$ ls -l /sys/bus/acpi/devices/INT3404:00/
total 0
-...
+ ...
-r--r--r-- 1 root root 4096 Dec 13 20:38 state0
-r--r--r-- 1 root root 4096 Dec 13 20:38 state1
-r--r--r-- 1 root root 4096 Dec 13 20:38 state10
and contains a colon-separated list of 5 integer numbers (fields) with the
following interpretation::
-control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw
+ control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw
* ``control_percent``: The percent value to be used to set the fan speed to a
specific level using the _FSL object (0-100).
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
Once the kernel is built and installed, a simple
.. code-block:: bash
+
modprobe example-test
...will run the tests.
[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
[2] Documentation/devicetree/bindings/power/power-domain.yaml
[3] Documentation/devicetree/bindings/thermal/thermal.txt
-[4] Documentation/devicetree/bindings/sram/sram.txt
+[4] Documentation/devicetree/bindings/sram/sram.yaml
[5] Documentation/devicetree/bindings/reset/reset.txt
Example:
[0] http://infocenter.arm.com/help/topic/com.arm.doc.dui0922b/index.html
[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
[2] Documentation/devicetree/bindings/thermal/thermal.txt
-[3] Documentation/devicetree/bindings/sram/sram.txt
+[3] Documentation/devicetree/bindings/sram/sram.yaml
[4] Documentation/devicetree/bindings/power/power-domain.yaml
Example:
Syscon reboot node:
-See Documentation/devicetree/bindings/power/reset/syscon-reboot.txt for the
+See Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml for the
detailed list of properties, the two values defined below are specific to the
BCM6328-style timer:
$ref: '/schemas/types.yaml#/definitions/phandle-array'
description: |
List of phandles to idle state nodes supported
- by this cpu (see ./idle-states.txt).
+ by this cpu (see ./idle-states.yaml).
capacity-dmips-mhz:
$ref: '/schemas/types.yaml#/definitions/uint32'
items:
- enum:
- armadeus,imx6dl-apf6 # APF6 (Solo) SoM
- - armadeus,imx6dl-apf6dldev # APF6 (Solo) SoM on APF6Dev board
+ - armadeus,imx6dl-apf6dev # APF6 (Solo) SoM on APF6Dev board
- eckelmann,imx6dl-ci4x10
- emtrion,emcon-mx6 # emCON-MX6S or emCON-MX6DL SoM
- emtrion,emcon-mx6-avari # emCON-MX6S or emCON-MX6DL SoM on Avari Base
* Hisilicon Hi3519 System Controller Block
This bindings use the following binding:
-Documentation/devicetree/bindings/mfd/syscon.txt
+Documentation/devicetree/bindings/mfd/syscon.yaml
Required properties:
- compatible: "hisilicon,hi3519-sysctrl".
};
};
-[1]. Documentation/devicetree/bindings/arm/idle-states.txt
+[1]. Documentation/devicetree/bindings/arm/idle-states.yaml
- pm-sram: Phandles to ocmcram nodes to be used for power management.
First should be type 'protect-exec' for the driver to use to copy
and run PM functions, second should be regular pool to be used for
- data region for code. See Documentation/devicetree/bindings/sram/sram.txt
+ data region for code. See Documentation/devicetree/bindings/sram/sram.yaml
for more details.
Examples:
bindings in [1]) must specify this property.
[1] Kernel documentation - ARM idle states bindings
- Documentation/devicetree/bindings/arm/idle-states.txt
-
- "#power-domain-cells":
- description:
- The number of cells in a PM domain specifier as per binding in [3].
- Must be 0 as to represent a single PM domain.
+ Documentation/devicetree/bindings/arm/idle-states.yaml
+patternProperties:
+ "^power-domain-":
+ allOf:
+ - $ref: "../power/power-domain.yaml#"
+ type: object
+ description: |
ARM systems can have multiple cores, sometimes in an hierarchical
arrangement. This often, but not always, maps directly to the processor
power topology of the system. Individual nodes in a topology have their
helps to implement support for OSI mode and OS implementations may choose
to mandate it.
- [3] Documentation/devicetree/bindings/power/power_domain.txt
- [4] Documentation/devicetree/bindings/power/domain-idle-state.txt
-
- power-domains:
- $ref: '/schemas/types.yaml#/definitions/phandle-array'
- description:
- List of phandles and PM domain specifiers, as defined by bindings of the
- PM domain provider.
+ [3] Documentation/devicetree/bindings/power/power-domain.yaml
+ [4] Documentation/devicetree/bindings/power/domain-idle-state.yaml
required:
- compatible
CPU0: cpu@0 {
device_type = "cpu";
- compatible = "arm,cortex-a53", "arm,armv8";
+ compatible = "arm,cortex-a53";
reg = <0x0>;
enable-method = "psci";
power-domains = <&CPU_PD0>;
CPU1: cpu@1 {
device_type = "cpu";
- compatible = "arm,cortex-a57", "arm,armv8";
+ compatible = "arm,cortex-a53";
reg = <0x100>;
enable-method = "psci";
power-domains = <&CPU_PD1>;
exit-latency-us = <10>;
min-residency-us = <100>;
};
+ };
+
+ domain-idle-states {
CLUSTER_RET: cluster-retention {
compatible = "domain-idle-state";
compatible = "arm,psci-1.0";
method = "smc";
- CPU_PD0: cpu-pd0 {
+ CPU_PD0: power-domain-cpu0 {
#power-domain-cells = <0>;
domain-idle-states = <&CPU_PWRDN>;
power-domains = <&CLUSTER_PD>;
};
- CPU_PD1: cpu-pd1 {
+ CPU_PD1: power-domain-cpu1 {
#power-domain-cells = <0>;
domain-idle-states = <&CPU_PWRDN>;
power-domains = <&CLUSTER_PD>;
};
- CLUSTER_PD: cluster-pd {
+ CLUSTER_PD: power-domain-cluster {
#power-domain-cells = <0>;
domain-idle-states = <&CLUSTER_RET>, <&CLUSTER_PWRDN>;
};
examples:
- |
- mlahb: ahb {
+ mlahb: ahb@38000000 {
compatible = "st,mlahb", "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
#size-cells = <0>;
pmic@3e3 {
- compatible = "...";
reg = <0x3e3>;
/* ... */
examples:
- |
- osc24M: clk@01c20050 {
+ osc24M: clk@1c20050 {
#clock-cells = <0>;
compatible = "allwinner,sun4i-a10-osc-clk";
reg = <0x01c20050 0x4>;
examples:
- |
- clk@0600005c {
+ clk@600005c {
#clock-cells = <0>;
compatible = "allwinner,sun9i-a80-gt-clk";
reg = <0x0600005c 0x4>;
be part of GCC and hence the TSENS properties can also be part
of the GCC/clock-controller node.
For more details on the TSENS properties please refer
- Documentation/devicetree/bindings/thermal/qcom-tsens.txt
+ Documentation/devicetree/bindings/thermal/qcom-tsens.yaml
nvmem-cell-names:
minItems: 1
resets = <&tcon_ch0_clk 0>;
port {
- #address-cells = <1>;
- #size-cells = <0>;
-
- tve0_in_tcon0: endpoint@0 {
- reg = <0>;
+ tve0_in_tcon0: endpoint {
remote-endpoint = <&tcon0_out_tve0>;
};
};
#size-cells = <0>;
anx6345_in: port@0 {
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
- anx6345_in_tcon0: endpoint@0 {
- reg = <0>;
+ anx6345_in_tcon0: endpoint {
remote-endpoint = <&tcon0_out_anx6345>;
};
};
anx6345_out: port@1 {
- #address-cells = <1>;
- #size-cells = <0>;
reg = <1>;
- anx6345_out_panel: endpoint@0 {
- reg = <0>;
+ anx6345_out_panel: endpoint {
remote-endpoint = <&panel_in_edp>;
};
};
dsi@ff450000 {
#address-cells = <1>;
#size-cells = <0>;
+ reg = <0xff450000 0x1000>;
+
panel@0 {
compatible = "leadtek,ltk500hd1829";
reg = <0>;
dsi@ff450000 {
#address-cells = <1>;
#size-cells = <0>;
+ reg = <0xff450000 0x1000>;
+
panel@0 {
compatible = "xinpeng,xpp055c272";
reg = <0>;
};
};
- soc@1c00000 {
- lcdc0: lcdc@1c0c000 {
- compatible = "allwinner,sun4i-a10-lcdc";
- };
- };
+ lcdc0: lcdc { };
...
supports a single port with a single endpoint.
- See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and
- Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting
+ Documentation/devicetree/bindings/display/bridge/ti,tfp410.txt for connecting
tfp410 DVI encoder or lcd panel to lcdc
[1] There is an errata about AM335x color wiring. For 16-bit color mode
#size-cells = <2>;
dma-coherent;
dma-ranges;
- ranges;
+ ranges = <0x0 0x30800000 0x0 0x30800000 0x0 0x05000000>;
ti,sci-dev-id = <118>;
ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */
};
};
-
- mcasp0: mcasp@02B00000 {
- dmas = <&main_udmap 0xc400>, <&main_udmap 0x4400>;
- dma-names = "tx", "rx";
- };
-
- crypto: crypto@4E00000 {
- compatible = "ti,sa2ul-crypto";
-
- dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>, <&main_udmap 0x4001>;
- dma-names = "tx", "rx1", "rx2";
- };
};
gpu_opp_table: opp_table0 {
compatible = "operating-points-v2";
- opp@533000000 {
+ opp-533000000 {
opp-hz = /bits/ 64 <533000000>;
opp-microvolt = <1250000>;
};
- opp@450000000 {
+ opp-450000000 {
opp-hz = /bits/ 64 <450000000>;
opp-microvolt = <1150000>;
};
- opp@400000000 {
+ opp-400000000 {
opp-hz = /bits/ 64 <400000000>;
opp-microvolt = <1125000>;
};
- opp@350000000 {
+ opp-350000000 {
opp-hz = /bits/ 64 <350000000>;
opp-microvolt = <1075000>;
};
- opp@266000000 {
+ opp-266000000 {
opp-hz = /bits/ 64 <266000000>;
opp-microvolt = <1025000>;
};
- opp@160000000 {
+ opp-160000000 {
opp-hz = /bits/ 64 <160000000>;
opp-microvolt = <925000>;
};
- opp@100000000 {
+ opp-100000000 {
opp-hz = /bits/ 64 <100000000>;
opp-microvolt = <912500>;
};
gpu_opp_table: opp_table0 {
compatible = "operating-points-v2";
- opp@533000000 {
+ opp-533000000 {
opp-hz = /bits/ 64 <533000000>;
opp-microvolt = <1250000>;
};
- opp@450000000 {
+ opp-450000000 {
opp-hz = /bits/ 64 <450000000>;
opp-microvolt = <1150000>;
};
- opp@400000000 {
+ opp-400000000 {
opp-hz = /bits/ 64 <400000000>;
opp-microvolt = <1125000>;
};
- opp@350000000 {
+ opp-350000000 {
opp-hz = /bits/ 64 <350000000>;
opp-microvolt = <1075000>;
};
- opp@266000000 {
+ opp-266000000 {
opp-hz = /bits/ 64 <266000000>;
opp-microvolt = <1025000>;
};
- opp@160000000 {
+ opp-160000000 {
opp-hz = /bits/ 64 <160000000>;
opp-microvolt = <925000>;
};
- opp@100000000 {
+ opp-100000000 {
opp-hz = /bits/ 64 <100000000>;
opp-microvolt = <912500>;
};
samsung,syscon-phandle = <&pmu_system_controller>;
/* NTC thermistor is a hwmon device */
- ncp15wb473@0 {
+ ncp15wb473 {
compatible = "murata,ncp15wb473";
pullup-uv = <1800000>;
pullup-ohm = <47000>;
examples:
- |
- i2c@00000000 {
+ i2c {
#address-cells = <1>;
#size-cells = <0>;
gt928@5d {
Texas Instruments TWL family (twl4030) pwrbutton module
This module is part of the TWL4030. For more details about the whole
-chip see Documentation/devicetree/bindings/mfd/twl-familly.txt.
+chip see Documentation/devicetree/bindings/mfd/twl-family.txt.
This module provides a simple power button event via an Interrupt.
# LED will act as a back-light, controlled by the framebuffer system
- backlight
# LED will turn on (but for leds-gpio see "default-state" property in
- # Documentation/devicetree/bindings/leds/leds-gpio.txt)
+ # Documentation/devicetree/bindings/leds/leds-gpio.yaml)
- default-on
# LED "double" flashes at a load average based rate
- heartbeat
single LED. The register bit LEDs appear as children to the
syscon device, with the proper compatible string. For the
syscon bindings see:
-Documentation/devicetree/bindings/mfd/syscon.txt
+Documentation/devicetree/bindings/mfd/syscon.yaml
Each LED is represented as a sub-node of the syscon device. Each
node's name represents the name of the corresponding LED.
};
};
- i2c5: i2c@4807c000 {
+ i2c {
clock-frequency = <400000>;
#address-cells = <1>;
#size-cells = <0>;
- sram : Phandles for generic sram driver nodes,
first should be type 'protect-exec' for the driver to use to copy
and run PM functions, second should be regular pool to be used for
- data region for code. See Documentation/devicetree/bindings/sram/sram.txt
+ data region for code. See Documentation/devicetree/bindings/sram/sram.yaml
for more details.
Optional properties:
regulators {
compatible = "maxim,max77650-regulator";
- max77650_ldo: regulator@0 {
+ max77650_ldo: regulator-ldo {
regulator-compatible = "ldo";
regulator-name = "max77650-ldo";
regulator-min-microvolt = <1350000>;
regulator-max-microvolt = <2937500>;
};
- max77650_sbb0: regulator@1 {
+ max77650_sbb0: regulator-sbb0 {
regulator-compatible = "sbb0";
regulator-name = "max77650-sbb0";
regulator-min-microvolt = <800000>;
ldo6, ldo7, ldo8
- xxx-supply: Input voltage supply regulator.
- These entries are require if regulators are enabled for a device. Missing of these
- properties can cause the regulator registration fails.
+ These entries are required if regulators are enabled for a device. Missing these
+ properties can cause the regulator registration to fail.
If some of input supply is powered through battery or always-on supply then
also it is require to have these parameters with proper node handle of always
on power supply.
+++ /dev/null
-Texas Instruments TWL family
-
-The TWLs are Integrated Power Management Chips.
-Some version might contain much more analog function like
-USB transceiver or Audio amplifier.
-These chips are connected to an i2c bus.
-
-
-Required properties:
-- compatible : Must be "ti,twl4030";
- For Integrated power-management/audio CODEC device used in OMAP3
- based boards
-- compatible : Must be "ti,twl6030";
- For Integrated power-management used in OMAP4 based boards
-- interrupts : This i2c device has an IRQ line connected to the main SoC
-- interrupt-controller : Since the twl support several interrupts internally,
- it is considered as an interrupt controller cascaded to the SoC one.
-- #interrupt-cells = <1>;
-
-Optional node:
-- Child nodes contain in the twl. The twl family is made of several variants
- that support a different number of features.
- The children nodes will thus depend of the capability of the variant.
-
-
-Example:
-/*
- * Integrated Power Management Chip
- * http://www.ti.com/lit/ds/symlink/twl6030.pdf
- */
-twl@48 {
- compatible = "ti,twl6030";
- reg = <0x48>;
- interrupts = <39>; /* IRQ_SYS_1N cascaded to gic */
- interrupt-controller;
- #interrupt-cells = <1>;
- interrupt-parent = <&gic>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- twl_rtc {
- compatible = "ti,twl_rtc";
- interrupts = <11>;
- reg = <0>;
- };
-};
--- /dev/null
+Texas Instruments TWL family
+
+The TWLs are Integrated Power Management Chips.
+Some version might contain much more analog function like
+USB transceiver or Audio amplifier.
+These chips are connected to an i2c bus.
+
+
+Required properties:
+- compatible : Must be "ti,twl4030";
+ For Integrated power-management/audio CODEC device used in OMAP3
+ based boards
+- compatible : Must be "ti,twl6030";
+ For Integrated power-management used in OMAP4 based boards
+- interrupts : This i2c device has an IRQ line connected to the main SoC
+- interrupt-controller : Since the twl support several interrupts internally,
+ it is considered as an interrupt controller cascaded to the SoC one.
+- #interrupt-cells = <1>;
+
+Optional node:
+- Child nodes contain in the twl. The twl family is made of several variants
+ that support a different number of features.
+ The children nodes will thus depend of the capability of the variant.
+
+
+Example:
+/*
+ * Integrated Power Management Chip
+ * http://www.ti.com/lit/ds/symlink/twl6030.pdf
+ */
+twl@48 {
+ compatible = "ti,twl6030";
+ reg = <0x48>;
+ interrupts = <39>; /* IRQ_SYS_1N cascaded to gic */
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&gic>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ twl_rtc {
+ compatible = "ti,twl_rtc";
+ interrupts = <11>;
+ reg = <0>;
+ };
+};
Device Description
------ -----------
rave-sp-wdt : Watchdog
-rave-sp-nvmem : Interface to onborad EEPROM
+rave-sp-nvmem : Interface to onboard EEPROM
rave-sp-backlight : Display backlight
rave-sp-hwmon : Interface to onboard hardware sensors
rave-sp-leds : Interface to onboard LEDs
Documentation/devicetree/bindings/iommu/iommu.txt.
For arm-smmu binding, see:
-Documentation/devicetree/bindings/iommu/arm,smmu.txt.
+Documentation/devicetree/bindings/iommu/arm,smmu.yaml.
Required properties:
mmc3: mmc@1c12000 {
#address-cells = <1>;
#size-cells = <0>;
+ reg = <0x1c12000 0x200>;
pinctrl-names = "default";
pinctrl-0 = <&mmc3_pins_a>;
vmmc-supply = <®_vmmc3>;
- reg: shall contain the native Chip Select ids from 0 to max supported by
the cadence nand flash controller
-See Documentation/devicetree/bindings/mtd/nand.txt for more details on
+See Documentation/devicetree/bindings/mtd/nand-controller.yaml for more details on
generic bindings.
Example:
switch queue
- resets: a single phandle and reset identifier pair. See
- Documentation/devicetree/binding/reset/reset.txt for details.
+ Documentation/devicetree/bindings/reset/reset.txt for details.
- reset-names: If the "reset" property is specified, this property should have
the value "switch" to denote the switch reset line.
qfprom: eeprom@700000 {
#address-cells = <1>;
#size-cells = <1>;
+ reg = <0x00700000 0x100000>;
+
wp-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
/* ... */
#include <dt-bindings/clock/sun4i-a10-ccu.h>
#include <dt-bindings/reset/sun4i-a10-ccu.h>
- usbphy: phy@01c13400 {
+ usbphy: phy@1c13400 {
#phy-cells = <1>;
compatible = "allwinner,sun4i-a10-usb-phy";
reg = <0x01c13400 0x10>, <0x01c14800 0x4>, <0x01c1c800 0x4>;
"aspeed,ast2400-scu", "syscon", "simple-mfd"
Refer to the the bindings described in
- Documentation/devicetree/bindings/mfd/syscon.txt
+ Documentation/devicetree/bindings/mfd/syscon.yaml
properties:
compatible:
"aspeed,g5-scu", "syscon", "simple-mfd"
Refer to the the bindings described in
- Documentation/devicetree/bindings/mfd/syscon.txt
+ Documentation/devicetree/bindings/mfd/syscon.yaml
properties:
compatible:
"aspeed,ast2600-scu", "syscon", "simple-mfd"
Refer to the the bindings described in
- Documentation/devicetree/bindings/mfd/syscon.txt
+ Documentation/devicetree/bindings/mfd/syscon.yaml
properties:
compatible:
};
//Example 3 pin groups
- pinctrl@60020000 {
+ pinctrl {
usart1_pins_a: usart1-0 {
pins1 {
pinmux = <STM32_PINMUX('A', 9, AF7)>;
"amlogic,meson-gx-hhi-sysctrl", "simple-mfd", "syscon"
Refer to the the bindings described in
- Documentation/devicetree/bindings/mfd/syscon.txt
+ Documentation/devicetree/bindings/mfd/syscon.yaml
properties:
compatible:
+++ /dev/null
-PM Domain Idle State Node:
-
-A domain idle state node represents the state parameters that will be used to
-select the state when there are no active components in the domain.
-
-The state node has the following parameters -
-
-- compatible:
- Usage: Required
- Value type: <string>
- Definition: Must be "domain-idle-state".
-
-- entry-latency-us
- Usage: Required
- Value type: <prop-encoded-array>
- Definition: u32 value representing worst case latency in
- microseconds required to enter the idle state.
- The exit-latency-us duration may be guaranteed
- only after entry-latency-us has passed.
-
-- exit-latency-us
- Usage: Required
- Value type: <prop-encoded-array>
- Definition: u32 value representing worst case latency
- in microseconds required to exit the idle state.
-
-- min-residency-us
- Usage: Required
- Value type: <prop-encoded-array>
- Definition: u32 value representing minimum residency duration
- in microseconds after which the idle state will yield
- power benefits after overcoming the overhead in entering
-i the idle state.
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/power/domain-idle-state.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: PM Domain Idle States binding description
+
+maintainers:
+ - Ulf Hansson <ulf.hansson@linaro.org>
+
+description:
+ A domain idle state node represents the state parameters that will be used to
+ select the state when there are no active components in the PM domain.
+
+properties:
+ $nodename:
+ const: domain-idle-states
+
+patternProperties:
+ "^(cpu|cluster|domain)-":
+ type: object
+ description:
+ Each state node represents a domain idle state description.
+
+ properties:
+ compatible:
+ const: domain-idle-state
+
+ entry-latency-us:
+ description:
+ The worst case latency in microseconds required to enter the idle
+ state. Note that, the exit-latency-us duration may be guaranteed only
+ after the entry-latency-us has passed.
+
+ exit-latency-us:
+ description:
+ The worst case latency in microseconds required to exit the idle
+ state.
+
+ min-residency-us:
+ description:
+ The minimum residency duration in microseconds after which the idle
+ state will yield power benefits, after overcoming the overhead while
+ entering the idle state.
+
+ required:
+ - compatible
+ - entry-latency-us
+ - exit-latency-us
+ - min-residency-us
+
+examples:
+ - |
+
+ domain-idle-states {
+ domain_retention: domain-retention {
+ compatible = "domain-idle-state";
+ entry-latency-us = <20>;
+ exit-latency-us = <40>;
+ min-residency-us = <80>;
+ };
+ };
+...
properties:
$nodename:
- pattern: "^(power-controller|power-domain)(@.*)?$"
+ pattern: "^(power-controller|power-domain)([@-].*)?$"
domain-idle-states:
$ref: /schemas/types.yaml#/definitions/phandle-array
- description:
- A phandle of an idle-state that shall be soaked into a generic domain
- power state. The idle state definitions are compatible with
- domain-idle-state specified in
- Documentation/devicetree/bindings/power/domain-idle-state.txt
- phandles that are not compatible with domain-idle-state will be ignored.
- The domain-idle-state property reflects the idle state of this PM domain
- and not the idle states of the devices or sub-domains in the PM domain.
- Devices and sub-domains have their own idle-states independent
- of the parent domain's idle states. In the absence of this property,
- the domain would be considered as capable of being powered-on
- or powered-off.
+ description: |
+ Phandles of idle states that defines the available states for the
+ power-domain provider. The idle state definitions are compatible with the
+ domain-idle-state bindings, specified in ./domain-idle-state.yaml.
+
+ Note that, the domain-idle-state property reflects the idle states of this
+ PM domain and not the idle states of the devices or sub-domains in the PM
+ domain. Devices and sub-domains have their own idle states independent of
+ the parent domain's idle states. In the absence of this property, the
+ domain would be considered as capable of being powered-on or powered-off.
operating-points-v2:
$ref: /schemas/types.yaml#/definitions/phandle-array
required-opps = <&domain1_opp_1>;
};
-[1]. Documentation/devicetree/bindings/power/domain-idle-state.txt
+[1]. Documentation/devicetree/bindings/power/domain-idle-state.yaml
sub-node is identified using the node's name, with valid values listed for each
of the PMICs below.
-pm8005:
+pm8004:
s2, s5
pm8005:
examples:
- |
- xyzreg: regulator@0 {
+ xyzreg: regulator {
regulator-min-microvolt = <1000000>;
regulator-max-microvolt = <2500000>;
regulator-always-on;
The RCC IP is both a reset and a clock controller.
-Please see Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.txt
+Please see Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
- clock-names: Must contain "sai_ck".
Must also contain "MCLK", if SAI shares a master clock,
with a SAI set as MCLK clock provider.
- - dmas: see Documentation/devicetree/bindings/dma/stm32-dma.txt
+ - dmas: see Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
- dma-names: identifier string for each DMA request line
"tx": if sai sub-block is configured as playback DAI
"rx": if sai sub-block is configured as capture DAI
- clock-names: must contain "kclk"
- interrupts: cpu DAI interrupt line
- dmas: DMA specifiers for audio data DMA and iec control flow DMA
- See STM32 DMA bindings, Documentation/devicetree/bindings/dma/stm32-dma.txt
+ See STM32 DMA bindings, Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
- dma-names: two dmas have to be defined, "rx" and "rx-ctrl"
Optional properties:
dmas:
description: |
DMA specifiers for tx and rx dma. DMA fifo mode must be used. See
- the STM32 DMA bindings Documentation/devicetree/bindings/dma/stm32-dma.txt.
+ the STM32 DMA bindings Documentation/devicetree/bindings/dma/st,stm32-dma.yaml.
items:
- description: rx DMA channel
- description: tx DMA channel
#size-cells = <1>;
ranges;
- sram_a: sram@00000000 {
+ sram_a: sram@0 {
compatible = "mmio-sram";
reg = <0x00000000 0xc000>;
#address-cells = <1>;
"brcm,bcm2711-avs-monitor", "syscon", "simple-mfd"
Refer to the the bindings described in
- Documentation/devicetree/bindings/mfd/syscon.txt
+ Documentation/devicetree/bindings/mfd/syscon.yaml
properties:
compatible:
examples:
- |
- timer {
+ timer@1c20c00 {
compatible = "allwinner,sun4i-a10-timer";
reg = <0x01c20c00 0x400>;
interrupts = <22>,
Note that callbacks will always be invoked from the DMA
engines tasklet, never from interrupt context.
-Optional: per descriptor metadata
----------------------------------
+ **Optional: per descriptor metadata**
+
DMAengine provides two ways for metadata support.
DESC_METADATA_CLIENT
DESC_METADATA_CLIENT
- DMA_MEM_TO_DEV / DEV_MEM_TO_MEM:
+
1. prepare the descriptor (dmaengine_prep_*)
construct the metadata in the client's buffer
2. use dmaengine_desc_attach_metadata() to attach the buffer to the
descriptor
3. submit the transfer
+
- DMA_DEV_TO_MEM:
+
1. prepare the descriptor (dmaengine_prep_*)
2. use dmaengine_desc_attach_metadata() to attach the buffer to the
descriptor
DESC_METADATA_ENGINE
- DMA_MEM_TO_DEV / DEV_MEM_TO_MEM:
+
1. prepare the descriptor (dmaengine_prep_*)
2. use dmaengine_desc_get_metadata_ptr() to get the pointer to the
engine's metadata area
4. use dmaengine_desc_set_metadata_len() to tell the DMA engine the
amount of data the client has placed into the metadata buffer
5. submit the transfer
+
- DMA_DEV_TO_MEM:
+
1. prepare the descriptor (dmaengine_prep_*)
2. submit the transfer
3. on transfer completion, use dmaengine_desc_get_metadata_ptr() to get
void dma_async_issue_pending(struct dma_chan *chan);
-Further APIs:
--------------
+Further APIs
+------------
1. Terminate APIs
-----------
This driver does not auto-detect devices. You will have to instantiate the
-devices explicitly. Please see Documentation/i2c/instantiating-devices for
-details.
+devices explicitly. Please see :doc:`/i2c/instantiating-devices` for details.
Sysfs entries
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
parallel="-j$parallel"
fi
-exec "$sphinx" "$parallel" "$@"
+exec "$sphinx" $parallel "$@"
tlb
mtrr
pat
- intel_mpx
intel-iommu
intel_txt
amd-memory-encryption
M: Yangtao Li <tiny.windzz@gmail.com>
L: linux-pm@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt
+F: Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml
F: drivers/cpufreq/sun50i-cpufreq-nvmem.c
ALLWINNER CRYPTO DRIVERS
S: Maintained
R: Enric Balletbo i Serra <enric.balletbo@collabora.com>
R: Guenter Roeck <groeck@chromium.org>
-F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt
+F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml
F: sound/soc/codecs/cros_ec_codec.*
CIRRUS LOGIC AUDIO CODEC DRIVERS
T: git git://linuxtv.org/media_tree.git
S: Maintained
F: drivers/media/platform/sunxi/sun6i-csi/
-F: Documentation/devicetree/bindings/media/sun6i-csi.txt
+F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml
CW1200 WLAN driver
M: Solomon Peachy <pizza@shaftnet.org>
T: git git://anongit.freedesktop.org/drm/drm-misc
S: Maintained
F: drivers/gpu/drm/stm
-F: Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
+F: Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml
DRM DRIVERS FOR TI LCDC
M: Jyri Sarha <jsarha@ti.com>
M: "K. Y. Srinivasan" <kys@microsoft.com>
M: Haiyang Zhang <haiyangz@microsoft.com>
M: Stephen Hemminger <sthemmin@microsoft.com>
-M: Sasha Levin <sashal@kernel.org>
+M: Wei Liu <wei.liu@kernel.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
L: linux-hyperv@vger.kernel.org
S: Supported
M: Andreas Klinger <ak@it-klinger.de>
L: linux-iio@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.txt
+F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.yaml
F: drivers/iio/proximity/mb1232.c
MAXIM MAX77650 PMIC MFD DRIVER
L: linux-media@vger.kernel.org
T: git git://linuxtv.org/media_tree.git
S: Supported
-F: Documentation/devicetree/bindings/media/st,stm32-dcmi.txt
+F: Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml
F: drivers/media/platform/stm32/stm32-dcmi.c
MEDIA DRIVERS FOR NVIDIA TEGRA - VDE
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>
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
-F: Documentation/devicetree/bindings/pci/pci-thunder-*
F: drivers/pci/controller/pci-thunder-*
PCIE DRIVER FOR HISILICON
F: drivers/pwm/pwm-stm32*
F: include/linux/*/stm32-*tim*
F: Documentation/ABI/testing/*timer-stm32
-F: Documentation/devicetree/bindings/*/stm32-*timer*
+F: Documentation/devicetree/bindings/*/*stm32-*timer*
F: Documentation/devicetree/bindings/pwm/pwm-stm32*
STMMAC ETHERNET DRIVER
VERSION = 5
PATCHLEVEL = 6
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+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
config HAVE_RELIABLE_STACKTRACE
bool
help
- Architecture has a save_stack_trace_tsk_reliable() function which
- only returns a stack trace if it can guarantee the trace is reliable.
+ Architecture has either save_stack_trace_tsk_reliable() or
+ arch_stack_walk_reliable() function which only returns a stack trace
+ if it can guarantee the trace is reliable.
config HAVE_ARCH_HASH
bool
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
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();
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);
}
CONFIG_CAVIUM_ERRATUM_27456));
}
-static int asids_init(void)
+static int asids_update_limit(void)
{
- asid_bits = get_cpu_asid_bits();
+ unsigned long num_available_asids = NUM_USER_ASIDS;
+
+ if (arm64_kernel_unmapped_at_el0())
+ num_available_asids /= 2;
/*
* Expect allocation after rollover to fail if we don't have at least
* one more ASID than CPUs. ASID #0 is reserved for init_mm.
*/
- WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
+ WARN_ON(num_available_asids - 1 <= num_possible_cpus());
+ pr_info("ASID allocator initialised with %lu entries\n",
+ num_available_asids);
+ return 0;
+}
+arch_initcall(asids_update_limit);
+
+static int asids_init(void)
+{
+ asid_bits = get_cpu_asid_bits();
atomic64_set(&asid_generation, ASID_FIRST_VERSION);
asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map),
GFP_KERNEL);
*/
if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0))
set_kpti_asid_bits();
-
- pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
return 0;
}
early_initcall(asids_init);
* oprofile_cpu_type already has a value, then we are
* possibly overriding a real PVR with a logical one,
* and, in that case, keep the current value for
- * oprofile_cpu_type.
+ * oprofile_cpu_type. Futhermore, let's ensure that the
+ * fix for the PMAO bug is enabled on compatibility mode.
*/
if (old.oprofile_cpu_type != NULL) {
t->oprofile_cpu_type = old.oprofile_cpu_type;
t->oprofile_type = old.oprofile_type;
+ t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
}
}
}
info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
- if (!dar_within_range(regs->dar, info))
- info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
-
- if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info))
- goto out;
+ if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ if (!dar_within_range(regs->dar, info))
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ } else {
+ if (!stepping_handler(regs, bp, info))
+ goto out;
+ }
/*
* As a policy, the callback is invoked in a 'trigger-after-execute'
*(.branch_lt)
}
+#ifdef CONFIG_DEBUG_INFO_BTF
+ .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) {
+ *(.BTF)
+ }
+#endif
+
.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
__start_opd = .;
KEEP(*(.opd))
*/
if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
mb(); /* sync */
+ allow_read_from_user((const void __user *)addr, L1_CACHE_BYTES);
icbi((void *)addr);
+ prevent_read_from_user((const void __user *)addr, L1_CACHE_BYTES);
mb(); /* sync */
isync();
return true;
config ARCH_SPARSEMEM_ENABLE
def_bool y
+ depends on MMU
select SPARSEMEM_VMEMMAP_ENABLE
config ARCH_SELECT_MEMORY_MODEL
help
This enables support for SiFive SoC platform hardware.
+config SOC_VIRT
+ bool "QEMU Virt Machine"
+ select VIRTIO_PCI
+ select VIRTIO_BALLOON
+ select VIRTIO_MMIO
+ select VIRTIO_CONSOLE
+ select VIRTIO_NET
+ select NET_9P_VIRTIO
+ select VIRTIO_BLK
+ select SCSI_VIRTIO
+ select DRM_VIRTIO_GPU
+ select HW_RANDOM_VIRTIO
+ select RPMSG_CHAR
+ select RPMSG_VIRTIO
+ select CRYPTO_DEV_VIRTIO
+ select VIRTIO_INPUT
+ select POWER_RESET_SYSCON
+ select POWER_RESET_SYSCON_POWEROFF
+ select GOLDFISH
+ select RTC_DRV_GOLDFISH
+ select SIFIVE_PLIC
+ help
+ This enables support for QEMU Virt Machine.
+
endmenu
ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
LDFLAGS_vmlinux := --no-relax
endif
-KBUILD_AFLAGS_MODULE += -fPIC
-KBUILD_CFLAGS_MODULE += -fPIC
+
+ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy)
+KBUILD_CFLAGS_MODULE += -mcmodel=medany
+endif
export BITS
ifeq ($(CONFIG_ARCH_RV64I),y)
/* Copyright (c) 2018-2019 SiFive, Inc */
#include "fu540-c000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
/* Clock frequency (in Hz) of the PCB crystal for rtcclk */
#define RTCCLK_FREQ 1000000
clock-frequency = <RTCCLK_FREQ>;
clock-output-names = "rtcclk";
};
+ gpio-restart {
+ compatible = "gpio-restart";
+ gpios = <&gpio 10 GPIO_ACTIVE_LOW>;
+ };
};
&uart0 {
CONFIG_EXPERT=y
CONFIG_BPF_SYSCALL=y
CONFIG_SOC_SIFIVE=y
+CONFIG_SOC_VIRT=y
CONFIG_SMP=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_IP_PNP_RARP=y
CONFIG_NETLINK_DIAG=y
CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
CONFIG_PCI=y
CONFIG_PCIEPORTBUS=y
CONFIG_PCI_HOST_GENERIC=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_BLK_DEV_LOOP=y
-CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_VIRTIO=y
CONFIG_ATA=y
CONFIG_SATA_AHCI=y
CONFIG_SATA_AHCI_PLATFORM=y
CONFIG_NETDEVICES=y
-CONFIG_VIRTIO_NET=y
CONFIG_MACB=y
CONFIG_E1000E=y
CONFIG_R8169=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_HVC_RISCV_SBI=y
-CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_VIRTIO=y
CONFIG_SPI=y
CONFIG_SPI_SIFIVE=y
# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_POWER_RESET=y
CONFIG_DRM=y
CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_USB=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_UAS=y
CONFIG_MMC=y
CONFIG_MMC_SPI=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_RPMSG_CHAR=y
-CONFIG_RPMSG_VIRTIO=y
+CONFIG_RTC_CLASS=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_AUTOFS4_FS=y
CONFIG_ROOT_NFS=y
CONFIG_9P_FS=y
CONFIG_CRYPTO_USER_API_HASH=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_PAGEALLOC=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
CONFIG_BPF_SYSCALL=y
+CONFIG_SOC_VIRT=y
CONFIG_ARCH_RV32I=y
CONFIG_SMP=y
CONFIG_MODULES=y
CONFIG_IP_PNP_RARP=y
CONFIG_NETLINK_DIAG=y
CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
CONFIG_PCI=y
CONFIG_PCIEPORTBUS=y
CONFIG_PCI_HOST_GENERIC=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_BLK_DEV_LOOP=y
-CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_VIRTIO=y
CONFIG_ATA=y
CONFIG_SATA_AHCI=y
CONFIG_SATA_AHCI_PLATFORM=y
CONFIG_NETDEVICES=y
-CONFIG_VIRTIO_NET=y
CONFIG_MACB=y
CONFIG_E1000E=y
CONFIG_R8169=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_HVC_RISCV_SBI=y
-CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_VIRTIO=y
# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_POWER_RESET=y
CONFIG_DRM=y
CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_USB=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_STORAGE=y
CONFIG_USB_UAS=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_RPMSG_CHAR=y
-CONFIG_RPMSG_VIRTIO=y
-CONFIG_SIFIVE_PLIC=y
+CONFIG_RTC_CLASS=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_AUTOFS4_FS=y
CONFIG_ROOT_NFS=y
CONFIG_9P_FS=y
CONFIG_CRYPTO_USER_API_HASH=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_PAGEALLOC=y
return regs->a7;
}
-static inline void syscall_set_nr(struct task_struct *task,
- struct pt_regs *regs,
- int sysno)
-{
- regs->a7 = sysno;
-}
-
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
/* Check to make sure we don't jump to a bogus syscall number. */
li t0, __NR_syscalls
la s0, sys_ni_syscall
- /*
- * The tracer can change syscall number to valid/invalid value.
- * We use syscall_set_nr helper in syscall_trace_enter thus we
- * cannot trust the current value in a7 and have to reload from
- * the current task pt_regs.
- */
- REG_L a7, PT_A7(sp)
/*
* Syscall number held in a7.
* If syscall number is above allowed value, redirect to ni_syscall.
*/
bge a7, t0, 1f
/*
- * Check if syscall is rejected by tracer or seccomp, i.e., a7 == -1.
+ * Check if syscall is rejected by tracer, i.e., a7 == -1.
* If yes, we pretend it was executed.
*/
li t1, -1
handle_syscall_trace_enter:
move a0, sp
call do_syscall_trace_enter
+ move t0, a0
REG_L a0, PT_A0(sp)
REG_L a1, PT_A1(sp)
REG_L a2, PT_A2(sp)
REG_L a5, PT_A5(sp)
REG_L a6, PT_A6(sp)
REG_L a7, PT_A7(sp)
+ bnez t0, ret_from_syscall_rejected
j check_syscall_nr
handle_syscall_trace_exit:
move a0, sp
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/moduleloader.h>
+#include <linux/vmalloc.h>
+#include <linux/sizes.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
{
return 0;
}
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+#define VMALLOC_MODULE_START \
+ max(PFN_ALIGN((unsigned long)&_end - SZ_2G), VMALLOC_START)
+void *module_alloc(unsigned long size)
+{
+ return __vmalloc_node_range(size, 1, VMALLOC_MODULE_START,
+ VMALLOC_END, GFP_KERNEL,
+ PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+ __builtin_return_address(0));
+}
+#endif
* Allows PTRACE_SYSCALL to work. These are called from entry.S in
* {handle,ret_from}_syscall.
*/
-__visible void do_syscall_trace_enter(struct pt_regs *regs)
+__visible int do_syscall_trace_enter(struct pt_regs *regs)
{
if (test_thread_flag(TIF_SYSCALL_TRACE))
if (tracehook_report_syscall_entry(regs))
- syscall_set_nr(current, regs, -1);
+ return -1;
/*
* Do the secure computing after ptrace; failures should be fast.
* If this fails we might have return value in a0 from seccomp
* (via SECCOMP_RET_ERRNO/TRACE).
*/
- if (secure_computing() == -1) {
- syscall_set_nr(current, regs, -1);
- return;
- }
+ if (secure_computing() == -1)
+ return -1;
#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
#endif
audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
+ return 0;
}
__visible void do_syscall_trace_exit(struct pt_regs *regs)
for_each_memblock(memory, reg) {
phys_addr_t end = reg->base + reg->size;
- if (reg->base <= vmlinux_end && vmlinux_end <= end) {
+ if (reg->base <= vmlinux_start && vmlinux_end <= end) {
mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
/*
return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
static inline int pmd_dirty(pmd_t pmd)
{
return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
if (zpci_use_mio(zdev))
pdev->resource[i].start =
- (resource_size_t __force) zdev->bars[i].mio_wb;
+ (resource_size_t __force) zdev->bars[i].mio_wt;
else
pdev->resource[i].start = (resource_size_t __force)
pci_iomap_range_fh(pdev, i, 0, 0);
flags |= IORESOURCE_MEM_64;
if (zpci_use_mio(zdev))
- addr = (unsigned long) zdev->bars[i].mio_wb;
+ addr = (unsigned long) zdev->bars[i].mio_wt;
else
addr = ZPCI_ADDR(entry);
size = 1UL << zdev->bars[i].size;
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) { }
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 */
* 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
}
}
+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;
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-y += -Werror
+ccflags-$(CONFIG_KVM_WERROR) += -Werror
KVM := ../../../virt/kvm
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 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);
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);
else
intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+ /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */
return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
}
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... */
default:
break;
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)
{
}
.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 */
*/
entity = &bfqg->entity;
for_each_entity(entity) {
- bfqg = container_of(entity, struct bfq_group, entity);
- if (bfqg != bfqd->root_group) {
- parent = bfqg_parent(bfqg);
+ struct bfq_group *curr_bfqg = container_of(entity,
+ struct bfq_group, entity);
+ if (curr_bfqg != bfqd->root_group) {
+ parent = bfqg_parent(curr_bfqg);
if (!parent)
parent = bfqd->root_group;
- bfq_group_set_parent(bfqg, parent);
+ bfq_group_set_parent(curr_bfqg, parent);
}
}
}
EXPORT_SYMBOL(kblockd_schedule_work);
-int kblockd_schedule_work_on(int cpu, struct work_struct *work)
-{
- return queue_work_on(cpu, kblockd_workqueue, work);
-}
-EXPORT_SYMBOL(kblockd_schedule_work_on);
-
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
unsigned long delay)
{
*/
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) {
}
#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);
{
struct swnode *swnode = kobj_to_swnode(kobj);
+ if (swnode->parent) {
+ ida_simple_remove(&swnode->parent->child_ids, swnode->id);
+ list_del(&swnode->entry);
+ } else {
+ ida_simple_remove(&swnode_root_ids, swnode->id);
+ }
+
if (swnode->allocated) {
property_entries_free(swnode->node->properties);
kfree(swnode->node);
if (!swnode)
return;
- if (swnode->parent) {
- ida_simple_remove(&swnode->parent->child_ids, swnode->id);
- list_del(&swnode->entry);
- } else {
- ida_simple_remove(&swnode_root_ids, swnode->id);
- }
-
kobject_put(&swnode->kobj);
}
EXPORT_SYMBOL_GPL(fwnode_remove_software_node);
#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,
};
struct blk_mq_tag_set tag_set;
struct blkfront_ring_info *rinfo;
unsigned int nr_rings;
+ unsigned int rinfo_size;
/* Save uncomplete reqs and bios for migration. */
struct list_head requests;
struct bio_list bio_list;
static void blkfront_gather_backend_features(struct blkfront_info *info);
static int negotiate_mq(struct blkfront_info *info);
+#define for_each_rinfo(info, ptr, idx) \
+ for ((ptr) = (info)->rinfo, (idx) = 0; \
+ (idx) < (info)->nr_rings; \
+ (idx)++, (ptr) = (void *)(ptr) + (info)->rinfo_size)
+
+static inline struct blkfront_ring_info *
+get_rinfo(const struct blkfront_info *info, unsigned int i)
+{
+ BUG_ON(i >= info->nr_rings);
+ return (void *)info->rinfo + i * info->rinfo_size;
+}
+
static int get_id_from_freelist(struct blkfront_ring_info *rinfo)
{
unsigned long free = rinfo->shadow_free;
struct blkfront_info *info = hctx->queue->queuedata;
struct blkfront_ring_info *rinfo = NULL;
- BUG_ON(info->nr_rings <= qid);
- rinfo = &info->rinfo[qid];
+ rinfo = get_rinfo(info, qid);
blk_mq_start_request(qd->rq);
spin_lock_irqsave(&rinfo->ring_lock, flags);
if (RING_FULL(&rinfo->ring))
static void xlvbd_release_gendisk(struct blkfront_info *info)
{
unsigned int minor, nr_minors, i;
+ struct blkfront_ring_info *rinfo;
if (info->rq == NULL)
return;
/* No more blkif_request(). */
blk_mq_stop_hw_queues(info->rq);
- for (i = 0; i < info->nr_rings; i++) {
- struct blkfront_ring_info *rinfo = &info->rinfo[i];
-
+ for_each_rinfo(info, rinfo, i) {
/* No more gnttab callback work. */
gnttab_cancel_free_callback(&rinfo->callback);
static void blkif_free(struct blkfront_info *info, int suspend)
{
unsigned int i;
+ struct blkfront_ring_info *rinfo;
/* Prevent new requests being issued until we fix things up. */
info->connected = suspend ?
if (info->rq)
blk_mq_stop_hw_queues(info->rq);
- for (i = 0; i < info->nr_rings; i++)
- blkif_free_ring(&info->rinfo[i]);
+ for_each_rinfo(info, rinfo, i)
+ blkif_free_ring(rinfo);
kvfree(info->rinfo);
info->rinfo = NULL;
int err;
unsigned int i, max_page_order;
unsigned int ring_page_order;
+ struct blkfront_ring_info *rinfo;
if (!info)
return -ENODEV;
if (err)
goto destroy_blkring;
- for (i = 0; i < info->nr_rings; i++) {
- struct blkfront_ring_info *rinfo = &info->rinfo[i];
-
+ for_each_rinfo(info, rinfo, i) {
/* Create shared ring, alloc event channel. */
err = setup_blkring(dev, rinfo);
if (err)
/* We already got the number of queues/rings in _probe */
if (info->nr_rings == 1) {
- err = write_per_ring_nodes(xbt, &info->rinfo[0], dev->nodename);
+ err = write_per_ring_nodes(xbt, info->rinfo, dev->nodename);
if (err)
goto destroy_blkring;
} else {
goto abort_transaction;
}
- for (i = 0; i < info->nr_rings; i++) {
+ for_each_rinfo(info, rinfo, i) {
memset(path, 0, pathsize);
snprintf(path, pathsize, "%s/queue-%u", dev->nodename, i);
- err = write_per_ring_nodes(xbt, &info->rinfo[i], path);
+ err = write_per_ring_nodes(xbt, rinfo, path);
if (err) {
kfree(path);
goto destroy_blkring;
goto destroy_blkring;
}
- for (i = 0; i < info->nr_rings; i++) {
+ for_each_rinfo(info, rinfo, i) {
unsigned int j;
- struct blkfront_ring_info *rinfo = &info->rinfo[i];
for (j = 0; j < BLK_RING_SIZE(info); j++)
rinfo->shadow[j].req.u.rw.id = j + 1;
{
unsigned int backend_max_queues;
unsigned int i;
+ struct blkfront_ring_info *rinfo;
BUG_ON(info->nr_rings);
if (!info->nr_rings)
info->nr_rings = 1;
- info->rinfo = kvcalloc(info->nr_rings,
- struct_size(info->rinfo, shadow,
- BLK_RING_SIZE(info)),
- GFP_KERNEL);
+ info->rinfo_size = struct_size(info->rinfo, shadow,
+ BLK_RING_SIZE(info));
+ info->rinfo = kvcalloc(info->nr_rings, info->rinfo_size, GFP_KERNEL);
if (!info->rinfo) {
xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure");
info->nr_rings = 0;
return -ENOMEM;
}
- for (i = 0; i < info->nr_rings; i++) {
- struct blkfront_ring_info *rinfo;
-
- rinfo = &info->rinfo[i];
+ for_each_rinfo(info, rinfo, i) {
INIT_LIST_HEAD(&rinfo->indirect_pages);
INIT_LIST_HEAD(&rinfo->grants);
rinfo->dev_info = info;
int rc;
struct bio *bio;
unsigned int segs;
+ struct blkfront_ring_info *rinfo;
blkfront_gather_backend_features(info);
/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
- for (r_index = 0; r_index < info->nr_rings; r_index++) {
- struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
-
+ for_each_rinfo(info, rinfo, r_index) {
rc = blkfront_setup_indirect(rinfo);
if (rc)
return rc;
/* Now safe for us to use the shared ring */
info->connected = BLKIF_STATE_CONNECTED;
- for (r_index = 0; r_index < info->nr_rings; r_index++) {
- struct blkfront_ring_info *rinfo;
-
- rinfo = &info->rinfo[r_index];
+ for_each_rinfo(info, rinfo, r_index) {
/* Kick any other new requests queued since we resumed */
kick_pending_request_queues(rinfo);
}
struct blkfront_info *info = dev_get_drvdata(&dev->dev);
int err = 0;
unsigned int i, j;
+ struct blkfront_ring_info *rinfo;
dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
bio_list_init(&info->bio_list);
INIT_LIST_HEAD(&info->requests);
- for (i = 0; i < info->nr_rings; i++) {
- struct blkfront_ring_info *rinfo = &info->rinfo[i];
+ for_each_rinfo(info, rinfo, i) {
struct bio_list merge_bio;
struct blk_shadow *shadow = rinfo->shadow;
unsigned int binfo;
char *envp[] = { "RESIZE=1", NULL };
int err, i;
+ struct blkfront_ring_info *rinfo;
switch (info->connected) {
case BLKIF_STATE_CONNECTED:
"physical-sector-size",
sector_size);
blkfront_gather_backend_features(info);
- for (i = 0; i < info->nr_rings; i++) {
- err = blkfront_setup_indirect(&info->rinfo[i]);
+ for_each_rinfo(info, rinfo, i) {
+ err = blkfront_setup_indirect(rinfo);
if (err) {
xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
info->xbdev->otherend);
/* Kick pending requests. */
info->connected = BLKIF_STATE_CONNECTED;
- for (i = 0; i < info->nr_rings; i++)
- kick_pending_request_queues(&info->rinfo[i]);
+ for_each_rinfo(info, rinfo, i)
+ kick_pending_request_queues(rinfo);
device_add_disk(&info->xbdev->dev, info->gd, NULL);
{
unsigned int i;
unsigned long flags;
+ struct blkfront_ring_info *rinfo;
- for (i = 0; i < info->nr_rings; i++) {
- struct blkfront_ring_info *rinfo = &info->rinfo[i];
+ for_each_rinfo(info, rinfo, i) {
struct grant *gnt_list_entry, *tmp;
spin_lock_irqsave(&rinfo->ring_lock, flags);
.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
};
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);
{
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);
dma_resv_fini(dmabuf->resv);
module_put(dmabuf->owner);
+ kfree(dmabuf->name);
kfree(dmabuf);
return 0;
}
return;
}
- spin_lock(&cohc->lock);
-
/*
* When we reach this point, at least one queue item
* should have been moved over from cohc->queue to
if (coh901318_queue_start(cohc) == NULL)
cohc->busy = 0;
- spin_unlock(&cohc->lock);
-
/*
* This tasklet will remove items from cohc->active
* and thus terminates them.
minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
if (minor < 0) {
rc = minor;
+ kfree(dev);
goto ida_err;
}
rc = device_register(dev);
if (rc < 0) {
dev_err(&idxd->pdev->dev, "device register failed\n");
- put_device(dev);
goto dev_reg_err;
}
idxd_cdev->minor = minor;
dev_reg_err:
ida_simple_remove(&cdev_ctx->minor_ida, MINOR(dev->devt));
+ put_device(dev);
ida_err:
- kfree(dev);
idxd_cdev->dev = NULL;
return rc;
}
rc = idxd_device_config(idxd);
if (rc < 0) {
spin_unlock_irqrestore(&idxd->dev_lock, flags);
+ module_put(THIS_MODULE);
dev_warn(dev, "Device config failed: %d\n", rc);
return rc;
}
rc = idxd_device_enable(idxd);
if (rc < 0) {
spin_unlock_irqrestore(&idxd->dev_lock, flags);
+ module_put(THIS_MODULE);
dev_warn(dev, "Device enable failed: %d\n", rc);
return rc;
}
rc = idxd_register_dma_device(idxd);
if (rc < 0) {
spin_unlock_irqrestore(&idxd->dev_lock, flags);
+ module_put(THIS_MODULE);
dev_dbg(dev, "Failed to register dmaengine device\n");
return rc;
}
if (val > idxd->max_tokens)
return -EINVAL;
- if (val > idxd->nr_tokens)
+ if (val > idxd->nr_tokens + group->tokens_reserved)
return -EINVAL;
group->tokens_reserved = val;
return sprintf(buf, "%u\n", wq->size);
}
+static int total_claimed_wq_size(struct idxd_device *idxd)
+{
+ int i;
+ int wq_size = 0;
+
+ for (i = 0; i < idxd->max_wqs; i++) {
+ struct idxd_wq *wq = &idxd->wqs[i];
+
+ wq_size += wq->size;
+ }
+
+ return wq_size;
+}
+
static ssize_t wq_size_store(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
if (wq->state != IDXD_WQ_DISABLED)
return -EPERM;
- if (size > idxd->max_wq_size)
+ if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size)
return -EINVAL;
wq->size = size;
return -EPERM;
old_type = wq->type;
- if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL]))
+ if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_NONE]))
+ wq->type = IDXD_WQT_NONE;
+ else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL]))
wq->type = IDXD_WQT_KERNEL;
else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_USER]))
wq->type = IDXD_WQT_USER;
else
- wq->type = IDXD_WQT_NONE;
+ return -EINVAL;
/* If we are changing queue type, clear the name */
if (wq->type != old_type)
sdma_channel_synchronize(chan);
- if (sdmac->event_id0)
+ if (sdmac->event_id0 >= 0)
sdma_event_disable(sdmac, sdmac->event_id0);
if (sdmac->event_id1)
sdma_event_disable(sdmac, sdmac->event_id1);
sdmac->event_id0 = 0;
sdmac->event_id1 = 0;
+ sdmac->context_loaded = false;
sdma_set_channel_priority(sdmac, 0);
memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
/* Set ENBLn earlier to make sure dma request triggered after that */
- if (sdmac->event_id0) {
+ if (sdmac->event_id0 >= 0) {
if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
return -EINVAL;
sdma_event_enable(sdmac, sdmac->event_id0);
/* Do not allocate if desc are waiting for ack */
list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) {
- if (async_tx_test_ack(&dma_desc->txd)) {
+ if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) {
list_del(&dma_desc->node);
spin_unlock_irqrestore(&tdc->lock, flags);
dma_desc->txd.flags = 0;
bool was_busy;
spin_lock_irqsave(&tdc->lock, flags);
- if (list_empty(&tdc->pending_sg_req)) {
- spin_unlock_irqrestore(&tdc->lock, flags);
- return 0;
- }
if (!tdc->busy)
goto skip_dma_stop;
*/
#include <linux/kernel.h>
+#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/dmapool.h>
u32 level_start_idx[];
};
+struct udma_hwdesc {
+ size_t cppi5_desc_size;
+ void *cppi5_desc_vaddr;
+ dma_addr_t cppi5_desc_paddr;
+
+ /* TR descriptor internal pointers */
+ void *tr_req_base;
+ struct cppi5_tr_resp_t *tr_resp_base;
+};
+
+struct udma_rx_flush {
+ struct udma_hwdesc hwdescs[2];
+
+ size_t buffer_size;
+ void *buffer_vaddr;
+ dma_addr_t buffer_paddr;
+};
+
struct udma_dev {
struct dma_device ddev;
struct device *dev;
struct list_head desc_to_purge;
spinlock_t lock;
+ struct udma_rx_flush rx_flush;
+
int tchan_cnt;
int echan_cnt;
int rchan_cnt;
u32 psil_base;
};
-struct udma_hwdesc {
- size_t cppi5_desc_size;
- void *cppi5_desc_vaddr;
- dma_addr_t cppi5_desc_paddr;
-
- /* TR descriptor internal pointers */
- void *tr_req_base;
- struct cppi5_tr_resp_t *tr_resp_base;
-};
-
struct udma_desc {
struct virt_dma_desc vd;
struct udma_tx_drain {
struct delayed_work work;
- unsigned long jiffie;
+ ktime_t tstamp;
u32 residue;
};
{
u32 val, pause_mask;
- switch (uc->desc->dir) {
+ switch (uc->config.dir) {
case DMA_DEV_TO_MEM:
val = udma_rchanrt_read(uc->rchan,
UDMA_RCHAN_RT_PEER_RT_EN_REG);
}
}
+static inline dma_addr_t udma_get_rx_flush_hwdesc_paddr(struct udma_chan *uc)
+{
+ return uc->ud->rx_flush.hwdescs[uc->config.pkt_mode].cppi5_desc_paddr;
+}
+
static int udma_push_to_ring(struct udma_chan *uc, int idx)
{
struct udma_desc *d = uc->desc;
-
struct k3_ring *ring = NULL;
- int ret = -EINVAL;
+ dma_addr_t paddr;
+ int ret;
switch (uc->config.dir) {
case DMA_DEV_TO_MEM:
ring = uc->tchan->t_ring;
break;
default:
- break;
+ return -EINVAL;
}
- if (ring) {
- dma_addr_t desc_addr = udma_curr_cppi5_desc_paddr(d, idx);
+ /* RX flush packet: idx == -1 is only passed in case of DEV_TO_MEM */
+ if (idx == -1) {
+ paddr = udma_get_rx_flush_hwdesc_paddr(uc);
+ } else {
+ paddr = udma_curr_cppi5_desc_paddr(d, idx);
wmb(); /* Ensure that writes are not moved over this point */
udma_sync_for_device(uc, idx);
- ret = k3_ringacc_ring_push(ring, &desc_addr);
- uc->in_ring_cnt++;
}
+ ret = k3_ringacc_ring_push(ring, &paddr);
+ if (!ret)
+ uc->in_ring_cnt++;
+
return ret;
}
+static bool udma_desc_is_rx_flush(struct udma_chan *uc, dma_addr_t addr)
+{
+ if (uc->config.dir != DMA_DEV_TO_MEM)
+ return false;
+
+ if (addr == udma_get_rx_flush_hwdesc_paddr(uc))
+ return true;
+
+ return false;
+}
+
static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr)
{
struct k3_ring *ring = NULL;
if (cppi5_desc_is_tdcm(*addr))
return ret;
+ /* Check for flush descriptor */
+ if (udma_desc_is_rx_flush(uc, *addr))
+ return -ENOENT;
+
d = udma_udma_desc_from_paddr(uc, *addr);
if (d)
switch (uc->config.dir) {
case DMA_DEV_TO_MEM:
+ if (!uc->cyclic && !uc->desc)
+ udma_push_to_ring(uc, -1);
+
udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG,
UDMA_PEER_RT_EN_ENABLE |
UDMA_PEER_RT_EN_TEARDOWN);
peer_bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG);
bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG);
+ /* Transfer is incomplete, store current residue and time stamp */
if (peer_bcnt < bcnt) {
uc->tx_drain.residue = bcnt - peer_bcnt;
- uc->tx_drain.jiffie = jiffies;
+ uc->tx_drain.tstamp = ktime_get();
return false;
}
tx_drain.work.work);
bool desc_done = true;
u32 residue_diff;
- unsigned long jiffie_diff, delay;
+ ktime_t time_diff;
+ unsigned long delay;
+
+ while (1) {
+ if (uc->desc) {
+ /* Get previous residue and time stamp */
+ residue_diff = uc->tx_drain.residue;
+ time_diff = uc->tx_drain.tstamp;
+ /*
+ * Get current residue and time stamp or see if
+ * transfer is complete
+ */
+ desc_done = udma_is_desc_really_done(uc, uc->desc);
+ }
- if (uc->desc) {
- residue_diff = uc->tx_drain.residue;
- jiffie_diff = uc->tx_drain.jiffie;
- desc_done = udma_is_desc_really_done(uc, uc->desc);
- }
-
- if (!desc_done) {
- jiffie_diff = uc->tx_drain.jiffie - jiffie_diff;
- residue_diff -= uc->tx_drain.residue;
- if (residue_diff) {
- /* Try to guess when we should check next time */
- residue_diff /= jiffie_diff;
- delay = uc->tx_drain.residue / residue_diff / 3;
- if (jiffies_to_msecs(delay) < 5)
- delay = 0;
- } else {
- /* No progress, check again in 1 second */
- delay = HZ;
+ if (!desc_done) {
+ /*
+ * Find the time delta and residue delta w.r.t
+ * previous poll
+ */
+ time_diff = ktime_sub(uc->tx_drain.tstamp,
+ time_diff) + 1;
+ residue_diff -= uc->tx_drain.residue;
+ if (residue_diff) {
+ /*
+ * Try to guess when we should check
+ * next time by calculating rate at
+ * which data is being drained at the
+ * peer device
+ */
+ delay = (time_diff / residue_diff) *
+ uc->tx_drain.residue;
+ } else {
+ /* No progress, check again in 1 second */
+ schedule_delayed_work(&uc->tx_drain.work, HZ);
+ break;
+ }
+
+ usleep_range(ktime_to_us(delay),
+ ktime_to_us(delay) + 10);
+ continue;
}
- schedule_delayed_work(&uc->tx_drain.work, delay);
- } else if (uc->desc) {
- struct udma_desc *d = uc->desc;
+ if (uc->desc) {
+ struct udma_desc *d = uc->desc;
- uc->bcnt += d->residue;
- udma_start(uc);
- vchan_cookie_complete(&d->vd);
+ uc->bcnt += d->residue;
+ udma_start(uc);
+ vchan_cookie_complete(&d->vd);
+ break;
+ }
+
+ break;
}
}
goto out;
}
- if (uc->cyclic) {
- /* push the descriptor back to the ring */
- if (d == uc->desc) {
+ if (d == uc->desc) {
+ /* active descriptor */
+ if (uc->cyclic) {
udma_cyclic_packet_elapsed(uc);
vchan_cyclic_callback(&d->vd);
- }
- } else {
- bool desc_done = false;
-
- if (d == uc->desc) {
- desc_done = udma_is_desc_really_done(uc, d);
-
- if (desc_done) {
+ } else {
+ if (udma_is_desc_really_done(uc, d)) {
uc->bcnt += d->residue;
udma_start(uc);
+ vchan_cookie_complete(&d->vd);
} else {
schedule_delayed_work(&uc->tx_drain.work,
0);
}
}
-
- if (desc_done)
- vchan_cookie_complete(&d->vd);
+ } else {
+ /*
+ * terminated descriptor, mark the descriptor as
+ * completed to update the channel's cookie marker
+ */
+ dma_cookie_complete(&d->vd.tx);
}
}
out:
return d;
}
+/**
+ * udma_get_tr_counters - calculate TR counters for a given length
+ * @len: Length of the trasnfer
+ * @align_to: Preferred alignment
+ * @tr0_cnt0: First TR icnt0
+ * @tr0_cnt1: First TR icnt1
+ * @tr1_cnt0: Second (if used) TR icnt0
+ *
+ * For len < SZ_64K only one TR is enough, tr1_cnt0 is not updated
+ * For len >= SZ_64K two TRs are used in a simple way:
+ * First TR: SZ_64K-alignment blocks (tr0_cnt0, tr0_cnt1)
+ * Second TR: the remaining length (tr1_cnt0)
+ *
+ * Returns the number of TRs the length needs (1 or 2)
+ * -EINVAL if the length can not be supported
+ */
+static int udma_get_tr_counters(size_t len, unsigned long align_to,
+ u16 *tr0_cnt0, u16 *tr0_cnt1, u16 *tr1_cnt0)
+{
+ if (len < SZ_64K) {
+ *tr0_cnt0 = len;
+ *tr0_cnt1 = 1;
+
+ return 1;
+ }
+
+ if (align_to > 3)
+ align_to = 3;
+
+realign:
+ *tr0_cnt0 = SZ_64K - BIT(align_to);
+ if (len / *tr0_cnt0 >= SZ_64K) {
+ if (align_to) {
+ align_to--;
+ goto realign;
+ }
+ return -EINVAL;
+ }
+
+ *tr0_cnt1 = len / *tr0_cnt0;
+ *tr1_cnt0 = len % *tr0_cnt0;
+
+ return 2;
+}
+
static struct udma_desc *
udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
unsigned int sglen, enum dma_transfer_direction dir,
unsigned long tx_flags, void *context)
{
- enum dma_slave_buswidth dev_width;
struct scatterlist *sgent;
struct udma_desc *d;
- size_t tr_size;
struct cppi5_tr_type1_t *tr_req = NULL;
+ u16 tr0_cnt0, tr0_cnt1, tr1_cnt0;
unsigned int i;
- u32 burst;
+ size_t tr_size;
+ int num_tr = 0;
+ int tr_idx = 0;
- if (dir == DMA_DEV_TO_MEM) {
- dev_width = uc->cfg.src_addr_width;
- burst = uc->cfg.src_maxburst;
- } else if (dir == DMA_MEM_TO_DEV) {
- dev_width = uc->cfg.dst_addr_width;
- burst = uc->cfg.dst_maxburst;
- } else {
- dev_err(uc->ud->dev, "%s: bad direction?\n", __func__);
+ if (!is_slave_direction(dir)) {
+ dev_err(uc->ud->dev, "Only slave cyclic is supported\n");
return NULL;
}
- if (!burst)
- burst = 1;
+ /* estimate the number of TRs we will need */
+ for_each_sg(sgl, sgent, sglen, i) {
+ if (sg_dma_len(sgent) < SZ_64K)
+ num_tr++;
+ else
+ num_tr += 2;
+ }
/* Now allocate and setup the descriptor. */
tr_size = sizeof(struct cppi5_tr_type1_t);
- d = udma_alloc_tr_desc(uc, tr_size, sglen, dir);
+ d = udma_alloc_tr_desc(uc, tr_size, num_tr, dir);
if (!d)
return NULL;
tr_req = d->hwdesc[0].tr_req_base;
for_each_sg(sgl, sgent, sglen, i) {
- d->residue += sg_dma_len(sgent);
+ dma_addr_t sg_addr = sg_dma_address(sgent);
+
+ num_tr = udma_get_tr_counters(sg_dma_len(sgent), __ffs(sg_addr),
+ &tr0_cnt0, &tr0_cnt1, &tr1_cnt0);
+ if (num_tr < 0) {
+ dev_err(uc->ud->dev, "size %u is not supported\n",
+ sg_dma_len(sgent));
+ udma_free_hwdesc(uc, d);
+ kfree(d);
+ return NULL;
+ }
cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false,
CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT);
- tr_req[i].addr = sg_dma_address(sgent);
- tr_req[i].icnt0 = burst * dev_width;
- tr_req[i].dim1 = burst * dev_width;
- tr_req[i].icnt1 = sg_dma_len(sgent) / tr_req[i].icnt0;
+ tr_req[tr_idx].addr = sg_addr;
+ tr_req[tr_idx].icnt0 = tr0_cnt0;
+ tr_req[tr_idx].icnt1 = tr0_cnt1;
+ tr_req[tr_idx].dim1 = tr0_cnt0;
+ tr_idx++;
+
+ if (num_tr == 2) {
+ cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1,
+ false, false,
+ CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+ cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+ CPPI5_TR_CSF_SUPR_EVT);
+
+ tr_req[tr_idx].addr = sg_addr + tr0_cnt1 * tr0_cnt0;
+ tr_req[tr_idx].icnt0 = tr1_cnt0;
+ tr_req[tr_idx].icnt1 = 1;
+ tr_req[tr_idx].dim1 = tr1_cnt0;
+ tr_idx++;
+ }
+
+ d->residue += sg_dma_len(sgent);
}
- cppi5_tr_csf_set(&tr_req[i - 1].flags, CPPI5_TR_CSF_EOP);
+ cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, CPPI5_TR_CSF_EOP);
return d;
}
size_t buf_len, size_t period_len,
enum dma_transfer_direction dir, unsigned long flags)
{
- enum dma_slave_buswidth dev_width;
struct udma_desc *d;
- size_t tr_size;
+ size_t tr_size, period_addr;
struct cppi5_tr_type1_t *tr_req;
- unsigned int i;
unsigned int periods = buf_len / period_len;
- u32 burst;
+ u16 tr0_cnt0, tr0_cnt1, tr1_cnt0;
+ unsigned int i;
+ int num_tr;
- if (dir == DMA_DEV_TO_MEM) {
- dev_width = uc->cfg.src_addr_width;
- burst = uc->cfg.src_maxburst;
- } else if (dir == DMA_MEM_TO_DEV) {
- dev_width = uc->cfg.dst_addr_width;
- burst = uc->cfg.dst_maxburst;
- } else {
- dev_err(uc->ud->dev, "%s: bad direction?\n", __func__);
+ if (!is_slave_direction(dir)) {
+ dev_err(uc->ud->dev, "Only slave cyclic is supported\n");
return NULL;
}
- if (!burst)
- burst = 1;
+ num_tr = udma_get_tr_counters(period_len, __ffs(buf_addr), &tr0_cnt0,
+ &tr0_cnt1, &tr1_cnt0);
+ if (num_tr < 0) {
+ dev_err(uc->ud->dev, "size %zu is not supported\n",
+ period_len);
+ return NULL;
+ }
/* Now allocate and setup the descriptor. */
tr_size = sizeof(struct cppi5_tr_type1_t);
- d = udma_alloc_tr_desc(uc, tr_size, periods, dir);
+ d = udma_alloc_tr_desc(uc, tr_size, periods * num_tr, dir);
if (!d)
return NULL;
tr_req = d->hwdesc[0].tr_req_base;
+ period_addr = buf_addr;
for (i = 0; i < periods; i++) {
- cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false,
- CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+ int tr_idx = i * num_tr;
- tr_req[i].addr = buf_addr + period_len * i;
- tr_req[i].icnt0 = dev_width;
- tr_req[i].icnt1 = period_len / dev_width;
- tr_req[i].dim1 = dev_width;
+ cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false,
+ false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+
+ tr_req[tr_idx].addr = period_addr;
+ tr_req[tr_idx].icnt0 = tr0_cnt0;
+ tr_req[tr_idx].icnt1 = tr0_cnt1;
+ tr_req[tr_idx].dim1 = tr0_cnt0;
+
+ if (num_tr == 2) {
+ cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+ CPPI5_TR_CSF_SUPR_EVT);
+ tr_idx++;
+
+ cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1,
+ false, false,
+ CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+
+ tr_req[tr_idx].addr = period_addr + tr0_cnt1 * tr0_cnt0;
+ tr_req[tr_idx].icnt0 = tr1_cnt0;
+ tr_req[tr_idx].icnt1 = 1;
+ tr_req[tr_idx].dim1 = tr1_cnt0;
+ }
if (!(flags & DMA_PREP_INTERRUPT))
- cppi5_tr_csf_set(&tr_req[i].flags,
+ cppi5_tr_csf_set(&tr_req[tr_idx].flags,
CPPI5_TR_CSF_SUPR_EVT);
+
+ period_addr += period_len;
}
return d;
return NULL;
}
- if (len < SZ_64K) {
- num_tr = 1;
- tr0_cnt0 = len;
- tr0_cnt1 = 1;
- } else {
- unsigned long align_to = __ffs(src | dest);
-
- if (align_to > 3)
- align_to = 3;
- /*
- * Keep simple: tr0: SZ_64K-alignment blocks,
- * tr1: the remaining
- */
- num_tr = 2;
- tr0_cnt0 = (SZ_64K - BIT(align_to));
- if (len / tr0_cnt0 >= SZ_64K) {
- dev_err(uc->ud->dev, "size %zu is not supported\n",
- len);
- return NULL;
- }
-
- tr0_cnt1 = len / tr0_cnt0;
- tr1_cnt0 = len % tr0_cnt0;
+ num_tr = udma_get_tr_counters(len, __ffs(src | dest), &tr0_cnt0,
+ &tr0_cnt1, &tr1_cnt0);
+ if (num_tr < 0) {
+ dev_err(uc->ud->dev, "size %zu is not supported\n",
+ len);
+ return NULL;
}
d = udma_alloc_tr_desc(uc, tr_size, num_tr, DMA_MEM_TO_MEM);
ret = dma_cookie_status(chan, cookie, txstate);
+ if (!udma_is_chan_running(uc))
+ ret = DMA_COMPLETE;
+
if (ret == DMA_IN_PROGRESS && udma_is_chan_paused(uc))
ret = DMA_PAUSED;
{
struct udma_chan *uc = to_udma_chan(chan);
- if (!uc->desc)
- return -EINVAL;
-
/* pause the channel */
- switch (uc->desc->dir) {
+ switch (uc->config.dir) {
case DMA_DEV_TO_MEM:
udma_rchanrt_update_bits(uc->rchan,
UDMA_RCHAN_RT_PEER_RT_EN_REG,
{
struct udma_chan *uc = to_udma_chan(chan);
- if (!uc->desc)
- return -EINVAL;
-
/* resume the channel */
- switch (uc->desc->dir) {
+ switch (uc->config.dir) {
case DMA_DEV_TO_MEM:
udma_rchanrt_update_bits(uc->rchan,
UDMA_RCHAN_RT_PEER_RT_EN_REG,
return ch_count;
}
+static int udma_setup_rx_flush(struct udma_dev *ud)
+{
+ struct udma_rx_flush *rx_flush = &ud->rx_flush;
+ struct cppi5_desc_hdr_t *tr_desc;
+ struct cppi5_tr_type1_t *tr_req;
+ struct cppi5_host_desc_t *desc;
+ struct device *dev = ud->dev;
+ struct udma_hwdesc *hwdesc;
+ size_t tr_size;
+
+ /* Allocate 1K buffer for discarded data on RX channel teardown */
+ rx_flush->buffer_size = SZ_1K;
+ rx_flush->buffer_vaddr = devm_kzalloc(dev, rx_flush->buffer_size,
+ GFP_KERNEL);
+ if (!rx_flush->buffer_vaddr)
+ return -ENOMEM;
+
+ rx_flush->buffer_paddr = dma_map_single(dev, rx_flush->buffer_vaddr,
+ rx_flush->buffer_size,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, rx_flush->buffer_paddr))
+ return -ENOMEM;
+
+ /* Set up descriptor to be used for TR mode */
+ hwdesc = &rx_flush->hwdescs[0];
+ tr_size = sizeof(struct cppi5_tr_type1_t);
+ hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size, 1);
+ hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size,
+ ud->desc_align);
+
+ hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size,
+ GFP_KERNEL);
+ if (!hwdesc->cppi5_desc_vaddr)
+ return -ENOMEM;
+
+ hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr,
+ hwdesc->cppi5_desc_size,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr))
+ return -ENOMEM;
+
+ /* Start of the TR req records */
+ hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size;
+ /* Start address of the TR response array */
+ hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size;
+
+ tr_desc = hwdesc->cppi5_desc_vaddr;
+ cppi5_trdesc_init(tr_desc, 1, tr_size, 0, 0);
+ cppi5_desc_set_pktids(tr_desc, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+ cppi5_desc_set_retpolicy(tr_desc, 0, 0);
+
+ tr_req = hwdesc->tr_req_base;
+ cppi5_tr_init(&tr_req->flags, CPPI5_TR_TYPE1, false, false,
+ CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+ cppi5_tr_csf_set(&tr_req->flags, CPPI5_TR_CSF_SUPR_EVT);
+
+ tr_req->addr = rx_flush->buffer_paddr;
+ tr_req->icnt0 = rx_flush->buffer_size;
+ tr_req->icnt1 = 1;
+
+ /* Set up descriptor to be used for packet mode */
+ hwdesc = &rx_flush->hwdescs[1];
+ hwdesc->cppi5_desc_size = ALIGN(sizeof(struct cppi5_host_desc_t) +
+ CPPI5_INFO0_HDESC_EPIB_SIZE +
+ CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE,
+ ud->desc_align);
+
+ hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size,
+ GFP_KERNEL);
+ if (!hwdesc->cppi5_desc_vaddr)
+ return -ENOMEM;
+
+ hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr,
+ hwdesc->cppi5_desc_size,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr))
+ return -ENOMEM;
+
+ desc = hwdesc->cppi5_desc_vaddr;
+ cppi5_hdesc_init(desc, 0, 0);
+ cppi5_desc_set_pktids(&desc->hdr, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+ cppi5_desc_set_retpolicy(&desc->hdr, 0, 0);
+
+ cppi5_hdesc_attach_buf(desc,
+ rx_flush->buffer_paddr, rx_flush->buffer_size,
+ rx_flush->buffer_paddr, rx_flush->buffer_size);
+
+ dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr,
+ hwdesc->cppi5_desc_size, DMA_TO_DEVICE);
+ return 0;
+}
+
#define TI_UDMAC_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
if (ud->desc_align < dma_get_cache_alignment())
ud->desc_align = dma_get_cache_alignment();
+ ret = udma_setup_rx_flush(ud);
+ if (ret)
+ return ret;
+
for (i = 0; i < ud->tchan_cnt; i++) {
struct udma_tchan *tchan = &ud->tchans[i];
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");
efivar_attr_read(struct efivar_entry *entry, char *buf)
{
struct efi_variable *var = &entry->var;
+ unsigned long size = sizeof(var->Data);
char *str = buf;
+ int ret;
if (!entry || !buf)
return -EINVAL;
- var->DataSize = 1024;
- if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+ ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+ var->DataSize = size;
+ if (ret)
return -EIO;
if (var->Attributes & EFI_VARIABLE_NON_VOLATILE)
efivar_size_read(struct efivar_entry *entry, char *buf)
{
struct efi_variable *var = &entry->var;
+ unsigned long size = sizeof(var->Data);
char *str = buf;
+ int ret;
if (!entry || !buf)
return -EINVAL;
- var->DataSize = 1024;
- if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+ ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+ var->DataSize = size;
+ if (ret)
return -EIO;
str += sprintf(str, "0x%lx\n", var->DataSize);
efivar_data_read(struct efivar_entry *entry, char *buf)
{
struct efi_variable *var = &entry->var;
+ unsigned long size = sizeof(var->Data);
+ int ret;
if (!entry || !buf)
return -EINVAL;
- var->DataSize = 1024;
- if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+ ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+ var->DataSize = size;
+ if (ret)
return -EIO;
memcpy(buf, var->Data, var->DataSize);
u8 *data;
int err;
+ if (!entry || !buf)
+ return -EINVAL;
+
if (in_compat_syscall()) {
struct compat_efi_variable *compat;
{
struct efi_variable *var = &entry->var;
struct compat_efi_variable *compat;
+ unsigned long datasize = sizeof(var->Data);
size_t size;
+ int ret;
if (!entry || !buf)
return 0;
- var->DataSize = 1024;
- if (efivar_entry_get(entry, &entry->var.Attributes,
- &entry->var.DataSize, entry->var.Data))
+ ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data);
+ var->DataSize = datasize;
+ if (ret)
return -EIO;
if (in_compat_syscall()) {
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;
* 1. Primary ring
* 2. Async ring
*/
-#define GFX10_NUM_GFX_RINGS 2
+#define GFX10_NUM_GFX_RINGS_NV1X 1
#define GFX10_MEC_HPD_SIZE 2048
#define F32_CE_PROGRAM_RAM_SIZE 65536
case CHIP_NAVI14:
case CHIP_NAVI12:
adev->gfx.me.num_me = 1;
- adev->gfx.me.num_pipe_per_me = 2;
+ adev->gfx.me.num_pipe_per_me = 1;
adev->gfx.me.num_queue_per_pipe = 1;
adev->gfx.mec.num_mec = 2;
adev->gfx.mec.num_pipe_per_mec = 4;
amdgpu_ring_commit(ring);
/* submit cs packet to copy state 0 to next available state */
- ring = &adev->gfx.gfx_ring[1];
- r = amdgpu_ring_alloc(ring, 2);
- if (r) {
- DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
- return r;
- }
-
- amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
- amdgpu_ring_write(ring, 0);
+ if (adev->gfx.num_gfx_rings > 1) {
+ /* maximum supported gfx ring is 2 */
+ ring = &adev->gfx.gfx_ring[1];
+ r = amdgpu_ring_alloc(ring, 2);
+ if (r) {
+ DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
+ return r;
+ }
- amdgpu_ring_commit(ring);
+ amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
+ amdgpu_ring_write(ring, 0);
+ amdgpu_ring_commit(ring);
+ }
return 0;
}
mutex_unlock(&adev->srbm_mutex);
/* Init gfx ring 1 for pipe 1 */
- mutex_lock(&adev->srbm_mutex);
- gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
- ring = &adev->gfx.gfx_ring[1];
- rb_bufsz = order_base_2(ring->ring_size / 8);
- tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
- tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
- WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
- /* Initialize the ring buffer's write pointers */
- ring->wptr = 0;
- WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
- WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr));
- /* Set the wb address wether it's enabled or not */
- rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
- WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
- WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
- CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
- wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
- WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
- lower_32_bits(wptr_gpu_addr));
- WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
- upper_32_bits(wptr_gpu_addr));
-
- mdelay(1);
- WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
-
- rb_addr = ring->gpu_addr >> 8;
- WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
- WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
- WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
-
- gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
- mutex_unlock(&adev->srbm_mutex);
-
+ if (adev->gfx.num_gfx_rings > 1) {
+ mutex_lock(&adev->srbm_mutex);
+ gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
+ /* maximum supported gfx ring is 2 */
+ ring = &adev->gfx.gfx_ring[1];
+ rb_bufsz = order_base_2(ring->ring_size / 8);
+ tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
+ tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
+ WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+ /* Initialize the ring buffer's write pointers */
+ ring->wptr = 0;
+ WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
+ WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr));
+ /* Set the wb address wether it's enabled or not */
+ rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+ WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
+ WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
+ CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
+ wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+ WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
+ lower_32_bits(wptr_gpu_addr));
+ WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
+ upper_32_bits(wptr_gpu_addr));
+
+ mdelay(1);
+ WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+
+ rb_addr = ring->gpu_addr >> 8;
+ WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
+ WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
+ WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
+
+ gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+ mutex_unlock(&adev->srbm_mutex);
+ }
/* Switch to pipe 0 */
mutex_lock(&adev->srbm_mutex);
gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
/* reset ring buffer */
ring->wptr = 0;
+ atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
amdgpu_ring_clear_ring(ring);
} else {
amdgpu_ring_clear_ring(ring);
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS;
+ adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS_NV1X;
+
adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
gfx_v10_0_set_kiq_pm4_funcs(adev);
/* reset ring buffer */
ring->wptr = 0;
+ atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
amdgpu_ring_clear_ring(ring);
} else {
amdgpu_ring_clear_ring(ring);
}
}
+/**
+ * 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;
drm_kms_helper_hotplug_event(dev);
}
+static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev)
+{
+ struct smu_context *smu = &adev->smu;
+ int ret = 0;
+
+ if (!is_support_sw_smu(adev))
+ return 0;
+
+ /* This interface is for dGPU Navi1x.Linux dc-pplib interface depends
+ * on window driver dc implementation.
+ * For Navi1x, clock settings of dcn watermarks are fixed. the settings
+ * should be passed to smu during boot up and resume from s3.
+ * boot up: dc calculate dcn watermark clock settings within dc_create,
+ * dcn20_resource_construct
+ * then call pplib functions below to pass the settings to smu:
+ * smu_set_watermarks_for_clock_ranges
+ * smu_set_watermarks_table
+ * navi10_set_watermarks_table
+ * smu_write_watermarks_table
+ *
+ * For Renoir, clock settings of dcn watermark are also fixed values.
+ * dc has implemented different flow for window driver:
+ * dc_hardware_init / dc_set_power_state
+ * dcn10_init_hw
+ * notify_wm_ranges
+ * set_wm_ranges
+ * -- Linux
+ * smu_set_watermarks_for_clock_ranges
+ * renoir_set_watermarks_table
+ * smu_write_watermarks_table
+ *
+ * For Linux,
+ * dc_hardware_init -> amdgpu_dm_init
+ * dc_set_power_state --> dm_resume
+ *
+ * therefore, this function apply to navi10/12/14 but not Renoir
+ * *
+ */
+ switch(adev->asic_type) {
+ case CHIP_NAVI10:
+ case CHIP_NAVI14:
+ case CHIP_NAVI12:
+ break;
+ default:
+ return 0;
+ }
+
+ mutex_lock(&smu->mutex);
+
+ /* pass data to smu controller */
+ if ((smu->watermarks_bitmap & WATERMARKS_EXIST) &&
+ !(smu->watermarks_bitmap & WATERMARKS_LOADED)) {
+ ret = smu_write_watermarks_table(smu);
+
+ if (ret) {
+ mutex_unlock(&smu->mutex);
+ DRM_ERROR("Failed to update WMTABLE!\n");
+ return ret;
+ }
+ smu->watermarks_bitmap |= WATERMARKS_LOADED;
+ }
+
+ mutex_unlock(&smu->mutex);
+
+ return 0;
+}
+
/**
* dm_hw_init() - Initialize DC device
* @handle: The base driver device containing the amdgpu_dm device.
amdgpu_dm_irq_resume_late(adev);
+ amdgpu_dm_smu_write_watermarks_table(adev);
+
return 0;
}
aconnector->dc_sink);
dc_sink_release(aconnector->dc_sink);
aconnector->dc_sink = NULL;
+ aconnector->dc_link->cur_link_settings.lane_count = 0;
}
drm_connector_unregister(connector);
hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe);
- swath_bytes_horz_wc = height * blk256_height * bpe;
- swath_bytes_vert_wc = width * blk256_width * bpe;
+ swath_bytes_horz_wc = width * blk256_height * bpe;
+ swath_bytes_vert_wc = height * blk256_width * bpe;
*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
false : /* full 256B request */
#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
{
int ret = 0;
- if (min <= 0 && max <= 0)
+ if (min < 0 && max < 0)
return -EINVAL;
if (!smu_clk_dpm_is_enabled(smu, clk_type))
CLK_MAP(GFXCLK, CLOCK_GFXCLK),
CLK_MAP(SCLK, CLOCK_GFXCLK),
CLK_MAP(SOCCLK, CLOCK_SOCCLK),
- CLK_MAP(UCLK, CLOCK_UMCCLK),
- CLK_MAP(MCLK, CLOCK_UMCCLK),
+ CLK_MAP(UCLK, CLOCK_FCLK),
+ CLK_MAP(MCLK, CLOCK_FCLK),
};
static struct smu_12_0_cmn2aisc_mapping renoir_table_map[SMU_TABLE_COUNT] = {
break;
case SMU_MCLK:
count = NUM_MEMCLK_DPM_LEVELS;
- cur_value = metrics.ClockFrequency[CLOCK_UMCCLK];
+ cur_value = metrics.ClockFrequency[CLOCK_FCLK];
break;
case SMU_DCEFCLK:
count = NUM_DCFCLK_DPM_LEVELS;
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;
{
int ret = 0;
- if (max < min)
- return -EINVAL;
-
switch (clk_type) {
case SMU_GFXCLK:
case SMU_SCLK:
if (err)
return err;
- dpcd[0] = drm_dp_max_link_rate(anx6345->dpcd);
- dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]);
+ dpcd[0] = dp_bw;
err = regmap_write(anx6345->map[I2C_IDX_DPTX],
SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]);
if (err)
if (ret)
goto err_zero_use;
- if (obj->import_attach)
+ if (obj->import_attach) {
shmem->vaddr = dma_buf_vmap(obj->import_attach->dmabuf);
- else
+ } else {
+ pgprot_t prot = PAGE_KERNEL;
+
+ if (!shmem->map_cached)
+ prot = pgprot_writecombine(prot);
shmem->vaddr = vmap(shmem->pages, obj->size >> PAGE_SHIFT,
- VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+ VM_MAP, prot);
+ }
if (!shmem->vaddr) {
DRM_DEBUG_KMS("Failed to vmap pages\n");
}
vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
- vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
- vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+ vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ if (!shmem->map_cached)
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
vma->vm_ops = &drm_gem_shmem_vm_ops;
return 0;
ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies),
dsi->supplies);
if (ret) {
- dev_info(dev, "failed to get regulators: %d\n", ret);
- return -EPROBE_DEFER;
+ if (ret != -EPROBE_DEFER)
+ dev_info(dev, "failed to get regulators: %d\n", ret);
+ return ret;
}
dsi->clks = devm_kcalloc(dev,
dsi->clks[i] = devm_clk_get(dev, clk_names[i]);
if (IS_ERR(dsi->clks[i])) {
if (strcmp(clk_names[i], "sclk_mipi") == 0) {
- strcpy(clk_names[i], OLD_SCLK_MIPI_CLK_NAME);
- i--;
- continue;
+ dsi->clks[i] = devm_clk_get(dev,
+ OLD_SCLK_MIPI_CLK_NAME);
+ if (!IS_ERR(dsi->clks[i]))
+ continue;
}
dev_info(dev, "failed to get the clock: %s\n",
hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en");
- if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) {
+ if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV)
if (IS_ERR(hdata->reg_hdmi_en))
return PTR_ERR(hdata->reg_hdmi_en);
- ret = regulator_enable(hdata->reg_hdmi_en);
- if (ret) {
- DRM_DEV_ERROR(dev,
- "failed to enable hdmi-en regulator\n");
- return ret;
- }
- }
-
return hdmi_bridge_init(hdata);
}
}
}
+ if (!IS_ERR(hdata->reg_hdmi_en)) {
+ ret = regulator_enable(hdata->reg_hdmi_en);
+ if (ret) {
+ DRM_DEV_ERROR(dev,
+ "failed to enable hdmi-en regulator\n");
+ goto err_hdmiphy;
+ }
+ }
+
pm_runtime_enable(dev);
audio_infoframe = &hdata->audio.infoframe;
err_rpm_disable:
pm_runtime_disable(dev);
-
+ if (!IS_ERR(hdata->reg_hdmi_en))
+ regulator_disable(hdata->reg_hdmi_en);
err_hdmiphy:
if (hdata->hdmiphy_port)
put_device(&hdata->hdmiphy_port->dev);
#define VSIZE_OFST 20
#define LDI_INT_EN 0x741C
#define FRAME_END_INT_EN_OFST 1
-#define UNDERFLOW_INT_EN_OFST 2
#define LDI_CTRL 0x7420
#define BPP_OFST 3
#define DATA_GATE_EN BIT(2)
struct clk *media_noc_clk;
struct clk *ade_pix_clk;
struct reset_control *reset;
- struct work_struct display_reset_wq;
bool power_on;
int irq;
*/
ade_update_bits(base + ADE_CTRL, FRM_END_START_OFST,
FRM_END_START_MASK, REG_EFFECTIVE_IN_ADEEN_FRMEND);
- ade_update_bits(base + LDI_INT_EN, UNDERFLOW_INT_EN_OFST, MASK(1), 1);
}
static bool ade_crtc_mode_fixup(struct drm_crtc *crtc,
MASK(1), 0);
}
-static void drm_underflow_wq(struct work_struct *work)
-{
- struct ade_hw_ctx *ctx = container_of(work, struct ade_hw_ctx,
- display_reset_wq);
- struct drm_device *drm_dev = ctx->crtc->dev;
- struct drm_atomic_state *state;
-
- state = drm_atomic_helper_suspend(drm_dev);
- drm_atomic_helper_resume(drm_dev, state);
-}
-
static irqreturn_t ade_irq_handler(int irq, void *data)
{
struct ade_hw_ctx *ctx = data;
MASK(1), 1);
drm_crtc_handle_vblank(crtc);
}
- if (status & BIT(UNDERFLOW_INT_EN_OFST)) {
- ade_update_bits(base + LDI_INT_CLR, UNDERFLOW_INT_EN_OFST,
- MASK(1), 1);
- DRM_ERROR("LDI underflow!");
- schedule_work(&ctx->display_reset_wq);
- }
return IRQ_HANDLED;
}
if (ret)
return ERR_PTR(-EIO);
- INIT_WORK(&ctx->display_reset_wq, drm_underflow_wq);
ctx->crtc = crtc;
return ctx;
$(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)
static void icl_mbus_init(struct drm_i915_private *dev_priv)
{
- u32 val;
+ u32 mask, val;
- val = MBUS_ABOX_BT_CREDIT_POOL1(16) |
- MBUS_ABOX_BT_CREDIT_POOL2(16) |
- MBUS_ABOX_B_CREDIT(1) |
- MBUS_ABOX_BW_CREDIT(1);
+ mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK |
+ MBUS_ABOX_BT_CREDIT_POOL2_MASK |
+ MBUS_ABOX_B_CREDIT_MASK |
+ MBUS_ABOX_BW_CREDIT_MASK;
+ val = I915_READ(MBUS_ABOX_CTL);
+ val &= ~mask;
+ val |= MBUS_ABOX_BT_CREDIT_POOL1(16) |
+ MBUS_ABOX_BT_CREDIT_POOL2(16) |
+ MBUS_ABOX_B_CREDIT(1) |
+ MBUS_ABOX_BW_CREDIT(1);
I915_WRITE(MBUS_ABOX_CTL, val);
}
I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE);
I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE);
} else {
+ u32 val;
+
I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask);
I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask);
+
+ /* Wa_22010178259:tgl */
+ val = I915_READ(BW_BUDDY1_CTL);
+ val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+ val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+ I915_WRITE(BW_BUDDY1_CTL, val);
+
+ val = I915_READ(BW_BUDDY2_CTL);
+ val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+ val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+ I915_WRITE(BW_BUDDY2_CTL, val);
}
}
{
struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
- if (!crtc_state->has_psr)
+ if (!CAN_PSR(dev_priv) || dev_priv->psr.dp != intel_dp)
return;
- if (WARN_ON(!CAN_PSR(dev_priv)))
+ dev_priv->psr.force_mode_changed = false;
+
+ if (!crtc_state->has_psr)
return;
WARN_ON(dev_priv->drrs.dp);
if (!CAN_PSR(dev_priv) || READ_ONCE(psr->dp) != intel_dp)
return;
+ dev_priv->psr.force_mode_changed = false;
+
mutex_lock(&dev_priv->psr.lock);
enable = crtc_state->has_psr && psr_global_enabled(psr->debug);
struct drm_crtc_state *crtc_state;
if (!CAN_PSR(dev_priv) || !new_state->crtc ||
- dev_priv->psr.initially_probed)
+ !dev_priv->psr.force_mode_changed)
return;
intel_connector = to_intel_connector(connector);
crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
new_state->crtc);
crtc_state->mode_changed = true;
- dev_priv->psr.initially_probed = true;
+}
+
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp)
+{
+ struct drm_i915_private *dev_priv;
+
+ if (!intel_dp)
+ return;
+
+ dev_priv = dp_to_i915(intel_dp);
+ if (!CAN_PSR(dev_priv) || intel_dp != dev_priv->psr.dp)
+ return;
+
+ dev_priv->psr.force_mode_changed = true;
}
void intel_psr_atomic_check(struct drm_connector *connector,
struct drm_connector_state *old_state,
struct drm_connector_state *new_state);
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp);
#endif /* __INTEL_PSR_H__ */
/* But keep the pointer alive for RCU-protected lookups */
call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
+ cond_resched();
}
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
}
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);
obj = i915_gem_object_create_internal(i915, size);
if (IS_ERR(obj))
- return PTR_ERR(obj);
+ return false;
mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
i915_gem_object_put(obj);
fence = i915_active_fence_get(&tl->last_request);
if (fence) {
+ mutex_unlock(&tl->mutex);
+
timeout = dma_fence_wait_timeout(fence,
interruptible,
timeout);
dma_fence_put(fence);
+
+ /* Retirement is best effort */
+ if (!mutex_trylock(&tl->mutex)) {
+ active_count++;
+ goto out_active;
+ }
}
}
if (!retire_requests(tl) || flush_submission(gt))
active_count++;
+ mutex_unlock(&tl->mutex);
- spin_lock(&timelines->lock);
+out_active: spin_lock(&timelines->lock);
- /* Resume iteration after dropping lock */
+ /* Resume list iteration after reacquiring spinlock */
list_safe_reset_next(tl, tn, link);
if (atomic_dec_and_test(&tl->active_count))
list_del(&tl->link);
- mutex_unlock(&tl->mutex);
/* Defer the final release to after the spinlock */
if (refcount_dec_and_test(&tl->kref.refcount)) {
static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
struct i915_wa_list *wal)
{
- u32 val;
-
/* Wa_1409142259:tgl */
WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
- /* Wa_1604555607:tgl */
- val = intel_uncore_read(engine->uncore, FF_MODE2);
- val &= ~FF_MODE2_TDS_TIMER_MASK;
- val |= FF_MODE2_TDS_TIMER_128;
/*
- * FIXME: FF_MODE2 register is not readable till TGL B0. We can
- * enable verification of WA from the later steppings, which enables
- * the read of FF_MODE2.
+ * Wa_1604555607:gen12 and Wa_1608008084:gen12
+ * FF_MODE2 register will return the wrong value when read. The default
+ * value for this register is zero for all fields and there are no bit
+ * masks. So instead of doing a RMW we should just write the TDS timer
+ * value for Wa_1604555607.
*/
- wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
- IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
- FF_MODE2_TDS_TIMER_MASK);
+ wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+ FF_MODE2_TDS_TIMER_128, 0);
}
static void
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;
#include "display/intel_hotplug.h"
#include "display/intel_overlay.h"
#include "display/intel_pipe_crc.h"
+#include "display/intel_psr.h"
#include "display/intel_sprite.h"
#include "display/intel_vga.h"
intel_init_ipc(i915);
+ intel_psr_set_force_mode_changed(i915->psr.dp);
+
return 0;
cleanup_gem:
bool dc3co_enabled;
u32 dc3co_exit_delay;
struct delayed_work idle_work;
- bool initially_probed;
+ bool force_mode_changed;
};
#define QUIRK_LVDS_SSC_DISABLE (1<<1)
.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 i915_vma_get(oa_bo->vma);
}
-static int emit_oa_config(struct i915_perf_stream *stream,
- struct i915_oa_config *oa_config,
- struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+ struct i915_oa_config *oa_config,
+ struct intel_context *ce)
{
struct i915_request *rq;
struct i915_vma *vma;
vma = get_oa_vma(stream, oa_config);
if (IS_ERR(vma))
- return PTR_ERR(vma);
+ return ERR_CAST(vma);
err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
if (err)
err = rq->engine->emit_bb_start(rq,
vma->node.start, 0,
I915_DISPATCH_SECURE);
+ if (err)
+ goto err_add_request;
+
+ i915_request_get(rq);
err_add_request:
i915_request_add(rq);
err_vma_unpin:
i915_vma_unpin(vma);
err_vma_put:
i915_vma_put(vma);
- return err;
+ return err ? ERR_PTR(err) : rq;
}
static struct intel_context *oa_context(struct i915_perf_stream *stream)
return stream->pinned_ctx ?: stream->engine->kernel_context;
}
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
{
struct intel_uncore *uncore = stream->uncore;
return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
}
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
{
struct intel_uncore *uncore = stream->uncore;
struct i915_oa_config *oa_config = stream->oa_config;
*/
ret = lrc_configure_all_contexts(stream, oa_config);
if (ret)
- return ret;
+ return ERR_PTR(ret);
return emit_oa_config(stream, oa_config, oa_context(stream));
}
0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
}
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
{
struct intel_uncore *uncore = stream->uncore;
struct i915_oa_config *oa_config = stream->oa_config;
*/
ret = gen12_configure_all_contexts(stream, oa_config);
if (ret)
- return ret;
+ return ERR_PTR(ret);
/*
* For Gen12, performance counters are context
if (stream->ctx) {
ret = gen12_configure_oar_context(stream, true);
if (ret)
- return ret;
+ return ERR_PTR(ret);
}
return emit_oa_config(stream, oa_config, oa_context(stream));
.read = i915_oa_read,
};
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+ struct i915_request *rq;
+
+ rq = stream->perf->ops.enable_metric_set(stream);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+
+ i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+ i915_request_put(rq);
+
+ return 0;
+}
+
/**
* i915_oa_stream_init - validate combined props for OA stream and init
* @stream: An i915 perf stream
stream->ops = &i915_oa_stream_ops;
perf->exclusive_stream = stream;
- ret = perf->ops.enable_metric_set(stream);
+ ret = i915_perf_stream_enable_sync(stream);
if (ret) {
DRM_DEBUG("Unable to enable metric set\n");
goto err_enable;
return -EINVAL;
if (config != stream->oa_config) {
- int err;
+ struct i915_request *rq;
/*
* If OA is bound to a specific context, emit the
* When set globally, we use a low priority kernel context,
* so it will effectively take effect when idle.
*/
- err = emit_oa_config(stream, config, oa_context(stream));
- if (err == 0)
+ rq = emit_oa_config(stream, config, oa_context(stream));
+ if (!IS_ERR(rq)) {
config = xchg(&stream->oa_config, config);
- else
- ret = err;
+ i915_request_put(rq);
+ } else {
+ ret = PTR_ERR(rq);
+ }
}
i915_oa_config_put(config);
* counter reports being sampled. May apply system constraints such as
* disabling EU clock gating as required.
*/
- int (*enable_metric_set)(struct i915_perf_stream *stream);
+ struct i915_request *
+ (*enable_metric_set)(struct i915_perf_stream *stream);
/**
* @disable_metric_set: Remove system constraints associated with using
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.
*/
#define BW_BUDDY1_CTL _MMIO(0x45140)
#define BW_BUDDY2_CTL _MMIO(0x45150)
#define BW_BUDDY_DISABLE REG_BIT(31)
+#define BW_BUDDY_TLB_REQ_TIMER_MASK REG_GENMASK(21, 16)
#define BW_BUDDY1_PAGE_MASK _MMIO(0x45144)
#define BW_BUDDY2_PAGE_MASK _MMIO(0x45154)
spin_unlock_irq(&rq->lock);
remove_from_client(rq);
- list_del(&rq->link);
+ list_del_rcu(&rq->link);
intel_context_exit(rq->context);
intel_context_unpin(rq->context);
rq->infix = rq->ring->emit; /* end of header; start of user payload */
intel_context_mark_active(ce);
+ list_add_tail_rcu(&rq->link, &tl->requests);
+
return rq;
err_unwind:
GEM_BUG_ON(i915_request_timeline(rq) ==
rcu_access_pointer(signal->timeline));
+ if (i915_request_started(signal))
+ return 0;
+
fence = NULL;
rcu_read_lock();
spin_lock_irq(&signal->lock);
- if (!i915_request_started(signal) &&
- !list_is_first(&signal->link,
- &rcu_dereference(signal->timeline)->requests)) {
- struct i915_request *prev = list_prev_entry(signal, link);
+ do {
+ struct list_head *pos = READ_ONCE(signal->link.prev);
+ struct i915_request *prev;
+
+ /* Confirm signal has not been retired, the link is valid */
+ if (unlikely(i915_request_started(signal)))
+ break;
+
+ /* Is signal the earliest request on its timeline? */
+ if (pos == &rcu_dereference(signal->timeline)->requests)
+ break;
/*
* Peek at the request before us in the timeline. That
* after acquiring a reference to it, confirm that it is
* still part of the signaler's timeline.
*/
- if (i915_request_get_rcu(prev)) {
- if (list_next_entry(prev, link) == signal)
- fence = &prev->fence;
- else
- i915_request_put(prev);
+ prev = list_entry(pos, typeof(*prev), link);
+ if (!i915_request_get_rcu(prev))
+ break;
+
+ /* After the strong barrier, confirm prev is still attached */
+ if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+ i915_request_put(prev);
+ break;
}
- }
+
+ fence = &prev->fence;
+ } while (0);
spin_unlock_irq(&signal->lock);
rcu_read_unlock();
if (!fence)
0);
}
- list_add_tail(&rq->link, &timeline->requests);
-
/*
* Make sure that no request gazumped us - if it was allocated after
* our i915_request_alloc() and called __i915_request_add() before
}
#if IS_REACHABLE(CONFIG_MTK_CMDQ)
if (mtk_crtc->cmdq_client) {
+ mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
static int mtk_drm_crtc_init(struct drm_device *drm,
struct mtk_drm_crtc *mtk_crtc,
- struct drm_plane *primary,
- struct drm_plane *cursor, unsigned int pipe)
+ unsigned int pipe)
{
- int ret;
+ struct drm_plane *primary = NULL;
+ struct drm_plane *cursor = NULL;
+ int i, ret;
+
+ for (i = 0; i < mtk_crtc->layer_nr; i++) {
+ if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_PRIMARY)
+ primary = &mtk_crtc->planes[i];
+ else if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_CURSOR)
+ cursor = &mtk_crtc->planes[i];
+ }
ret = drm_crtc_init_with_planes(drm, &mtk_crtc->base, primary, cursor,
&mtk_crtc_funcs, NULL);
}
static inline
-enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx)
+enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx,
+ unsigned int num_planes)
{
if (plane_idx == 0)
return DRM_PLANE_TYPE_PRIMARY;
- else if (plane_idx == 1)
+ else if (plane_idx == (num_planes - 1))
return DRM_PLANE_TYPE_CURSOR;
else
return DRM_PLANE_TYPE_OVERLAY;
ret = mtk_plane_init(drm_dev,
&mtk_crtc->planes[mtk_crtc->layer_nr],
BIT(pipe),
- mtk_drm_crtc_plane_type(mtk_crtc->layer_nr),
+ mtk_drm_crtc_plane_type(mtk_crtc->layer_nr,
+ num_planes),
mtk_ddp_comp_supported_rotations(comp));
if (ret)
return ret;
return ret;
}
- ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0],
- mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] :
- NULL, pipe);
+ ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, pipe);
if (ret < 0)
return ret;
drm_crtc_index(&mtk_crtc->base));
mtk_crtc->cmdq_client = NULL;
}
- ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events",
+ ret = of_property_read_u32_index(priv->mutex_node,
+ "mediatek,gce-events",
drm_crtc_index(&mtk_crtc->base),
&mtk_crtc->cmdq_event);
if (ret)
/* Only DMA capable components need the LARB property */
comp->larb_dev = NULL;
if (type != MTK_DISP_OVL &&
+ type != MTK_DISP_OVL_2L &&
type != MTK_DISP_RDMA &&
type != MTK_DISP_WDMA)
return 0;
struct drm_plane_state *state)
{
struct drm_crtc_state *crtc_state;
+ int ret;
if (plane != state->crtc->cursor)
return -EINVAL;
if (!plane->state->fb)
return -EINVAL;
+ ret = mtk_drm_crtc_plane_check(state->crtc, plane,
+ to_mtk_plane_state(state));
+ if (ret)
+ return ret;
+
if (state->state)
crtc_state = drm_atomic_get_existing_crtc_state(state->state,
state->crtc);
plane->state->src_y = new_state->src_y;
plane->state->src_h = new_state->src_h;
plane->state->src_w = new_state->src_w;
+ swap(plane->state->fb, new_state->fb);
state->pending.async_dirty = true;
mtk_drm_crtc_async_update(new_state->crtc, plane, new_state);
source_id = (fault_status >> 16);
/* Page fault only */
- if ((status & mask) == BIT(i)) {
- WARN_ON(exception_type < 0xC1 || exception_type > 0xC4);
-
+ ret = -1;
+ if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0)
ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
- if (!ret) {
- mmu_write(pfdev, MMU_INT_CLEAR, BIT(i));
- status &= ~mask;
- continue;
- }
- }
- /* terminal fault, print info about the fault */
- dev_err(pfdev->dev,
- "Unhandled Page fault in AS%d at VA 0x%016llX\n"
- "Reason: %s\n"
- "raw fault status: 0x%X\n"
- "decoded fault status: %s\n"
- "exception type 0x%X: %s\n"
- "access type 0x%X: %s\n"
- "source id 0x%X\n",
- i, addr,
- "TODO",
- fault_status,
- (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
- exception_type, panfrost_exception_name(pfdev, exception_type),
- access_type, access_type_name(pfdev, fault_status),
- source_id);
+ if (ret)
+ /* terminal fault, print info about the fault */
+ dev_err(pfdev->dev,
+ "Unhandled Page fault in AS%d at VA 0x%016llX\n"
+ "Reason: %s\n"
+ "raw fault status: 0x%X\n"
+ "decoded fault status: %s\n"
+ "exception type 0x%X: %s\n"
+ "access type 0x%X: %s\n"
+ "source id 0x%X\n",
+ i, addr,
+ "TODO",
+ fault_status,
+ (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
+ exception_type, panfrost_exception_name(pfdev, exception_type),
+ access_type, access_type_name(pfdev, fault_status),
+ source_id);
mmu_write(pfdev, MMU_INT_CLEAR, mask);
#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;
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_XRGB4444,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ARGB4444,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_ABGR4444,
.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_XBGR4444,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_RGBA4444,
.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_RGBX4444,
+ .de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_BGRA4444,
.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_BGRX4444,
+ .de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_ARGB1555,
.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_XRGB1555,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_ABGR1555,
.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_XBGR1555,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_RGBA5551,
.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_RGBX5551,
+ .de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_BGRA5551,
.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
.rgb = true,
.csc = SUN8I_CSC_MODE_OFF,
},
+ {
+ /* for DE2 VI layer which ignores alpha */
+ .drm_fmt = DRM_FORMAT_BGRX5551,
+ .de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
+ {
+ .drm_fmt = DRM_FORMAT_ARGB2101010,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ARGB2101010,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
+ {
+ .drm_fmt = DRM_FORMAT_ABGR2101010,
+ .de2_fmt = SUN8I_MIXER_FBFMT_ABGR2101010,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
+ {
+ .drm_fmt = DRM_FORMAT_RGBA1010102,
+ .de2_fmt = SUN8I_MIXER_FBFMT_RGBA1010102,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
+ {
+ .drm_fmt = DRM_FORMAT_BGRA1010102,
+ .de2_fmt = SUN8I_MIXER_FBFMT_BGRA1010102,
+ .rgb = true,
+ .csc = SUN8I_CSC_MODE_OFF,
+ },
{
.drm_fmt = DRM_FORMAT_UYVY,
.de2_fmt = SUN8I_MIXER_FBFMT_UYVY,
.rgb = false,
.csc = SUN8I_CSC_MODE_YUV2RGB,
},
- {
- .drm_fmt = DRM_FORMAT_YUV444,
- .de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
- .rgb = true,
- .csc = SUN8I_CSC_MODE_YUV2RGB,
- },
{
.drm_fmt = DRM_FORMAT_YUV422,
.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
.rgb = false,
.csc = SUN8I_CSC_MODE_YUV2RGB,
},
- {
- .drm_fmt = DRM_FORMAT_YVU444,
- .de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
- .rgb = true,
- .csc = SUN8I_CSC_MODE_YVU2RGB,
- },
{
.drm_fmt = DRM_FORMAT_YVU422,
.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
.rgb = false,
.csc = SUN8I_CSC_MODE_YVU2RGB,
},
+ {
+ .drm_fmt = DRM_FORMAT_P010,
+ .de2_fmt = SUN8I_MIXER_FBFMT_P010_YUV,
+ .rgb = false,
+ .csc = SUN8I_CSC_MODE_YUV2RGB,
+ },
+ {
+ .drm_fmt = DRM_FORMAT_P210,
+ .de2_fmt = SUN8I_MIXER_FBFMT_P210_YUV,
+ .rgb = false,
+ .csc = SUN8I_CSC_MODE_YUV2RGB,
+ },
};
const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
#define SUN8I_MIXER_FBFMT_ABGR1555 17
#define SUN8I_MIXER_FBFMT_RGBA5551 18
#define SUN8I_MIXER_FBFMT_BGRA5551 19
+#define SUN8I_MIXER_FBFMT_ARGB2101010 20
+#define SUN8I_MIXER_FBFMT_ABGR2101010 21
+#define SUN8I_MIXER_FBFMT_RGBA1010102 22
+#define SUN8I_MIXER_FBFMT_BGRA1010102 23
#define SUN8I_MIXER_FBFMT_YUYV 0
#define SUN8I_MIXER_FBFMT_UYVY 1
/* format 12 is semi-planar YUV411 UVUV */
/* format 13 is semi-planar YUV411 VUVU */
#define SUN8I_MIXER_FBFMT_YUV411 14
+/* format 15 doesn't exist */
+/* format 16 is P010 YVU */
+#define SUN8I_MIXER_FBFMT_P010_YUV 17
+/* format 18 is P210 YVU */
+#define SUN8I_MIXER_FBFMT_P210_YUV 19
+/* format 20 is packed YVU444 10-bit */
+/* format 21 is packed YUV444 10-bit */
/*
* Sub-engines listed bellow are unused for now. The EN registers are here only
};
/*
- * While all RGB formats are supported, VI planes don't support
- * alpha blending, so there is no point having formats with alpha
- * channel if their opaque analog exist.
+ * While DE2 VI layer supports same RGB formats as UI layer, alpha
+ * channel is ignored. This structure lists all unique variants
+ * where alpha channel is replaced with "don't care" (X) channel.
*/
static const u32 sun8i_vi_layer_formats[] = {
+ DRM_FORMAT_BGR565,
+ DRM_FORMAT_BGR888,
+ DRM_FORMAT_BGRX4444,
+ DRM_FORMAT_BGRX5551,
+ DRM_FORMAT_BGRX8888,
+ DRM_FORMAT_RGB565,
+ DRM_FORMAT_RGB888,
+ DRM_FORMAT_RGBX4444,
+ DRM_FORMAT_RGBX5551,
+ DRM_FORMAT_RGBX8888,
+ DRM_FORMAT_XBGR1555,
+ DRM_FORMAT_XBGR4444,
+ DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_XRGB1555,
+ DRM_FORMAT_XRGB4444,
+ DRM_FORMAT_XRGB8888,
+
+ DRM_FORMAT_NV16,
+ DRM_FORMAT_NV12,
+ DRM_FORMAT_NV21,
+ DRM_FORMAT_NV61,
+ DRM_FORMAT_UYVY,
+ DRM_FORMAT_VYUY,
+ DRM_FORMAT_YUYV,
+ DRM_FORMAT_YVYU,
+ DRM_FORMAT_YUV411,
+ DRM_FORMAT_YUV420,
+ DRM_FORMAT_YUV422,
+ DRM_FORMAT_YVU411,
+ DRM_FORMAT_YVU420,
+ DRM_FORMAT_YVU422,
+};
+
+static const u32 sun8i_vi_layer_de3_formats[] = {
DRM_FORMAT_ABGR1555,
+ DRM_FORMAT_ABGR2101010,
DRM_FORMAT_ABGR4444,
+ DRM_FORMAT_ABGR8888,
DRM_FORMAT_ARGB1555,
+ DRM_FORMAT_ARGB2101010,
DRM_FORMAT_ARGB4444,
+ DRM_FORMAT_ARGB8888,
DRM_FORMAT_BGR565,
DRM_FORMAT_BGR888,
+ DRM_FORMAT_BGRA1010102,
DRM_FORMAT_BGRA5551,
DRM_FORMAT_BGRA4444,
+ DRM_FORMAT_BGRA8888,
DRM_FORMAT_BGRX8888,
DRM_FORMAT_RGB565,
DRM_FORMAT_RGB888,
+ DRM_FORMAT_RGBA1010102,
DRM_FORMAT_RGBA4444,
DRM_FORMAT_RGBA5551,
+ DRM_FORMAT_RGBA8888,
DRM_FORMAT_RGBX8888,
DRM_FORMAT_XBGR8888,
DRM_FORMAT_XRGB8888,
DRM_FORMAT_NV12,
DRM_FORMAT_NV21,
DRM_FORMAT_NV61,
+ DRM_FORMAT_P010,
+ DRM_FORMAT_P210,
DRM_FORMAT_UYVY,
DRM_FORMAT_VYUY,
DRM_FORMAT_YUYV,
DRM_FORMAT_YUV411,
DRM_FORMAT_YUV420,
DRM_FORMAT_YUV422,
- DRM_FORMAT_YUV444,
DRM_FORMAT_YVU411,
DRM_FORMAT_YVU420,
DRM_FORMAT_YVU422,
- DRM_FORMAT_YVU444,
};
struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
int index)
{
u32 supported_encodings, supported_ranges;
+ unsigned int plane_cnt, format_count;
struct sun8i_vi_layer *layer;
- unsigned int plane_cnt;
+ const u32 *formats;
int ret;
layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
if (!layer)
return ERR_PTR(-ENOMEM);
+ if (mixer->cfg->is_de3) {
+ formats = sun8i_vi_layer_de3_formats;
+ format_count = ARRAY_SIZE(sun8i_vi_layer_de3_formats);
+ } else {
+ formats = sun8i_vi_layer_formats;
+ format_count = ARRAY_SIZE(sun8i_vi_layer_formats);
+ }
+
/* possible crtcs are set later */
ret = drm_universal_plane_init(drm, &layer->plane, 0,
&sun8i_vi_layer_funcs,
- sun8i_vi_layer_formats,
- ARRAY_SIZE(sun8i_vi_layer_formats),
+ formats, format_count,
NULL, DRM_PLANE_TYPE_OVERLAY, NULL);
if (ret) {
dev_err(drm->dev, "Couldn't initialize layer\n");
fbo->base.base.resv = &fbo->base.base._resv;
dma_resv_init(&fbo->base.base._resv);
+ fbo->base.base.dev = NULL;
ret = dma_resv_trylock(&fbo->base.base._resv);
WARN_ON(!ret);
* "f91a9dd35715 Fix unlinking resources from hash
* table." (Feb 2019) fixes the bug.
*/
- static int handle;
- handle++;
+ static atomic_t seqno = ATOMIC_INIT(0);
+ int handle = atomic_inc_return(&seqno);
*resid = handle + 1;
} else {
int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
return NULL;
bo->base.base.funcs = &virtio_gpu_gem_funcs;
+ bo->base.map_cached = true;
return &bo->base.base;
}
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) {
goto cleanup;
/* The pointer is not NULL when we resume from hibernation */
- if (input_device->hid_desc != NULL)
- kfree(input_device->hid_desc);
+ kfree(input_device->hid_desc);
input_device->hid_desc = kmemdup(desc, desc->bLength, GFP_ATOMIC);
if (!input_device->hid_desc)
}
/* The pointer is not NULL when we resume from hibernation */
- if (input_device->report_desc != NULL)
- kfree(input_device->report_desc);
+ kfree(input_device->report_desc);
input_device->report_desc = kzalloc(input_device->report_desc_size,
GFP_ATOMIC);
{ 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);
return 0x95;
break;
}
- return -ENODEV;
+ return 0;
}
/* Provide labels for sysfs */
#define XDPE122_AMD_625MV 0x10 /* AMD mode 6.25mV */
#define XDPE122_PAGE_NUM 2
+static int xdpe122_read_word_data(struct i2c_client *client, int page, int reg)
+{
+ const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
+ long val;
+ s16 exponent;
+ s32 mantissa;
+ int ret;
+
+ switch (reg) {
+ case PMBUS_VOUT_OV_FAULT_LIMIT:
+ case PMBUS_VOUT_UV_FAULT_LIMIT:
+ ret = pmbus_read_word_data(client, page, reg);
+ if (ret < 0)
+ return ret;
+
+ /* Convert register value to LINEAR11 data. */
+ exponent = ((s16)ret) >> 11;
+ mantissa = ((s16)((ret & GENMASK(10, 0)) << 5)) >> 5;
+ val = mantissa * 1000L;
+ if (exponent >= 0)
+ val <<= exponent;
+ else
+ val >>= -exponent;
+
+ /* Convert data to VID register. */
+ switch (info->vrm_version[page]) {
+ case vr13:
+ if (val >= 500)
+ return 1 + DIV_ROUND_CLOSEST(val - 500, 10);
+ return 0;
+ case vr12:
+ if (val >= 250)
+ return 1 + DIV_ROUND_CLOSEST(val - 250, 5);
+ return 0;
+ case imvp9:
+ if (val >= 200)
+ return 1 + DIV_ROUND_CLOSEST(val - 200, 10);
+ return 0;
+ case amd625mv:
+ if (val >= 200 && val <= 1550)
+ return DIV_ROUND_CLOSEST((1550 - val) * 100,
+ 625);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ default:
+ return -ENODATA;
+ }
+
+ return 0;
+}
+
static int xdpe122_identify(struct i2c_client *client,
struct pmbus_driver_info *info)
{
PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP |
PMBUS_HAVE_POUT | PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT,
.identify = xdpe122_identify,
+ .read_word_data = xdpe122_read_word_data,
};
static int xdpe122_probe(struct i2c_client *client,
/* 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,
/* Sharing an ib_cm_id with different handlers is not
* supported */
spin_unlock_irqrestore(&cm.lock, flags);
+ ib_destroy_cm_id(cm_id);
return ERR_PTR(-EINVAL);
}
refcount_inc(&cm_id_priv->refcount);
int ret;
id_priv = container_of(id, struct rdma_id_private, id);
+ memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
if (id_priv->state == RDMA_CM_IDLE) {
ret = cma_bind_addr(id, src_addr, dst_addr);
- if (ret)
+ if (ret) {
+ memset(cma_dst_addr(id_priv), 0,
+ rdma_addr_size(dst_addr));
return ret;
+ }
}
- if (cma_family(id_priv) != dst_addr->sa_family)
+ if (cma_family(id_priv) != dst_addr->sa_family) {
+ memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
return -EINVAL;
+ }
- if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))
+ if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) {
+ memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
return -EINVAL;
+ }
- memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
if (cma_any_addr(dst_addr)) {
ret = cma_resolve_loopback(id_priv);
} else {
qp->pd = pd;
qp->uobject = uobj;
qp->real_qp = qp;
+
+ qp->qp_type = attr->qp_type;
+ qp->rwq_ind_tbl = attr->rwq_ind_tbl;
+ qp->send_cq = attr->send_cq;
+ qp->recv_cq = attr->recv_cq;
+ qp->srq = attr->srq;
+ qp->rwq_ind_tbl = attr->rwq_ind_tbl;
+ qp->event_handler = attr->event_handler;
+
+ atomic_set(&qp->usecnt, 0);
+ spin_lock_init(&qp->mr_lock);
+ INIT_LIST_HEAD(&qp->rdma_mrs);
+ INIT_LIST_HEAD(&qp->sig_mrs);
+
/*
* We don't track XRC QPs for now, because they don't have PD
* and more importantly they are created internaly by driver,
{
struct list_head *e, *tmp;
- list_for_each_safe(e, tmp, &cm_id_priv->work_free_list)
+ list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) {
+ list_del(e);
kfree(list_entry(e, struct iwcm_work, free_list));
+ }
}
static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count)
if (ret)
goto err_msg;
} else {
+ if (!tb[RDMA_NLDEV_ATTR_RES_LQPN])
+ goto err_msg;
qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]);
if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) {
cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
return 1;
}
+static void rdma_rw_unmap_sg(struct ib_device *dev, struct scatterlist *sg,
+ u32 sg_cnt, enum dma_data_direction dir)
+{
+ if (is_pci_p2pdma_page(sg_page(sg)))
+ pci_p2pdma_unmap_sg(dev->dma_device, sg, sg_cnt, dir);
+ else
+ ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
+}
+
+static int rdma_rw_map_sg(struct ib_device *dev, struct scatterlist *sg,
+ u32 sg_cnt, enum dma_data_direction dir)
+{
+ if (is_pci_p2pdma_page(sg_page(sg)))
+ return pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir);
+ return ib_dma_map_sg(dev, sg, sg_cnt, dir);
+}
+
/**
* rdma_rw_ctx_init - initialize a RDMA READ/WRITE context
* @ctx: context to initialize
struct ib_device *dev = qp->pd->device;
int ret;
- if (is_pci_p2pdma_page(sg_page(sg)))
- ret = pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir);
- else
- ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
-
+ ret = rdma_rw_map_sg(dev, sg, sg_cnt, dir);
if (!ret)
return -ENOMEM;
sg_cnt = ret;
return ret;
out_unmap_sg:
- ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
+ rdma_rw_unmap_sg(dev, sg, sg_cnt, dir);
return ret;
}
EXPORT_SYMBOL(rdma_rw_ctx_init);
break;
}
- if (is_pci_p2pdma_page(sg_page(sg)))
- pci_p2pdma_unmap_sg(qp->pd->device->dma_device, sg,
- sg_cnt, dir);
- else
- ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+ rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
}
EXPORT_SYMBOL(rdma_rw_ctx_destroy);
return NULL;
if (qp_attr_mask & IB_QP_PORT)
- new_pps->main.port_num =
- (qp_pps) ? qp_pps->main.port_num : qp_attr->port_num;
+ new_pps->main.port_num = qp_attr->port_num;
+ else if (qp_pps)
+ new_pps->main.port_num = qp_pps->main.port_num;
+
if (qp_attr_mask & IB_QP_PKEY_INDEX)
- new_pps->main.pkey_index = (qp_pps) ? qp_pps->main.pkey_index :
- qp_attr->pkey_index;
+ new_pps->main.pkey_index = qp_attr->pkey_index;
+ else if (qp_pps)
+ new_pps->main.pkey_index = qp_pps->main.pkey_index;
+
if ((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT))
new_pps->main.state = IB_PORT_PKEY_VALID;
- if (!(qp_attr_mask & (IB_QP_PKEY_INDEX || IB_QP_PORT)) && qp_pps) {
+ if (!(qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) && qp_pps) {
new_pps->main.port_num = qp_pps->main.port_num;
new_pps->main.pkey_index = qp_pps->main.pkey_index;
if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID)
odp_data->page_shift = PAGE_SHIFT;
odp_data->notifier.ops = ops;
+ /*
+ * A mmget must be held when registering a notifier, the owming_mm only
+ * has a mm_grab at this point.
+ */
+ if (!mmget_not_zero(umem->owning_mm)) {
+ ret = -EFAULT;
+ goto out_free;
+ }
+
odp_data->tgid = get_pid(root->tgid);
ret = ib_init_umem_odp(odp_data, ops);
- if (ret) {
- put_pid(odp_data->tgid);
- kfree(odp_data);
- return ERR_PTR(ret);
- }
+ if (ret)
+ goto out_tgid;
+ mmput(umem->owning_mm);
return odp_data;
+
+out_tgid:
+ put_pid(odp_data->tgid);
+ mmput(umem->owning_mm);
+out_free:
+ kfree(odp_data);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL(ib_umem_odp_alloc_child);
if (ret)
goto err_cb;
- qp->pd = pd;
- qp->send_cq = attr.send_cq;
- qp->recv_cq = attr.recv_cq;
- qp->srq = attr.srq;
- qp->rwq_ind_tbl = ind_tbl;
- qp->event_handler = attr.event_handler;
- qp->qp_type = attr.qp_type;
- atomic_set(&qp->usecnt, 0);
atomic_inc(&pd->usecnt);
- qp->port = 0;
if (attr.send_cq)
atomic_inc(&attr.send_cq->usecnt);
if (attr.recv_cq)
if (ret)
goto err;
- qp->qp_type = qp_init_attr->qp_type;
- qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl;
-
- atomic_set(&qp->usecnt, 0);
- qp->mrs_used = 0;
- spin_lock_init(&qp->mr_lock);
- INIT_LIST_HEAD(&qp->rdma_mrs);
- INIT_LIST_HEAD(&qp->sig_mrs);
- qp->port = 0;
-
if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) {
struct ib_qp *xrc_qp =
create_xrc_qp_user(qp, qp_init_attr, udata);
opa_get_lid(packet->dlid, 9B));
if (!mcast)
goto drop;
+ rcu_read_lock();
list_for_each_entry_rcu(p, &mcast->qp_list, list) {
packet->qp = p->qp;
if (hfi1_do_pkey_check(packet))
- goto drop;
+ goto unlock_drop;
spin_lock_irqsave(&packet->qp->r_lock, flags);
packet_handler = qp_ok(packet);
if (likely(packet_handler))
ibp->rvp.n_pkt_drops++;
spin_unlock_irqrestore(&packet->qp->r_lock, flags);
}
+ rcu_read_unlock();
/*
* Notify rvt_multicast_detach() if it is waiting for us
* to finish.
/* For ODP and implicit */
atomic_t num_deferred_work;
+ wait_queue_head_t q_deferred_work;
struct xarray implicit_children;
union {
struct rcu_head rcu;
mr->parent = NULL;
mlx5_mr_cache_free(mr->dev, mr);
ib_umem_odp_release(odp);
- atomic_dec(&imr->num_deferred_work);
+ if (atomic_dec_and_test(&imr->num_deferred_work))
+ wake_up(&imr->q_deferred_work);
}
static void free_implicit_child_mr_work(struct work_struct *work)
imr->umem = &umem_odp->umem;
imr->is_odp_implicit = true;
atomic_set(&imr->num_deferred_work, 0);
+ init_waitqueue_head(&imr->q_deferred_work);
xa_init(&imr->implicit_children);
err = mlx5_ib_update_xlt(imr, 0,
* under xa_lock while the child is in the xarray. Thus at this point
* it is only decreasing, and all work holding it is now on the wq.
*/
- if (atomic_read(&imr->num_deferred_work)) {
- flush_workqueue(system_unbound_wq);
- WARN_ON(atomic_read(&imr->num_deferred_work));
- }
+ wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work));
/*
* Fence the imr before we destroy the children. This allows us to
/* Wait for all running page-fault handlers to finish. */
synchronize_srcu(&mr->dev->odp_srcu);
- if (atomic_read(&mr->num_deferred_work)) {
- flush_workqueue(system_unbound_wq);
- WARN_ON(atomic_read(&mr->num_deferred_work));
- }
+ wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work));
dma_fence_odp_mr(mr);
}
u32 i;
for (i = 0; i < work->num_sge; ++i)
- atomic_dec(&work->frags[i].mr->num_deferred_work);
+ if (atomic_dec_and_test(&work->frags[i].mr->num_deferred_work))
+ wake_up(&work->frags[i].mr->q_deferred_work);
kvfree(work);
}
if (mcast == NULL)
goto drop;
this_cpu_inc(ibp->pmastats->n_multicast_rcv);
+ rcu_read_lock();
list_for_each_entry_rcu(p, &mcast->qp_list, list)
qib_qp_rcv(rcd, hdr, 1, data, tlen, p->qp);
+ rcu_read_unlock();
/*
* Notify rvt_multicast_detach() if it is waiting for us
* to finish.
{ .max_segment_size = SZ_2G };
base_dev->num_comp_vectors = num_possible_cpus();
+ xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
+ xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1);
+
ib_set_device_ops(base_dev, &siw_device_ops);
rv = ib_device_set_netdev(base_dev, netdev, 1);
if (rv)
sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR;
sdev->attrs.max_srq_sge = SIW_MAX_SGE;
- xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
- xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1);
-
INIT_LIST_HEAD(&sdev->cep_list);
INIT_LIST_HEAD(&sdev->qp_list);
/* 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 = {
#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/random.h>
-#include <linux/sched/signal.h>
#include <trace/events/bcache.h>
#define MAX_OPEN_BUCKETS 128
int bch_cache_allocator_start(struct cache *ca)
{
- struct task_struct *k;
-
- /*
- * In case previous btree check operation occupies too many
- * system memory for bcache btree node cache, and the
- * registering process is selected by OOM killer. Here just
- * ignore the SIGKILL sent by OOM killer if there is, to
- * avoid kthread_run() being failed by pending signals. The
- * bcache registering process will exit after the registration
- * done.
- */
- if (signal_pending(current))
- flush_signals(current);
-
- k = kthread_run(bch_allocator_thread, ca, "bcache_allocator");
+ struct task_struct *k = kthread_run(bch_allocator_thread,
+ ca, "bcache_allocator");
if (IS_ERR(k))
return PTR_ERR(k);
#include <linux/random.h>
#include <linux/rcupdate.h>
#include <linux/sched/clock.h>
-#include <linux/sched/signal.h>
#include <linux/rculist.h>
#include <linux/delay.h>
#include <trace/events/bcache.h>
int bch_gc_thread_start(struct cache_set *c)
{
- /*
- * In case previous btree check operation occupies too many
- * system memory for bcache btree node cache, and the
- * registering process is selected by OOM killer. Here just
- * ignore the SIGKILL sent by OOM killer if there is, to
- * avoid kthread_run() being failed by pending signals. The
- * bcache registering process will exit after the registration
- * done.
- */
- if (signal_pending(current))
- flush_signals(current);
-
c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc");
return PTR_ERR_OR_ZERO(c->gc_thread);
}
struct dm_bio_details {
struct gendisk *bi_disk;
u8 bi_partno;
+ int __bi_remaining;
unsigned long bi_flags;
struct bvec_iter bi_iter;
+ bio_end_io_t *bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+ struct bio_integrity_payload *bi_integrity;
+#endif
};
static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
bd->bi_partno = bio->bi_partno;
bd->bi_flags = bio->bi_flags;
bd->bi_iter = bio->bi_iter;
+ bd->__bi_remaining = atomic_read(&bio->__bi_remaining);
+ bd->bi_end_io = bio->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+ bd->bi_integrity = bio_integrity(bio);
+#endif
}
static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
bio->bi_partno = bd->bi_partno;
bio->bi_flags = bd->bi_flags;
bio->bi_iter = bd->bi_iter;
+ atomic_set(&bio->__bi_remaining, bd->__bi_remaining);
+ bio->bi_end_io = bd->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+ bio->bi_integrity = bd->bi_integrity;
+#endif
}
#endif
prevent_background_work(cache);
BUG_ON(atomic_read(&cache->nr_io_migrations));
- cancel_delayed_work(&cache->waker);
- flush_workqueue(cache->wq);
+ cancel_delayed_work_sync(&cache->waker);
+ drain_workqueue(cache->wq);
WARN_ON(cache->tracker.in_flight);
/*
static struct target_type cache_target = {
.name = "cache",
- .version = {2, 1, 0},
+ .version = {2, 2, 0},
.module = THIS_MODULE,
.ctr = cache_ctr,
.dtr = cache_dtr,
* This file is released under the GPL.
*/
+#include "dm-bio-record.h"
+
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/device-mapper.h>
__u8 log2_blocks_per_bitmap_bit;
unsigned char mode;
- int suspending;
int failed;
struct crypto_shash *internal_hash;
+ struct dm_target *ti;
+
/* these variables are locked with endio_wait.lock */
struct rb_root in_progress;
struct list_head wait_list;
wait_queue_head_t endio_wait;
struct workqueue_struct *wait_wq;
+ struct workqueue_struct *offload_wq;
unsigned char commit_seq;
commit_id_t commit_ids[N_COMMIT_IDS];
struct completion *completion;
- struct gendisk *orig_bi_disk;
- u8 orig_bi_partno;
- bio_end_io_t *orig_bi_end_io;
- struct bio_integrity_payload *orig_bi_integrity;
- struct bvec_iter orig_bi_iter;
+ struct dm_bio_details bio_details;
};
struct journal_completion {
dio->range.logical_sector += dio->range.n_sectors;
bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
return;
}
do_endio_flush(ic, dio);
{
struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
- bio->bi_iter = dio->orig_bi_iter;
- bio->bi_disk = dio->orig_bi_disk;
- bio->bi_partno = dio->orig_bi_partno;
- if (dio->orig_bi_integrity) {
- bio->bi_integrity = dio->orig_bi_integrity;
+ dm_bio_restore(&dio->bio_details, bio);
+ if (bio->bi_integrity)
bio->bi_opf |= REQ_INTEGRITY;
- }
- bio->bi_end_io = dio->orig_bi_end_io;
if (dio->completion)
complete(dio->completion);
}
}
- __bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) {
+ __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
unsigned pos;
char *mem, *checksums_ptr;
if (likely(checksums != checksums_onstack))
kfree(checksums);
} else {
- struct bio_integrity_payload *bip = dio->orig_bi_integrity;
+ struct bio_integrity_payload *bip = dio->bio_details.bi_integrity;
if (bip) {
struct bio_vec biv;
if (need_sync_io && from_map) {
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->metadata_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
return;
}
} else
dio->completion = NULL;
- dio->orig_bi_iter = bio->bi_iter;
-
- dio->orig_bi_disk = bio->bi_disk;
- dio->orig_bi_partno = bio->bi_partno;
+ dm_bio_record(&dio->bio_details, bio);
bio_set_dev(bio, ic->dev->bdev);
-
- dio->orig_bi_integrity = bio_integrity(bio);
bio->bi_integrity = NULL;
bio->bi_opf &= ~REQ_INTEGRITY;
-
- dio->orig_bi_end_io = bio->bi_end_io;
bio->bi_end_io = integrity_end_io;
-
bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT;
+
generic_make_request(bio);
if (need_sync_io) {
unsigned prev_free_sectors;
/* the following test is not needed, but it tests the replay code */
- if (READ_ONCE(ic->suspending) && !ic->meta_dev)
+ if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
return;
spin_lock_irq(&ic->endio_wait.lock);
next_chunk:
- if (unlikely(READ_ONCE(ic->suspending)))
+ if (unlikely(dm_suspended(ic->ti)))
goto unlock_ret;
range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
remove_range(ic, &dio->range);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
} else {
block_bitmap_op(ic, ic->journal, dio->range.logical_sector,
dio->range.n_sectors, BITMAP_OP_SET);
remove_range(ic, &dio->range);
INIT_WORK(&dio->work, integrity_bio_wait);
- queue_work(ic->wait_wq, &dio->work);
+ queue_work(ic->offload_wq, &dio->work);
}
queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
del_timer_sync(&ic->autocommit_timer);
- WRITE_ONCE(ic->suspending, 1);
-
if (ic->recalc_wq)
drain_workqueue(ic->recalc_wq);
#endif
}
- WRITE_ONCE(ic->suspending, 0);
-
BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
ic->journal_uptodate = true;
} else {
replay_journal(ic);
if (ic->mode == 'B') {
- int mode;
ic->sb->flags |= cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
ic->sb->log2_blocks_per_bitmap_bit = ic->log2_blocks_per_bitmap_bit;
r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
if (unlikely(r))
dm_integrity_io_error(ic, "writing superblock", r);
- mode = ic->recalculate_flag ? BITMAP_OP_SET : BITMAP_OP_CLEAR;
- block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, mode);
- block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, mode);
- block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, mode);
+ block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+ block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+ block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+ le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors) {
+ block_bitmap_op(ic, ic->journal, le64_to_cpu(ic->sb->recalc_sector),
+ ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+ block_bitmap_op(ic, ic->recalc_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+ ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+ block_bitmap_op(ic, ic->may_write_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+ ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+ }
rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
}
DMEMIT(" meta_device:%s", ic->meta_dev->name);
if (ic->sectors_per_block != 1)
DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT);
- if (ic->recalculate_flag)
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
DMEMIT(" recalculate");
DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
}
ti->private = ic;
ti->per_io_data_size = sizeof(struct dm_integrity_io);
+ ic->ti = ti;
ic->in_progress = RB_ROOT;
INIT_LIST_HEAD(&ic->wait_list);
goto bad;
}
+ ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM,
+ METADATA_WORKQUEUE_MAX_ACTIVE);
+ if (!ic->offload_wq) {
+ ti->error = "Cannot allocate workqueue";
+ r = -ENOMEM;
+ goto bad;
+ }
+
ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1);
if (!ic->commit_wq) {
ti->error = "Cannot allocate workqueue";
destroy_workqueue(ic->metadata_wq);
if (ic->wait_wq)
destroy_workqueue(ic->wait_wq);
+ if (ic->offload_wq)
+ destroy_workqueue(ic->offload_wq);
if (ic->commit_wq)
destroy_workqueue(ic->commit_wq);
if (ic->writer_wq)
static struct target_type integrity_target = {
.name = "integrity",
- .version = {1, 4, 0},
+ .version = {1, 5, 0},
.module = THIS_MODULE,
.features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
.ctr = dm_integrity_ctr,
*---------------------------------------------------------------*/
static struct target_type multipath_target = {
.name = "multipath",
- .version = {1, 13, 0},
+ .version = {1, 14, 0},
.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE |
DM_TARGET_PASSES_INTEGRITY,
.module = THIS_MODULE,
DMWARN("%s: __commit_transaction() failed, error = %d",
__func__, r);
}
+ pmd_write_unlock(pmd);
if (!pmd->fail_io)
__destroy_persistent_data_objects(pmd);
- pmd_write_unlock(pmd);
kfree(pmd);
return 0;
static struct target_type verity_target = {
.name = "verity",
- .version = {1, 5, 0},
+ .version = {1, 6, 0},
.module = THIS_MODULE,
.ctr = verity_ctr,
.dtr = verity_dtr,
wc->freelist_size++;
}
+static inline void writecache_verify_watermark(struct dm_writecache *wc)
+{
+ if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
+ queue_work(wc->writeback_wq, &wc->writeback_work);
+}
+
static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector)
{
struct wc_entry *e;
list_del(&e->lru);
}
wc->freelist_size--;
- if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
- queue_work(wc->writeback_wq, &wc->writeback_work);
+
+ writecache_verify_watermark(wc);
return e;
}
}
wc_unlock(wc);
- flush_workqueue(wc->writeback_wq);
+ drain_workqueue(wc->writeback_wq);
wc_lock(wc);
if (flush_on_suspend)
writecache_commit_flushed(wc, false);
}
+ writecache_verify_watermark(wc);
+
wc_unlock(wc);
}
static struct target_type writecache_target = {
.name = "writecache",
- .version = {1, 1, 1},
+ .version = {1, 2, 0},
.module = THIS_MODULE,
.ctr = writecache_ctr,
.dtr = writecache_dtr,
/* Get the BIO chunk work. If one is not active yet, create one */
cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
- if (!cw) {
-
+ if (cw) {
+ dmz_get_chunk_work(cw);
+ } else {
/* Create a new chunk work */
cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO);
if (unlikely(!cw)) {
}
INIT_WORK(&cw->work, dmz_chunk_work);
- refcount_set(&cw->refcount, 0);
+ refcount_set(&cw->refcount, 1);
cw->target = dmz;
cw->chunk = chunk;
bio_list_init(&cw->bio_list);
}
bio_list_add(&cw->bio_list, bio);
- dmz_get_chunk_work(cw);
dmz_reclaim_bio_acc(dmz->reclaim);
if (queue_work(dmz->chunk_wq, &cw->work))
static struct target_type dmz_type = {
.name = "zoned",
- .version = {1, 0, 0},
+ .version = {1, 1, 0},
.features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
.module = THIS_MODULE,
.ctr = dmz_ctr,
* With request-based DM we only need to check the
* top-level queue for congestion.
*/
- r = md->queue->backing_dev_info->wb.state & bdi_bits;
+ struct backing_dev_info *bdi = md->queue->backing_dev_info;
+ r = bdi->wb.congested->state & bdi_bits;
} else {
map = dm_get_live_table_fast(md);
if (map)
static void dm_wq_work(struct work_struct *work);
-static void dm_init_normal_md_queue(struct mapped_device *md)
-{
- /*
- * Initialize aspects of queue that aren't relevant for blk-mq
- */
- md->queue->backing_dev_info->congested_data = md;
- md->queue->backing_dev_info->congested_fn = dm_any_congested;
-}
-
static void cleanup_mapped_device(struct mapped_device *md)
{
if (md->wq)
}
EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+static void dm_init_congested_fn(struct mapped_device *md)
+{
+ md->queue->backing_dev_info->congested_data = md;
+ md->queue->backing_dev_info->congested_fn = dm_any_congested;
+}
+
/*
* Setup the DM device's queue based on md's type
*/
DMERR("Cannot initialize queue for request-based dm-mq mapped device");
return r;
}
+ dm_init_congested_fn(md);
break;
case DM_TYPE_BIO_BASED:
case DM_TYPE_DAX_BIO_BASED:
case DM_TYPE_NVME_BIO_BASED:
- dm_init_normal_md_queue(md);
+ dm_init_congested_fn(md);
break;
case DM_TYPE_NONE:
WARN_ON_ONCE(true);
map = dm_get_live_table(md, &srcu_idx);
if (!dm_suspended_md(md)) {
dm_table_presuspend_targets(map);
+ set_bit(DMF_SUSPENDED, &md->flags);
dm_table_postsuspend_targets(map);
}
/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
return -EINVAL;
for (i = 0; i < entity->num_pads; i++) {
- if (entity->pads[i].flags == MEDIA_PAD_FL_SINK)
+ if (entity->pads[i].flags & MEDIA_PAD_FL_SINK)
pad_is_sink = true;
- else if (entity->pads[i].flags == MEDIA_PAD_FL_SOURCE)
+ else if (entity->pads[i].flags & MEDIA_PAD_FL_SOURCE)
pad_is_sink = false;
else
continue; /* This is an error! */
{ V4L2_PIX_FMT_BGR24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_RGB24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_HSV24, 3, 3, 1, 3, 3, 1, 1, 3, 1, FWHT_FL_PIXENC_HSV},
- { V4L2_PIX_FMT_BGR32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_XBGR32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_BGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_XBGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_ABGR32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_RGB32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_XRGB32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_RGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_XRGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_ARGB32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_BGRX32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_BGRX32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_BGRA32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_RGBX32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_RGB},
+ { V4L2_PIX_FMT_RGBX32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
{ V4L2_PIX_FMT_RGBA32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_RGB},
- { V4L2_PIX_FMT_HSV32, 4, 4, 1, 4, 4, 1, 1, 3, 1, FWHT_FL_PIXENC_HSV},
+ { V4L2_PIX_FMT_HSV32, 4, 4, 1, 4, 4, 1, 1, 4, 1, FWHT_FL_PIXENC_HSV},
{ V4L2_PIX_FMT_GREY, 1, 1, 1, 1, 0, 1, 1, 1, 1, FWHT_FL_PIXENC_RGB},
};
case V4L2_PIX_FMT_RGB32:
case V4L2_PIX_FMT_XRGB32:
case V4L2_PIX_FMT_HSV32:
- rf->cr = rf->luma + 1;
- rf->cb = rf->cr + 2;
- rf->luma += 2;
- break;
- case V4L2_PIX_FMT_BGR32:
- case V4L2_PIX_FMT_XBGR32:
- rf->cb = rf->luma;
- rf->cr = rf->cb + 2;
- rf->luma++;
- break;
case V4L2_PIX_FMT_ARGB32:
rf->alpha = rf->luma;
rf->cr = rf->luma + 1;
rf->cb = rf->cr + 2;
rf->luma += 2;
break;
+ case V4L2_PIX_FMT_BGR32:
+ case V4L2_PIX_FMT_XBGR32:
case V4L2_PIX_FMT_ABGR32:
rf->cb = rf->luma;
rf->cr = rf->cb + 2;
rf->alpha = rf->cr + 1;
break;
case V4L2_PIX_FMT_BGRX32:
- rf->cb = rf->luma + 1;
- rf->cr = rf->cb + 2;
- rf->luma += 2;
- break;
case V4L2_PIX_FMT_BGRA32:
rf->alpha = rf->luma;
rf->cb = rf->luma + 1;
rf->luma += 2;
break;
case V4L2_PIX_FMT_RGBX32:
- rf->cr = rf->luma;
- rf->cb = rf->cr + 2;
- rf->luma++;
- break;
case V4L2_PIX_FMT_RGBA32:
rf->alpha = rf->luma + 3;
rf->cr = rf->luma;
cancel_delayed_work_sync(&pulse8->ping_eeprom_work);
cancel_work_sync(&pulse8->irq_work);
cancel_work_sync(&pulse8->tx_work);
- serio_close(pulse8->serio);
- serio_set_drvdata(pulse8->serio, NULL);
kfree(pulse8);
}
struct pulse8 *pulse8 = serio_get_drvdata(serio);
cec_unregister_adapter(pulse8->adap);
+ pulse8->serio = NULL;
+ serio_set_drvdata(serio, NULL);
+ serio_close(serio);
}
static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio,
serio_set_drvdata(serio, pulse8);
INIT_WORK(&pulse8->irq_work, pulse8_irq_work_handler);
INIT_WORK(&pulse8->tx_work, pulse8_tx_work_handler);
+ INIT_DELAYED_WORK(&pulse8->ping_eeprom_work,
+ pulse8_ping_eeprom_work_handler);
mutex_init(&pulse8->lock);
spin_lock_init(&pulse8->msg_lock);
pulse8->config_pending = false;
pulse8->restoring_config = true;
}
- INIT_DELAYED_WORK(&pulse8->ping_eeprom_work,
- pulse8_ping_eeprom_work_handler);
schedule_delayed_work(&pulse8->ping_eeprom_work, PING_PERIOD);
return 0;
close_serio:
+ pulse8->serio = NULL;
+ serio_set_drvdata(serio, NULL);
serio_close(serio);
delete_adap:
cec_delete_adapter(pulse8->adap);
- serio_set_drvdata(serio, NULL);
free_device:
kfree(pulse8);
return err;
goto err_rel_entity1;
/* Connect the three entities */
- ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1,
+ ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 0,
MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
if (ret)
goto err_rel_entity2;
- ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0,
+ ret = media_create_pad_link(&m2m_dev->proc, 1, &m2m_dev->sink, 0,
MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
if (ret)
goto err_rm_links0;
/* 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 (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;
}
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;
}
*/
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;
}
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)
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);
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);
#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
{
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);
{
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;
}
#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");
}
}
+ 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);
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");
}
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;
}
* 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);
int gsi, trigger;
gicc = acpi_cpu_get_madt_gicc(cpu);
- if (WARN_ON(!gicc))
- return -EINVAL;
gsi = gicc->performance_interrupt;
int gsi;
gicc = acpi_cpu_get_madt_gicc(cpu);
- if (!gicc)
- return;
gsi = gicc->performance_interrupt;
- acpi_unregister_gsi(gsi);
+ if (gsi)
+ acpi_unregister_gsi(gsi);
}
#if IS_ENABLED(CONFIG_ARM_SPE_PMU)
if (enable) {
/*
- * must disable first, then enable again
- * otherwise, cycle counter will not work
- * if previous state is enabled.
+ * cycle counter is special which should firstly write 0 then
+ * write 1 into CLEAR bit to clear it. Other counters only
+ * need write 0 into CLEAR bit and it turns out to be 1 by
+ * hardware. Below enable flow is harmless for all counters.
*/
writel(0, pmu->base + reg);
val = CNTL_EN | CNTL_CLEAR;
writel(val, pmu->base + reg);
} else {
/* Disable counter */
- writel(0, pmu->base + reg);
+ val = readl_relaxed(pmu->base + reg) & CNTL_EN_MASK;
+ writel(val, pmu->base + reg);
}
}
#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 {
}
val = readl_relaxed(priv->base + STM32_VREFBUF_CSR);
- val = (val & ~STM32_ENVR) | STM32_HIZ;
+ val &= ~STM32_ENVR;
writel_relaxed(val, priv->base + STM32_VREFBUF_CSR);
pm_runtime_mark_last_busy(priv->dev);
.volt_table = stm32_vrefbuf_voltages,
.n_voltages = ARRAY_SIZE(stm32_vrefbuf_voltages),
.ops = &stm32_vrefbuf_volt_ops,
+ .off_on_delay = 1000,
.type = REGULATOR_VOLTAGE,
.owner = THIS_MODULE,
};
u8 cb_util;
u8 a_util;
u8 res2;
- u16 temperature;
+ s16 temperature;
u16 vcc;
u16 tx_bias;
u16 tx_power;
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);
}
/**
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,
struct clk *qspick;
struct platform_device *pdev;
const struct atmel_qspi_caps *caps;
+ resource_size_t mmap_size;
u32 pending;
u32 mr;
u32 scr;
u32 sr, offset;
int err;
+ /*
+ * Check if the address exceeds the MMIO window size. An improvement
+ * would be to add support for regular SPI mode and fall back to it
+ * when the flash memories overrun the controller's memory space.
+ */
+ if (op->addr.val + op->data.nbytes > aq->mmap_size)
+ return -ENOTSUPP;
+
err = atmel_qspi_set_cfg(aq, op, &offset);
if (err)
return err;
goto exit;
}
+ aq->mmap_size = resource_size(res);
+
/* Get the peripheral clock */
aq->pclk = devm_clk_get(&pdev->dev, "pclk");
if (IS_ERR(aq->pclk))
goto out_disable_clk;
rate = clk_get_rate(pll_clk);
- clk_disable_unprepare(pll_clk);
if (!rate) {
ret = -EINVAL;
goto out_disable_pll_clk;
int fifo_depth;
bool slave_aborted;
unsigned int pin_dir:1;
+ size_t max_xfer_len;
};
struct omap2_mcspi_cs {
* Note that we currently allow DMA only if we get a channel
* for both rx and tx. Otherwise we'll do PIO for both rx and tx.
*/
-static int omap2_mcspi_request_dma(struct spi_device *spi)
+static int omap2_mcspi_request_dma(struct omap2_mcspi *mcspi,
+ struct omap2_mcspi_dma *mcspi_dma)
{
- struct spi_master *master = spi->master;
- struct omap2_mcspi *mcspi;
- struct omap2_mcspi_dma *mcspi_dma;
int ret = 0;
- mcspi = spi_master_get_devdata(master);
- mcspi_dma = mcspi->dma_channels + spi->chip_select;
-
- init_completion(&mcspi_dma->dma_rx_completion);
- init_completion(&mcspi_dma->dma_tx_completion);
-
- mcspi_dma->dma_rx = dma_request_chan(&master->dev,
+ mcspi_dma->dma_rx = dma_request_chan(mcspi->dev,
mcspi_dma->dma_rx_ch_name);
if (IS_ERR(mcspi_dma->dma_rx)) {
ret = PTR_ERR(mcspi_dma->dma_rx);
goto no_dma;
}
- mcspi_dma->dma_tx = dma_request_chan(&master->dev,
+ mcspi_dma->dma_tx = dma_request_chan(mcspi->dev,
mcspi_dma->dma_tx_ch_name);
if (IS_ERR(mcspi_dma->dma_tx)) {
ret = PTR_ERR(mcspi_dma->dma_tx);
mcspi_dma->dma_rx = NULL;
}
+ init_completion(&mcspi_dma->dma_rx_completion);
+ init_completion(&mcspi_dma->dma_tx_completion);
+
no_dma:
return ret;
}
+static void omap2_mcspi_release_dma(struct spi_master *master)
+{
+ struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+ struct omap2_mcspi_dma *mcspi_dma;
+ int i;
+
+ for (i = 0; i < master->num_chipselect; i++) {
+ mcspi_dma = &mcspi->dma_channels[i];
+
+ if (mcspi_dma->dma_rx) {
+ dma_release_channel(mcspi_dma->dma_rx);
+ mcspi_dma->dma_rx = NULL;
+ }
+ if (mcspi_dma->dma_tx) {
+ dma_release_channel(mcspi_dma->dma_tx);
+ mcspi_dma->dma_tx = NULL;
+ }
+ }
+}
+
static int omap2_mcspi_setup(struct spi_device *spi)
{
int ret;
struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
struct omap2_mcspi_regs *ctx = &mcspi->ctx;
- struct omap2_mcspi_dma *mcspi_dma;
struct omap2_mcspi_cs *cs = spi->controller_state;
- mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-
if (!cs) {
cs = kzalloc(sizeof *cs, GFP_KERNEL);
if (!cs)
}
}
- if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) {
- ret = omap2_mcspi_request_dma(spi);
- if (ret)
- dev_warn(&spi->dev, "not using DMA for McSPI (%d)\n",
- ret);
- }
-
ret = pm_runtime_get_sync(mcspi->dev);
if (ret < 0) {
pm_runtime_put_noidle(mcspi->dev);
static void omap2_mcspi_cleanup(struct spi_device *spi)
{
- struct omap2_mcspi *mcspi;
- struct omap2_mcspi_dma *mcspi_dma;
struct omap2_mcspi_cs *cs;
- mcspi = spi_master_get_devdata(spi->master);
-
if (spi->controller_state) {
/* Unlink controller state from context save list */
cs = spi->controller_state;
kfree(cs);
}
- if (spi->chip_select < spi->master->num_chipselect) {
- mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-
- if (mcspi_dma->dma_rx) {
- dma_release_channel(mcspi_dma->dma_rx);
- mcspi_dma->dma_rx = NULL;
- }
- if (mcspi_dma->dma_tx) {
- dma_release_channel(mcspi_dma->dma_tx);
- mcspi_dma->dma_tx = NULL;
- }
- }
-
if (gpio_is_valid(spi->cs_gpio))
gpio_free(spi->cs_gpio);
}
if (spi_controller_is_slave(master))
return true;
+ master->dma_rx = mcspi_dma->dma_rx;
+ master->dma_tx = mcspi_dma->dma_tx;
+
return (xfer->len >= DMA_MIN_BYTES);
}
+static size_t omap2_mcspi_max_xfer_size(struct spi_device *spi)
+{
+ struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+ struct omap2_mcspi_dma *mcspi_dma =
+ &mcspi->dma_channels[spi->chip_select];
+
+ if (mcspi->max_xfer_len && mcspi_dma->dma_rx)
+ return mcspi->max_xfer_len;
+
+ return SIZE_MAX;
+}
+
static int omap2_mcspi_controller_setup(struct omap2_mcspi *mcspi)
{
struct spi_master *master = mcspi->master;
.regs_offset = OMAP4_MCSPI_REG_OFFSET,
};
+static struct omap2_mcspi_platform_config am654_pdata = {
+ .regs_offset = OMAP4_MCSPI_REG_OFFSET,
+ .max_xfer_len = SZ_4K - 1,
+};
+
static const struct of_device_id omap_mcspi_of_match[] = {
{
.compatible = "ti,omap2-mcspi",
.compatible = "ti,omap4-mcspi",
.data = &omap4_pdata,
},
+ {
+ .compatible = "ti,am654-mcspi",
+ .data = &am654_pdata,
+ },
{ },
};
MODULE_DEVICE_TABLE(of, omap_mcspi_of_match);
mcspi->pin_dir = pdata->pin_dir;
}
regs_offset = pdata->regs_offset;
+ if (pdata->max_xfer_len) {
+ mcspi->max_xfer_len = pdata->max_xfer_len;
+ master->max_transfer_size = omap2_mcspi_max_xfer_size;
+ }
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mcspi->base = devm_ioremap_resource(&pdev->dev, r);
for (i = 0; i < master->num_chipselect; i++) {
sprintf(mcspi->dma_channels[i].dma_rx_ch_name, "rx%d", i);
sprintf(mcspi->dma_channels[i].dma_tx_ch_name, "tx%d", i);
+
+ status = omap2_mcspi_request_dma(mcspi,
+ &mcspi->dma_channels[i]);
+ if (status == -EPROBE_DEFER)
+ goto free_master;
}
status = platform_get_irq(pdev, 0);
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
free_master:
+ omap2_mcspi_release_dma(master);
spi_master_put(master);
return status;
}
struct spi_master *master = platform_get_drvdata(pdev);
struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+ omap2_mcspi_release_dma(master);
+
pm_runtime_dont_use_autosuspend(mcspi->dev);
pm_runtime_put_sync(mcspi->dev);
pm_runtime_disable(&pdev->dev);
#define LPSS_CAPS_CS_EN_SHIFT 9
#define LPSS_CAPS_CS_EN_MASK (0xf << LPSS_CAPS_CS_EN_SHIFT)
+#define LPSS_PRIV_CLOCK_GATE 0x38
+#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK 0x3
+#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON 0x3
+
struct lpss_config {
/* LPSS offset from drv_data->ioaddr */
unsigned offset;
unsigned cs_sel_shift;
unsigned cs_sel_mask;
unsigned cs_num;
+ /* Quirks */
+ unsigned cs_clk_stays_gated : 1;
};
/* Keep these sorted with enum pxa_ssp_type */
.tx_threshold_hi = 56,
.cs_sel_shift = 8,
.cs_sel_mask = 3 << 8,
+ .cs_clk_stays_gated = true,
},
};
else
value |= LPSS_CS_CONTROL_CS_HIGH;
__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
+ if (config->cs_clk_stays_gated) {
+ u32 clkgate;
+
+ /*
+ * Changing CS alone when dynamic clock gating is on won't
+ * actually flip CS at that time. This ruins SPI transfers
+ * that specify delays, or have no data. Toggle the clock mode
+ * to force on briefly to poke the CS pin to move.
+ */
+ clkgate = __lpss_ssp_read_priv(drv_data, LPSS_PRIV_CLOCK_GATE);
+ value = (clkgate & ~LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK) |
+ LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON;
+
+ __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, value);
+ __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, clkgate);
+ }
}
static void cs_assert(struct spi_device *spi)
struct spi_qup *controller = spi_master_get_devdata(master);
int ret;
+ if (pm_runtime_suspended(device)) {
+ ret = spi_qup_pm_resume_runtime(device);
+ if (ret)
+ return ret;
+ }
ret = spi_master_suspend(master);
if (ret)
return ret;
if (ret)
return ret;
- if (!pm_runtime_suspended(device)) {
- clk_disable_unprepare(controller->cclk);
- clk_disable_unprepare(controller->iclk);
- }
+ clk_disable_unprepare(controller->cclk);
+ clk_disable_unprepare(controller->iclk);
return 0;
}
zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, genfifoentry);
- /* Dummy generic FIFO entry */
- zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, 0x0);
-
/* Manually start the generic FIFO command */
zynqmp_gqspi_write(xqspi, GQSPI_CONFIG_OFST,
zynqmp_gqspi_read(xqspi, GQSPI_CONFIG_OFST) |
if (ctlr->use_gpio_descriptors) {
status = spi_get_gpio_descs(ctlr);
if (status)
- return status;
+ goto free_bus_id;
/*
* A controller using GPIO descriptors always
* supports SPI_CS_HIGH if need be.
/* Legacy code path for GPIOs from DT */
status = of_spi_get_gpio_numbers(ctlr);
if (status)
- return status;
+ goto free_bus_id;
}
}
* Even if it's just one always-selected device, there must
* be at least one chipselect.
*/
- if (!ctlr->num_chipselect)
- return -EINVAL;
+ if (!ctlr->num_chipselect) {
+ status = -EINVAL;
+ goto free_bus_id;
+ }
status = device_add(&ctlr->dev);
- if (status < 0) {
- /* free bus id */
- mutex_lock(&board_lock);
- idr_remove(&spi_master_idr, ctlr->bus_num);
- mutex_unlock(&board_lock);
- goto done;
- }
+ if (status < 0)
+ goto free_bus_id;
dev_dbg(dev, "registered %s %s\n",
spi_controller_is_slave(ctlr) ? "slave" : "master",
dev_name(&ctlr->dev));
status = spi_controller_initialize_queue(ctlr);
if (status) {
device_del(&ctlr->dev);
- /* free bus id */
- mutex_lock(&board_lock);
- idr_remove(&spi_master_idr, ctlr->bus_num);
- mutex_unlock(&board_lock);
- goto done;
+ goto free_bus_id;
}
}
/* add statistics */
/* Register devices from the device tree and ACPI */
of_register_spi_devices(ctlr);
acpi_register_spi_devices(ctlr);
-done:
+ return status;
+
+free_bus_id:
+ mutex_lock(&board_lock);
+ idr_remove(&spi_master_idr, ctlr->bus_num);
+ mutex_unlock(&board_lock);
return status;
}
EXPORT_SYMBOL_GPL(spi_register_controller);
else
retval = get_user(tmp, (u32 __user *)arg);
if (retval == 0) {
+ struct spi_controller *ctlr = spi->controller;
u32 save = spi->mode;
if (tmp & ~SPI_MODE_MASK) {
break;
}
+ if (ctlr->use_gpio_descriptors && ctlr->cs_gpiods &&
+ ctlr->cs_gpiods[spi->chip_select])
+ tmp |= SPI_CS_HIGH;
+
tmp |= spi->mode & ~SPI_MODE_MASK;
spi->mode = (u16)tmp;
retval = spi_setup(spi);
goto err_rel_entity1;
/* Connect the three entities */
- ret = media_create_pad_link(&func->vdev.entity, 0, &func->proc, 1,
+ ret = media_create_pad_link(&func->vdev.entity, 0, &func->proc, 0,
MEDIA_LNK_FL_IMMUTABLE |
MEDIA_LNK_FL_ENABLED);
if (ret)
goto err_rel_entity2;
- ret = media_create_pad_link(&func->proc, 0, &func->sink, 0,
+ ret = media_create_pad_link(&func->proc, 1, &func->sink, 0,
MEDIA_LNK_FL_IMMUTABLE |
MEDIA_LNK_FL_ENABLED);
if (ret)
Must contains 64 hexadecimal digits. Not supported in current version.
WFx driver also supports `mac-address` and `local-mac-address` as described in
-Documentation/devicetree/binding/net/ethernet.txt
+Documentation/devicetree/bindings/net/ethernet.txt
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;
}
static int vgacon_resize(struct vc_data *c, unsigned int width,
unsigned int height, unsigned int user)
{
+ if ((width << 1) * height > vga_vram_size)
+ return -EINVAL;
+
if (width % 2 || width > screen_info.orig_video_cols ||
height > (screen_info.orig_video_lines * vga_default_font_height)/
c->vc_font.height)
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);
}
unsigned int ack_intr:1; /* .. and ACK-ing */
unsigned long handled;
unsigned int irq; /* Saved in case device transitions to MSI/MSI-X */
- char irq_name[0]; /* xen-pcibk[000:04:00.0] */
+ char irq_name[]; /* xen-pcibk[000:04:00.0] */
};
/* Used by XenBus and xen_pcibk_ops.c */
req->msg.type = state.msg.type;
req->msg.len = state.msg.len;
req->body = state.body;
+ /* write body, then update state */
+ virt_wmb();
req->state = xb_req_state_got_reply;
req->cb(req);
} else
if (state.req->state == xb_req_state_aborted)
kfree(state.req);
else {
+ /* write err, then update state */
+ virt_wmb();
state.req->state = xb_req_state_got_reply;
wake_up(&state.req->wq);
}
goto fail;
}
- spin_lock(&dev->reclaim_lock);
+ down(&dev->reclaim_sem);
err = drv->probe(dev, id);
- spin_unlock(&dev->reclaim_lock);
+ up(&dev->reclaim_sem);
if (err)
goto fail_put;
free_otherend_watch(dev);
if (drv->remove) {
- spin_lock(&dev->reclaim_lock);
+ down(&dev->reclaim_sem);
drv->remove(dev);
- spin_unlock(&dev->reclaim_lock);
+ up(&dev->reclaim_sem);
}
module_put(drv->driver.owner);
goto fail;
dev_set_name(&xendev->dev, "%s", devname);
- spin_lock_init(&xendev->reclaim_lock);
+ sema_init(&xendev->reclaim_sem, 1);
/* Register with generic device framework. */
err = device_register(&xendev->dev);
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/export.h>
+#include <linux/semaphore.h>
#include <asm/page.h>
#include <asm/pgtable.h>
drv = to_xenbus_driver(dev->driver);
if (drv && drv->reclaim_memory) {
xdev = to_xenbus_device(dev);
- if (!spin_trylock(&xdev->reclaim_lock))
+ if (down_trylock(&xdev->reclaim_sem))
return 0;
drv->reclaim_memory(xdev);
- spin_unlock(&xdev->reclaim_lock);
+ up(&xdev->reclaim_sem);
}
return 0;
}
static bool test_reply(struct xb_req_data *req)
{
- if (req->state == xb_req_state_got_reply || !xenbus_ok())
+ if (req->state == xb_req_state_got_reply || !xenbus_ok()) {
+ /* read req->state before all other fields */
+ virt_rmb();
return true;
+ }
/* Make sure to reread req->state each time. */
barrier();
static void *read_reply(struct xb_req_data *req)
{
- while (req->state != xb_req_state_got_reply) {
+ do {
wait_event(req->wq, test_reply(req));
if (!xenbus_ok())
if (req->err)
return ERR_PTR(req->err);
- }
+ } while (req->state != xb_req_state_got_reply);
return req->body;
}
{
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
+ u16 csum_size;
blk_status_t ret;
/*
file_offset -= dip->logical_offset;
file_offset >>= inode->i_sb->s_blocksize_bits;
- io_bio->csum = (u8 *)(((u32 *)orig_io_bio->csum) + file_offset);
+ csum_size = btrfs_super_csum_size(btrfs_sb(inode->i_sb)->super_copy);
+ io_bio->csum = orig_io_bio->csum + csum_size * file_offset;
return 0;
}
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 ext4_sb_info *sbi = EXT4_SB(sb);
struct flex_groups **old_groups, **new_groups;
- int size, i;
+ int size, i, j;
if (!sbi->s_log_groups_per_flex)
return 0;
sizeof(struct flex_groups)),
GFP_KERNEL);
if (!new_groups[i]) {
- for (i--; i >= sbi->s_flex_groups_allocated; i--)
- kvfree(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 NULL;
init_rwsem(&ei->truncate_lock);
+ /* Zeroing to allow iput() even if partial initialized inode. */
+ ei->mmu_private = 0;
+ ei->i_start = 0;
+ ei->i_logstart = 0;
+ ei->i_attrs = 0;
+ ei->i_pos = 0;
+
return &ei->vfs_inode;
}
return 0;
}
-static void fat_dummy_inode_init(struct inode *inode)
-{
- /* Initialize this dummy inode to work as no-op. */
- MSDOS_I(inode)->mmu_private = 0;
- MSDOS_I(inode)->i_start = 0;
- MSDOS_I(inode)->i_logstart = 0;
- MSDOS_I(inode)->i_attrs = 0;
- MSDOS_I(inode)->i_pos = 0;
-}
-
static int fat_read_root(struct inode *inode)
{
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
fat_inode = new_inode(sb);
if (!fat_inode)
goto out_fail;
- fat_dummy_inode_init(fat_inode);
sbi->fat_inode = fat_inode;
fsinfo_inode = new_inode(sb);
if (!fsinfo_inode)
goto out_fail;
- fat_dummy_inode_init(fsinfo_inode);
fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
sbi->fsinfo_inode = fsinfo_inode;
insert_inode_hash(fsinfo_inode);
return;
switch (signum) {
- kernel_siginfo_t si;
- default:
+ default: {
+ kernel_siginfo_t si;
+
/* Queue a rt signal with the appropriate fd as its
value. We use SI_SIGIO as the source, not
SI_KERNEL, since kernel signals always get
si.si_fd = fd;
if (!do_send_sig_info(signum, &si, p, type))
break;
+ }
/* fall-through - fall back on the old plain SIGIO signal */
case 0:
do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type);
if (worker->mm)
work->flags |= IO_WQ_WORK_HAS_MM;
- if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) {
+ if (wq->get_work) {
put_work = work;
wq->get_work(work);
}
} 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);
return true;
}
+static void io_run_cancel(struct io_wq_work *work)
+{
+ do {
+ struct io_wq_work *old_work = work;
+
+ work->flags |= IO_WQ_WORK_CANCEL;
+ work->func(&work);
+ work = (work == old_work) ? NULL : work;
+ } while (work);
+}
+
static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
{
struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
* It's close enough to not be an issue, fork() has the same delay.
*/
if (unlikely(!io_wq_can_queue(wqe, acct, work))) {
- work->flags |= IO_WQ_WORK_CANCEL;
- work->func(&work);
+ io_run_cancel(work);
return;
}
spin_unlock_irqrestore(&wqe->lock, flags);
if (found) {
- work->flags |= IO_WQ_WORK_CANCEL;
- work->func(&work);
+ io_run_cancel(work);
return IO_WQ_CANCEL_OK;
}
spin_unlock_irqrestore(&wqe->lock, flags);
if (found) {
- work->flags |= IO_WQ_WORK_CANCEL;
- work->func(&work);
+ io_run_cancel(work);
return IO_WQ_CANCEL_OK;
}
return ret;
}
-struct io_wq_flush_data {
- struct io_wq_work work;
- struct completion done;
-};
-
-static void io_wq_flush_func(struct io_wq_work **workptr)
-{
- struct io_wq_work *work = *workptr;
- struct io_wq_flush_data *data;
-
- data = container_of(work, struct io_wq_flush_data, work);
- complete(&data->done);
-}
-
-/*
- * Doesn't wait for previously queued work to finish. When this completes,
- * it just means that previously queued work was started.
- */
-void io_wq_flush(struct io_wq *wq)
-{
- struct io_wq_flush_data data;
- int node;
-
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
-
- if (!node_online(node))
- continue;
- init_completion(&data.done);
- INIT_IO_WORK(&data.work, io_wq_flush_func);
- data.work.flags |= IO_WQ_WORK_INTERNAL;
- io_wqe_enqueue(wqe, &data.work);
- wait_for_completion(&data.done);
- }
-}
-
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
{
int ret = -ENOMEM, node;
IO_WQ_WORK_HAS_MM = 2,
IO_WQ_WORK_HASHED = 4,
IO_WQ_WORK_UNBOUND = 32,
- IO_WQ_WORK_INTERNAL = 64,
IO_WQ_WORK_CB = 128,
IO_WQ_WORK_NO_CANCEL = 256,
IO_WQ_WORK_CONCURRENT = 512,
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 *);
void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
-void io_wq_flush(struct io_wq *wq);
void io_wq_cancel_all(struct io_wq *wq);
enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
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 rcu_head rcu;
};
struct io_ring_ctx {
if (ret != -1) {
atomic_inc(&req->ctx->cq_timeouts);
list_del_init(&req->list);
+ req->flags |= REQ_F_COMP_LOCKED;
io_cqring_fill_event(req, 0);
io_put_req(req);
}
__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)
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) {
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 */
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 */
{
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_getevents(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);
* 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();
prepare_to_wait(&ctx->sqo_wait, &wait,
TASK_INTERRUPTIBLE);
+ /*
+ * 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 ((ctx->flags & IORING_SETUP_IOPOLL) &&
+ !list_empty_careful(&ctx->poll_list)) {
+ finish_wait(&ctx->sqo_wait, &wait);
+ continue;
+ }
+
/* 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);
complete(&data->done);
}
+static void __io_file_ref_exit_and_free(struct rcu_head *rcu)
+{
+ struct fixed_file_data *data = container_of(rcu, struct fixed_file_data,
+ rcu);
+ percpu_ref_exit(&data->refs);
+ kfree(data);
+}
+
+static void io_file_ref_exit_and_free(struct rcu_head *rcu)
+{
+ /*
+ * We need to order our exit+free call against the potentially
+ * existing call_rcu() for switching to atomic. One way to do that
+ * is to have this rcu callback queue the final put and free, as we
+ * could otherwise have a pre-existing atomic switch complete _after_
+ * the free callback we queued.
+ */
+ call_rcu(rcu, __io_file_ref_exit_and_free);
+}
+
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
struct fixed_file_data *data = ctx->file_data;
flush_work(&data->ref_work);
wait_for_completion(&data->done);
io_ring_file_ref_flush(data);
- percpu_ref_exit(&data->refs);
__io_sqe_files_unregister(ctx);
nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
for (i = 0; i < nr_tables; i++)
kfree(data->table[i].files);
kfree(data->table);
- kfree(data);
+ call_rcu(&data->rcu, io_file_ref_exit_and_free);
ctx->file_data = NULL;
ctx->nr_user_files = 0;
return 0;
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,
/* 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:
* 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)
{
int status = -ENOENT;
- /*
- * If fl_blocker is NULL, it won't be set again as this thread
- * "owns" the lock and is the only one that might try to claim
- * the lock. So it is safe to test fl_blocker locklessly.
- * Also if fl_blocker is NULL, this waiter is not listed on
- * fl_blocked_requests for some lock, so no other request can
- * be added to the list of fl_blocked_requests for this
- * request. So if fl_blocker is NULL, it is safe to
- * locklessly check if fl_blocked_requests is empty. If both
- * of these checks succeed, there is no need to take the lock.
- */
- if (waiter->fl_blocker == NULL &&
- list_empty(&waiter->fl_blocked_requests))
- return status;
spin_lock(&blocked_lock_lock);
if (waiter->fl_blocker)
status = 0;
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))
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))
/*******************************************************************************
*
* The address are un-mapped when the count reaches zero.
*/
unsigned int vmap_use_count;
+
+ /**
+ * @map_cached: map object cached (instead of using writecombine).
+ */
+ bool map_cached;
};
#define to_drm_gem_shmem_obj(obj) \
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
/*
}
int kblockd_schedule_work(struct work_struct *work);
-int kblockd_schedule_work_on(int cpu, struct work_struct *work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
**/
#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;
};
#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);
#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);
#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+/*
+ * When called in DEBUG_PAGEALLOC context, the call should most likely be
+ * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static()
+ */
static inline void
kernel_map_pages(struct page *page, int numpages, int enable)
{
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) \
unsigned short num_cs;
unsigned int regs_offset;
unsigned int pin_dir:1;
+ size_t max_xfer_len;
};
struct omap2_mcspi_device_config {
((i) < rtd->num_codecs) && ((dai) = rtd->codec_dais[i]); \
(i)++)
#define for_each_rtd_codec_dai_rollback(rtd, i, dai) \
- for (; ((--i) >= 0) && ((dai) = rtd->codec_dais[i]);)
+ for (; (--(i) >= 0) && ((dai) = rtd->codec_dais[i]);)
void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd);
#define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
#define DM_VERSION_MAJOR 4
-#define DM_VERSION_MINOR 41
+#define DM_VERSION_MINOR 42
#define DM_VERSION_PATCHLEVEL 0
-#define DM_VERSION_EXTRA "-ioctl (2019-09-16)"
+#define DM_VERSION_EXTRA "-ioctl (2020-02-27)"
/* Status bits */
#define DM_READONLY_FLAG (1 << 0) /* In/Out */
uint8_t pad;
uint8_t nr_extra_pages; /* extra pages for long packets; may be zero */
- uint32_t extra_pages[0]; /* grant IDs; length in nr_extra_pages */
+ uint32_t extra_pages[]; /* grant IDs; length in nr_extra_pages */
};
#endif
#include <linux/completion.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/semaphore.h>
#include <xen/interface/xen.h>
#include <xen/interface/grant_table.h>
#include <xen/interface/io/xenbus.h>
enum xenbus_state state;
struct completion down;
struct work_struct work;
- spinlock_t reclaim_lock;
+ struct semaphore reclaim_sem;
};
static inline struct xenbus_device *to_xenbus_device(struct device *dev)
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. */
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;
}
}
reaper = find_new_reaper(father, reaper);
list_for_each_entry(p, &father->children, sibling) {
for_each_thread(p, t) {
- t->real_parent = reaper;
- BUG_ON((!t->ptrace) != (t->parent == father));
+ RCU_INIT_POINTER(t->real_parent, reaper);
+ BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father));
if (likely(!t->ptrace))
t->parent = t->real_parent;
if (t->pdeath_signal)
return 0;
}
sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
- rcu_assign_pointer(tsk->sighand, sig);
+ RCU_INIT_POINTER(tsk->sighand, sig);
if (!sig)
return -ENOMEM;
* 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
*
sgs->group_capacity = group->sgc->capacity;
+ sgs->group_weight = group->group_weight;
+
sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
/*
{
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);
}
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);
+ bt = rcu_dereference_protected(q->blk_trace,
+ lockdep_is_held(&q->blk_trace_mutex));
+ }
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);
return;
flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
- pmdval = *pvmw->pmd;
- pmdp_invalidate(vma, address, pvmw->pmd);
+ pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
if (pmd_dirty(pmdval))
set_page_dirty(page);
entry = make_migration_entry(page, pmd_write(pmdval));
bool ret;
void *kaddr;
void __user *uaddr;
- bool force_mkyoung;
+ bool locked = false;
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = vmf->address;
* On architectures with software "accessed" bits, we would
* take a double page fault, so mark it accessed here.
*/
- force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte);
- if (force_mkyoung) {
+ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
pte_t entry;
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+ locked = true;
if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
/*
* Other thread has already handled the fault
* zeroes.
*/
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+ if (locked)
+ goto warn;
+
+ /* Re-validate under PTL if the page is still mapped */
+ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+ locked = true;
+ if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+ /* The PTE changed under us. Retry page fault. */
+ ret = false;
+ goto pte_unlock;
+ }
+
/*
- * Give a warn in case there can be some obscure
- * use-case
+ * The same page can be mapped back since last copy attampt.
+ * Try to copy again under PTL.
*/
- WARN_ON_ONCE(1);
- clear_page(kaddr);
+ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+ /*
+ * Give a warn in case there can be some obscure
+ * use-case
+ */
+warn:
+ WARN_ON_ONCE(1);
+ clear_page(kaddr);
+ }
}
ret = true;
pte_unlock:
- if (force_mkyoung)
+ if (locked)
pte_unmap_unlock(vmf->pte, vmf->ptl);
kunmap_atomic(kaddr);
flush_dcache_page(dst);
void generic_online_page(struct page *page, unsigned int order)
{
- kernel_map_pages(page, 1 << order, 1);
+ /*
+ * Freeing the page with debug_pagealloc enabled will try to unmap it,
+ * so we should map it first. This is better than introducing a special
+ * case in page freeing fast path.
+ */
+ if (debug_pagealloc_enabled_static())
+ kernel_map_pages(page, 1 << order, 1);
__free_pages_core(page, order);
totalram_pages_add(1UL << order);
#ifdef CONFIG_HIGHMEM
return pages;
}
+/*
+ * Used when setting automatic NUMA hinting protection where it is
+ * critical that a numa hinting PMD is not confused with a bad PMD.
+ */
+static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
+{
+ pmd_t pmdval = pmd_read_atomic(pmd);
+
+ /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ barrier();
+#endif
+
+ if (pmd_none(pmdval))
+ return 1;
+ if (pmd_trans_huge(pmdval))
+ return 0;
+ if (unlikely(pmd_bad(pmdval))) {
+ pmd_clear_bad(pmd);
+ return 1;
+ }
+
+ return 0;
+}
+
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pud_t *pud, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
unsigned long this_pages;
next = pmd_addr_end(addr, end);
- if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
- && pmd_none_or_clear_bad(pmd))
+
+ /*
+ * Automatic NUMA balancing walks the tables with mmap_sem
+ * held for read. It's possible a parallel update to occur
+ * between pmd_trans_huge() and a pmd_none_or_clear_bad()
+ * check leading to a false positive and clearing.
+ * Hence, it's necessary to atomically read the PMD value
+ * for all the checks.
+ */
+ if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
+ pmd_none_or_clear_bad_unless_trans_huge(pmd))
goto next;
/* invoke the mmu notifier if the pmd is populated */
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
-#include <linux/rwlock.h>
#include <linux/zpool.h>
#include <linux/magic.h>
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) &&
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;
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;
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 },
#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);
{
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;
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;
(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;
}
}
+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;
}
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",
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))
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)
{
if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) {
hlist_del(&hinfo->node);
+ htable_remove_proc_entry(hinfo);
mutex_unlock(&hashlimit_mutex);
- htable_destroy(hinfo);
+
+ cancel_delayed_work_sync(&hinfo->gc_work);
+ htable_selective_cleanup(hinfo, true);
+ kfree(hinfo->name);
+ vfree(hinfo);
}
}
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;
+ 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 */
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 */
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) {
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)
static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = {
.open = snd_sgio2audio_playback1_open,
.close = snd_sgio2audio_pcm_close,
- .hw_params = snd_sgio2audio_pcm_hw_params,
- .hw_free = snd_sgio2audio_pcm_hw_free,
.prepare = snd_sgio2audio_pcm_prepare,
.trigger = snd_sgio2audio_pcm_trigger,
.pointer = snd_sgio2audio_pcm_pointer,
static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
.open = snd_sgio2audio_playback2_open,
.close = snd_sgio2audio_pcm_close,
- .hw_params = snd_sgio2audio_pcm_hw_params,
- .hw_free = snd_sgio2audio_pcm_hw_free,
.prepare = snd_sgio2audio_pcm_prepare,
.trigger = snd_sgio2audio_pcm_trigger,
.pointer = snd_sgio2audio_pcm_pointer,
static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
.open = snd_sgio2audio_capture_open,
.close = snd_sgio2audio_pcm_close,
- .hw_params = snd_sgio2audio_pcm_hw_params,
- .hw_free = snd_sgio2audio_pcm_hw_free,
.prepare = snd_sgio2audio_pcm_prepare,
.trigger = snd_sgio2audio_pcm_trigger,
.pointer = snd_sgio2audio_pcm_pointer,
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(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_CLEVO_P950),
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),
ALC289_FIXUP_DUAL_SPK,
ALC294_FIXUP_SPK2_TO_DAC1,
ALC294_FIXUP_ASUS_DUAL_SPK,
-
+ ALC285_FIXUP_THINKPAD_HEADSET_JACK,
+ ALC294_FIXUP_ASUS_HPE,
};
static const struct hda_fixup alc269_fixups[] = {
[ALC285_FIXUP_SPEAKER2_TO_DAC1] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_speaker2_to_dac1,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI
},
[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
.type = HDA_FIXUP_PINS,
.chained = true,
.chain_id = ALC294_FIXUP_SPK2_TO_DAC1
},
-
+ [ALC285_FIXUP_THINKPAD_HEADSET_JACK] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_headset_jack,
+ .chained = true,
+ .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1
+ },
+ [ALC294_FIXUP_ASUS_HPE] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ /* Set EAPD high */
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x7774 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
+ SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
- SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1),
- SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1),
+ SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
depends on SND_SOC_I2C_AND_SPI
config SND_SOC_WM8741
- tristate "Wolfson Microelectronics WM8737 DAC"
+ tristate "Wolfson Microelectronics WM8741 DAC"
depends on SND_SOC_I2C_AND_SPI
config SND_SOC_WM8750
}
pcm512x->sclk = devm_clk_get(dev, NULL);
- if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
+ if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto err;
+ }
if (!IS_ERR(pcm512x->sclk)) {
ret = clk_prepare_enable(pcm512x->sclk);
if (ret != 0) {
dev_err(dev, "Failed to enable SCLK: %d\n", ret);
- return ret;
+ goto err;
}
}
snd_soc_component_update_bits(component, RT1015_TDM_MASTER,
RT1015_I2S_DL_MASK, val_len);
snd_soc_component_update_bits(component, RT1015_CLK2,
- RT1015_FS_PD_MASK, pre_div);
+ RT1015_FS_PD_MASK, pre_div << RT1015_FS_PD_SFT);
return 0;
}
.rates = RT1015_STEREO_RATES,
.formats = RT1015_FORMATS,
},
+ .ops = &rt1015_aif_dai_ops,
}
};
break;
default:
- dev_info(tas2562->dev, "Not supported params format\n");
+ dev_info(tas2562->dev, "Unsupported bitwidth format\n");
+ return -EINVAL;
}
ret = snd_soc_component_update_bits(tas2562->component,
ret = tas2562_set_samplerate(tas2562, params_rate(params));
if (ret)
- dev_err(tas2562->dev, "set bitwidth failed, %d\n", ret);
+ dev_err(tas2562->dev, "set sample rate failed, %d\n", ret);
return ret;
}
int i;
ssize_t ret = 0;
- for (i = 0; i < max_pin; i++)
- ret += snprintf(buf + size, MOD_BUF - size,
+ for (i = 0; i < max_pin; i++) {
+ ret += scnprintf(buf + size, MOD_BUF - size,
"%s %d\n\tModule %d\n\tInstance %d\n\t"
"In-used %s\n\tType %s\n"
"\tState %d\n\tIndex %d\n",
m_pin[i].in_use ? "Used" : "Unused",
m_pin[i].is_dynamic ? "Dynamic" : "Static",
m_pin[i].pin_state, i);
+ size += ret;
+ }
return ret;
}
static ssize_t skl_print_fmt(struct skl_module_fmt *fmt, char *buf,
ssize_t size, bool direction)
{
- return snprintf(buf + size, MOD_BUF - size,
+ return scnprintf(buf + size, MOD_BUF - size,
"%s\n\tCh %d\n\tFreq %d\n\tBit depth %d\n\t"
"Valid bit depth %d\n\tCh config %#x\n\tInterleaving %d\n\t"
"Sample Type %d\n\tCh Map %#x\n",
if (!buf)
return -ENOMEM;
- ret = snprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n"
+ ret = scnprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n"
"\tInstance id %d\n\tPvt_id %d\n", mconfig->guid,
mconfig->id.module_id, mconfig->id.instance_id,
mconfig->id.pvt_id);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Resources:\n\tCPC %#x\n\tIBS %#x\n\tOBS %#x\t\n",
res->cpc, res->ibs, res->obs);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Module data:\n\tCore %d\n\tIn queue %d\n\t"
"Out queue %d\n\tType %s\n",
mconfig->core_id, mconfig->max_in_queue,
ret += skl_print_fmt(mconfig->in_fmt, buf, ret, true);
ret += skl_print_fmt(mconfig->out_fmt, buf, ret, false);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Fixup:\n\tParams %#x\n\tConverter %#x\n",
mconfig->params_fixup, mconfig->converter);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Module Gateway:\n\tType %#x\n\tVbus %#x\n\tHW conn %#x\n\tSlot %#x\n",
mconfig->dev_type, mconfig->vbus_id,
mconfig->hw_conn_type, mconfig->time_slot);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Pipeline:\n\tID %d\n\tPriority %d\n\tConn Type %d\n\t"
"Pages %#x\n", mconfig->pipe->ppl_id,
mconfig->pipe->pipe_priority, mconfig->pipe->conn_type,
mconfig->pipe->memory_pages);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"\tParams:\n\t\tHost DMA %d\n\t\tLink DMA %d\n",
mconfig->pipe->p_params->host_dma_id,
mconfig->pipe->p_params->link_dma_id);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"\tPCM params:\n\t\tCh %d\n\t\tFreq %d\n\t\tFormat %d\n",
mconfig->pipe->p_params->ch,
mconfig->pipe->p_params->s_freq,
mconfig->pipe->p_params->s_fmt);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"\tLink %#x\n\tStream %#x\n",
mconfig->pipe->p_params->linktype,
mconfig->pipe->p_params->stream);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"\tState %d\n\tPassthru %s\n",
mconfig->pipe->state,
mconfig->pipe->passthru ? "true" : "false");
ret += skl_print_pins(mconfig->m_out_pin, buf,
mconfig->max_out_queue, ret, false);
- ret += snprintf(buf + ret, MOD_BUF - ret,
+ ret += scnprintf(buf + ret, MOD_BUF - ret,
"Other:\n\tDomain %d\n\tHomogeneous Input %s\n\t"
"Homogeneous Output %s\n\tIn Queue Mask %d\n\t"
"Out Queue Mask %d\n\tDMA ID %d\n\tMem Pages %d\n\t"
__ioread32_copy(d->fw_read_buff, fw_reg_addr, w0_stat_sz >> 2);
for (offset = 0; offset < FW_REG_SIZE; offset += 16) {
- ret += snprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset);
+ ret += scnprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset);
hex_dump_to_buffer(d->fw_read_buff + offset, 16, 16, 4,
tmp + ret, FW_REG_BUF - ret, 0);
ret += strlen(tmp + ret);
&clks[i], clk_pdata, i);
if (IS_ERR(data->clk[data->avail_clk_cnt])) {
- ret = PTR_ERR(data->clk[data->avail_clk_cnt++]);
+ ret = PTR_ERR(data->clk[data->avail_clk_cnt]);
goto err_unreg_skl_clk;
}
+
+ data->avail_clk_cnt++;
}
platform_set_drvdata(pdev, data);
#include <linux/module.h>
#include <sound/pcm_params.h>
#include <linux/regmap.h>
+#include <linux/reset.h>
#include <sound/soc.h>
#include <sound/soc-dai.h>
struct device *dev = &pdev->dev;
void __iomem *regs;
struct regmap *map;
+ int ret;
+
+ ret = device_reset(dev);
+ if (ret)
+ return ret;
regs = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(regs))
int i, ret;
for_each_rtd_components(rtd, i, component) {
- if (component->driver->ioctl) {
+ if (component->driver->sync_stop) {
ret = component->driver->sync_stop(component,
substream);
if (ret < 0)
for_each_dpcm_be(fe, stream, dpcm)
dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
- snd_soc_dapm_stream_stop(fe, stream);
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
continue;
if (w->power) {
dapm_seq_insert(w, &down_list, false);
- w->power = 0;
+ w->new_power = 0;
powerdown = 1;
}
}
soc_pcm_close(substream);
/* run the stream event for each BE */
- snd_soc_dapm_stream_stop(fe, stream);
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
unsigned long flags;
/* FE state */
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
"[%s - %s]\n", fe->dai_link->name,
stream ? "Capture" : "Playback");
- offset += snprintf(buf + offset, size - offset, "State: %s\n",
+ offset += scnprintf(buf + offset, size - offset, "State: %s\n",
dpcm_state_string(fe->dpcm[stream].state));
if ((fe->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) &&
(fe->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP))
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
"Hardware Params: "
"Format = %s, Channels = %d, Rate = %d\n",
snd_pcm_format_name(params_format(params)),
params_rate(params));
/* BEs state */
- offset += snprintf(buf + offset, size - offset, "Backends:\n");
+ offset += scnprintf(buf + offset, size - offset, "Backends:\n");
if (list_empty(&fe->dpcm[stream].be_clients)) {
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
" No active DSP links\n");
goto out;
}
struct snd_soc_pcm_runtime *be = dpcm->be;
params = &dpcm->hw_params;
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
"- %s\n", be->dai_link->name);
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
" State: %s\n",
dpcm_state_string(be->dpcm[stream].state));
if ((be->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) &&
(be->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP))
- offset += snprintf(buf + offset, size - offset,
+ offset += scnprintf(buf + offset, size - offset,
" Hardware Params: "
"Format = %s, Channels = %d, Rate = %d\n",
snd_pcm_format_name(params_format(params)),
}
ret = soc_tplg_link_config(tplg, _link);
- if (ret < 0)
+ if (ret < 0) {
+ if (!abi_match)
+ kfree(_link);
return ret;
+ }
/* offset by version-specific struct size and
* real priv data size
{
struct snd_soc_tplg_manifest *manifest, *_manifest;
bool abi_match;
- int err;
+ int ret = 0;
if (tplg->pass != SOC_TPLG_PASS_MANIFEST)
return 0;
_manifest = manifest;
} else {
abi_match = false;
- err = manifest_new_ver(tplg, manifest, &_manifest);
- if (err < 0)
- return err;
+ ret = manifest_new_ver(tplg, manifest, &_manifest);
+ if (ret < 0)
+ return ret;
}
/* pass control to component driver for optional further init */
if (tplg->comp && tplg->ops && tplg->ops->manifest)
- return tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
+ ret = tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
if (!abi_match) /* free the duplicated one */
kfree(_manifest);
- return 0;
+ return ret;
}
/* validate header magic, size and type */
/* send IPC to the DSP */
err = sof_ipc_tx_message(sdev->ipc,
- stream.hdr.cmd, &stream, sizeof(stream), &posn,
+ stream.hdr.cmd, &stream, sizeof(stream), posn,
sizeof(*posn));
if (err < 0) {
dev_err(sdev->dev, "error: failed to get stream %d position\n",
return ret;
}
- ret = devm_snd_soc_register_component(&pdev->dev, &stm32_component,
- &sai->cpu_dai_drv, 1);
+ ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0);
+ if (ret) {
+ dev_err(&pdev->dev, "Could not register pcm dma\n");
+ return ret;
+ }
+
+ ret = snd_soc_register_component(&pdev->dev, &stm32_component,
+ &sai->cpu_dai_drv, 1);
if (ret)
return ret;
if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
conf = &stm32_sai_pcm_config_spdif;
- ret = devm_snd_dmaengine_pcm_register(&pdev->dev, conf, 0);
- if (ret) {
- dev_err(&pdev->dev, "Could not register pcm dma\n");
- return ret;
- }
-
return 0;
}
struct stm32_sai_sub_data *sai = dev_get_drvdata(&pdev->dev);
clk_unprepare(sai->pdata->pclk);
+ snd_dmaengine_pcm_unregister(&pdev->dev);
+ snd_soc_unregister_component(&pdev->dev);
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
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'])
all:
TEST_PROGS := ftracetest
-TEST_FILES := test.d
+TEST_FILES := test.d settings
EXTRA_CLEAN := $(OUTPUT)/logs/*
include ../lib.mk
test-state.sh \
test-ftrace.sh
+TEST_FILES := settings
+
include ../lib.mk
--- /dev/null
+*.sh
+!run.sh
TEST_GEN_FILES = mptcp_connect
+TEST_FILES := settings
+
EXTRA_CLEAN := *.pcap
include ../../lib.mk
KSELFTEST_SKIP=4
# Available test groups:
+# - reported_issues: check for issues that were reported in the past
# - correctness: check that packets match given entries, and only those
# - concurrency: attempt races between insertion, deletion and lookup
# - timeout: check that packets match entries until they expire
# - performance: estimate matching rate, compare with rbtree and hash baselines
-TESTS="correctness concurrency timeout"
+TESTS="reported_issues correctness concurrency timeout"
[ "${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 ${desc}; do
pidfd_poll_test
pidfd_test
pidfd_wait
+pidfd_fdinfo_test
pidfd_getfd_test
CLANG_FLAGS += -no-integrated-as
endif
-CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(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
TEST_GEN_PROGS_EXTENDED = setdate
+TEST_FILES := settings
+
include ../lib.mk
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