DAPM_ENUM_EXT("LBENR Mux", lbenr_mux_enum,
- snd_soc_dapm_get_enum_double,
- max98090_dapm_put_enum_double);
+ SOC_DAPM_ENUM("LBENR Mux", lbenr_mux_enum);
static const char *stenl_mux_text[] = { "Normal", "Sidetone Left" };
SND_SOC_DAPM_INPUT("IN56"),
SND_SOC_DAPM_SUPPLY("MICBIAS", M98090_REG_INPUT_ENABLE,
- M98090_MBEN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_MBEN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("SHDN", M98090_REG_DEVICE_SHUTDOWN,
M98090_SHDNN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("SDIEN", M98090_REG_IO_CONFIGURATION,
- M98090_SDIEN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_SDIEN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("SDOEN", M98090_REG_IO_CONFIGURATION,
- M98090_SDOEN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_SDOEN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("DMICL_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
- M98090_DIGMICL_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_DIGMICL_SHIFT, 0, max98090_shdn_event,
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_SUPPLY("DMICR_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
- M98090_DIGMICR_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_DIGMICR_SHIFT, 0, max98090_shdn_event,
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_SUPPLY("AHPF", M98090_REG_FILTER_CONFIG,
- M98090_AHPF_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_AHPF_SHIFT, 0, NULL, 0),
/*
* Note: Sysclk and misc power supplies are taken care of by SHDN
&max98090_lineb_mixer_controls[0],
ARRAY_SIZE(max98090_lineb_mixer_controls)),
- SND_SOC_DAPM_PGA_E("LINEA Input", M98090_REG_INPUT_ENABLE,
- M98090_LINEAEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
- SND_SOC_DAPM_PGA_E("LINEB Input", M98090_REG_INPUT_ENABLE,
- M98090_LINEBEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ SND_SOC_DAPM_PGA("LINEA Input", M98090_REG_INPUT_ENABLE,
+ M98090_LINEAEN_SHIFT, 0, NULL, 0),
+ SND_SOC_DAPM_PGA("LINEB Input", M98090_REG_INPUT_ENABLE,
+ M98090_LINEBEN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_MIXER("Left ADC Mixer", SND_SOC_NOPM, 0, 0,
&max98090_left_adc_mixer_controls[0],
ARRAY_SIZE(max98090_right_adc_mixer_controls)),
SND_SOC_DAPM_ADC_E("ADCL", NULL, M98090_REG_INPUT_ENABLE,
- M98090_ADLEN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_ADLEN_SHIFT, 0, max98090_shdn_event,
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_ADC_E("ADCR", NULL, M98090_REG_INPUT_ENABLE,
- M98090_ADREN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_ADREN_SHIFT, 0, max98090_shdn_event,
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_AIF_OUT("AIFOUTL", "HiFi Capture", 0,
SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_AIF_IN("AIFINL", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_AIF_IN("AIFINR", "HiFi Playback", 1, SND_SOC_NOPM, 0, 0),
- SND_SOC_DAPM_DAC_E("DACL", NULL, M98090_REG_OUTPUT_ENABLE,
- M98090_DALEN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
- SND_SOC_DAPM_DAC_E("DACR", NULL, M98090_REG_OUTPUT_ENABLE,
- M98090_DAREN_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ SND_SOC_DAPM_DAC("DACL", NULL, M98090_REG_OUTPUT_ENABLE,
+ M98090_DALEN_SHIFT, 0),
+ SND_SOC_DAPM_DAC("DACR", NULL, M98090_REG_OUTPUT_ENABLE,
+ M98090_DAREN_SHIFT, 0),
SND_SOC_DAPM_MIXER("Left Headphone Mixer", SND_SOC_NOPM, 0, 0,
&max98090_left_hp_mixer_controls[0],
SND_SOC_DAPM_MUX("MIXHPRSEL Mux", SND_SOC_NOPM, 0, 0,
&max98090_mixhprsel_mux),
- SND_SOC_DAPM_PGA_E("HP Left Out", M98090_REG_OUTPUT_ENABLE,
- M98090_HPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
- SND_SOC_DAPM_PGA_E("HP Right Out", M98090_REG_OUTPUT_ENABLE,
- M98090_HPREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-
- SND_SOC_DAPM_PGA_E("SPK Left Out", M98090_REG_OUTPUT_ENABLE,
- M98090_SPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
- SND_SOC_DAPM_PGA_E("SPK Right Out", M98090_REG_OUTPUT_ENABLE,
- M98090_SPREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-
- SND_SOC_DAPM_PGA_E("RCV Left Out", M98090_REG_OUTPUT_ENABLE,
- M98090_RCVLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
- SND_SOC_DAPM_PGA_E("RCV Right Out", M98090_REG_OUTPUT_ENABLE,
- M98090_RCVREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ SND_SOC_DAPM_PGA("HP Left Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_HPLEN_SHIFT, 0, NULL, 0),
+ SND_SOC_DAPM_PGA("HP Right Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_HPREN_SHIFT, 0, NULL, 0),
+
+ SND_SOC_DAPM_PGA("SPK Left Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_SPLEN_SHIFT, 0, NULL, 0),
+ SND_SOC_DAPM_PGA("SPK Right Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_SPREN_SHIFT, 0, NULL, 0),
+
+ SND_SOC_DAPM_PGA("RCV Left Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_RCVLEN_SHIFT, 0, NULL, 0),
+ SND_SOC_DAPM_PGA("RCV Right Out", M98090_REG_OUTPUT_ENABLE,
+ M98090_RCVREN_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_OUTPUT("HPL"),
SND_SOC_DAPM_OUTPUT("HPR"),
SND_SOC_DAPM_INPUT("DMIC4"),
SND_SOC_DAPM_SUPPLY("DMIC3_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
- M98090_DIGMIC3_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_DIGMIC3_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("DMIC4_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
- M98090_DIGMIC4_SHIFT, 0, max98090_dapm_event,
- SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+ M98090_DIGMIC4_SHIFT, 0, NULL, 0),
};
static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
return;
}
- /*
- * Master mode: no need to save and restore SHDN for the following
- * sensitive registers.
- */
-
/* Check for supported PCLK to LRCLK ratios */
for (i = 0; i < ARRAY_SIZE(pclk_rates); i++) {
if ((pclk_rates[i] == max98090->sysclk) &&
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
/* Set to slave mode PLL - MAS mode off */
- max98090_shdn_save(max98090);
snd_soc_component_write(component,
M98090_REG_CLOCK_RATIO_NI_MSB, 0x00);
snd_soc_component_write(component,
M98090_REG_CLOCK_RATIO_NI_LSB, 0x00);
snd_soc_component_update_bits(component, M98090_REG_CLOCK_MODE,
M98090_USE_M1_MASK, 0);
- max98090_shdn_restore(max98090);
max98090->master = false;
break;
case SND_SOC_DAIFMT_CBM_CFM:
dev_err(component->dev, "DAI clock mode unsupported");
return -EINVAL;
}
- max98090_shdn_save(max98090);
snd_soc_component_write(component, M98090_REG_MASTER_MODE, regval);
- max98090_shdn_restore(max98090);
regval = 0;
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
if (max98090->tdm_slots > 1)
regval ^= M98090_BCI_MASK;
- max98090_shdn_save(max98090);
snd_soc_component_write(component,
M98090_REG_INTERFACE_FORMAT, regval);
- max98090_shdn_restore(max98090);
}
return 0;
struct snd_soc_component *component = codec_dai->component;
struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
struct max98090_cdata *cdata;
-
cdata = &max98090->dai[0];
if (slots < 0 || slots > 4)
max98090->tdm_width = slot_width;
if (max98090->tdm_slots > 1) {
- max98090_shdn_save(max98090);
/* SLOTL SLOTR SLOTDLY */
snd_soc_component_write(component, M98090_REG_TDM_FORMAT,
0 << M98090_TDM_SLOTL_SHIFT |
snd_soc_component_update_bits(component, M98090_REG_TDM_CONTROL,
M98090_TDM_MASK,
M98090_TDM_MASK);
- max98090_shdn_restore(max98090);
}
/*
dmic_freq = dmic_table[pclk_index].settings[micclk_index].freq;
dmic_comp = dmic_table[pclk_index].settings[micclk_index].comp[i];
- max98090_shdn_save(max98090);
regmap_update_bits(max98090->regmap, M98090_REG_DIGITAL_MIC_ENABLE,
M98090_MICCLK_MASK,
micclk_index << M98090_MICCLK_SHIFT);
M98090_DMIC_COMP_MASK | M98090_DMIC_FREQ_MASK,
dmic_comp << M98090_DMIC_COMP_SHIFT |
dmic_freq << M98090_DMIC_FREQ_SHIFT);
- max98090_shdn_restore(max98090);
return 0;
}
switch (params_width(params)) {
case 16:
- max98090_shdn_save(max98090);
snd_soc_component_update_bits(component, M98090_REG_INTERFACE_FORMAT,
M98090_WS_MASK, 0);
- max98090_shdn_restore(max98090);
break;
default:
return -EINVAL;
cdata->rate = max98090->lrclk;
- max98090_shdn_save(max98090);
/* Update filter mode */
if (max98090->lrclk < 24000)
snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG,
else
snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG,
M98090_DHF_MASK, M98090_DHF_MASK);
- max98090_shdn_restore(max98090);
max98090_configure_dmic(max98090, max98090->dmic_freq, max98090->pclk,
max98090->lrclk);
* 0x02 (when master clk is 20MHz to 40MHz)..
* 0x03 (when master clk is 40MHz to 60MHz)..
*/
- max98090_shdn_save(max98090);
if ((freq >= 10000000) && (freq <= 20000000)) {
snd_soc_component_write(component, M98090_REG_SYSTEM_CLOCK,
M98090_PSCLK_DIV1);
max98090->pclk = freq >> 2;
} else {
dev_err(component->dev, "Invalid master clock frequency\n");
- max98090_shdn_restore(max98090);
return -EINVAL;
}
- max98090_shdn_restore(max98090);
max98090->sysclk = freq;
*/
/* Toggle shutdown OFF then ON */
- mutex_lock(&component->card->dapm_mutex);
snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
M98090_SHDNN_MASK, 0);
snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
M98090_SHDNN_MASK, M98090_SHDNN_MASK);
- mutex_unlock(&component->card->dapm_mutex);
for (i = 0; i < 10; ++i) {
/* Give PLL time to lock */
*/
snd_soc_component_read32(component, M98090_REG_DEVICE_STATUS);
- /*
- * SHDN should be 0 at the point, no need to save/restore for the
- * following registers.
- *
- * High Performance is default
- */
+ /* High Performance is default */
snd_soc_component_update_bits(component, M98090_REG_DAC_CONTROL,
M98090_DACHP_MASK,
1 << M98090_DACHP_SHIFT);
M98090_ADCHP_MASK,
1 << M98090_ADCHP_SHIFT);
- /*
- * SHDN should be 0 at the point, no need to save/restore for the
- * following registers.
- *
- * Turn on VCM bandgap reference
- */
+ /* Turn on VCM bandgap reference */
snd_soc_component_write(component, M98090_REG_BIAS_CONTROL,
M98090_VCM_MODE_MASK);
max98090->component = NULL;
}
+static void max98090_seq_notifier(struct snd_soc_component *component,
+ enum snd_soc_dapm_type event, int subseq)
+{
+ struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
+
+ if (max98090->shdn_pending) {
+ snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
+ M98090_SHDNN_MASK, 0);
+ msleep(40);
+ snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
+ M98090_SHDNN_MASK, M98090_SHDNN_MASK);
+ max98090->shdn_pending = false;
+ }
+}
+
static const struct snd_soc_component_driver soc_component_dev_max98090 = {
.probe = max98090_probe,
.remove = max98090_remove,
+ .seq_notifier = max98090_seq_notifier,
.set_bias_level = max98090_set_bias_level,
.idle_bias_on = 1,
.use_pmdown_time = 1,
unsigned int pa2en;
unsigned int sidetone;
bool master;
- int saved_count;
- int saved_shdn;
+ bool shdn_pending;
};
int max98090_mic_detect(struct snd_soc_component *component,
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
&fsl_sai_dai, 1);
if (ret)
- return ret;
+ goto err_pm_disable;
- if (sai->soc_data->use_imx_pcm)
- return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
- else
- return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+ if (sai->soc_data->use_imx_pcm) {
+ ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
+ if (ret)
+ goto err_pm_disable;
+ } else {
+ ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+ if (ret)
+ goto err_pm_disable;
+ }
+
+ return ret;
+
+err_pm_disable:
+ pm_runtime_disable(&pdev->dev);
+
+ return ret;
}
static int fsl_sai_remove(struct platform_device *pdev)
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_get_enum_double);
-static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol, int locked)
+/**
+ * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback
+ * @kcontrol: mixer control
+ * @ucontrol: control element information
+ *
+ * Callback to set the value of a dapm enumerated double mixer control.
+ *
+ * Returns 0 for success.
+ */
+int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
struct snd_soc_card *card = dapm->card;
mask |= e->mask << e->shift_r;
}
- if (!locked)
- mutex_lock_nested(&card->dapm_mutex,
- SND_SOC_DAPM_CLASS_RUNTIME);
+ mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
change = dapm_kcontrol_set_value(kcontrol, val);
card->update = NULL;
}
- if (!locked)
- mutex_unlock(&card->dapm_mutex);
+ mutex_unlock(&card->dapm_mutex);
if (ret > 0)
soc_dpcm_runtime_update(card);
return change;
}
-
-/**
- * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to set the value of a dapm enumerated double mixer control.
- *
- * Returns 0 for success.
- */
-int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 0);
-}
EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double);
-/**
- * snd_soc_dapm_put_enum_double_locked - dapm enumerated double mixer set
- * callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to set the value of a dapm enumerated double mixer control.
- * Must acquire dapm_mutex before calling the function.
- *
- * Returns 0 for success.
- */
-int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_value *ucontrol)
-{
- dapm_assert_locked(snd_soc_dapm_kcontrol_dapm(kcontrol));
- return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 1);
-}
-EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double_locked);
-
/**
* snd_soc_dapm_info_pin_switch - Info for a pin switch
*
runtime->rate = params_rate(params);
out:
- if (ret < 0)
- kfree(runtime);
-
kfree(params);
return ret;
}
{
struct hdac_bus *bus = sof_to_bus(sdev);
- dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable);
- snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable);
+ if (HDA_IDISP_CODEC(bus->codec_mask)) {
+ dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable);
+ snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable);
+ }
}
EXPORT_SYMBOL_NS(hda_codec_i915_display_power, SND_SOC_SOF_HDA_AUDIO_CODEC_I915);
if (ret < 0)
return ret;
- hda_codec_i915_display_power(sdev, true);
+ /* codec_mask not yet known, power up for probe */
+ snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, true);
return 0;
}
struct hdac_bus *bus = sof_to_bus(sdev);
int ret;
- hda_codec_i915_display_power(sdev, false);
+ /* power down unconditionally */
+ snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false);
ret = snd_hdac_i915_exit(bus);
return ret;
}
+ /* display codec can powered off after link reset */
+ hda_codec_i915_display_power(sdev, false);
+
return 0;
}
#endif
int ret;
+ /* display codec must be powered before link reset */
+ hda_codec_i915_display_power(sdev, true);
+
/*
* clear TCSEL to clear playback on some HD Audio
* codecs. PCI TCSEL is defined in the Intel manuals.
struct pci_dev *pci = to_pci_dev(sdev->dev);
if (sdev->s0_suspend) {
+ hda_codec_i915_display_power(sdev, true);
+
/* restore L1SEN bit */
if (hda->l1_support_changed)
snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
int ret;
if (sdev->s0_suspend) {
+ /* we can't keep a wakeref to display driver at suspend */
+ hda_codec_i915_display_power(sdev, false);
+
/* enable L1SEN to make sure the system can enter S0Ix */
hda->l1_support_changed =
snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
/* HDA base */
sdev->bar[HDA_DSP_HDA_BAR] = bus->remap_addr;
+ /* init i915 and HDMI codecs */
+ ret = hda_codec_i915_init(sdev);
+ if (ret < 0) {
+ dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n");
+ return ret;
+ }
+
/* get controller capabilities */
ret = hda_dsp_ctrl_get_caps(sdev);
if (ret < 0)
if (bus->ppcap)
dev_dbg(sdev->dev, "PP capability, will probe DSP later.\n");
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
- /* init i915 and HDMI codecs */
- ret = hda_codec_i915_init(sdev);
- if (ret < 0) {
- dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n");
- return ret;
- }
-#endif
-
/* Init HDA controller after i915 init */
ret = hda_dsp_ctrl_init_chip(sdev, true);
if (ret < 0) {
hda_codec_probe_bus(sdev, hda_codec_use_common_hdmi);
if (!HDA_IDISP_CODEC(bus->codec_mask))
- hda_codec_i915_display_power(sdev, false);
+ hda_codec_i915_exit(sdev);
/*
* we are done probing so decrement link counts
iounmap(sdev->bar[HDA_DSP_BAR]);
hdac_bus_unmap:
iounmap(bus->remap_addr);
+ hda_codec_i915_exit(sdev);
err:
return ret;
}
#define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK GENMASK(15, 12)
#define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK GENMASK(11, 8)
+#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK GENMASK(3, 2)
#define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK GENMASK(5, 4)
#define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK GENMASK(8, 6)
#define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK GENMASK(12, 9)
return -EINVAL;
}
regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL,
- BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT),
+ SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK,
value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT);
return 0;
#define MSR_K7_HWCR 0xc0010015
#define MSR_K7_HWCR_SMMLOCK_BIT 0
#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT 30
+#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
#include <stdio.h>
-/* controllable printf */
-extern int pr_output;
-#define printk(fmt, ...) \
- (pr_output ? printf(fmt, ##__VA_ARGS__) : 0)
+#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__)
#define pr_err printk
#define pr_warn printk
#include <linux/kernel.h>
#include <linux/bootconfig.h>
-int pr_output = 1;
-
static int xbc_show_array(struct xbc_node *node)
{
const char *val;
struct stat stat;
int ret;
u32 size = 0, csum = 0, rcsum;
+ char magic[BOOTCONFIG_MAGIC_LEN];
ret = fstat(fd, &stat);
if (ret < 0)
return -errno;
- if (stat.st_size < 8)
+ if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
+ return 0;
+
+ if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
+ pr_err("Failed to lseek: %d\n", -errno);
+ return -errno;
+ }
+ if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
+ return -errno;
+ /* Check the bootconfig magic bytes */
+ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
return 0;
- if (lseek(fd, -8, SEEK_END) < 0) {
+ if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
if (read(fd, &csum, sizeof(u32)) < 0)
return -errno;
- /* Wrong size, maybe no boot config here */
- if (stat.st_size < size + 8)
- return 0;
+ /* Wrong size error */
+ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
+ pr_err("bootconfig size is too big\n");
+ return -E2BIG;
+ }
- if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) {
+ if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
+ SEEK_SET) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
if (ret < 0)
return ret;
- /* Wrong Checksum, maybe no boot config here */
+ /* Wrong Checksum */
rcsum = checksum((unsigned char *)*buf, size);
if (csum != rcsum) {
pr_err("checksum error: %d != %d\n", csum, rcsum);
- return 0;
+ return -EINVAL;
}
ret = xbc_init(*buf);
- /* Wrong data, maybe no boot config here */
+ /* Wrong data */
if (ret < 0)
- return 0;
+ return ret;
return size;
}
return -errno;
}
- /*
- * Suppress error messages in xbc_init() because it can be just a
- * data which concidentally matches the size and checksum footer.
- */
- pr_output = 0;
size = load_xbc_from_initrd(fd, &buf);
- pr_output = 1;
if (size < 0) {
ret = size;
pr_err("Failed to load a boot config from initrd: %d\n", ret);
} else if (size > 0) {
ret = fstat(fd, &stat);
if (!ret)
- ret = ftruncate(fd, stat.st_size - size - 8);
+ ret = ftruncate(fd, stat.st_size
+ - size - 8 - BOOTCONFIG_MAGIC_LEN);
if (ret)
ret = -errno;
} /* Ignore if there is no boot config in initrd */
pr_err("Failed to apply a boot config: %d\n", ret);
return ret;
}
+ /* Write a magic word of the bootconfig */
+ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+ if (ret < 0) {
+ pr_err("Failed to apply a boot config magic: %d\n", ret);
+ return ret;
+ }
close(fd);
free(data);
--- /dev/null
+# value -> subkey pattern
+key = value
+key.subkey = another-value
--- /dev/null
+# subkey -> value pattern
+key.subkey = value
+key = another-value
--- /dev/null
+# Same key value is not allowed
+key {
+ foo = value
+ bar = value2
+}
+key.foo = value
NG=0
cleanup() {
- rm -f $INITRD $TEMPCONF
+ rm -f $INITRD $TEMPCONF $OUTFILE
exit $NG
}
new_size=$(stat -c %s $INITRD)
echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9)
+xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
echo "Apply command repeat test"
xpass $BOOTCONF -a $TEMPCONF $INITRD
$BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1
xfail grep -i "failed" $OUTFILE
xfail grep -i "error" $OUTFILE
-rm $OUTFILE
echo "Max node number check"
echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0')
xpass $BOOTCONF -a $TEMPCONF $INITRD
+echo "Adding same-key values"
+cat > $TEMPCONF << EOF
+key = bar, baz
+key += qux
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xpass grep -q "bar" $OUTFILE
+xpass grep -q "baz" $OUTFILE
+xpass grep -q "qux" $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
* supports redirection to the egress interface, and accepts no
* flag at all.
*
- * The same effect can be attained with the more generic
- * **bpf_redirect_map**\ (), which requires specific maps to be
- * used but offers better performance.
+ * The same effect can also be attained with the more generic
+ * **bpf_redirect_map**\ (), which uses a BPF map to store the
+ * redirect target instead of providing it directly to the helper.
* Return
* For XDP, the helper returns **XDP_REDIRECT** on success or
* **XDP_ABORTED** on error. For other program types, the values
* the caller. Any higher bits in the *flags* argument must be
* unset.
*
- * When used to redirect packets to net devices, this helper
- * provides a high performance increase over **bpf_redirect**\ ().
- * This is due to various implementation details of the underlying
- * mechanisms, one of which is the fact that **bpf_redirect_map**\
- * () tries to send packet as a "bulk" to the device.
+ * See also bpf_redirect(), which only supports redirecting to an
+ * ifindex, but doesn't require a map to do so.
* Return
- * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * **XDP_REDIRECT** on success, or the value of the two lower bits
+ * of the **flags* argument on error.
*
* int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
* Description
#include <endian.h>
#include <fcntl.h>
#include <errno.h>
+#include <ctype.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
static char *internal_map_name(struct bpf_object *obj,
enum libbpf_map_type type)
{
- char map_name[BPF_OBJ_NAME_LEN];
+ char map_name[BPF_OBJ_NAME_LEN], *p;
const char *sfx = libbpf_type_to_btf_name[type];
int sfx_len = max((size_t)7, strlen(sfx));
int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
sfx_len, libbpf_type_to_btf_name[type]);
+ /* sanitise map name to characters allowed by kernel */
+ for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
+ if (!isalnum(*p) && *p != '_' && *p != '.')
+ *p = '_';
+
return strdup(map_name);
}
set buildid.dir to /dev/null. The default is $HOME/.debug
annotate.*::
- These options work only for TUI.
These are in control of addresses, jump function, source code
in lines of assembly code from a specific program.
│ mov (%rdi),%rdx
│ return n;
+ This option works with tui, stdio2 browsers.
+
annotate.use_offset::
Basing on a first address of a loaded function, offset can be used.
Instead of using original addresses of assembly code,
368:│ mov 0x8(%r14),%rdi
+ This option works with tui, stdio2 browsers.
+
annotate.jump_arrows::
There can be jump instruction among assembly code.
Depending on a boolean value of jump_arrows,
│1330: mov %r15,%r10
│1333: cmp %r15,%r14
+ This option works with tui browser.
+
annotate.show_linenr::
When showing source code if this option is 'true',
line numbers are printed as below.
│ array++;
│ }
+ This option works with tui, stdio2 browsers.
+
annotate.show_nr_jumps::
Let's see a part of assembly code.
│1 1382: movb $0x1,-0x270(%rbp)
+ This option works with tui, stdio2 browsers.
+
annotate.show_total_period::
To compare two records on an instruction base, with this option
provided, display total number of samples that belong to a line
99.93 │ mov %eax,%eax
+ This option works with tui, stdio2, stdio browsers.
+
+ annotate.show_nr_samples::
+ By default perf annotate shows percentage of samples. This option
+ can be used to print absolute number of samples. Ex, when set as
+ false:
+
+ Percent│
+ 74.03 │ mov %fs:0x28,%rax
+
+ When set as true:
+
+ Samples│
+ 6 │ mov %fs:0x28,%rax
+
+ This option works with tui, stdio2, stdio browsers.
+
annotate.offset_level::
Default is '1', meaning just jump targets will have offsets show right beside
the instruction. When set to '2' 'call' instructions will also have its offsets
shown, 3 or higher will show offsets for all instructions.
+ This option works with tui, stdio2 browsers.
+
hist.*::
hist.percentage::
This option control the way to calculate overhead of filtered entries -
column by default.
The default is 'true'.
+ top.call-graph::
+ This is identical to 'call-graph.record-mode', except it is
+ applicable only for 'top' subcommand. This option ONLY setup
+ the unwind method. To enable 'perf top' to actually use it,
+ the command line option -g must be specified.
+
man.*::
man.viewer::
This option can assign a tool to view manual pages when 'help'
But if this option is 'no-cache', it will not update the build-id cache.
'skip' skips post-processing and does not update the cache.
+ record.call-graph::
+ This is identical to 'call-graph.record-mode', except it is
+ applicable only for 'record' subcommand. This option ONLY setup
+ the unwind method. To enable 'perf record' to actually use it,
+ the command line option -g must be specified.
+
+ record.aio::
+ Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+ mode ('n' default: 1, max: 4).
+
diff.*::
diff.order::
This option sets the number of columns to sort the result.
"libbeauty", the default, to use the same argument beautifiers used in the
strace-like sys_enter+sys_exit lines.
+ftrace.*::
+ ftrace.tracer::
+ Can be used to select the default tracer. Possible values are
+ 'function' and 'function_graph'.
+
llvm.*::
llvm.clang-path::
Path to clang. If omit, search it from $PATH.
The script gets the same options passed as a full perf script,
in particular -i perfdata file, --cpu, --tid
+convert.*::
+
+ convert.queue-size::
+ Limit the size of ordered_events queue, so we could control
+ allocation size of perf data files without proper finished
+ round events.
+
+intel-pt.*::
+
+ intel-pt.cache-divisor::
+
+ intel-pt.mispred-all::
+ If set, Intel PT decoder will set the mispred flag on all
+ branches.
+
+auxtrace.*::
+
+ auxtrace.dumpdir::
+ s390 only. The directory to save the auxiliary trace buffer
+ can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+ If the directory does not exist or has the wrong file type,
+ the current directory is used.
+
SEE ALSO
--------
linkperf:perf[1]
free(ptr);
}
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct cs_etm_recording *ptr =
- container_of(itr, struct cs_etm_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(ptr->evlist, evsel) {
- if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
- return perf_evlist__enable_event_idx(ptr->evlist,
- evsel, idx);
- }
-
- return -EINVAL;
-}
-
struct auxtrace_record *cs_etm_record_init(int *err)
{
struct perf_pmu *cs_etm_pmu;
}
ptr->cs_etm_pmu = cs_etm_pmu;
+ ptr->itr.pmu = cs_etm_pmu;
ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options;
ptr->itr.recording_options = cs_etm_recording_options;
ptr->itr.info_priv_size = cs_etm_info_priv_size;
ptr->itr.snapshot_finish = cs_etm_snapshot_finish;
ptr->itr.reference = cs_etm_reference;
ptr->itr.free = cs_etm_recording_free;
- ptr->itr.read_finish = cs_etm_read_finish;
+ ptr->itr.read_finish = auxtrace_record__read_finish;
*err = 0;
return &ptr->itr;
free(sper);
}
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct arm_spe_recording *sper =
- container_of(itr, struct arm_spe_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(sper->evlist, evsel) {
- if (evsel->core.attr.type == sper->arm_spe_pmu->type)
- return perf_evlist__enable_event_idx(sper->evlist,
- evsel, idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *arm_spe_recording_init(int *err,
struct perf_pmu *arm_spe_pmu)
{
}
sper->arm_spe_pmu = arm_spe_pmu;
+ sper->itr.pmu = arm_spe_pmu;
sper->itr.recording_options = arm_spe_recording_options;
sper->itr.info_priv_size = arm_spe_info_priv_size;
sper->itr.info_fill = arm_spe_info_fill;
sper->itr.free = arm_spe_recording_free;
sper->itr.reference = arm_spe_reference;
- sper->itr.read_finish = arm_spe_read_finish;
+ sper->itr.read_finish = auxtrace_record__read_finish;
sper->itr.alignment = 0;
*err = 0;
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 nospu clone3 ppc_clone3
+437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
return err;
}
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct intel_bts_recording *btsr =
- container_of(itr, struct intel_bts_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(btsr->evlist, evsel) {
- if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
- return perf_evlist__enable_event_idx(btsr->evlist,
- evsel, idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *intel_bts_recording_init(int *err)
{
struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
}
btsr->intel_bts_pmu = intel_bts_pmu;
+ btsr->itr.pmu = intel_bts_pmu;
btsr->itr.recording_options = intel_bts_recording_options;
btsr->itr.info_priv_size = intel_bts_info_priv_size;
btsr->itr.info_fill = intel_bts_info_fill;
btsr->itr.find_snapshot = intel_bts_find_snapshot;
btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
btsr->itr.reference = intel_bts_reference;
- btsr->itr.read_finish = intel_bts_read_finish;
+ btsr->itr.read_finish = auxtrace_record__read_finish;
btsr->itr.alignment = sizeof(struct branch);
return &btsr->itr;
}
return rdtsc();
}
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
- struct intel_pt_recording *ptr =
- container_of(itr, struct intel_pt_recording, itr);
- struct evsel *evsel;
-
- evlist__for_each_entry(ptr->evlist, evsel) {
- if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
- return perf_evlist__enable_event_idx(ptr->evlist, evsel,
- idx);
- }
- return -EINVAL;
-}
-
struct auxtrace_record *intel_pt_recording_init(int *err)
{
struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
}
ptr->intel_pt_pmu = intel_pt_pmu;
+ ptr->itr.pmu = intel_pt_pmu;
ptr->itr.recording_options = intel_pt_recording_options;
ptr->itr.info_priv_size = intel_pt_info_priv_size;
ptr->itr.info_fill = intel_pt_info_fill;
ptr->itr.find_snapshot = intel_pt_find_snapshot;
ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
ptr->itr.reference = intel_pt_reference;
- ptr->itr.read_finish = intel_pt_read_finish;
+ ptr->itr.read_finish = auxtrace_record__read_finish;
/*
* Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
* should give at least 1 PSB per sample.
if (ret < 0)
return ret;
+ annotation_config__init(&annotate.opts);
+
argc = parse_options(argc, argv, options, annotate_usage, 0);
if (argc) {
/*
if (ret < 0)
goto out_delete;
- annotation_config__init();
-
symbol_conf.try_vmlinux_path = true;
ret = symbol__init(&annotate.session->header.env);
ret = probe_file__del_strlist(kfd, klist);
if (ret < 0)
goto error;
- }
+ } else if (ret == -ENOMEM)
+ goto error;
ret2 = probe_file__get_events(ufd, filter, ulist);
if (ret2 == 0) {
ret2 = probe_file__del_strlist(ufd, ulist);
if (ret2 < 0)
goto error;
- }
+ } else if (ret2 == -ENOMEM)
+ goto error;
if (ret == -ENOENT && ret2 == -ENOENT)
pr_warning("\"%s\" does not hit any event.\n", str);
symbol_conf.priv_size += sizeof(u32);
symbol_conf.sort_by_name = true;
}
- annotation_config__init();
+ annotation_config__init(&report.annotation_opts);
}
if (symbol__init(&session->header.env) < 0)
return err;
}
- err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL);
+ err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
if (err == 0) {
top->sym_filter_entry = he;
} else {
if (status < 0)
goto out_delete_evlist;
- annotation_config__init();
+ annotation_config__init(&top.annotation_opts);
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
status = symbol__init(NULL);
#ifndef _PERF_BPF_PID_FILTER_
#define _PERF_BPF_PID_FILTER_
-#include <bpf/bpf.h>
+#include <bpf.h>
#define pid_filter(name) pid_map(name, bool)
// SPDX-License-Identifier: GPL-2.0
-#include <bpf/bpf.h>
+#include <bpf.h>
struct bpf_map SEC("maps") __bpf_stdout__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
// SPDX-License-Identifier: LGPL-2.1
-#include <bpf/bpf.h>
+#include <bpf.h>
static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
if [ $had_vfs_getname -eq 1 ] ; then
line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
- perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+ perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
fi
}
"? Search string backwards\n");
continue;
case 'r':
- {
- script_browse(NULL, NULL);
- continue;
- }
+ script_browse(NULL, NULL);
+ annotate_browser__show(&browser->b, title, help);
+ continue;
case 'k':
notes->options->show_linenr = !notes->options->show_linenr;
break;
map_symbol__annotation_dump(ms, evsel, browser->opts);
continue;
case 't':
- if (notes->options->show_total_period) {
- notes->options->show_total_period = false;
- notes->options->show_nr_samples = true;
- } else if (notes->options->show_nr_samples)
- notes->options->show_nr_samples = false;
+ if (symbol_conf.show_total_period) {
+ symbol_conf.show_total_period = false;
+ symbol_conf.show_nr_samples = true;
+ } else if (symbol_conf.show_nr_samples)
+ symbol_conf.show_nr_samples = false;
else
- notes->options->show_total_period = true;
+ symbol_conf.show_total_period = true;
annotation__update_column_widths(notes);
continue;
case 'c':
if (ms->map->dso->annotate_warned)
return -1;
- err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL);
+ err = symbol__annotate(ms, evsel, &annotation__default_options, NULL);
if (err) {
char msg[BUFSIZ];
symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
}
struct annotate_args {
- size_t privsize;
- struct arch *arch;
- struct map_symbol ms;
- struct evsel *evsel;
+ struct arch *arch;
+ struct map_symbol ms;
+ struct evsel *evsel;
struct annotation_options *options;
- s64 offset;
- char *line;
- int line_nr;
+ s64 offset;
+ char *line;
+ int line_nr;
};
-static void annotation_line__delete(struct annotation_line *al)
+static void annotation_line__init(struct annotation_line *al,
+ struct annotate_args *args,
+ int nr)
{
- void *ptr = (void *) al - al->privsize;
+ al->offset = args->offset;
+ al->line = strdup(args->line);
+ al->line_nr = args->line_nr;
+ al->data_nr = nr;
+}
+static void annotation_line__exit(struct annotation_line *al)
+{
free_srcline(al->path);
zfree(&al->line);
- free(ptr);
}
-/*
- * Allocating the annotation line data with following
- * structure:
- *
- * --------------------------------------
- * private space | struct annotation_line
- * --------------------------------------
- *
- * Size of the private space is stored in 'struct annotation_line'.
- *
- */
-static struct annotation_line *
-annotation_line__new(struct annotate_args *args, size_t privsize)
+static size_t disasm_line_size(int nr)
{
struct annotation_line *al;
- struct evsel *evsel = args->evsel;
- size_t size = privsize + sizeof(*al);
- int nr = 1;
-
- if (perf_evsel__is_group_event(evsel))
- nr = evsel->core.nr_members;
- size += sizeof(al->data[0]) * nr;
-
- al = zalloc(size);
- if (al) {
- al = (void *) al + privsize;
- al->privsize = privsize;
- al->offset = args->offset;
- al->line = strdup(args->line);
- al->line_nr = args->line_nr;
- al->data_nr = nr;
- }
-
- return al;
+ return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
}
/*
* Allocating the disasm annotation line data with
* following structure:
*
- * ------------------------------------------------------------
- * privsize space | struct disasm_line | struct annotation_line
- * ------------------------------------------------------------
+ * -------------------------------------------
+ * struct disasm_line | struct annotation_line
+ * -------------------------------------------
*
* We have 'struct annotation_line' member as last member
* of 'struct disasm_line' to have an easy access.
- *
*/
static struct disasm_line *disasm_line__new(struct annotate_args *args)
{
struct disasm_line *dl = NULL;
- struct annotation_line *al;
- size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+ int nr = 1;
- al = annotation_line__new(args, privsize);
- if (al != NULL) {
- dl = disasm_line(al);
+ if (perf_evsel__is_group_event(args->evsel))
+ nr = args->evsel->core.nr_members;
- if (dl->al.line == NULL)
- goto out_delete;
+ dl = zalloc(disasm_line_size(nr));
+ if (!dl)
+ return NULL;
- if (args->offset != -1) {
- if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
- goto out_free_line;
+ annotation_line__init(&dl->al, args, nr);
+ if (dl->al.line == NULL)
+ goto out_delete;
- disasm_line__init_ins(dl, args->arch, &args->ms);
- }
+ if (args->offset != -1) {
+ if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+ goto out_free_line;
+
+ disasm_line__init_ins(dl, args->arch, &args->ms);
}
return dl;
else
ins__delete(&dl->ops);
zfree(&dl->ins.name);
- annotation_line__delete(&dl->al);
+ annotation_line__exit(&dl->al);
+ free(dl);
}
int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
annotation__calc_percent(notes, evsel, symbol__size(sym));
}
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize,
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
struct annotation_options *options, struct arch **parch)
{
struct symbol *sym = ms->sym;
struct annotation *notes = symbol__annotation(sym);
struct annotate_args args = {
- .privsize = privsize,
.evsel = evsel,
.options = options,
};
struct annotation_line *al;
notes->max_line_len = 0;
+ notes->nr_entries = 0;
+ notes->nr_asm_entries = 0;
list_for_each_entry(al, ¬es->src->source, node) {
size_t line_len = strlen(al->line);
struct symbol *sym = ms->sym;
struct rb_root source_line = RB_ROOT;
- if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0)
+ if (symbol__annotate(ms, evsel, opts, NULL) < 0)
return -1;
symbol__calc_percent(sym, evsel);
percent = annotation_data__percent(&al->data[i], percent_type);
obj__set_percent_color(obj, percent, current_entry);
- if (notes->options->show_total_period) {
+ if (symbol_conf.show_total_period) {
obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
- } else if (notes->options->show_nr_samples) {
+ } else if (symbol_conf.show_nr_samples) {
obj__printf(obj, "%6" PRIu64 " ",
al->data[i].he.nr_samples);
} else {
obj__printf(obj, "%-*s", pcnt_width, " ");
else {
obj__printf(obj, "%-*s", pcnt_width,
- notes->options->show_total_period ? "Period" :
- notes->options->show_nr_samples ? "Samples" : "Percent");
+ symbol_conf.show_total_period ? "Period" :
+ symbol_conf.show_nr_samples ? "Samples" : "Percent");
}
}
if (perf_evsel__is_group_event(evsel))
nr_pcnt = evsel->core.nr_members;
- err = symbol__annotate(ms, evsel, 0, options, parch);
+ err = symbol__annotate(ms, evsel, options, parch);
if (err)
goto out_free_offsets;
return err;
}
-#define ANNOTATION__CFG(n) \
- { .name = #n, .value = &annotation__default_options.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotation_config {
- const char *name;
- void *value;
-} annotation__configs[] = {
- ANNOTATION__CFG(hide_src_code),
- ANNOTATION__CFG(jump_arrows),
- ANNOTATION__CFG(offset_level),
- ANNOTATION__CFG(show_linenr),
- ANNOTATION__CFG(show_nr_jumps),
- ANNOTATION__CFG(show_nr_samples),
- ANNOTATION__CFG(show_total_period),
- ANNOTATION__CFG(use_offset),
-};
-
-#undef ANNOTATION__CFG
-
-static int annotation_config__cmp(const void *name, const void *cfgp)
-{
- const struct annotation_config *cfg = cfgp;
-
- return strcmp(name, cfg->name);
-}
-
-static int annotation__config(const char *var, const char *value,
- void *data __maybe_unused)
+static int annotation__config(const char *var, const char *value, void *data)
{
- struct annotation_config *cfg;
- const char *name;
+ struct annotation_options *opt = data;
if (!strstarts(var, "annotate."))
return 0;
- name = var + 9;
- cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
- sizeof(struct annotation_config), annotation_config__cmp);
-
- if (cfg == NULL)
- pr_debug("%s variable unknown, ignoring...", var);
- else if (strcmp(var, "annotate.offset_level") == 0) {
- perf_config_int(cfg->value, name, value);
-
- if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
- *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
- else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
- *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+ if (!strcmp(var, "annotate.offset_level")) {
+ perf_config_u8(&opt->offset_level, "offset_level", value);
+
+ if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+ opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
+ else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
+ opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+ } else if (!strcmp(var, "annotate.hide_src_code")) {
+ opt->hide_src_code = perf_config_bool("hide_src_code", value);
+ } else if (!strcmp(var, "annotate.jump_arrows")) {
+ opt->jump_arrows = perf_config_bool("jump_arrows", value);
+ } else if (!strcmp(var, "annotate.show_linenr")) {
+ opt->show_linenr = perf_config_bool("show_linenr", value);
+ } else if (!strcmp(var, "annotate.show_nr_jumps")) {
+ opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
+ } else if (!strcmp(var, "annotate.show_nr_samples")) {
+ symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
+ value);
+ } else if (!strcmp(var, "annotate.show_total_period")) {
+ symbol_conf.show_total_period = perf_config_bool("show_total_period",
+ value);
+ } else if (!strcmp(var, "annotate.use_offset")) {
+ opt->use_offset = perf_config_bool("use_offset", value);
} else {
- *(bool *)cfg->value = perf_config_bool(name, value);
+ pr_debug("%s variable unknown, ignoring...", var);
}
+
return 0;
}
-void annotation_config__init(void)
+void annotation_config__init(struct annotation_options *opt)
{
- perf_config(annotation__config, NULL);
-
- annotation__default_options.show_total_period = symbol_conf.show_total_period;
- annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples;
+ perf_config(annotation__config, opt);
}
static unsigned int parse_percent_type(char *str1, char *str2)
full_path,
show_linenr,
show_nr_jumps,
- show_nr_samples,
- show_total_period,
show_minmax_cycle,
show_asm_raw,
annotate_src;
u64 cycles;
u64 cycles_max;
u64 cycles_min;
- size_t privsize;
char *path;
u32 idx;
int idx_asm;
static inline int annotation__pcnt_width(struct annotation *notes)
{
- return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+ return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
}
static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
void symbol__annotate_zero_histograms(struct symbol *sym);
int symbol__annotate(struct map_symbol *ms,
- struct evsel *evsel, size_t privsize,
+ struct evsel *evsel,
struct annotation_options *options,
struct arch **parch);
int symbol__annotate2(struct map_symbol *ms,
}
#endif
-void annotation_config__init(void);
+void annotation_config__init(struct annotation_options *opt);
int annotate_parse_percent_type(const struct option *opt, const char *_str,
int unset);
struct evlist *evlist,
struct record_opts *opts)
{
- if (itr)
+ if (itr) {
+ itr->evlist = evlist;
return itr->recording_options(itr, evlist, opts);
+ }
return 0;
}
return -EINVAL;
}
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
+{
+ struct evsel *evsel;
+
+ if (!itr->evlist || !itr->pmu)
+ return -EINVAL;
+
+ evlist__for_each_entry(itr->evlist, evsel) {
+ if (evsel->core.attr.type == itr->pmu->type) {
+ if (evsel->disabled)
+ return 0;
+ return perf_evlist__enable_event_idx(itr->evlist, evsel,
+ idx);
+ }
+ }
+ return -EINVAL;
+}
+
/*
* Event record size is 16-bit which results in a maximum size of about 64KiB.
* Allow about 4KiB for the rest of the sample record, to give a maximum
struct perf_record_auxtrace_error;
struct perf_record_auxtrace_info;
struct events_stats;
+struct perf_pmu;
enum auxtrace_error_type {
PERF_AUXTRACE_ERROR_ITRACE = 1,
* @read_finish: called after reading from an auxtrace mmap
* @alignment: alignment (if any) for AUX area data
* @default_aux_sample_size: default sample size for --aux sample option
+ * @pmu: associated pmu
+ * @evlist: selected events list
*/
struct auxtrace_record {
int (*recording_options)(struct auxtrace_record *itr,
int (*read_finish)(struct auxtrace_record *itr, int idx);
unsigned int alignment;
unsigned int default_aux_sample_size;
+ struct perf_pmu *pmu;
+ struct evlist *evlist;
};
/**
struct auxtrace_mmap *mm,
unsigned char *data, u64 *head, u64 *old);
u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx);
int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
off_t file_offset);
return 0;
}
+int perf_config_u8(u8 *dest, const char *name, const char *value)
+{
+ long ret = 0;
+
+ if (!perf_parse_long(value, &ret)) {
+ bad_config(name);
+ return -1;
+ }
+ *dest = ret;
+ return 0;
+}
+
static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
{
int ret;
int perf_default_config(const char *, const char *, void *);
int perf_config(config_fn_t fn, void *);
int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u8(u8 *dest, const char *name, const char *value);
int perf_config_u64(u64 *dest, const char *, const char *);
int perf_config_bool(const char *, const char *);
int config_error_nonbool(const char *);
p = strchr(ent->s, ':');
if ((p && strfilter__compare(filter, p + 1)) ||
strfilter__compare(filter, ent->s)) {
- strlist__add(plist, ent->s);
+ ret = strlist__add(plist, ent->s);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out;
+ }
ret = 0;
}
}
+out:
strlist__delete(namelist);
return ret;
ret = -EINVAL;
goto out;
}
- strlist__add(entry->tevlist, buf);
+ ret = strlist__add(entry->tevlist, buf);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out;
+ }
}
}
out:
command = synthesize_probe_trace_command(&tevs[i]);
if (!command)
goto out_err;
- strlist__add(entry->tevlist, command);
+ ret = strlist__add(entry->tevlist, command);
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ goto out_err;
+ }
+
free(command);
}
list_add_tail(&entry->node, &pcache->entries);
break;
}
- strlist__add(entry->tevlist, buf);
+ ret = strlist__add(entry->tevlist, buf);
+
free(buf);
entry = NULL;
+
+ if (ret == -ENOMEM) {
+ pr_err("strlist__add failed with -ENOMEM\n");
+ break;
+ }
}
if (entry) {
list_del_init(&entry->node);
KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig'])
+KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0]
+
class KunitStatus(Enum):
SUCCESS = auto()
CONFIG_FAILURE = auto()
shutil.copyfile('arch/um/configs/kunit_defconfig',
kunit_kernel.kunitconfig_path)
+def get_kernel_root_path():
+ parts = sys.argv[0] if not __file__ else __file__
+ parts = os.path.realpath(parts).split('tools/testing/kunit')
+ if len(parts) != 2:
+ sys.exit(1)
+ return parts[0]
+
def run_tests(linux: kunit_kernel.LinuxSourceTree,
request: KunitRequest) -> KunitResult:
config_start = time.time()
cli_args = parser.parse_args(argv)
if cli_args.subcommand == 'run':
+ if get_kernel_root_path():
+ os.chdir(get_kernel_root_path())
+
if cli_args.build_dir:
if not os.path.exists(cli_args.build_dir):
os.mkdir(cli_args.build_dir)
return False
return True
+ def validate_config(self, build_dir):
+ kconfig_path = get_kconfig_path(build_dir)
+ validated_kconfig = kunit_config.Kconfig()
+ validated_kconfig.read_from_file(kconfig_path)
+ if not self._kconfig.is_subset_of(validated_kconfig):
+ invalid = self._kconfig.entries() - validated_kconfig.entries()
+ message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \
+ 'but not in .config: %s' % (
+ ', '.join([str(e) for e in invalid])
+ )
+ logging.error(message)
+ return False
+ return True
+
def build_config(self, build_dir):
kconfig_path = get_kconfig_path(build_dir)
if build_dir and not os.path.exists(build_dir):
except ConfigError as e:
logging.error(e)
return False
- validated_kconfig = kunit_config.Kconfig()
- validated_kconfig.read_from_file(kconfig_path)
- if not self._kconfig.is_subset_of(validated_kconfig):
- logging.error('Provided Kconfig is not contained in validated .config!')
- return False
- return True
+ return self.validate_config(build_dir)
def build_reconfig(self, build_dir):
"""Creates a new .config if it is not a subset of the .kunitconfig."""
except (ConfigError, BuildError) as e:
logging.error(e)
return False
- used_kconfig = kunit_config.Kconfig()
- used_kconfig.read_from_file(get_kconfig_path(build_dir))
- if not self._kconfig.is_subset_of(used_kconfig):
- logging.error('Provided Kconfig is not contained in final config!')
- return False
- return True
+ return self.validate_config(build_dir)
def run_kernel(self, args=[], timeout=None, build_dir=''):
args.extend(['mem=256M'])
override TARGETS := $(TMP)
endif
+# User can set FORCE_TARGETS to 1 to require all targets to be successfully
+# built; make will fail if any of the targets cannot be built. If
+# FORCE_TARGETS is not set (the default), make will succeed if at least one
+# of the targets gets built.
+FORCE_TARGETS ?=
+
# Clear LDFLAGS and MAKEFLAGS if called from main
# Makefile to avoid test build failures when test
# Makefile doesn't have explicit build rules.
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
mkdir $$BUILD_TARGET -p; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET; \
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \
+ $(if $(FORCE_TARGETS),|| exit); \
ret=$$((ret * $$?)); \
done; exit $$ret;
@ret=1; \
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \
+ $(if $(FORCE_TARGETS),|| exit); \
ret=$$((ret * $$?)); \
done; exit $$ret;
.pass_on_failure = 0,
};
- if (type != SOCK_STREAM)
+ if (type != SOCK_STREAM) {
+ test__skip();
return;
+ }
/*
* +1 for TCP-SYN and
goto out;
saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+ if (saved_tcp_fo < 0)
+ goto out;
saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
- if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0)
+ if (saved_tcp_syncookie < 0)
goto out;
if (enable_fastopen())
#include "test_progs.h"
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
static int connected_socket_v4(void)
{
struct sockaddr_in addr = {
all:
TEST_PROGS := ftracetest
-TEST_FILES := test.d
+TEST_FILES := test.d settings
EXTRA_CLEAN := $(OUTPUT)/logs/*
include ../lib.mk
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: ftrace - function pid filters
+# flags: instance
# Make sure that function pid matching filter works.
# Also test it on an instance directory
}
do_test
-
-mkdir instances/foo
-cd instances/foo
-do_test
-cd ../../
-rmdir instances/foo
-
do_reset
exit 0
# SPDX-License-Identifier: GPL-2.0
INCLUDES := -I../include -I../../
CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
-LDFLAGS := $(LDFLAGS) -pthread -lrt
+LDLIBS := -lpthread -lrt
HEADERS := \
../include/futextest.h \
$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
endif
+define INSTALL_SINGLE_RULE
+ $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
+ $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+ $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+endef
+
define INSTALL_RULE
- @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
- mkdir -p ${INSTALL_PATH}; \
- echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \
- rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \
- fi
- @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \
- mkdir -p ${INSTALL_PATH}; \
- echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \
- rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \
- fi
+ $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+ $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
endef
install: all
test-state.sh \
test-ftrace.sh
+TEST_FILES := settings
+
include ../lib.mk
include ../lib.mk
$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
-$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
-$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
+$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
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 dev-only
+ 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 dev veth1"
+ check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+ log_test $? 0 "Multipath with dev-only"
+
# 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"
{
local tundev=$1; shift
local direction=$1; shift
- local prot=$1; shift
local what=$1; shift
- local swp3mac=$(mac_get $swp3)
- local h3mac=$(mac_get $h3)
+ case "$direction" in
+ ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2)
+ ;;
+ egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1)
+ ;;
+ esac
RET=0
mirror_install $swp1 $direction $tundev "matchall $tcflags"
- tc filter add dev $h3 ingress pref 77 prot $prot \
- flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
- action pass
+ icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac"
- mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+ mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10
- tc filter del dev $h3 ingress pref 77
+ icmp_capture_uninstall h3-${tundev}
mirror_uninstall $swp1 $direction
log_test "$direction $what: envelope MAC ($tcflags)"
test_gretap_mac()
{
- test_span_gre_mac gt4 ingress ip "mirror to gretap"
- test_span_gre_mac gt4 egress ip "mirror to gretap"
+ test_span_gre_mac gt4 ingress "mirror to gretap"
+ test_span_gre_mac gt4 egress "mirror to gretap"
}
test_ip6gretap_mac()
{
- test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
- test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+ test_span_gre_mac gt6 ingress "mirror to ip6gretap"
+ test_span_gre_mac gt6 egress "mirror to ip6gretap"
}
test_all()
RET=0
tc filter add dev v1 egress pref 77 prot ip \
- flower ip_tos 0x40 action pass
- vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
- vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+ flower ip_tos 0x14 action pass
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10
+ vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0
tc filter del dev v1 egress pref 77 prot ip
log_test "VXLAN: envelope TOS inheritance"
TEST_GEN_FILES = mptcp_connect
+TEST_FILES := settings
+
EXTRA_CLEAN := *.pcap
include ../../lib.mk
KSELFTEST_SKIP=4
# Available test groups:
+# - reported_issues: check for issues that were reported in the past
# - correctness: check that packets match given entries, and only those
# - concurrency: attempt races between insertion, deletion and lookup
# - timeout: check that packets match entries until they expire
# - performance: estimate matching rate, compare with rbtree and hash baselines
-TESTS="correctness concurrency timeout"
+TESTS="reported_issues correctness concurrency timeout"
[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance"
# Set types, defined by TYPE_ variables below
net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
net_port_mac_proto_net"
+# Reported bugs, also described by TYPE_ variables below
+BUGS="flush_remove_add"
+
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
perf_duration 0
"
+# Definition of tests for bugs reported in the past:
+# display display text for test report
+TYPE_flush_remove_add="
+display Add two elements, flush, re-add
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
# Check that at least one of the needed tools is available
check_tools() {
+ [ -z "${tools}" ] && return 0
+
__tools=
for tool in ${tools}; do
if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \
add() {
if ! nft add element inet filter test "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
add_perf_norange() {
if ! nft add element netdev perf norange "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
add_perf_noconcat() {
if ! nft add element netdev perf noconcat "${1}"; then
err "Failed to add ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
del() {
if ! nft delete element inet filter test "${1}"; then
err "Failed to delete ${1} given ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
err " $(for f in ${src}; do
eval format_\$f "${2}"; printf ' '; done)"
err "should have matched ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
nft reset counter inet filter test >/dev/null
err " $(for f in ${src}; do
eval format_\$f "${2}"; printf ' '; done)"
err "should not have matched ruleset:"
- err "$(nft list ruleset -a)"
+ err "$(nft -a list ruleset)"
return 1
fi
}
kill "${perf_pid}"
}
+test_bug_flush_remove_add() {
+ set_cmd='{ set s { type ipv4_addr . inet_service; flags interval; }; }'
+ elem1='{ 10.0.0.1 . 22-25, 10.0.0.1 . 10-20 }'
+ elem2='{ 10.0.0.1 . 10-20, 10.0.0.1 . 22-25 }'
+ for i in `seq 1 100`; do
+ nft add table t ${set_cmd} || return ${KSELFTEST_SKIP}
+ nft add element t s ${elem1} 2>/dev/null || return 1
+ nft flush set t s 2>/dev/null || return 1
+ nft add element t s ${elem2} 2>/dev/null || return 1
+ done
+ nft flush ruleset
+}
+
+test_reported_issues() {
+ eval test_bug_"${subtest}"
+}
+
# Run everything in a separate network namespace
[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
tmp="$(mktemp)"
# Entry point for test runs
passed=0
for name in ${TESTS}; do
- printf "TEST: %s\n" "${name}"
- for type in ${TYPES}; do
- eval desc=\$TYPE_"${type}"
+ printf "TEST: %s\n" "$(echo ${name} | tr '_' ' ')"
+ if [ "${name}" = "reported_issues" ]; then
+ SUBTESTS="${BUGS}"
+ else
+ SUBTESTS="${TYPES}"
+ fi
+
+ for subtest in ${SUBTESTS}; do
+ eval desc=\$TYPE_"${subtest}"
IFS='
'
for __line in ${desc}; do
int touchat(int dfd, const char *path)
{
- int fd = openat(dfd, path, O_CREAT);
+ int fd = openat(dfd, path, O_CREAT, 0700);
if (fd >= 0)
close(fd);
return fd;
{ .name = "[in_root] garbage link to /root",
.path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
.out.path = "root", .pass = true },
- { .name = "[in_root] chainged garbage links to /root",
+ { .name = "[in_root] chained garbage links to /root",
.path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
.out.path = "root", .pass = true },
{ .name = "[in_root] relative path to 'root'",
CLANG_FLAGS += -no-integrated-as
endif
-CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
$(CLANG_FLAGS)
LDLIBS += -lpthread
TEST_PROGS = run_param_test.sh
+TEST_FILES := settings
+
include ../lib.mk
$(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
TEST_GEN_PROGS = rtctest
TEST_GEN_PROGS_EXTENDED = setdate
+TEST_FILES := settings
+
include ../lib.mk
TEST_GEN_PROGS_EXTENDED := gettime_perf
CFLAGS := -Wall -Werror -pthread
-LDFLAGS := -lrt -ldl
+LDLIBS := -lrt -ldl
include ../lib.mk
#!/bin/bash
# SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+self.flags = flags
-python -m unittest -v tpm2_tests.SmokeTest
-python -m unittest -v tpm2_tests.AsyncTest
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+
+if [ -f /dev/tpm0 ] ; then
+ python -m unittest -v tpm2_tests.SmokeTest
+ python -m unittest -v tpm2_tests.AsyncTest
+else
+ exit $ksft_skip
+fi
CLEAR_CMD=$(which tpm2_clear)
if [ -n $CLEAR_CMD ]; then
#!/bin/bash
# SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
-python -m unittest -v tpm2_tests.SpaceTest
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if [ -f /dev/tpmrm0 ] ; then
+ python -m unittest -v tpm2_tests.SpaceTest
+else
+ exit $ksft_skip
+fi
echo " https://github.com/libhugetlbfs/libhugetlbfs.git for"
echo " hugetlb regression testing."
+echo "---------------------------"
+echo "running map_fixed_noreplace"
+echo "---------------------------"
+./map_fixed_noreplace
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "-------------------"
echo "running userfaultfd"
echo "-------------------"
echo "[PASS]"
fi
+echo "-------------------------"
+echo "running mlock-random-test"
+echo "-------------------------"
+./mlock-random-test
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "--------------------"
echo "running mlock2-tests"
echo "--------------------"
echo "[PASS]"
fi
+echo "-----------------"
+echo "running thuge-gen"
+echo "-----------------"
+./thuge-gen
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
if [ $VADDR64 -ne 0 ]; then
echo "-----------------------------"
echo "running virtual_address_range"
define file_download =
$(DISTFILES_PATH)/$(1):
mkdir -p $(DISTFILES_PATH)
- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
endef
$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
$(MAKE) -C $(IPERF_PATH)
$(STRIP) -s $@
-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- touch $@
-
-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
- cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
- $(MAKE) -C $(LIBMNL_PATH)
- sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
-
$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
+ mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
touch $@
-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
$(STRIP) -s $@
$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
+ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
touch $@
-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
- $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
+ $(STRIP) -s $@
-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
- $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
+ $(STRIP) -s $@
$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
mkdir -p $(BUILD_PATH)
sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
touch $@
-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
+ cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
$(MAKE) -C $(IPTABLES_PATH)
$(STRIP) -s $@
guest_enter_irqoff();
if (has_vhe()) {
- kvm_arm_vhe_guest_enter();
ret = kvm_vcpu_run_vhe(vcpu);
- kvm_arm_vhe_guest_exit();
} else {
ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
}
#include <kvm/arm_arch_timer.h>
#include <linux/tracepoint.h>
+#include <asm/kvm_arm.h>
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
projects / linux-2.6-microblaze.git / commitdiff